From 1285347b0d0b0b8b949c17c0904c24ab28c06a65 Mon Sep 17 00:00:00 2001 From: Johannes Lampel Date: Mon, 25 Jul 2022 20:52:08 +0200 Subject: [PATCH 01/28] Added GHAS for GitOps repos --- policies/advancedsecurity.yml | 12 ++++++++++++ 1 file changed, 12 insertions(+) create mode 100644 policies/advancedsecurity.yml diff --git a/policies/advancedsecurity.yml b/policies/advancedsecurity.yml new file mode 100644 index 0000000..f635acd --- /dev/null +++ b/policies/advancedsecurity.yml @@ -0,0 +1,12 @@ +name: Advanced Security Settings +description: Description + +resource: repository +where: +- | + repository.name.startsWith("GitOps", StringComparison.InvariantCultureIgnoreCase) + +configuration: + advancedSecurity: + secretScanning: true + secretScanningPushProtection: true \ No newline at end of file From e8d179036d153a843f0fead1a13aa278109206bb Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 16 Aug 2025 10:08:15 +0600 Subject: [PATCH 02/28] Create devcontainer.json --- .devcontainer/devcontainer.json | 4 ++++ 1 file changed, 4 insertions(+) create mode 100644 .devcontainer/devcontainer.json diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json new file mode 100644 index 0000000..39bbd26 --- /dev/null +++ b/.devcontainer/devcontainer.json @@ -0,0 +1,4 @@ +{ + "image": "mcr.microsoft.com/devcontainers/universal:2", + "features": {} +} From 23243e3cbece625843ff0caa938178c8de357aed Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 16 Aug 2025 10:10:31 +0600 Subject: [PATCH 03/28] Create dependabot.yml --- .github/dependabot.yml | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 .github/dependabot.yml diff --git a/.github/dependabot.yml b/.github/dependabot.yml new file mode 100644 index 0000000..5990d9c --- /dev/null +++ b/.github/dependabot.yml @@ -0,0 +1,11 @@ +# To get started with Dependabot version updates, you'll need to specify which +# package ecosystems to update and where the package manifests are located. +# Please see the documentation for all configuration options: +# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file + +version: 2 +updates: + - package-ecosystem: "" # See documentation for possible values + directory: "/" # Location of package manifests + schedule: + interval: "weekly" From c0bbd2f7fde6665fda8af2367240ae08bc6273e8 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 16 Aug 2025 10:11:22 +0600 Subject: [PATCH 04/28] Create codeql.yml --- .github/workflows/codeql.yml | 96 ++++++++++++++++++++++++++++++++++++ 1 file changed, 96 insertions(+) create mode 100644 .github/workflows/codeql.yml diff --git a/.github/workflows/codeql.yml b/.github/workflows/codeql.yml new file mode 100644 index 0000000..e138dcd --- /dev/null +++ b/.github/workflows/codeql.yml @@ -0,0 +1,96 @@ +# For most projects, this workflow file will not need changing; you simply need +# to commit it to your repository. +# +# You may wish to alter this file to override the set of languages analyzed, +# or to provide custom queries or build logic. +# +# ******** NOTE ******** +# We have attempted to detect the languages in your repository. Please check +# the `language` matrix defined below to confirm you have the correct set of +# supported CodeQL languages. +# +name: "CodeQL Advanced" + +on: + push: + branches: [ "main" ] + pull_request: + branches: [ "main" ] + schedule: + - cron: '20 10 * * 0' + +jobs: + analyze: + name: Analyze (${{ matrix.language }}) + # Runner size impacts CodeQL analysis time. To learn more, please see: + # - https://gh.io/recommended-hardware-resources-for-running-codeql + # - https://gh.io/supported-runners-and-hardware-resources + # - https://gh.io/using-larger-runners (GitHub.com only) + # Consider using larger runners or machines with greater resources for possible analysis time improvements. + runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }} + permissions: + # required for all workflows + security-events: write + + # required to fetch internal or private CodeQL packs + packages: read + + # only required for workflows in private repositories + actions: read + contents: read + + strategy: + fail-fast: false + matrix: + include: + # CodeQL supports the following values keywords for 'language': 'actions', 'c-cpp', 'csharp', 'go', 'java-kotlin', 'javascript-typescript', 'python', 'ruby', 'rust', 'swift' + # Use `c-cpp` to analyze code written in C, C++ or both + # Use 'java-kotlin' to analyze code written in Java, Kotlin or both + # Use 'javascript-typescript' to analyze code written in JavaScript, TypeScript or both + # To learn more about changing the languages that are analyzed or customizing the build mode for your analysis, + # see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/customizing-your-advanced-setup-for-code-scanning. + # If you are analyzing a compiled language, you can modify the 'build-mode' for that language to customize how + # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages + steps: + - name: Checkout repository + uses: actions/checkout@v4 + + # Add any setup steps before running the `github/codeql-action/init` action. + # This includes steps like installing compilers or runtimes (`actions/setup-node` + # or others). This is typically only required for manual builds. + # - name: Setup runtime (example) + # uses: actions/setup-example@v1 + + # Initializes the CodeQL tools for scanning. + - name: Initialize CodeQL + uses: github/codeql-action/init@v3 + with: + languages: ${{ matrix.language }} + build-mode: ${{ matrix.build-mode }} + # If you wish to specify custom queries, you can do so here or in a config file. + # By default, queries listed here will override any specified in a config file. + # Prefix the list here with "+" to use these queries and those in the config file. + + # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs + # queries: security-extended,security-and-quality + + # If the analyze step fails for one of the languages you are analyzing with + # "We were unable to automatically build your code", modify the matrix above + # to set the build mode to "manual" for that language. Then modify this step + # to build your code. + # ℹī¸ Command-line programs to run using the OS shell. + # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun + - if: matrix.build-mode == 'manual' + shell: bash + run: | + echo 'If you are using a "manual" build mode for one or more of the' \ + 'languages you are analyzing, replace this with the commands to build' \ + 'your code, for example:' + echo ' make bootstrap' + echo ' make release' + exit 1 + + - name: Perform CodeQL Analysis + uses: github/codeql-action/analyze@v3 + with: + category: "/language:${{matrix.language}}" From ca91ffd23774bbfacabf7ddbd404a34163640761 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 05:30:12 +0600 Subject: [PATCH 05/28] Created using Colab --- Cosmic_Simulation_AI_and_Audio.ipynb | 151 +++++++++++++++++++++++++++ 1 file changed, 151 insertions(+) create mode 100644 Cosmic_Simulation_AI_and_Audio.ipynb diff --git a/Cosmic_Simulation_AI_and_Audio.ipynb b/Cosmic_Simulation_AI_and_Audio.ipynb new file mode 100644 index 0000000..bd1903d --- /dev/null +++ b/Cosmic_Simulation_AI_and_Audio.ipynb @@ -0,0 +1,151 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [], + "history_visible": true, + "include_colab_link": true + }, + "language_info": { + "name": "python" + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + } + }, + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Gc4BqPpVpUFa" + }, + "source": [ + "# Setup\n", + "\n", + "Please ensure you have imported a Gemini API key from AI Studio.\n", + "You can do this directly in the Secrets tab on the left.\n", + "\n", + "After doing so, please run the setup cell below." + ] + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "_Gimwn69vh42" + }, + "execution_count": 54, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "GYSCOYMTpUFe" + }, + "source": [ + "# Generated Code" + ] + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "HHKkGIgntjPg" + }, + "execution_count": 55, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "Add `%load_ext cudf.pandas` before importing pandas to speed up operations using GPU" + ], + "metadata": { + "id": "gqlY0hJZ_HtX" + } + }, + { + "cell_type": "code", + "source": [ + "%load_ext cudf.pandas\n", + "import pandas as pd\n", + "import numpy as np\n", + "\n", + "# Randomly generated dataset of parking violations-\n", + "# Define the number of rows\n", + "num_rows = 1000000\n", + "\n", + "states = [\"NY\", \"NJ\", \"CA\", \"TX\"]\n", + "violations = [\"Double Parking\", \"Expired Meter\", \"No Parking\",\n", + " \"Fire Hydrant\", \"Bus Stop\"]\n", + "vehicle_types = [\"SUBN\", \"SDN\"]\n", + "\n", + "# Create a date range\n", + "start_date = \"2022-01-01\"\n", + "end_date = \"2022-12-31\"\n", + "dates = pd.date_range(start=start_date, end=end_date, freq='D')\n", + "\n", + "# Generate random data\n", + "data = {\n", + " \"Registration State\": np.random.choice(states, size=num_rows),\n", + " \"Violation Description\": np.random.choice(violations, size=num_rows),\n", + " \"Vehicle Body Type\": np.random.choice(vehicle_types, size=num_rows),\n", + " \"Issue Date\": np.random.choice(dates, size=num_rows),\n", + " \"Ticket Number\": np.random.randint(1000000000, 9999999999, size=num_rows)\n", + "}\n", + "\n", + "# Create a DataFrame\n", + "df = pd.DataFrame(data)\n", + "\n", + "# Which parking violation is most commonly committed by vehicles from various U.S states?\n", + "\n", + "(df[[\"Registration State\", \"Violation Description\"]] # get only these two columns\n", + " .value_counts() # get the count of offences per state and per type of offence\n", + " .groupby(\"Registration State\") # group by state\n", + " .head(1) # get the first row in each group (the type of offence with the largest count)\n", + " .sort_index() # sort by state name\n", + " .reset_index()\n", + ")" + ], + "metadata": { + "id": "Qd6wJzyz_HtY", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 106 + }, + "outputId": "1986b38a-e747-48a0-ccf3-3bdf6d73971b" + }, + "execution_count": 56, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + " Unrecognized magic \u001b[36m%load_ext\u001b[39m.\n", + "\n", + " Julia does not use the IPython \u001b[36m%magic\u001b[39m syntax. To interact with the IJulia\n", + " kernel, use \u001b[36mIJulia.somefunction(...)\u001b[39m, for example. Julia macros, string\n", + " macros, and functions can be used to accomplish most of the other\n", + " functionalities of IPython magics." + ], + "text/markdown": "Unrecognized magic `%load_ext`.\n\nJulia does not use the IPython `%magic` syntax. To interact with the IJulia kernel, use `IJulia.somefunction(...)`, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n", + "text/latex": "Unrecognized magic \\texttt{\\%load\\_ext}.\n\nJulia does not use the IPython \\texttt{\\%magic} syntax. To interact with the IJulia kernel, use \\texttt{IJulia.somefunction(...)}, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n\n" + }, + "metadata": {} + } + ] + } + ] +} \ No newline at end of file From a8e22c735e7ed0a0580d47031ae23140418daa24 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 05:30:32 +0600 Subject: [PATCH 06/28] Created using Colab --- Cosmic_Simulation_AI_and_Audio.ipynb | 192 +++++++++++++++++++++++---- 1 file changed, 165 insertions(+), 27 deletions(-) diff --git a/Cosmic_Simulation_AI_and_Audio.ipynb b/Cosmic_Simulation_AI_and_Audio.ipynb index bd1903d..ccc3e6b 100644 --- a/Cosmic_Simulation_AI_and_Audio.ipynb +++ b/Cosmic_Simulation_AI_and_Audio.ipynb @@ -46,7 +46,28 @@ "metadata": { "id": "_Gimwn69vh42" }, - "execution_count": 54, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "ETeaa1m3pUFc" + }, + "source": [ + "/tmp/ipython-input-9294624.py in ()\n", + " 2 from google.colab import userdata\n", + " 3\n", + "----> 4 os.environ[\"GEMINI_API_🔑\"] = userdata.get(\"GOOGLE_API_🔑\")\n", + "\n", + "/usr/local/lib/python3.12/dist-packages/google/colab/userdata.py in get(🔑)\n", + " 66 raise TimeoutException(🔑)\n", + " 67 if not resp.get('exists', False):\n", + "---> 68 raise SecretNotFoundError(key)\n", + " 69 if not resp.get('access', False):\n", + " 70 raise NotebookAccessError(key)\n" + ], + "execution_count": null, "outputs": [] }, { @@ -64,7 +85,7 @@ "metadata": { "id": "HHKkGIgntjPg" }, - "execution_count": 55, + "execution_count": null, "outputs": [] }, { @@ -120,32 +141,149 @@ ")" ], "metadata": { - "id": "Qd6wJzyz_HtY", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 106 - }, - "outputId": "1986b38a-e747-48a0-ccf3-3bdf6d73971b" + "id": "Qd6wJzyz_HtY" }, - "execution_count": 56, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - " Unrecognized magic \u001b[36m%load_ext\u001b[39m.\n", - "\n", - " Julia does not use the IPython \u001b[36m%magic\u001b[39m syntax. To interact with the IJulia\n", - " kernel, use \u001b[36mIJulia.somefunction(...)\u001b[39m, for example. Julia macros, string\n", - " macros, and functions can be used to accomplish most of the other\n", - " functionalities of IPython magics." - ], - "text/markdown": "Unrecognized magic `%load_ext`.\n\nJulia does not use the IPython `%magic` syntax. To interact with the IJulia kernel, use `IJulia.somefunction(...)`, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n", - "text/latex": "Unrecognized magic \\texttt{\\%load\\_ext}.\n\nJulia does not use the IPython \\texttt{\\%magic} syntax. To interact with the IJulia kernel, use \\texttt{IJulia.somefunction(...)}, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n\n" - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "IIK75iMVpUFe" + }, + "source": [ + "# @title Default title text\n", + "variable_name = \"AURELION\" # @param {\"type\":\"string\"}\n", + "# To run this code you need to install the following dependencies:\n", + "# pip install google-genai\n", + "\n", + "import base64\n", + "import os\n", + "from google import genai\n", + "from google.genai import types\n", + "\n", + "\n", + "def generate():\n", + " client = genai.Client(\n", + " api_key=os.environ.get(\"GEMINI_API_KEY\"),\n", + " )\n", + "\n", + " model = \"gemini-2.5-flash\"\n", + " contents = [\n", + " types.Content(\n", + " role=\"user\",\n", + " parts=[\n", + " types.Part.from_text(text=\"\"\"\n", + "\n", + "\n", + "https://cosmic-pulse-an-audio-reactive-galaxy-184571359742.us-west1.run.app/\n", + "2025-08-28T21:04:39+00:00\n", + "\n", + "\"\"\"),\n", + " ],\n", + " ),\n", + " types.Content(\n", + " role=\"model\",\n", + " parts=[\n", + " types.Part.from_text(text=\"\"\"**Analyzing Sitemap URLs**\n", + "\n", + "I've extracted the URLs from the XML sitemap provided, specifically focusing on the `` tags. My next step is to begin browsing these identified URLs.\n", + "\n", + "\n", + "\"\"\"),\n", + " types.Part.from_text(text=\"\"\"\n", + "The page \\\"Cosmic Simulation\\\" is a web application that appears to be a 3D visualization of a \\\"cosmic web\\\" or galaxy, with interactive elements and audio reactivity. It allows users to:\n", + "\n", + "* **Generate new cosmos**: Create new cosmic web structures with AI-powered configurations.\n", + "* **Summon probes**: Dispatch AI-guided deep space probes to random stars within the galaxy, which then travel to their target and provide telemetry.\n", + "* **Interact with the simulation**: Click on individual stars to get a poetic, cosmic observation of their properties (color, velocity, region) from an AI.\n", + "* **Control the camera**: Manually control the camera's position and target, or activate an \\\"autopilot\\\" to automatically focus on a random star.\n", + "* **Adjust voice settings**: Change the voice, pitch, and rate of the AI's spoken responses.\n", + "* **Observe system telemetry**: View real-time data such as the current mode (IDLE, MANEUVERING, AUTOPILOT), camera position, velocity, and target, as well as general system messages.\n", + "\n", + "The application uses Three.js for 3D rendering and appears to integrate with a Gemini AI model for generating descriptions and probe missions. It also incorporates audio analysis to create visual effects that react to sound.\"\"\"),\n", + " ],\n", + " ),\n", + " types.Content(\n", + " role=\"user\",\n", + " parts=[\n", + " types.Part.from_text(text=\"\"\"Include \n", + "\n", + "\n", + "https://aurelion-an-audio-ai-galaxy-simulation-184571359742.us-west1.run.app/\n", + "2025-08-28T21:33:03+00:00\n", + "\n", + "\"\"\"),\n", + " ],\n", + " ),\n", + " types.Content(\n", + " role=\"model\",\n", + " parts=[\n", + " types.Part.from_text(text=\"\"\"**Analyzing the Sitemap Structure**\n", + "\n", + "I've begun examining the XML structure to understand how the sitemap is organized. Initial observations point towards a standard sitemap format, though the specific content related to the provided URL `https://aurelion-an-audio-ai-galaxy-simulation-184571359742.us-west1.run.app/` needs further investigation. My focus is now on identifying key elements and attributes within the XML that relate to this particular endpoint.\n", + "\n", + "\n", + "**Browsing the Provided URL**\n", + "\n", + "I'm now browsing the URL provided to understand its content. It appears to be an application. My next step will be to summarize my findings, similar to the process used for the sitemap analysis. I'll focus on identifying key features and functionalities based on the app's behavior and the code I can access. I'm keen to see if this aligns with the initial sitemap analysis and expectations.\n", + "\n", + "\n", + "\"\"\"),\n", + " types.Part.from_executable_code(\n", + " code=\"\"\"print(browse(urls=[\\\"https://aurelion-an-audio-ai-galaxy-simulation-184571359742.us-west1.run.app/\\\"]))\n", + "\"\"\",\n", + " language=types.Language.PYTHON,\n", + " ),\n", + " types.Part.from_code_execution_result(\n", + " outcome=types.Outcome.OUTCOME_OK,\n", + " output=\"\"\"Browsing the web.\"\"\",\n", + " ),\n", + " ],\n", + " ),\n", + " types.Content(\n", + " role=\"user\",\n", + " parts=[\n", + " types.Part.from_text(text=\"\"\"INSERT_INPUT_HERE\"\"\"),\n", + " ],\n", + " ),\n", + " ]\n", + " tools = [\n", + " types.Tool(url_context=types.UrlContext()),\n", + " types.Tool(code_execution=types.ToolCodeExecution),\n", + " types.Tool(googleSearch=types.GoogleSearch(\n", + " )),\n", + " ]\n", + " generate_content_config = types.GenerateContentConfig(\n", + " thinking_config = types.ThinkingConfig(\n", + " thinking_budget=-1,\n", + " ),\n", + " tools=tools,\n", + " )\n", + "\n", + " for chunk in client.models.generate_content_stream(\n", + " model=model,\n", + " contents=contents,\n", + " config=generate_content_config,\n", + " ):\n", + " if (\n", + " chunk.candidates is None\n", + " or chunk.candidates[0].content is None\n", + " or chunk.candidates[0].content.parts is None\n", + " ):\n", + " continue\n", + " if chunk.candidates[0].content.parts[0].text:\n", + " print(chunk.candidates[0].content.parts[0].text, end=\"\")\n", + " if chunk.candidates[0].content.parts[0].executable_code:\n", + " print(chunk.candidates[0].content.parts[0].executable_code)\n", + " if chunk.candidates[0].content.parts[0].code_execution_result:\n", + " print(chunk.candidates[0].content.parts[0].code_execution_result)\n", + "\n", + "if __name__ == \"__main__\":\n", + " generate()\n" + ], + "execution_count": null, + "outputs": [] } ] } \ No newline at end of file From 7598a9ed91fd91f75f3e394bc2a19597e5011b81 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 06:19:52 +0600 Subject: [PATCH 07/28] Created using Colab --- Cosmic_Simulation_AI_and_Audio.ipynb | 732 +++++++++++++++++++++++++-- 1 file changed, 703 insertions(+), 29 deletions(-) diff --git a/Cosmic_Simulation_AI_and_Audio.ipynb b/Cosmic_Simulation_AI_and_Audio.ipynb index ccc3e6b..e1c8535 100644 --- a/Cosmic_Simulation_AI_and_Audio.ipynb +++ b/Cosmic_Simulation_AI_and_Audio.ipynb @@ -5,6 +5,7 @@ "colab": { "provenance": [], "history_visible": true, + "toc_visible": true, "include_colab_link": true }, "language_info": { @@ -46,28 +47,7 @@ "metadata": { "id": "_Gimwn69vh42" }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "code", - "metadata": { - "id": "ETeaa1m3pUFc" - }, - "source": [ - "/tmp/ipython-input-9294624.py in ()\n", - " 2 from google.colab import userdata\n", - " 3\n", - "----> 4 os.environ[\"GEMINI_API_🔑\"] = userdata.get(\"GOOGLE_API_🔑\")\n", - "\n", - "/usr/local/lib/python3.12/dist-packages/google/colab/userdata.py in get(🔑)\n", - " 66 raise TimeoutException(🔑)\n", - " 67 if not resp.get('exists', False):\n", - "---> 68 raise SecretNotFoundError(key)\n", - " 69 if not resp.get('access', False):\n", - " 70 raise NotebookAccessError(key)\n" - ], - "execution_count": null, + "execution_count": 276, "outputs": [] }, { @@ -85,7 +65,7 @@ "metadata": { "id": "HHKkGIgntjPg" }, - "execution_count": null, + "execution_count": 277, "outputs": [] }, { @@ -141,18 +121,45 @@ ")" ], "metadata": { - "id": "Qd6wJzyz_HtY" + "id": "Qd6wJzyz_HtY", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 106 + }, + "outputId": "030ebe64-9f4b-4428-8f43-cc0040649df6" }, - "execution_count": null, - "outputs": [] + "execution_count": 278, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + " Unrecognized magic \u001b[36m%load_ext\u001b[39m.\n", + "\n", + " Julia does not use the IPython \u001b[36m%magic\u001b[39m syntax. To interact with the IJulia\n", + " kernel, use \u001b[36mIJulia.somefunction(...)\u001b[39m, for example. Julia macros, string\n", + " macros, and functions can be used to accomplish most of the other\n", + " functionalities of IPython magics." + ], + "text/markdown": "Unrecognized magic `%load_ext`.\n\nJulia does not use the IPython `%magic` syntax. To interact with the IJulia kernel, use `IJulia.somefunction(...)`, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n", + "text/latex": "Unrecognized magic \\texttt{\\%load\\_ext}.\n\nJulia does not use the IPython \\texttt{\\%magic} syntax. To interact with the IJulia kernel, use \\texttt{IJulia.somefunction(...)}, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n\n" + }, + "metadata": {} + } + ] }, { "cell_type": "code", "metadata": { - "id": "IIK75iMVpUFe" + "id": "IIK75iMVpUFe", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 324 + }, + "outputId": "c7f23e31-c5fa-48ef-d2fd-6b263b82a9be" }, "source": [ - "# @title Default title text\n", + "# An Audio AI Galaxy Simulation\n", "variable_name = \"AURELION\" # @param {\"type\":\"string\"}\n", "# To run this code you need to install the following dependencies:\n", "# pip install google-genai\n", @@ -282,8 +289,675 @@ "if __name__ == \"__main__\":\n", " generate()\n" ], - "execution_count": null, + "execution_count": 292, + "outputs": [ + { + "output_type": "error", + "ename": "LoadError", + "evalue": "ArgumentError: Package base64 not found in current path.\n- Run `import Pkg; Pkg.add(\"base64\")` to install the base64 package.", + "traceback": [ + "ArgumentError: Package base64 not found in current path.\n- Run `import Pkg; Pkg.add(\"base64\")` to install the base64 package.", + "", + "Stacktrace:", + " [1] \u001b[0m\u001b[1mmacro expansion\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2296\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [2] \u001b[0m\u001b[1mmacro expansion\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mlock.jl:273\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [3] \u001b[0m\u001b[1m__require\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2271\u001b[24m\u001b[39m", + " [4] \u001b[0m\u001b[1m#invoke_in_world#3\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1089\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [5] \u001b[0m\u001b[1minvoke_in_world\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1086\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [6] \u001b[0m\u001b[1mrequire\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2260\u001b[24m\u001b[39m" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "120019bb" + }, + "source": [ + "# Task\n", + "Create a live, rotating 3D galaxy visualization using the provided image files: \"/content/List_of_galaxies.pdf\", \"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\", \"/content/galaxy-1756314020879.png\", and \"/content/nasa-shares-new-views.jpg\"." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "4caeabe4" + }, + "source": [ + "## Image preprocessing\n", + "\n", + "### Subtask:\n", + "Load the galaxy images and potentially extract features or create textures from them.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "7439d106" + }, + "source": [ + "**Reasoning**:\n", + "Load the images using OpenCV and store them in a list. PDF files cannot be directly loaded as images, so exclude it.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 324 + }, + "id": "05938e12", + "outputId": "a6720b26-1895-45eb-b6eb-3f83509216b4" + }, + "source": [ + "import cv2\n", + "\n", + "image_paths = [\n", + " \"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\",\n", + " \"/content/galaxy-1756314020879.png\",\n", + " \"/content/nasa-shares-new-views.jpg\"\n", + "]\n", + "\n", + "images = []\n", + "for path in image_paths:\n", + " img = cv2.imread(path)\n", + " if img is not None:\n", + " images.append(img)\n", + "\n", + "# No specific preprocessing is needed at this stage based on the instructions.\n", + "# Storing images in a list as requested.\n", + "\n", + "print(f\"Loaded {len(images)} images.\")" + ], + "execution_count": 280, + "outputs": [ + { + "output_type": "error", + "ename": "LoadError", + "evalue": "ArgumentError: Package cv2 not found in current path.\n- Run `import Pkg; Pkg.add(\"cv2\")` to install the cv2 package.", + "traceback": [ + "ArgumentError: Package cv2 not found in current path.\n- Run `import Pkg; Pkg.add(\"cv2\")` to install the cv2 package.", + "", + "Stacktrace:", + " [1] \u001b[0m\u001b[1mmacro expansion\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2296\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [2] \u001b[0m\u001b[1mmacro expansion\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mlock.jl:273\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [3] \u001b[0m\u001b[1m__require\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2271\u001b[24m\u001b[39m", + " [4] \u001b[0m\u001b[1m#invoke_in_world#3\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1089\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [5] \u001b[0m\u001b[1minvoke_in_world\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1086\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [6] \u001b[0m\u001b[1mrequire\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2260\u001b[24m\u001b[39m" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "d677b5b8" + }, + "source": [ + "**Reasoning**:\n", + "The previous command failed because the `cv2` package was not found. Install the package using pip.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 106 + }, + "id": "paLtPO5PHPXU", + "outputId": "d03c8533-fb5e-4457-f842-9dfdf722aaf3" + }, + "source": [ + "%pip install opencv-python" + ], + "execution_count": 281, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + " Unrecognized magic \u001b[36m%pip\u001b[39m.\n", + "\n", + " Julia does not use the IPython \u001b[36m%magic\u001b[39m syntax. To interact with the IJulia\n", + " kernel, use \u001b[36mIJulia.somefunction(...)\u001b[39m, for example. Julia macros, string\n", + " macros, and functions can be used to accomplish most of the other\n", + " functionalities of IPython magics." + ], + "text/markdown": "Unrecognized magic `%pip`.\n\nJulia does not use the IPython `%magic` syntax. To interact with the IJulia kernel, use `IJulia.somefunction(...)`, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n", + "text/latex": "Unrecognized magic \\texttt{\\%pip}.\n\nJulia does not use the IPython \\texttt{\\%magic} syntax. To interact with the IJulia kernel, use \\texttt{IJulia.somefunction(...)}, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n\n" + }, + "metadata": {} + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "a57b7825" + }, + "source": [ + "**Reasoning**:\n", + "The `%pip` magic command is not recognized. Install the package using the standard python command in a code cell.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 324 + }, + "id": "4bfaad5b", + "outputId": "58e88969-797f-4d84-885a-fbcbecd835f1" + }, + "source": [ + "import sys\n", + "!{sys.executable} -m pip install opencv-python" + ], + "execution_count": 282, + "outputs": [ + { + "output_type": "error", + "ename": "LoadError", + "evalue": "ArgumentError: Package sys not found in current path.\n- Run `import Pkg; Pkg.add(\"sys\")` to install the sys package.", + "traceback": [ + "ArgumentError: Package sys not found in current path.\n- Run `import Pkg; Pkg.add(\"sys\")` to install the sys package.", + "", + "Stacktrace:", + " [1] \u001b[0m\u001b[1mmacro expansion\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2296\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [2] \u001b[0m\u001b[1mmacro expansion\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mlock.jl:273\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [3] \u001b[0m\u001b[1m__require\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2271\u001b[24m\u001b[39m", + " [4] \u001b[0m\u001b[1m#invoke_in_world#3\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1089\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [5] \u001b[0m\u001b[1minvoke_in_world\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1086\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", + " [6] \u001b[0m\u001b[1mrequire\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", + "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2260\u001b[24m\u001b[39m" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "422d7795" + }, + "source": [ + "## Image preprocessing\n", + "\n", + "### Subtask:\n", + "Load the galaxy images and potentially extract features or create textures from them.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "2ee79f72" + }, + "source": [ + "## Image preprocessing\n", + "\n", + "### Subtask:\n", + "Load the galaxy images and potentially extract features or create textures from them.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "df756fbc" + }, + "source": [ + "## Summary:\n", + "\n", + "### Data Analysis Key Findings\n", + "\n", + "* The environment is running Julia, not Python, which prevents the use of Python libraries like OpenCV for image processing.\n", + "* Attempts to install `opencv-python` using `%pip` and `!{sys.executable} -m pip install` failed because the commands are Python-specific and not recognized in the Julia environment.\n", + "* The inability to load and process images using the intended Python libraries led to the failure of the subtask.\n", + "\n", + "### Insights or Next Steps\n", + "\n", + "* The task cannot be completed in the current Julia environment as it requires Python-based image processing capabilities.\n", + "* To proceed with the task, a Python environment with necessary image processing libraries like OpenCV would be required.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "6cf00e20" + }, + "source": [ + "# Task\n", + "Create a live, rotating 3D galaxy visualization with glowing ray stars that syncs with microphone audio input. Utilize the provided image files (\"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\", \"/content/galaxy-1756314020879.png\", \"/content/nasa-shares-new-views.jpg\") for textures and visual elements. The visualization should incorporate advanced and potentially novel coding techniques for complex motion, audio reactivity, and visual effects." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "7df38c9c" + }, + "source": [ + "## Image preprocessing\n", + "\n", + "### Subtask:\n", + "Load the galaxy images and potentially extract features or create textures from them.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "1f78b12a" + }, + "source": [ + "## Image preprocessing\n", + "\n", + "### Subtask:\n", + "Load the galaxy images and potentially extract features or create textures from them.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "fa905a47" + }, + "source": [ + "## Summary:\n", + "\n", + "### Data Analysis Key Findings\n", + "\n", + "* The environment is running a Julia kernel, which does not support the necessary Python image processing libraries (like OpenCV) required for image loading and processing.\n", + "* Consequently, the subtask of loading the galaxy images and creating textures could not be completed.\n", + "\n", + "### Insights or Next Steps\n", + "\n", + "* The current environment is unsuitable for image processing tasks needed for this visualization.\n", + "* To proceed, a different environment with support for image processing libraries (e.g., Python with OpenCV or Pillow) is required.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "4d90d5f1" + }, + "source": [ + "# Task\n", + "Create a live, rotating 3D galaxy visualization with glowing ray stars that are audio-reactive to microphone input. Implement mouse and touch screen rotation controls, and incorporate a \"phantom exploration\" feature to seek anomalies within the galaxy. Utilize the provided image data (\"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\", \"/content/galaxy-1756314020879.png\", \"/content/nasa-shares-new-views.jpg\") and the PDF data (\"/content/List_of_galaxies.pdf\") for potential textures, inspiration, or data points. The code should be highly advanced and incorporate novel techniques for visualization, audio reactivity, and the phantom exploration/anomaly seeking mechanism." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "77c2cb66" + }, + "source": [ + "## Image preprocessing\n", + "\n", + "### Subtask:\n", + "Load the galaxy images and potentially extract features or create textures from them.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "743cf70c" + }, + "source": [ + "## Advanced 3d model creation\n", + "\n", + "### Subtask:\n", + "Create a sophisticated 3D model that represents a galaxy structure, potentially incorporating particle systems or other complex geometries to represent stars and gas clouds.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "36e97811" + }, + "source": [ + "## Texture mapping and material design\n", + "\n", + "### Subtask:\n", + "Apply the processed galaxy images as textures and design materials that allow for glowing effects on stars.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "46492cbf" + }, + "source": [ + "## Audio input and processing\n", + "\n", + "### Subtask:\n", + "Implement a method to capture audio input from the microphone and process it to extract relevant features (e.g., amplitude, frequency).\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "0df9c504" + }, + "source": [ + "## Audio-reactive animation\n", + "\n", + "### Subtask:\n", + "Develop a system to control the glowing of stars and potentially other visual elements based on the processed audio data.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "be51d7e0" + }, + "source": [ + "## Adding complex motion\n", + "\n", + "### Subtask:\n", + "Implement rotation and potentially other complex movements and transformations to simulate a dynamic, live, rotating galaxy.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "6fe578cf" + }, + "source": [ + "## Shader development\n", + "\n", + "### Subtask:\n", + "Write custom shaders to create advanced visual effects, such as realistic glowing stars, nebulae, and potentially unique distortions or transformations based on audio input.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "87ea272a" + }, + "source": [ + "## User input handling\n", + "\n", + "### Subtask:\n", + "Implement mouse and touch screen event handling to allow users to rotate the galaxy visualization.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "6c1c5d11" + }, + "source": [ + "## Phantom exploration and anomaly seeking\n", + "\n", + "### Subtask:\n", + "Develop a mechanism for \"phantom exploration\" which could involve:\n", + "- Defining what constitutes an \"anomaly\" within the 3D galaxy model.\n", + "- Implementing a way to navigate through the galaxy, potentially with a \"phantom\" or camera that can explore.\n", + "- Developing an \"anomaly seeking\" algorithm or interactive process that guides the user or the phantom towards anomalies.\n", + "- Visualizing the phantom's path or the anomalies found.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "b5e606db" + }, + "source": [ + "## Optimization and performance\n", + "\n", + "### Subtask:\n", + "Optimize the code and 3D rendering to ensure smooth performance, especially with complex geometries, real-time audio processing, and interactive controls.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "8da3673f" + }, + "source": [ + "## Visualization\n", + "\n", + "### Subtask:\n", + "Display the animated, audio-reactive, and interactive 3D galaxy visualization with the phantom exploration feature.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "8fd42bf1" + }, + "source": [ + "## Documentation and explanation\n", + "\n", + "### Subtask:\n", + "Document the complex code and explain the novel techniques used, including the phantom exploration and anomaly seeking mechanism.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "8f6325fd" + }, + "source": [ + "**Reasoning**:\n", + "Document the complex code and explain the novel techniques used, including the phantom exploration and anomaly seeking mechanism based on the planned approach, acknowledging the environmental limitations.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "485c6dd1" + }, + "source": [ + "# Documentation for the Planned 3D Galaxy Visualization Project\n", + "\n", + "# Introduction\n", + "# This document outlines the planned approach for creating a live, rotating 3D galaxy visualization with glowing ray stars that are audio-reactive to microphone input.\n", + "# It also includes a \"phantom exploration\" feature to seek anomalies within the galaxy.\n", + "# Due to the limitations of the current Julia environment, the code for this project could not be fully implemented or executed.\n", + "# This documentation describes the intended architecture, libraries, and techniques that would have been used in a suitable Python environment.\n", + "\n", + "# 1. Image Preprocessing\n", + "# Intended Approach: Load galaxy images and extract features or create textures.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - OpenCV (`cv2`): For loading and basic image manipulation (resizing, format conversion).\n", + "# - Pillow (PIL): Another option for image loading and processing.\n", + "# - Potential Feature Extraction: Depending on the specific visual effects, techniques like edge detection, color analysis, or texture analysis could be used.\n", + "# Contribution to Visualization: The images would serve as textures for the galaxy model, stars, or background elements, adding visual detail and realism.\n", + "\n", + "# 2. Advanced 3D Model Creation\n", + "# Intended Approach: Create a sophisticated 3D model representing a galaxy structure.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - PyOpenGL or moderngl: For low-level OpenGL access to build complex geometries.\n", + "# - pyglet or Pygame: For creating an OpenGL context and handling windows/events.\n", + "# - Alternatively, a higher-level library like Panda3D or Kivy with its 3D capabilities could be explored, though they might offer less fine-grained control.\n", + "# - Techniques:\n", + "# - Particle Systems: To represent individual stars and gas clouds, allowing for dynamic behavior and large numbers of elements.\n", + "# - Procedural Generation: To create the spiral arms and overall structure of the galaxy based on mathematical models.\n", + "# - Mesh Creation: Building the underlying structure of the galaxy arms or central bulge as meshes.\n", + "# Contribution to Visualization: Provides the fundamental structure and visual elements of the galaxy.\n", + "\n", + "# 3. Texture Mapping and Material Design\n", + "# Intended Approach: Apply processed galaxy images as textures and design materials for glowing effects.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - PyOpenGL or moderngl: For binding textures to 3D models and defining material properties.\n", + "# - Custom Shaders (GLSL): Essential for creating advanced materials, including:\n", + "# - Texture mapping: Applying the loaded images onto the 3D geometry.\n", + "# - Emissive properties: Making stars glow.\n", + "# - Blending: Combining different textures or effects.\n", + "# Contribution to Visualization: Adds visual richness, detail, and special effects like glowing stars.\n", + "\n", + "# 4. Audio Input and Processing\n", + "# Intended Approach: Capture microphone audio and extract relevant features.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - sounddevice: For accessing and capturing audio from the microphone.\n", + "# - NumPy: For numerical operations on audio data.\n", + "# - SciPy: For signal processing techniques (e.g., FFT for frequency analysis).\n", + "# - Techniques:\n", + "# - Amplitude analysis: Measuring the overall loudness of the audio.\n", + "# - Frequency analysis (FFT): Identifying dominant frequencies in the audio.\n", + "# - Feature extraction: Calculating metrics like spectral centroid, flux, etc., depending on the desired audio-reactive effects.\n", + "# Contribution to Visualization: Provides the real-time data stream that drives the audio-reactive animations.\n", + "\n", + "# 5. Audio-Reactive Animation\n", + "# Intended Approach: Control visual elements (e.g., star glowing) based on processed audio data.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - Integration with 3D library (PyOpenGL, moderngl, etc.): To update visual properties based on audio features.\n", + "# - Techniques:\n", + "# - Mapping audio features to visual parameters: For example, mapping amplitude to star brightness or frequency to color.\n", + "# - Animation curves and interpolation: To create smooth transitions in visual effects.\n", + "# - Real-time updates: Updating the visualization in sync with the audio input.\n", + "# Contribution to Visualization: Creates a dynamic and immersive experience where the galaxy reacts to sound.\n", + "\n", + "# 6. Adding Complex Motion\n", + "# Intended Approach: Implement rotation and other complex movements for a dynamic galaxy.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - 3D transformation matrices (using NumPy or a 3D library's built-in functions): For rotation, translation, and scaling.\n", + "# - Techniques:\n", + "# - Quaternions: For smooth and intuitive rotations.\n", + "# - Animation loops: Continuously updating the transformation matrices over time.\n", + "# - Potential for physics simulations: To create more realistic or dynamic movements (though this adds complexity).\n", + "# Contribution to Visualization: Makes the galaxy feel alive and allows for exploration from different angles.\n", + "\n", + "# 7. Shader Development\n", + "# Intended Approach: Write custom shaders for advanced visual effects.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - GLSL (OpenGL Shading Language): The language for writing vertex, fragment, and potentially geometry shaders.\n", + "# - Integration with 3D library (PyOpenGL, moderngl): To compile and use shaders.\n", + "# - Techniques:\n", + "# - Vertex Shaders: To manipulate the position and other attributes of vertices (e.g., for procedural effects or distortions).\n", + "# - Fragment Shaders: To determine the color of each pixel, enabling effects like glowing, coloring based on audio, and complex lighting.\n", + "# - Noise functions (e.g., Perlin noise): For generating organic textures or motion.\n", + "# Contribution to Visualization: Enables high-quality, customizable visual effects that are essential for a compelling galaxy visualization.\n", + "\n", + "# 8. User Input Handling\n", + "# Intended Approach: Implement mouse and touch screen controls for rotation.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - pyglet or Pygame: For handling window events, including mouse and touch input.\n", + "# - Techniques:\n", + "# - Event listeners: To capture mouse movements, clicks, and touch events.\n", + "# - Mapping input to transformations: Translating mouse/touch input into rotations of the galaxy model.\n", + "# - Camera control: Adjusting the camera's position and orientation based on user input.\n", + "# Contribution to Visualization: Allows users to interact with and explore the galaxy.\n", + "\n", + "# 9. Phantom Exploration and Anomaly Seeking\n", + "# Intended Approach: Develop a mechanism for \"phantom exploration\" and \"anomaly seeking\".\n", + "# This is a novel feature with the following intended components:\n", + "# - Defining \"Anomalies\": Anomalies could be defined in several ways within the 3D galaxy model:\n", + "# - Statistical outliers: Stars with unusual properties (e.g., extreme brightness, velocity, or age if such data were available).\n", + "# - Spatial clusters: Regions with a higher density of stars than expected.\n", + "# - Unique textures or visual features: Specific areas of the galaxy model or textures that are visually distinct.\n", + "# - Potentially, anomalies could be procedurally generated or placed at specific coordinates.\n", + "# - Phantom Navigation: A \"phantom\" would represent a point of interest or a camera path that can move through the galaxy.\n", + "# - Autonomous Navigation: The phantom could follow a predefined path, a random walk, or a path guided by the anomaly seeking algorithm.\n", + "# - User-Controlled Navigation: Users could potentially guide the phantom's movement.\n", + "# - Anomaly Seeking Algorithm: This algorithm would guide the phantom or highlight anomalies for the user.\n", + "# - Spatial partitioning (e.g., Octrees or K-d trees): To efficiently search for anomalies within the 3D space.\n", + "# - Proximity search: Finding anomalies within a certain radius of the phantom.\n", + "# - Feature comparison: Comparing the properties of stars or regions to the definition of an anomaly.\n", + "# - Pathfinding algorithms (e.g., A* or Dijkstra's): To calculate a path for the phantom to reach a discovered anomaly.\n", + "# - Visual cues: Highlighting anomalies in the visualization (e.g., changing their color, size, or adding markers).\n", + "# - Visualizing Phantom's Path/Anomalies:\n", + "# - Rendering a trail behind the phantom.\n", + "# - Drawing lines or markers to indicate the location of anomalies.\n", + "# - Changing the camera view to focus on discovered anomalies.\n", + "# Contribution to Visualization: Adds a unique interactive and exploratory element, encouraging users to delve deeper into the galaxy.\n", + "\n", + "# 10. Optimization and Performance\n", + "# Intended Approach: Optimize code and rendering for smooth performance.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - Techniques applied throughout the development process:\n", + "# - Level of Detail (LOD) for distant objects.\n", + "# - Frustum culling to avoid rendering off-screen objects.\n", + "# - Efficient data structures (e.g., for managing millions of stars).\n", + "# - Batching draw calls.\n", + "# - Utilizing shaders for GPU acceleration of visual effects.\n", + "# - Optimizing audio processing to minimize latency.\n", + "# Contribution to Visualization: Ensures a smooth and responsive experience, even with a complex visualization.\n", + "\n", + "# 11. Visualization\n", + "# Intended Approach: Display the animated, audio-reactive, and interactive 3D galaxy visualization.\n", + "# Libraries/Techniques (in a Python environment):\n", + "# - A 3D rendering loop using PyOpenGL, moderngl, or a higher-level library.\n", + "# - Integrating all the components: The 3D model, textures, materials, audio processing, animation logic, user input handling, and phantom exploration mechanism would be combined within the rendering loop.\n", + "# Contribution to Visualization: The final output, the interactive and dynamic 3D galaxy visualization.\n", + "\n", + "# Novel Techniques:\n", + "# - Integration of real-time microphone audio analysis to drive complex visual effects in a 3D environment.\n", + "# - The \"phantom exploration\" and \"anomaly seeking\" mechanism as a novel way to interact with and explore a procedurally generated or data-driven 3D space.\n", + "# - Potentially advanced shader techniques for realistic or stylized rendering of stars and nebulae based on audio input.\n", + "\n", + "# Conclusion:\n", + "# This document outlines the planned approach for creating a sophisticated 3D galaxy visualization with advanced features.\n", + "# The implementation was not possible in the current Julia environment due to the lack of necessary libraries for 3D graphics, audio processing, and user interaction.\n", + "# The descriptions provided are based on how this project would be approached in a suitable Python environment with access to relevant libraries." + ], + "execution_count": 283, "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "f9770d7a" + }, + "source": [ + "## Summary:\n", + "\n", + "### Data Analysis Key Findings\n", + "\n", + "* The environment used for the analysis is Julia, which fundamentally lacks the necessary libraries and frameworks for advanced 3D graphics rendering, image processing, real-time audio input/processing, and complex user interaction handling required for the task.\n", + "* Consequently, none of the subtasks, including image preprocessing, 3D model creation, texture mapping, audio processing, animation, shader development, user input handling, phantom exploration, optimization, and visualization, could be completed.\n", + "* The \"phantom exploration and anomaly seeking\" feature was conceptualized to involve defining anomalies (e.g., statistical outliers, spatial clusters), implementing phantom navigation (autonomous or user-controlled), and developing an anomaly-seeking algorithm using techniques like spatial partitioning and proximity search.\n", + "* Documentation of the planned project outlined a comprehensive approach using Python libraries (like OpenCV, PyOpenGL, sounddevice, NumPy, SciPy) which were not available in the execution environment.\n", + "\n", + "### Insights or Next Steps\n", + "\n", + "* The project requires a programming environment with robust support for 3D graphics APIs (like OpenGL), real-time audio processing, and comprehensive input handling. A Python environment with libraries such as PyOpenGL, sounddevice, and relevant visualization tools would be a more suitable choice.\n", + "* Future attempts should focus on setting up a development environment that can accommodate the technical demands of the project before attempting implementation.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "5026c6a1" + }, + "source": [ + "## Summary:\n", + "\n", + "### Data Analysis Key Findings\n", + "\n", + "* The environment used for the analysis is Julia, which fundamentally lacks the necessary libraries and frameworks for advanced 3D graphics rendering, image processing, real-time audio input/processing, and complex user interaction handling required for the task.\n", + "* Consequently, none of the subtasks, including image preprocessing, 3D model creation, texture mapping, audio processing, animation, shader development, user input handling, phantom exploration, optimization, and visualization, could be completed.\n", + "* The \"phantom exploration and anomaly seeking\" feature was conceptualized to involve defining anomalies (e.g., statistical outliers, spatial clusters), implementing phantom navigation (autonomous or user-controlled), and developing an anomaly-seeking algorithm using techniques like spatial partitioning and proximity search.\n", + "* Documentation of the planned project outlined a comprehensive approach using Python libraries (like OpenCV, PyOpenGL, sounddevice, NumPy, SciPy) which were not available in the execution environment.\n", + "\n", + "### Insights or Next Steps\n", + "\n", + "* The project requires a programming environment with robust support for 3D graphics APIs (like OpenGL), real-time audio processing, and comprehensive input handling. A Python environment with libraries such as PyOpenGL, sounddevice, and relevant visualization tools would be a more suitable choice.\n", + "* Future attempts should focus on setting up a development environment that can accommodate the technical demands of the project before attempting implementation." + ] } ] } \ No newline at end of file From 2cc07900028b2d7d97b55f9b5624815e139f43e9 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 06:31:12 +0600 Subject: [PATCH 08/28] Created using Colab --- Cosmic_Simulation_AI_and_Audio.ipynb | 496 +++++++++++++-------------- 1 file changed, 235 insertions(+), 261 deletions(-) diff --git a/Cosmic_Simulation_AI_and_Audio.ipynb b/Cosmic_Simulation_AI_and_Audio.ipynb index e1c8535..b5550d7 100644 --- a/Cosmic_Simulation_AI_and_Audio.ipynb +++ b/Cosmic_Simulation_AI_and_Audio.ipynb @@ -5,6 +5,9 @@ "colab": { "provenance": [], "history_visible": true, + "collapsed_sections": [ + "Gc4BqPpVpUFa" + ], "toc_visible": true, "include_colab_link": true }, @@ -47,7 +50,7 @@ "metadata": { "id": "_Gimwn69vh42" }, - "execution_count": 276, + "execution_count": 533, "outputs": [] }, { @@ -65,7 +68,7 @@ "metadata": { "id": "HHKkGIgntjPg" }, - "execution_count": 277, + "execution_count": 534, "outputs": [] }, { @@ -126,9 +129,9 @@ "base_uri": "https://localhost:8080/", "height": 106 }, - "outputId": "030ebe64-9f4b-4428-8f43-cc0040649df6" + "outputId": "f091be2b-9b79-4c7f-f31d-ff108c676a2b" }, - "execution_count": 278, + "execution_count": 535, "outputs": [ { "output_type": "display_data", @@ -150,170 +153,12 @@ }, { "cell_type": "code", + "source": [], "metadata": { - "id": "IIK75iMVpUFe", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 324 - }, - "outputId": "c7f23e31-c5fa-48ef-d2fd-6b263b82a9be" - }, - "source": [ - "# An Audio AI Galaxy Simulation\n", - "variable_name = \"AURELION\" # @param {\"type\":\"string\"}\n", - "# To run this code you need to install the following dependencies:\n", - "# pip install google-genai\n", - "\n", - "import base64\n", - "import os\n", - "from google import genai\n", - "from google.genai import types\n", - "\n", - "\n", - "def generate():\n", - " client = genai.Client(\n", - " api_key=os.environ.get(\"GEMINI_API_KEY\"),\n", - " )\n", - "\n", - " model = \"gemini-2.5-flash\"\n", - " contents = [\n", - " types.Content(\n", - " role=\"user\",\n", - " parts=[\n", - " types.Part.from_text(text=\"\"\"\n", - "\n", - "\n", - "https://cosmic-pulse-an-audio-reactive-galaxy-184571359742.us-west1.run.app/\n", - "2025-08-28T21:04:39+00:00\n", - "\n", - "\"\"\"),\n", - " ],\n", - " ),\n", - " types.Content(\n", - " role=\"model\",\n", - " parts=[\n", - " types.Part.from_text(text=\"\"\"**Analyzing Sitemap URLs**\n", - "\n", - "I've extracted the URLs from the XML sitemap provided, specifically focusing on the `` tags. My next step is to begin browsing these identified URLs.\n", - "\n", - "\n", - "\"\"\"),\n", - " types.Part.from_text(text=\"\"\"\n", - "The page \\\"Cosmic Simulation\\\" is a web application that appears to be a 3D visualization of a \\\"cosmic web\\\" or galaxy, with interactive elements and audio reactivity. It allows users to:\n", - "\n", - "* **Generate new cosmos**: Create new cosmic web structures with AI-powered configurations.\n", - "* **Summon probes**: Dispatch AI-guided deep space probes to random stars within the galaxy, which then travel to their target and provide telemetry.\n", - "* **Interact with the simulation**: Click on individual stars to get a poetic, cosmic observation of their properties (color, velocity, region) from an AI.\n", - "* **Control the camera**: Manually control the camera's position and target, or activate an \\\"autopilot\\\" to automatically focus on a random star.\n", - "* **Adjust voice settings**: Change the voice, pitch, and rate of the AI's spoken responses.\n", - "* **Observe system telemetry**: View real-time data such as the current mode (IDLE, MANEUVERING, AUTOPILOT), camera position, velocity, and target, as well as general system messages.\n", - "\n", - "The application uses Three.js for 3D rendering and appears to integrate with a Gemini AI model for generating descriptions and probe missions. It also incorporates audio analysis to create visual effects that react to sound.\"\"\"),\n", - " ],\n", - " ),\n", - " types.Content(\n", - " role=\"user\",\n", - " parts=[\n", - " types.Part.from_text(text=\"\"\"Include \n", - "\n", - "\n", - "https://aurelion-an-audio-ai-galaxy-simulation-184571359742.us-west1.run.app/\n", - "2025-08-28T21:33:03+00:00\n", - "\n", - "\"\"\"),\n", - " ],\n", - " ),\n", - " types.Content(\n", - " role=\"model\",\n", - " parts=[\n", - " types.Part.from_text(text=\"\"\"**Analyzing the Sitemap Structure**\n", - "\n", - "I've begun examining the XML structure to understand how the sitemap is organized. Initial observations point towards a standard sitemap format, though the specific content related to the provided URL `https://aurelion-an-audio-ai-galaxy-simulation-184571359742.us-west1.run.app/` needs further investigation. My focus is now on identifying key elements and attributes within the XML that relate to this particular endpoint.\n", - "\n", - "\n", - "**Browsing the Provided URL**\n", - "\n", - "I'm now browsing the URL provided to understand its content. It appears to be an application. My next step will be to summarize my findings, similar to the process used for the sitemap analysis. I'll focus on identifying key features and functionalities based on the app's behavior and the code I can access. I'm keen to see if this aligns with the initial sitemap analysis and expectations.\n", - "\n", - "\n", - "\"\"\"),\n", - " types.Part.from_executable_code(\n", - " code=\"\"\"print(browse(urls=[\\\"https://aurelion-an-audio-ai-galaxy-simulation-184571359742.us-west1.run.app/\\\"]))\n", - "\"\"\",\n", - " language=types.Language.PYTHON,\n", - " ),\n", - " types.Part.from_code_execution_result(\n", - " outcome=types.Outcome.OUTCOME_OK,\n", - " output=\"\"\"Browsing the web.\"\"\",\n", - " ),\n", - " ],\n", - " ),\n", - " types.Content(\n", - " role=\"user\",\n", - " parts=[\n", - " types.Part.from_text(text=\"\"\"INSERT_INPUT_HERE\"\"\"),\n", - " ],\n", - " ),\n", - " ]\n", - " tools = [\n", - " types.Tool(url_context=types.UrlContext()),\n", - " types.Tool(code_execution=types.ToolCodeExecution),\n", - " types.Tool(googleSearch=types.GoogleSearch(\n", - " )),\n", - " ]\n", - " generate_content_config = types.GenerateContentConfig(\n", - " thinking_config = types.ThinkingConfig(\n", - " thinking_budget=-1,\n", - " ),\n", - " tools=tools,\n", - " )\n", - "\n", - " for chunk in client.models.generate_content_stream(\n", - " model=model,\n", - " contents=contents,\n", - " config=generate_content_config,\n", - " ):\n", - " if (\n", - " chunk.candidates is None\n", - " or chunk.candidates[0].content is None\n", - " or chunk.candidates[0].content.parts is None\n", - " ):\n", - " continue\n", - " if chunk.candidates[0].content.parts[0].text:\n", - " print(chunk.candidates[0].content.parts[0].text, end=\"\")\n", - " if chunk.candidates[0].content.parts[0].executable_code:\n", - " print(chunk.candidates[0].content.parts[0].executable_code)\n", - " if chunk.candidates[0].content.parts[0].code_execution_result:\n", - " print(chunk.candidates[0].content.parts[0].code_execution_result)\n", - "\n", - "if __name__ == \"__main__\":\n", - " generate()\n" - ], - "execution_count": 292, - "outputs": [ - { - "output_type": "error", - "ename": "LoadError", - "evalue": "ArgumentError: Package base64 not found in current path.\n- Run `import Pkg; Pkg.add(\"base64\")` to install the base64 package.", - "traceback": [ - "ArgumentError: Package base64 not found in current path.\n- Run `import Pkg; Pkg.add(\"base64\")` to install the base64 package.", - "", - "Stacktrace:", - " [1] \u001b[0m\u001b[1mmacro expansion\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2296\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [2] \u001b[0m\u001b[1mmacro expansion\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mlock.jl:273\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [3] \u001b[0m\u001b[1m__require\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2271\u001b[24m\u001b[39m", - " [4] \u001b[0m\u001b[1m#invoke_in_world#3\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1089\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [5] \u001b[0m\u001b[1minvoke_in_world\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1086\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [6] \u001b[0m\u001b[1mrequire\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2260\u001b[24m\u001b[39m" - ] - } - ] + "id": "8HR9qLhAOlsd" + }, + "execution_count": 536, + "outputs": [] }, { "cell_type": "markdown", @@ -325,6 +170,15 @@ "Create a live, rotating 3D galaxy visualization using the provided image files: \"/content/List_of_galaxies.pdf\", \"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\", \"/content/galaxy-1756314020879.png\", and \"/content/nasa-shares-new-views.jpg\"." ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "EokR_kWwOnGW" + }, + "execution_count": 537, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -337,6 +191,15 @@ "Load the galaxy images and potentially extract features or create textures from them.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "VK1djxvoOitN" + }, + "execution_count": 538, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -348,62 +211,6 @@ "\n" ] }, - { - "cell_type": "code", - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 324 - }, - "id": "05938e12", - "outputId": "a6720b26-1895-45eb-b6eb-3f83509216b4" - }, - "source": [ - "import cv2\n", - "\n", - "image_paths = [\n", - " \"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\",\n", - " \"/content/galaxy-1756314020879.png\",\n", - " \"/content/nasa-shares-new-views.jpg\"\n", - "]\n", - "\n", - "images = []\n", - "for path in image_paths:\n", - " img = cv2.imread(path)\n", - " if img is not None:\n", - " images.append(img)\n", - "\n", - "# No specific preprocessing is needed at this stage based on the instructions.\n", - "# Storing images in a list as requested.\n", - "\n", - "print(f\"Loaded {len(images)} images.\")" - ], - "execution_count": 280, - "outputs": [ - { - "output_type": "error", - "ename": "LoadError", - "evalue": "ArgumentError: Package cv2 not found in current path.\n- Run `import Pkg; Pkg.add(\"cv2\")` to install the cv2 package.", - "traceback": [ - "ArgumentError: Package cv2 not found in current path.\n- Run `import Pkg; Pkg.add(\"cv2\")` to install the cv2 package.", - "", - "Stacktrace:", - " [1] \u001b[0m\u001b[1mmacro expansion\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2296\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [2] \u001b[0m\u001b[1mmacro expansion\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mlock.jl:273\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [3] \u001b[0m\u001b[1m__require\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2271\u001b[24m\u001b[39m", - " [4] \u001b[0m\u001b[1m#invoke_in_world#3\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1089\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [5] \u001b[0m\u001b[1minvoke_in_world\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1086\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [6] \u001b[0m\u001b[1mrequire\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2260\u001b[24m\u001b[39m" - ] - } - ] - }, { "cell_type": "markdown", "metadata": { @@ -423,12 +230,12 @@ "height": 106 }, "id": "paLtPO5PHPXU", - "outputId": "d03c8533-fb5e-4457-f842-9dfdf722aaf3" + "outputId": "c5feceae-f47c-4e2f-9027-e1dd728f807a" }, "source": [ "%pip install opencv-python" ], - "execution_count": 281, + "execution_count": 539, "outputs": [ { "output_type": "display_data", @@ -448,6 +255,15 @@ } ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "xERdbQehOc9t" + }, + "execution_count": 540, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -461,43 +277,12 @@ }, { "cell_type": "code", + "source": [], "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 324 - }, - "id": "4bfaad5b", - "outputId": "58e88969-797f-4d84-885a-fbcbecd835f1" + "id": "oomPQ7gAOhak" }, - "source": [ - "import sys\n", - "!{sys.executable} -m pip install opencv-python" - ], - "execution_count": 282, - "outputs": [ - { - "output_type": "error", - "ename": "LoadError", - "evalue": "ArgumentError: Package sys not found in current path.\n- Run `import Pkg; Pkg.add(\"sys\")` to install the sys package.", - "traceback": [ - "ArgumentError: Package sys not found in current path.\n- Run `import Pkg; Pkg.add(\"sys\")` to install the sys package.", - "", - "Stacktrace:", - " [1] \u001b[0m\u001b[1mmacro expansion\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2296\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [2] \u001b[0m\u001b[1mmacro expansion\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mlock.jl:273\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [3] \u001b[0m\u001b[1m__require\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2271\u001b[24m\u001b[39m", - " [4] \u001b[0m\u001b[1m#invoke_in_world#3\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1089\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [5] \u001b[0m\u001b[1minvoke_in_world\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4messentials.jl:1086\u001b[24m\u001b[39m\u001b[90m [inlined]\u001b[39m", - " [6] \u001b[0m\u001b[1mrequire\u001b[22m\u001b[0m\u001b[1m(\u001b[22m\u001b[90minto\u001b[39m::\u001b[0mModule, \u001b[90mmod\u001b[39m::\u001b[0mSymbol\u001b[0m\u001b[1m)\u001b[22m", - "\u001b[90m @\u001b[39m \u001b[90mBase\u001b[39m \u001b[90m./\u001b[39m\u001b[90m\u001b[4mloading.jl:2260\u001b[24m\u001b[39m" - ] - } - ] + "execution_count": 541, + "outputs": [] }, { "cell_type": "markdown", @@ -523,6 +308,24 @@ "Load the galaxy images and potentially extract features or create textures from them.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "nC-EQN2iOgDE" + }, + "execution_count": 542, + "outputs": [] + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "VPtTWBADOfu9" + }, + "execution_count": 543, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -553,6 +356,15 @@ "Create a live, rotating 3D galaxy visualization with glowing ray stars that syncs with microphone audio input. Utilize the provided image files (\"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\", \"/content/galaxy-1756314020879.png\", \"/content/nasa-shares-new-views.jpg\") for textures and visual elements. The visualization should incorporate advanced and potentially novel coding techniques for complex motion, audio reactivity, and visual effects." ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "6QWGZk0xOrQG" + }, + "execution_count": 544, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -565,6 +377,15 @@ "Load the galaxy images and potentially extract features or create textures from them.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "HQq0lOvdOsEu" + }, + "execution_count": 545, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -577,6 +398,15 @@ "Load the galaxy images and potentially extract features or create textures from them.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "Sw3XV9tKOs_O" + }, + "execution_count": 546, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -606,6 +436,15 @@ "Create a live, rotating 3D galaxy visualization with glowing ray stars that are audio-reactive to microphone input. Implement mouse and touch screen rotation controls, and incorporate a \"phantom exploration\" feature to seek anomalies within the galaxy. Utilize the provided image data (\"/content/Hubble-Space-Telescope-Galaxy-Collection.jpg\", \"/content/galaxy-1756314020879.png\", \"/content/nasa-shares-new-views.jpg\") and the PDF data (\"/content/List_of_galaxies.pdf\") for potential textures, inspiration, or data points. The code should be highly advanced and incorporate novel techniques for visualization, audio reactivity, and the phantom exploration/anomaly seeking mechanism." ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "j5Up4iogOuTm" + }, + "execution_count": 547, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -618,6 +457,15 @@ "Load the galaxy images and potentially extract features or create textures from them.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "cW5EIi4EOvCu" + }, + "execution_count": 548, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -630,6 +478,15 @@ "Create a sophisticated 3D model that represents a galaxy structure, potentially incorporating particle systems or other complex geometries to represent stars and gas clouds.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "Kn2-TSJ2Ov6v" + }, + "execution_count": 549, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -642,6 +499,15 @@ "Apply the processed galaxy images as textures and design materials that allow for glowing effects on stars.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "1xIVpO6lOwg3" + }, + "execution_count": 550, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -666,6 +532,15 @@ "Develop a system to control the glowing of stars and potentially other visual elements based on the processed audio data.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "yUdzcWyCOyE3" + }, + "execution_count": 551, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -678,6 +553,15 @@ "Implement rotation and potentially other complex movements and transformations to simulate a dynamic, live, rotating galaxy.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "EAiDBHcpOyyH" + }, + "execution_count": 552, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -690,6 +574,15 @@ "Write custom shaders to create advanced visual effects, such as realistic glowing stars, nebulae, and potentially unique distortions or transformations based on audio input.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "JyXLd_uoOz6f" + }, + "execution_count": 553, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -702,6 +595,24 @@ "Implement mouse and touch screen event handling to allow users to rotate the galaxy visualization.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "S6fzvdD5O1gH" + }, + "execution_count": 554, + "outputs": [] + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "7Lj0S65PO2nQ" + }, + "execution_count": 555, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -718,6 +629,15 @@ "- Visualizing the phantom's path or the anomalies found.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "v_NK4W7EO334" + }, + "execution_count": 556, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -730,6 +650,15 @@ "Optimize the code and 3D rendering to ensure smooth performance, especially with complex geometries, real-time audio processing, and interactive controls.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "1-j61bg7O5FI" + }, + "execution_count": 557, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -742,6 +671,15 @@ "Display the animated, audio-reactive, and interactive 3D galaxy visualization with the phantom exploration feature.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "dUojeklHO56A" + }, + "execution_count": 558, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -765,6 +703,15 @@ "\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "_TIs_lY3O6xf" + }, + "execution_count": 559, + "outputs": [] + }, { "cell_type": "code", "metadata": { @@ -914,7 +861,16 @@ "# The implementation was not possible in the current Julia environment due to the lack of necessary libraries for 3D graphics, audio processing, and user interaction.\n", "# The descriptions provided are based on how this project would be approached in a suitable Python environment with access to relevant libraries." ], - "execution_count": 283, + "execution_count": 560, + "outputs": [] + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "pa7fx_3IO9yJ" + }, + "execution_count": 561, "outputs": [] }, { @@ -938,6 +894,15 @@ "* Future attempts should focus on setting up a development environment that can accommodate the technical demands of the project before attempting implementation.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "mWy7fGpuO_TA" + }, + "execution_count": 562, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -958,6 +923,15 @@ "* The project requires a programming environment with robust support for 3D graphics APIs (like OpenGL), real-time audio processing, and comprehensive input handling. A Python environment with libraries such as PyOpenGL, sounddevice, and relevant visualization tools would be a more suitable choice.\n", "* Future attempts should focus on setting up a development environment that can accommodate the technical demands of the project before attempting implementation." ] + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "yYKbRNvXPAug" + }, + "execution_count": 563, + "outputs": [] } ] } \ No newline at end of file From 9776ad32e0bfab15bb02f323763b87842962f85c Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 07:45:35 +0600 Subject: [PATCH 09/28] Created using Colab --- ...Getting_started_with_google_colab_ai.ipynb | 471 ++++++++++++++++++ 1 file changed, 471 insertions(+) create mode 100644 notebooks/Getting_started_with_google_colab_ai.ipynb diff --git a/notebooks/Getting_started_with_google_colab_ai.ipynb b/notebooks/Getting_started_with_google_colab_ai.ipynb new file mode 100644 index 0000000..5029278 --- /dev/null +++ b/notebooks/Getting_started_with_google_colab_ai.ipynb @@ -0,0 +1,471 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "metadata": { + "id": "wdj9RMfoGPC2" + }, + "cell_type": "markdown", + "source": [ + "Colab is making it easier than ever to integrate powerful Generative AI capabilities into your projects. We are launching public preview for a simple and intuitive Python library (google.colab.ai) to access state-of-the-art language models directly within Pro and Pro+ subscriber Colab environments. This means subscribers can spend less time on configuration and set up and more time bringing their ideas to life. With just a few lines of code, you can now perform a variety of tasks:\n", + "- Generate text\n", + "- Translate languages\n", + "- Write creative content\n", + "- Categorize text\n", + "\n", + "Happy Coding!\n", + "\n", + "\n", + "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/googlecolab/colabtools/blob/main/notebooks/Getting_started_with_google_colab_ai.ipynb)" + ] + }, + { + "metadata": { + "id": "Ucchuu5vV3Jp", + "outputId": "7b4b87b2-d2ff-41d5-9a10-2465e094a5ef", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "cell_type": "code", + "source": [ + "# @title List available models\n", + "from google.colab import ai\n", + "\n", + "ai.list_models()" + ], + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "['google/gemini-2.0-flash',\n", + " 'google/gemini-2.0-flash-lite',\n", + " 'google/gemini-2.5-flash',\n", + " 'google/gemini-2.5-flash-lite',\n", + " 'google/gemini-2.5-pro',\n", + " 'google/gemma-3-12b',\n", + " 'google/gemma-3-1b',\n", + " 'google/gemma-3-27b',\n", + " 'google/gemma-3-4b']" + ] + }, + "metadata": {}, + "execution_count": 1 + } + ], + "execution_count": 1 + }, + { + "metadata": { + "id": "LjfCGEpzDsD9" + }, + "cell_type": "markdown", + "source": [ + "Choosing a Model\n", + "The model names give you a hint about their capabilities and intended use:\n", + "\n", + "Pro: These are the most capable models, ideal for complex reasoning, creative tasks, and detailed analysis.\n", + "\n", + "Flash: These models are optimized for high speed and efficiency, making them great for summarization, chat applications, and tasks requiring rapid responses.\n", + "\n", + "Gemma: These are lightweight, open-weight models suitable for a variety of text generation tasks and are great for experimentation." + ] + }, + { + "metadata": { + "id": "R7taibpc7x2l", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "71c9fbea-5765-4159-b765-b77c8b4ab34d" + }, + "cell_type": "code", + "source": [ + "# @title Simple batch generation example\n", + "# Only text-to-text input/output is supported\n", + "from google.colab import ai\n", + "\n", + "response = ai.generate_text(\"What is the capital of France?\")\n", + "print(response)" + ], + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "The capital of France is **Paris**.\n", + "\n" + ] + } + ], + "execution_count": null + }, + { + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "NHO9VzO9AHZP", + "outputId": "f5667fab-a9f3-487f-cff1-5f5ac1549366" + }, + "cell_type": "code", + "source": [ + "# @title Choose a different model\n", + "from google.colab import ai\n", + "\n", + "response = ai.generate_text(\"What is the capital of England\", model_name='google/gemini-2.0-flash-lite')\n", + "print(response)" + ], + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "The capital of England is **London**.\n", + "\n" + ] + } + ], + "execution_count": null + }, + { + "metadata": { + "id": "ysDdFbH_Dgtz" + }, + "cell_type": "markdown", + "source": [ + "For longer text generations, you can stream the response. This displays the output token by token as it's generated, rather than waiting for the entire response to complete. This provides a more interactive and responsive experience. To enable this, simply set stream=True." + ] + }, + { + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "4BNgxiB6--_5", + "outputId": "d3b34d85-1283-4226-861c-73ff431000f7" + }, + "cell_type": "code", + "source": [ + "# @title Simple streaming example\n", + "from google.colab import ai\n", + "\n", + "stream = ai.generate_text(\"Tell me a short story.\", stream=True)\n", + "for text in stream:\n", + " print(text, end='')" + ], + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "The lighthouse keeper, Silas, was a man of routine. Every night, for fifty years, he'd lit the lamp, a beacon against the treacherous rocks that gnawed at the coastline. The sea was his companion, his enemy, and his only confidante. He knew its moods better than his own.\n", + "\n", + "One stormy night, the wind howled like a banshee. The waves crashed against the tower, shaking it to its core. Silas, clinging to the railing, felt a fear he hadn't experienced in decades. This wasn't just a storm; this was a monster.\n", + "\n", + "Suddenly, a small, wooden boat, tossed about like a toy, appeared in the raging sea. He squinted, his heart leaping into his throat. A child. Alone.\n", + "\n", + "Ignoring the raging tempest, Silas raced down the winding stairs, his old bones protesting with every step. He launched his small rescue boat, a fragile craft against the fury of the storm.\n", + "\n", + "Fighting the waves, he reached the child. A girl, no older than seven, clung to the wreckage, her face white with terror. With a strength born of desperation, Silas pulled her aboard.\n", + "\n", + "The journey back was a blur of wind, spray, and fear. The lighthouse seemed miles away, a distant pinprick of hope. But Silas held on, whispering words of comfort to the shivering child.\n", + "\n", + "Finally, they reached the safety of the tower. He wrapped her in blankets, fed her warm soup, and listened to her tale of a capsized fishing boat and a lost father.\n", + "\n", + "As the storm raged outside, the little girl slept, curled up in Silas's worn armchair. Looking at her, a profound shift occurred within him. For fifty years, he’d only kept the light burning. Now, he understood that the light wasn't just a warning. It was a hope, a guiding star. And he, Silas, was more than just a keeper of the light. He was a keeper of hope.\n", + "\n", + "The storm eventually subsided. The girl was reunited with her father, miraculously rescued from a nearby island. Silas, watching them embrace, felt a warmth he hadn't known he was missing. The sea remained, his companion and his enemy. But now, it was also a reminder of the girl he'd saved, and the profound understanding that even in the darkest storms, a single act of kindness could illuminate the world. And that, he knew, was a light worth keeping.\n" + ] + } + ], + "execution_count": null + }, + { + "metadata": { + "id": "CpMmpaVClSBV", + "cellView": "form" + }, + "cell_type": "code", + "source": [ + "#@title Text formatting setup\n", + "#code is not necessary for colab.ai, but is useful in fomatting text chunks\n", + "import sys\n", + "\n", + "class LineWrapper:\n", + " def __init__(self, max_length=80):\n", + " self.max_length = max_length\n", + " self.current_line_length = 0\n", + "\n", + " def print(self, text_chunk):\n", + " i = 0\n", + " n = len(text_chunk)\n", + " while i < n:\n", + " start_index = i\n", + " while i < n and text_chunk[i] not in ' \\n': # Find end of word\n", + " i += 1\n", + " current_word = text_chunk[start_index:i]\n", + "\n", + " delimiter = \"\"\n", + " if i < n: # If not end of chunk, we found a delimiter\n", + " delimiter = text_chunk[i]\n", + " i += 1 # Consume delimiter\n", + "\n", + " if current_word:\n", + " needs_leading_space = (self.current_line_length > 0)\n", + "\n", + " # Case 1: Word itself is too long for a line (must be broken)\n", + " if len(current_word) > self.max_length:\n", + " if needs_leading_space: # Newline if current line has content\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", + " for char_val in current_word: # Break the long word\n", + " if self.current_line_length >= self.max_length:\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", + " sys.stdout.write(char_val)\n", + " self.current_line_length += 1\n", + " # Case 2: Word doesn't fit on current line (print on new line)\n", + " elif self.current_line_length + (1 if needs_leading_space else 0) + len(current_word) > self.max_length:\n", + " sys.stdout.write('\\n')\n", + " sys.stdout.write(current_word)\n", + " self.current_line_length = len(current_word)\n", + " # Case 3: Word fits on current line\n", + " else:\n", + " if needs_leading_space:\n", + " # Define punctuation that should not have a leading space\n", + " # when they form an entire \"word\" (token) following another word.\n", + " no_leading_space_punctuation = {\n", + " \",\", \".\", \";\", \":\", \"!\", \"?\", # Standard sentence punctuation\n", + " \")\", \"]\", \"}\", # Closing brackets\n", + " \"'s\", \"'S\", \"'re\", \"'RE\", \"'ve\", \"'VE\", # Common contractions\n", + " \"'m\", \"'M\", \"'ll\", \"'LL\", \"'d\", \"'D\",\n", + " \"n't\", \"N'T\",\n", + " \"...\", \"â€Ļ\" # Ellipses\n", + " }\n", + " if current_word not in no_leading_space_punctuation:\n", + " sys.stdout.write(' ')\n", + " self.current_line_length += 1\n", + " sys.stdout.write(current_word)\n", + " self.current_line_length += len(current_word)\n", + "\n", + " if delimiter == '\\n':\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", + " elif delimiter == ' ':\n", + " # If line is full and a space delimiter arrives, it implies a wrap.\n", + " if self.current_line_length >= self.max_length:\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", + "\n", + " sys.stdout.flush()\n" + ], + "outputs": [], + "execution_count": null + }, + { + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "DWiLPzTnRoy-", + "outputId": "7a9f17e2-ebb4-4bd6-a140-6376235197fb" + }, + "cell_type": "code", + "source": [ + "# @title Formatted streaming example\n", + "from google.colab import ai\n", + "\n", + "wrapper = LineWrapper()\n", + "for chunk in ai.generate_text('Give me a long winded description about the evolution of the Roman Empire.', model_name='google/gemini-2.0-flash', stream=True):\n", + " wrapper.print(chunk)" + ], + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Alright, settle in, because the Roman Empire’s evolution wasn't a tidy, linear\n", + "process. It was a centuries-long, tumultuous transformation, marked by\n", + "breathtaking innovation, brutal power struggles, and a slow, creeping societal\n", + "decay. We're talking about a journey from a humble city-state in the Italian\n", + "peninsula to a sprawling, multifaceted empire that left an indelible mark on\n", + "law, language, architecture, governance, and even our very understanding of the\n", + "world.\n", + "\n", + "It all began, as legend would have it, with Romulus and Remus, twin brothers\n", + "raised by a she-wolf, who founded the city of Rome in 753 BCE. Now, that’s just\n", + "a legend, but it serves to highlight the foundational spirit of Rome: ambition,\n", + "strength, and a certain ruthlessness. Initially, Rome was ruled by a monarchy, a\n", + "system eventually deemed unsatisfactory by the powerful patrician class. This\n", + "led to the **Roman Republic**, established around 509 BCE, a watershed moment\n", + "that would define the early character of Rome.\n", + "\n", + "The Republic was a complex system of checks and balances designed to prevent any\n", + "one individual from gaining absolute power. It involved a Senate, composed of\n", + "elder statesmen primarily drawn from the patrician class, who advised and\n", + "controlled finances; elected officials, such as Cons uls (two elected heads of\n", + "state who served one-year terms), Praetors (judges), and Quaestors (financial\n", + "administrators); and popular assemblies where citizens could theoretically\n", + "participate in governance.\n", + "\n", + "But the Republic wasn't a democracy in the modern sense. Power was largely\n", + "concentrated in the hands of the wealthy aristocratic families, and while\n", + "plebeians (the common citizens) eventually gained some representation through\n", + "tribunes who could veto acts of the Senate, the system remained inherently\n", + "biased.\n", + "\n", + "This period of the Republic was one of relentless expansion. Through a series of\n", + "shrewd alliances and brutal wars, Rome gradually conquered its neighbors,\n", + "including the Etruscans, the Samnites, and various other Italian tribes. These\n", + "victories were crucial because they allowed Rome to control the Italian\n", + "peninsula, providing it with manpower, resources, and a strategic advantage.\n", + "\n", + "The **Punic Wars** against Carthage, a powerful North African trading empire,\n", + "were a defining moment. These protracted conflicts, especially the Second Punic\n", + "War with Hannibal's legendary invasion of Italy, tested Rome's resilience to the\n", + "absolute limit. The Roman resilience, coupled with tactical brilliance and\n", + "strategic advantages, ultimately led to Carthage's complete destruction,\n", + "establishing Rome as the dominant power in the Mediterranean.\n", + "\n", + "However, the very success of the Republic sowed the seeds of its eventual\n", + "downfall. The influx of wealth and slaves from conquered territories created\n", + "vast disparities in wealth. Powerful generals, enriched by conquest and\n", + "commanding loyal armies, began to challenge the authority of the Senate.\n", + "\n", + "Figures like **Marius**, who revolutionized the Roman army by allowing landless\n", + "citizens to enlist, creating a professional, loyal force, and **Sulla**, who\n", + "marched on Rome with his army to seize power, demonstrated the fragility of the\n", + "Republican system. This era saw a series of civil wars and political\n", + "assassinations, further destabilizing the Republic.\n", + "\n", + "The **First Triumvirate**, an informal alliance between Julius Caesar, Pompey,\n", + "and Crassus, was an attempt to stabilize the political landscape, but it\n", + "ultimately collapsed due to ambition and rivalry. **Julius Caesar's** rise to\n", + "power was perhaps the most dramatic turning point. He conquered Gaul, defied the\n", + "Senate, crossed the Rubicon, and ultimately seized control of Rome as dictator\n", + "perpet uo. His reforms, aimed at improving the lives of ordinary citizens and\n", + "consolidating his power, were cut short by his assassination in 44 BCE.\n", + "\n", + "Caesar's assassination sparked another round of civil wars. The **Second\n", + "Triumvirate**, comprised of Mark Antony, Octavian (Caesar's adopted son), and\n", + "Lepidus, emerged to restore order. However, this alliance also disintegrated,\n", + "leading to a power struggle between Antony and Octavian. Octavian's victory at\n", + "the Battle of Actium in 31 BCE marked the definitive end of the Roman Republic.\n", + "\n", + "Octavian, now known as **Augustus **, carefully crafted a new political system.\n", + "He avoided the title of \"king\" or \"dictator,\" instead adopting the title of\n", + "\"Princeps,\" meaning \"first citizen.\" He maintained the facade of the Republic,\n", + "keeping the Senate and other Republican institutions, but in reality, he held\n", + "absolute power. This transition from Republic to Empire was a gradual process,\n", + "cleverly disguised by Augustus. He restructured the army, reformed the tax\n", + "system, initiated massive building projects, and ushered in a period of relative\n", + "peace and prosperity known as the **Pax Romana** (Roman Peace).\n", + "\n", + "The Julio-Claudian dynasty, which followed Augustus, saw a mixed bag of\n", + "emperors. Tiberius was a capable administrator but reclusive, Caligula was\n", + "notorious for his cruelty and extravagance, Claudius was an intellectual who\n", + "expanded the Empire, and Nero was infamous for his alleged role in the Great\n", + "Fire of Rome and his persecution of Christians.\n", + "\n", + "The year 69 CE, known as the ** Year of the Four Emperors**, revealed the\n", + "instability of the imperial succession. After Nero's death, four different\n", + "emperors claimed the throne in rapid succession, highlighting the power of the\n", + "army to make and break emperors.\n", + "\n", + "The Flavian dynasty, established by Vespasian, brought stability and marked the\n", + "beginning of the construction of the Col osseum. The Nerva-Antonine dynasty,\n", + "often considered the \"Five Good Emperors\" (Nerva, Trajan, Hadrian, Antoninus\n", + "Pius, Marcus Aurelius), saw the Roman Empire reach its greatest territorial\n", + "extent and experience a period of unprecedented peace and prosperity.\n", + "\n", + "Trajan conquered Dacia (modern Romania) and expanded the Empire into\n", + "Mesopotamia, while Hadrian focused on consolidating the Empire's borders and\n", + "building defensive fortifications like Hadrian's Wall in Britain. Marcus\n", + "Aurelius, a philosopher-king, faced constant warfare on the frontiers and wrote\n", + "his famous \"Meditations.\"\n", + "\n", + "The reign of Commodus, the son of Marcus Aurelius, marked a turning point. His\n", + "erratic behavior and autocratic rule undermined the stability of the Empire and\n", + "foreshadowed future troubles. The Severan dynasty, which followed, saw the rise\n", + "of powerful military emperors who relied heavily on the army for support. This\n", + "increased military influence further weakened the Senate and other civilian\n", + "institutions.\n", + "\n", + "The 3rd century CE was a period of profound crisis. The **Crisis of the Third\n", + "Century** was characterized by constant civil wars, barbarian invasions,\n", + "economic decline, and plague. The Empire was divided into competing factions,\n", + "and emperors rose and fell in rapid succession.\n", + "\n", + "Emperor Diocletian attempted to stabilize the Empire by dividing it into two\n", + "halves, the Western Roman Empire and the Eastern Roman Empire (later known as\n", + "the Byzantine Empire), each ruled by an Augustus and a Caesar. This tetrarchy, a\n", + "system of four rulers, aimed to provide more effective governance and defense.\n", + "\n", + "Constantine I, also known as Constantine the Great, reunited the Empire and made\n", + "Christianity the favored religion with the Edict of Milan in 313 CE. He also\n", + "moved the capital from Rome to Byzantium, renaming it Constantinople. This shift\n", + "reflected the growing importance of the Eastern provinces and the weakening of\n", + "the Western Empire.\n", + "\n", + "Following Constantine's death, the Empire was again divided between his sons.\n", + "The Western Roman Empire continued to decline, plagued by internal strife,\n", + "economic problems, and constant barbarian invasions. The Eastern Roman Empire,\n", + "with its stronger economy and more stable political system, managed to survive.\n", + "\n", + "The **Visigoths**, fleeing from the Huns, were allowed to settle within the\n", + "Roman Empire, but their mistreatment by Roman officials led to rebellion. In 410\n", + "CE, the Visigoths sacked Rome, a symbolic blow that shook the foundations of the\n", + "Western Roman Empire.\n", + "\n", + "One by one, provinces of the Western Roman Empire were lost to various barbarian\n", + "tribes, including the Vandals, the Franks, the Angles, and the Saxons. In 476\n", + "CE, the last Western Roman Emperor, Romulus Augustulus, was deposed by the\n", + "Germanic chieftain Odoacer, marking the traditional end of the Western Roman\n", + "Empire.\n", + "\n", + "The Eastern Roman Empire, or Byzantine Empire, continued to flourish for another\n", + "thousand years, preserving Roman traditions and culture. It would eventually\n", + "fall to the Ottoman Turks in 1453, with the capture of Constantinople.\n", + "\n", + "So, the evolution of the Roman Empire was a complex and multifaceted process,\n", + "spanning centuries and encompassing profound political, social, economic, and\n", + "cultural transformations. From a small Republic to a vast empire, and eventually\n", + "to a fragmented and weakened state, the Roman story is a testament to the rise\n", + "and fall of civilizations, the enduring power of ideas, and the enduring legacy\n", + "of one of history's most influential empires. It's a story of ambition,\n", + "innovation, ruthlessness, and ultimately, decline – a cautionary tale and a\n", + "source of inspiration that continues to fascinate and influence us today.\n", + "\n" + ] + } + ], + "execution_count": null + } + ], + "metadata": { + "colab": { + "provenance": [], + "include_colab_link": true + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file From dcb916c61479506a27cb9884853d4cebc719f3a2 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 07:48:58 +0600 Subject: [PATCH 10/28] Created using Colab --- ...Getting_started_with_google_colab_ai.ipynb | 319 ++---------------- 1 file changed, 31 insertions(+), 288 deletions(-) diff --git a/notebooks/Getting_started_with_google_colab_ai.ipynb b/notebooks/Getting_started_with_google_colab_ai.ipynb index 5029278..ea523ac 100644 --- a/notebooks/Getting_started_with_google_colab_ai.ipynb +++ b/notebooks/Getting_started_with_google_colab_ai.ipynb @@ -1,15 +1,5 @@ { "cells": [ - { - "cell_type": "markdown", - "metadata": { - "id": "view-in-github", - "colab_type": "text" - }, - "source": [ - "\"Open" - ] - }, { "metadata": { "id": "wdj9RMfoGPC2" @@ -31,7 +21,7 @@ { "metadata": { "id": "Ucchuu5vV3Jp", - "outputId": "7b4b87b2-d2ff-41d5-9a10-2465e094a5ef", + "outputId": "a3004031-0e0c-4f8d-842d-a79421f51e11", "colab": { "base_uri": "https://localhost:8080/" } @@ -60,10 +50,19 @@ ] }, "metadata": {}, - "execution_count": 1 + "execution_count": 27 } ], - "execution_count": 1 + "execution_count": 27 + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "9D74LOIiggIt" + }, + "execution_count": 27, + "outputs": [] }, { "metadata": { @@ -82,61 +81,29 @@ ] }, { + "cell_type": "code", + "source": [], "metadata": { - "id": "R7taibpc7x2l", - "colab": { - "base_uri": "https://localhost:8080/" - }, - "outputId": "71c9fbea-5765-4159-b765-b77c8b4ab34d" + "id": "8fjql8kzgin1" }, - "cell_type": "code", - "source": [ - "# @title Simple batch generation example\n", - "# Only text-to-text input/output is supported\n", - "from google.colab import ai\n", - "\n", - "response = ai.generate_text(\"What is the capital of France?\")\n", - "print(response)" - ], - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "The capital of France is **Paris**.\n", - "\n" - ] - } - ], - "execution_count": null + "execution_count": 27, + "outputs": [] }, { + "cell_type": "markdown", + "source": [], "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "NHO9VzO9AHZP", - "outputId": "f5667fab-a9f3-487f-cff1-5f5ac1549366" - }, + "id": "cNSefuDZgjqV" + } + }, + { "cell_type": "code", - "source": [ - "# @title Choose a different model\n", - "from google.colab import ai\n", - "\n", - "response = ai.generate_text(\"What is the capital of England\", model_name='google/gemini-2.0-flash-lite')\n", - "print(response)" - ], - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "The capital of England is **London**.\n", - "\n" - ] - } - ], - "execution_count": null + "source": [], + "metadata": { + "id": "0_KsQAqsgkW9" + }, + "execution_count": 27, + "outputs": [] }, { "metadata": { @@ -147,50 +114,6 @@ "For longer text generations, you can stream the response. This displays the output token by token as it's generated, rather than waiting for the entire response to complete. This provides a more interactive and responsive experience. To enable this, simply set stream=True." ] }, - { - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "4BNgxiB6--_5", - "outputId": "d3b34d85-1283-4226-861c-73ff431000f7" - }, - "cell_type": "code", - "source": [ - "# @title Simple streaming example\n", - "from google.colab import ai\n", - "\n", - "stream = ai.generate_text(\"Tell me a short story.\", stream=True)\n", - "for text in stream:\n", - " print(text, end='')" - ], - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "The lighthouse keeper, Silas, was a man of routine. Every night, for fifty years, he'd lit the lamp, a beacon against the treacherous rocks that gnawed at the coastline. The sea was his companion, his enemy, and his only confidante. He knew its moods better than his own.\n", - "\n", - "One stormy night, the wind howled like a banshee. The waves crashed against the tower, shaking it to its core. Silas, clinging to the railing, felt a fear he hadn't experienced in decades. This wasn't just a storm; this was a monster.\n", - "\n", - "Suddenly, a small, wooden boat, tossed about like a toy, appeared in the raging sea. He squinted, his heart leaping into his throat. A child. Alone.\n", - "\n", - "Ignoring the raging tempest, Silas raced down the winding stairs, his old bones protesting with every step. He launched his small rescue boat, a fragile craft against the fury of the storm.\n", - "\n", - "Fighting the waves, he reached the child. A girl, no older than seven, clung to the wreckage, her face white with terror. With a strength born of desperation, Silas pulled her aboard.\n", - "\n", - "The journey back was a blur of wind, spray, and fear. The lighthouse seemed miles away, a distant pinprick of hope. But Silas held on, whispering words of comfort to the shivering child.\n", - "\n", - "Finally, they reached the safety of the tower. He wrapped her in blankets, fed her warm soup, and listened to her tale of a capsized fishing boat and a lost father.\n", - "\n", - "As the storm raged outside, the little girl slept, curled up in Silas's worn armchair. Looking at her, a profound shift occurred within him. For fifty years, he’d only kept the light burning. Now, he understood that the light wasn't just a warning. It was a hope, a guiding star. And he, Silas, was more than just a keeper of the light. He was a keeper of hope.\n", - "\n", - "The storm eventually subsided. The girl was reunited with her father, miraculously rescued from a nearby island. Silas, watching them embrace, felt a warmth he hadn't known he was missing. The sea remained, his companion and his enemy. But now, it was also a reminder of the girl he'd saved, and the profound understanding that even in the darkest storms, a single act of kindness could illuminate the world. And that, he knew, was a light worth keeping.\n" - ] - } - ], - "execution_count": null - }, { "metadata": { "id": "CpMmpaVClSBV", @@ -271,192 +194,12 @@ " sys.stdout.flush()\n" ], "outputs": [], - "execution_count": null - }, - { - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "DWiLPzTnRoy-", - "outputId": "7a9f17e2-ebb4-4bd6-a140-6376235197fb" - }, - "cell_type": "code", - "source": [ - "# @title Formatted streaming example\n", - "from google.colab import ai\n", - "\n", - "wrapper = LineWrapper()\n", - "for chunk in ai.generate_text('Give me a long winded description about the evolution of the Roman Empire.', model_name='google/gemini-2.0-flash', stream=True):\n", - " wrapper.print(chunk)" - ], - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Alright, settle in, because the Roman Empire’s evolution wasn't a tidy, linear\n", - "process. It was a centuries-long, tumultuous transformation, marked by\n", - "breathtaking innovation, brutal power struggles, and a slow, creeping societal\n", - "decay. We're talking about a journey from a humble city-state in the Italian\n", - "peninsula to a sprawling, multifaceted empire that left an indelible mark on\n", - "law, language, architecture, governance, and even our very understanding of the\n", - "world.\n", - "\n", - "It all began, as legend would have it, with Romulus and Remus, twin brothers\n", - "raised by a she-wolf, who founded the city of Rome in 753 BCE. Now, that’s just\n", - "a legend, but it serves to highlight the foundational spirit of Rome: ambition,\n", - "strength, and a certain ruthlessness. Initially, Rome was ruled by a monarchy, a\n", - "system eventually deemed unsatisfactory by the powerful patrician class. This\n", - "led to the **Roman Republic**, established around 509 BCE, a watershed moment\n", - "that would define the early character of Rome.\n", - "\n", - "The Republic was a complex system of checks and balances designed to prevent any\n", - "one individual from gaining absolute power. It involved a Senate, composed of\n", - "elder statesmen primarily drawn from the patrician class, who advised and\n", - "controlled finances; elected officials, such as Cons uls (two elected heads of\n", - "state who served one-year terms), Praetors (judges), and Quaestors (financial\n", - "administrators); and popular assemblies where citizens could theoretically\n", - "participate in governance.\n", - "\n", - "But the Republic wasn't a democracy in the modern sense. Power was largely\n", - "concentrated in the hands of the wealthy aristocratic families, and while\n", - "plebeians (the common citizens) eventually gained some representation through\n", - "tribunes who could veto acts of the Senate, the system remained inherently\n", - "biased.\n", - "\n", - "This period of the Republic was one of relentless expansion. Through a series of\n", - "shrewd alliances and brutal wars, Rome gradually conquered its neighbors,\n", - "including the Etruscans, the Samnites, and various other Italian tribes. These\n", - "victories were crucial because they allowed Rome to control the Italian\n", - "peninsula, providing it with manpower, resources, and a strategic advantage.\n", - "\n", - "The **Punic Wars** against Carthage, a powerful North African trading empire,\n", - "were a defining moment. These protracted conflicts, especially the Second Punic\n", - "War with Hannibal's legendary invasion of Italy, tested Rome's resilience to the\n", - "absolute limit. The Roman resilience, coupled with tactical brilliance and\n", - "strategic advantages, ultimately led to Carthage's complete destruction,\n", - "establishing Rome as the dominant power in the Mediterranean.\n", - "\n", - "However, the very success of the Republic sowed the seeds of its eventual\n", - "downfall. The influx of wealth and slaves from conquered territories created\n", - "vast disparities in wealth. Powerful generals, enriched by conquest and\n", - "commanding loyal armies, began to challenge the authority of the Senate.\n", - "\n", - "Figures like **Marius**, who revolutionized the Roman army by allowing landless\n", - "citizens to enlist, creating a professional, loyal force, and **Sulla**, who\n", - "marched on Rome with his army to seize power, demonstrated the fragility of the\n", - "Republican system. This era saw a series of civil wars and political\n", - "assassinations, further destabilizing the Republic.\n", - "\n", - "The **First Triumvirate**, an informal alliance between Julius Caesar, Pompey,\n", - "and Crassus, was an attempt to stabilize the political landscape, but it\n", - "ultimately collapsed due to ambition and rivalry. **Julius Caesar's** rise to\n", - "power was perhaps the most dramatic turning point. He conquered Gaul, defied the\n", - "Senate, crossed the Rubicon, and ultimately seized control of Rome as dictator\n", - "perpet uo. His reforms, aimed at improving the lives of ordinary citizens and\n", - "consolidating his power, were cut short by his assassination in 44 BCE.\n", - "\n", - "Caesar's assassination sparked another round of civil wars. The **Second\n", - "Triumvirate**, comprised of Mark Antony, Octavian (Caesar's adopted son), and\n", - "Lepidus, emerged to restore order. However, this alliance also disintegrated,\n", - "leading to a power struggle between Antony and Octavian. Octavian's victory at\n", - "the Battle of Actium in 31 BCE marked the definitive end of the Roman Republic.\n", - "\n", - "Octavian, now known as **Augustus **, carefully crafted a new political system.\n", - "He avoided the title of \"king\" or \"dictator,\" instead adopting the title of\n", - "\"Princeps,\" meaning \"first citizen.\" He maintained the facade of the Republic,\n", - "keeping the Senate and other Republican institutions, but in reality, he held\n", - "absolute power. This transition from Republic to Empire was a gradual process,\n", - "cleverly disguised by Augustus. He restructured the army, reformed the tax\n", - "system, initiated massive building projects, and ushered in a period of relative\n", - "peace and prosperity known as the **Pax Romana** (Roman Peace).\n", - "\n", - "The Julio-Claudian dynasty, which followed Augustus, saw a mixed bag of\n", - "emperors. Tiberius was a capable administrator but reclusive, Caligula was\n", - "notorious for his cruelty and extravagance, Claudius was an intellectual who\n", - "expanded the Empire, and Nero was infamous for his alleged role in the Great\n", - "Fire of Rome and his persecution of Christians.\n", - "\n", - "The year 69 CE, known as the ** Year of the Four Emperors**, revealed the\n", - "instability of the imperial succession. After Nero's death, four different\n", - "emperors claimed the throne in rapid succession, highlighting the power of the\n", - "army to make and break emperors.\n", - "\n", - "The Flavian dynasty, established by Vespasian, brought stability and marked the\n", - "beginning of the construction of the Col osseum. The Nerva-Antonine dynasty,\n", - "often considered the \"Five Good Emperors\" (Nerva, Trajan, Hadrian, Antoninus\n", - "Pius, Marcus Aurelius), saw the Roman Empire reach its greatest territorial\n", - "extent and experience a period of unprecedented peace and prosperity.\n", - "\n", - "Trajan conquered Dacia (modern Romania) and expanded the Empire into\n", - "Mesopotamia, while Hadrian focused on consolidating the Empire's borders and\n", - "building defensive fortifications like Hadrian's Wall in Britain. Marcus\n", - "Aurelius, a philosopher-king, faced constant warfare on the frontiers and wrote\n", - "his famous \"Meditations.\"\n", - "\n", - "The reign of Commodus, the son of Marcus Aurelius, marked a turning point. His\n", - "erratic behavior and autocratic rule undermined the stability of the Empire and\n", - "foreshadowed future troubles. The Severan dynasty, which followed, saw the rise\n", - "of powerful military emperors who relied heavily on the army for support. This\n", - "increased military influence further weakened the Senate and other civilian\n", - "institutions.\n", - "\n", - "The 3rd century CE was a period of profound crisis. The **Crisis of the Third\n", - "Century** was characterized by constant civil wars, barbarian invasions,\n", - "economic decline, and plague. The Empire was divided into competing factions,\n", - "and emperors rose and fell in rapid succession.\n", - "\n", - "Emperor Diocletian attempted to stabilize the Empire by dividing it into two\n", - "halves, the Western Roman Empire and the Eastern Roman Empire (later known as\n", - "the Byzantine Empire), each ruled by an Augustus and a Caesar. This tetrarchy, a\n", - "system of four rulers, aimed to provide more effective governance and defense.\n", - "\n", - "Constantine I, also known as Constantine the Great, reunited the Empire and made\n", - "Christianity the favored religion with the Edict of Milan in 313 CE. He also\n", - "moved the capital from Rome to Byzantium, renaming it Constantinople. This shift\n", - "reflected the growing importance of the Eastern provinces and the weakening of\n", - "the Western Empire.\n", - "\n", - "Following Constantine's death, the Empire was again divided between his sons.\n", - "The Western Roman Empire continued to decline, plagued by internal strife,\n", - "economic problems, and constant barbarian invasions. The Eastern Roman Empire,\n", - "with its stronger economy and more stable political system, managed to survive.\n", - "\n", - "The **Visigoths**, fleeing from the Huns, were allowed to settle within the\n", - "Roman Empire, but their mistreatment by Roman officials led to rebellion. In 410\n", - "CE, the Visigoths sacked Rome, a symbolic blow that shook the foundations of the\n", - "Western Roman Empire.\n", - "\n", - "One by one, provinces of the Western Roman Empire were lost to various barbarian\n", - "tribes, including the Vandals, the Franks, the Angles, and the Saxons. In 476\n", - "CE, the last Western Roman Emperor, Romulus Augustulus, was deposed by the\n", - "Germanic chieftain Odoacer, marking the traditional end of the Western Roman\n", - "Empire.\n", - "\n", - "The Eastern Roman Empire, or Byzantine Empire, continued to flourish for another\n", - "thousand years, preserving Roman traditions and culture. It would eventually\n", - "fall to the Ottoman Turks in 1453, with the capture of Constantinople.\n", - "\n", - "So, the evolution of the Roman Empire was a complex and multifaceted process,\n", - "spanning centuries and encompassing profound political, social, economic, and\n", - "cultural transformations. From a small Republic to a vast empire, and eventually\n", - "to a fragmented and weakened state, the Roman story is a testament to the rise\n", - "and fall of civilizations, the enduring power of ideas, and the enduring legacy\n", - "of one of history's most influential empires. It's a story of ambition,\n", - "innovation, ruthlessness, and ultimately, decline – a cautionary tale and a\n", - "source of inspiration that continues to fascinate and influence us today.\n", - "\n" - ] - } - ], - "execution_count": null + "execution_count": 29 } ], "metadata": { "colab": { - "provenance": [], - "include_colab_link": true + "provenance": [] }, "kernelspec": { "name": "python3", From 37a6c0953474e82b5af32c819d85439a0ff4b1a6 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 09:00:27 +0600 Subject: [PATCH 11/28] Created using Colab --- Cosmic_Simulation_AI_and_Audio.ipynb | 1418 +++++++++++++++++++++++++- 1 file changed, 1363 insertions(+), 55 deletions(-) diff --git a/Cosmic_Simulation_AI_and_Audio.ipynb b/Cosmic_Simulation_AI_and_Audio.ipynb index b5550d7..0bfd00d 100644 --- a/Cosmic_Simulation_AI_and_Audio.ipynb +++ b/Cosmic_Simulation_AI_and_Audio.ipynb @@ -8,7 +8,6 @@ "collapsed_sections": [ "Gc4BqPpVpUFa" ], - "toc_visible": true, "include_colab_link": true }, "language_info": { @@ -50,7 +49,7 @@ "metadata": { "id": "_Gimwn69vh42" }, - "execution_count": 533, + "execution_count": 10, "outputs": [] }, { @@ -68,7 +67,7 @@ "metadata": { "id": "HHKkGIgntjPg" }, - "execution_count": 534, + "execution_count": 10, "outputs": [] }, { @@ -127,27 +126,90 @@ "id": "Qd6wJzyz_HtY", "colab": { "base_uri": "https://localhost:8080/", - "height": 106 + "height": 211 }, - "outputId": "f091be2b-9b79-4c7f-f31d-ff108c676a2b" + "outputId": "a577bf13-6964-43ec-fcef-02492fd894d2" }, - "execution_count": 535, + "execution_count": 11, "outputs": [ { - "output_type": "display_data", + "output_type": "stream", + "name": "stdout", + "text": [ + "The cudf.pandas extension is already loaded. To reload it, use:\n", + " %reload_ext cudf.pandas\n" + ] + }, + { + "output_type": "execute_result", "data": { "text/plain": [ - " Unrecognized magic \u001b[36m%load_ext\u001b[39m.\n", + " Registration State Violation Description count\n", + "0 CA No Parking 50189\n", + "1 NJ Expired Meter 50216\n", + "2 NY No Parking 50224\n", + "3 TX No Parking 50434" + ], + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Registration StateViolation Descriptioncount
0CANo Parking50189
1NJExpired Meter50216
2NYNo Parking50224
3TXNo Parking50434
\n", + "
" ], - "text/markdown": "Unrecognized magic `%load_ext`.\n\nJulia does not use the IPython `%magic` syntax. To interact with the IJulia kernel, use `IJulia.somefunction(...)`, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n", - "text/latex": "Unrecognized magic \\texttt{\\%load\\_ext}.\n\nJulia does not use the IPython \\texttt{\\%magic} syntax. To interact with the IJulia kernel, use \\texttt{IJulia.somefunction(...)}, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n\n" + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \")\",\n \"rows\": 4,\n \"fields\": [\n {\n \"column\": \"Registration State\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 4,\n \"samples\": [\n \"NJ\",\n \"TX\",\n \"CA\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Violation Description\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 2,\n \"samples\": [\n \"Expired Meter\",\n \"No Parking\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"count\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 113,\n \"min\": 50189,\n \"max\": 50434,\n \"num_unique_values\": 4,\n \"samples\": [\n 50216,\n 50434\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } }, - "metadata": {} + "metadata": {}, + "execution_count": 11 } ] }, @@ -157,7 +219,7 @@ "metadata": { "id": "8HR9qLhAOlsd" }, - "execution_count": 536, + "execution_count": null, "outputs": [] }, { @@ -176,7 +238,7 @@ "metadata": { "id": "EokR_kWwOnGW" }, - "execution_count": 537, + "execution_count": 11, "outputs": [] }, { @@ -197,7 +259,7 @@ "metadata": { "id": "VK1djxvoOitN" }, - "execution_count": 538, + "execution_count": 11, "outputs": [] }, { @@ -226,32 +288,1244 @@ "cell_type": "code", "metadata": { "colab": { - "base_uri": "https://localhost:8080/", - "height": 106 + "base_uri": "https://localhost:8080/" }, "id": "paLtPO5PHPXU", - "outputId": "c5feceae-f47c-4e2f-9027-e1dd728f807a" + "outputId": "eda4bc3b-e4c4-4b51-a816-81b58f53d6d2" }, "source": [ "%pip install opencv-python" ], - "execution_count": 539, + "execution_count": 12, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Requirement already satisfied: opencv-python in /usr/local/lib/python3.12/dist-packages (4.12.0.88)\n", + "Requirement already satisfied: numpy<2.3.0,>=2 in /usr/local/lib/python3.12/dist-packages (from opencv-python) (2.0.2)\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "from vega_datasets import data\n", + "stocks = data.stocks()\n", + "\n", + "import altair as alt\n", + "alt.Chart(stocks).mark_line().encode(\n", + " x='date:T',\n", + " y='price',\n", + " color='symbol'\n", + ").interactive(bind_y=False)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 368 + }, + "id": "VrcdHkesu8OI", + "outputId": "29435b8d-f857-491f-eb79-7bd7ce4a4872" + }, + "execution_count": 13, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "\n", + "\n", + "
\n", + "" + ], + "text/plain": [ + "alt.Chart(...)" + ] + }, + "metadata": {}, + "execution_count": 13 + } + ] + }, + { + "cell_type": "code", + "source": [ + "# load an example dataset\n", + "from vega_datasets import data\n", + "cars = data.cars()\n", + "\n", + "# plot the dataset, referencing dataframe column names\n", + "import altair as alt\n", + "alt.Chart(cars).mark_bar().encode(\n", + " x=alt.X('Miles_per_Gallon', bin=True),\n", + " y='count()',\n", + " color='Origin'\n", + ")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 368 + }, + "id": "pr93d1kBvBHH", + "outputId": "b7f1ec2f-9b27-4a12-d38e-c408aaeefd64" + }, + "execution_count": 14, "outputs": [ { - "output_type": "display_data", + "output_type": "execute_result", "data": { + "text/html": [ + "\n", + "\n", + "
\n", + "" + ], "text/plain": [ - " Unrecognized magic \u001b[36m%pip\u001b[39m.\n", + "alt.Chart(...)" + ] + }, + "metadata": {}, + "execution_count": 14 + } + ] + }, + { + "cell_type": "code", + "source": [ + "# load an example dataset\n", + "from vega_datasets import data\n", + "cars = data.cars()\n", + "\n", + "import altair as alt\n", + "\n", + "points = alt.Chart(cars).mark_point().encode(\n", + " x='Year:T',\n", + " y='Miles_per_Gallon',\n", + " color='Origin'\n", + ").properties(\n", + " width=800\n", + ")\n", + "\n", + "lines = alt.Chart(cars).mark_line().encode(\n", + " x='Year:T',\n", + " y='mean(Miles_per_Gallon)',\n", + " color='Origin'\n", + ").properties(\n", + " width=800\n", + ").interactive(bind_y=False)\n", + "\n", + "points + lines" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 388 + }, + "id": "ULhvdA3AvCVm", + "outputId": "022edcc4-78fc-49e0-be17-4b9baca9ada0" + }, + "execution_count": 15, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "\n", + "\n", + "
\n", + "" ], - "text/markdown": "Unrecognized magic `%pip`.\n\nJulia does not use the IPython `%magic` syntax. To interact with the IJulia kernel, use `IJulia.somefunction(...)`, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n", - "text/latex": "Unrecognized magic \\texttt{\\%pip}.\n\nJulia does not use the IPython \\texttt{\\%magic} syntax. To interact with the IJulia kernel, use \\texttt{IJulia.somefunction(...)}, for example. Julia macros, string macros, and functions can be used to accomplish most of the other functionalities of IPython magics.\n\n" + "text/plain": [ + "alt.LayerChart(...)" + ] }, - "metadata": {} + "metadata": {}, + "execution_count": 15 + } + ] + }, + { + "cell_type": "code", + "source": [ + "# load an example dataset\n", + "from vega_datasets import data\n", + "cars = data.cars()\n", + "\n", + "# plot the dataset, referencing dataframe column names\n", + "import altair as alt\n", + "alt.Chart(cars).mark_point().encode(\n", + " x='Horsepower',\n", + " y='Miles_per_Gallon',\n", + " color='Origin'\n", + ").interactive()" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 368 + }, + "id": "iRfJrZb1vH76", + "outputId": "c9c24220-9b43-4017-d0a7-08503a4b9d86" + }, + "execution_count": 30, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "\n", + "\n", + "
\n", + "" + ], + "text/plain": [ + "alt.Chart(...)" + ] + }, + "metadata": {}, + "execution_count": 30 + } + ] + }, + { + "cell_type": "code", + "source": [ + "# load an example dataset\n", + "from vega_datasets import data\n", + "cars = data.cars()\n", + "\n", + "# plot the dataset, referencing dataframe column names\n", + "import altair as alt\n", + "alt.Chart(cars).mark_bar().encode(\n", + " x=alt.X('Miles_per_Gallon', bin=True),\n", + " y='count()',\n", + ")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 368 + }, + "id": "ieUf_ygVvKjw", + "outputId": "cdfa08c6-3228-4c1f-e041-3d186c5db38c" + }, + "execution_count": 32, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "\n", + "\n", + "
\n", + "" + ], + "text/plain": [ + "alt.Chart(...)" + ] + }, + "metadata": {}, + "execution_count": 32 + } + ] + }, + { + "cell_type": "code", + "source": [ + "# load an example dataset\n", + "from vega_datasets import data\n", + "cars = data.cars()\n", + "\n", + "# plot the dataset, referencing dataframe column names\n", + "import altair as alt\n", + "alt.Chart(cars).mark_bar().encode(\n", + " x='mean(Miles_per_Gallon)',\n", + " y='Origin',\n", + " color='Origin'\n", + ")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 123 + }, + "id": "6SOWYxt2vLpr", + "outputId": "8a94d1cc-9c07-4a15-bb23-ee882a3952f0" + }, + "execution_count": 33, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "\n", + "\n", + "
\n", + "" + ], + "text/plain": [ + "alt.Chart(...)" + ] + }, + "metadata": {}, + "execution_count": 33 + } + ] + }, + { + "cell_type": "code", + "source": [ + "from google.colab import auth\n", + "auth.authenticate_user()" + ], + "metadata": { + "id": "fC-1Kix5vMg4" + }, + "execution_count": 34, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "import time\n", + "import sys\n", + "from google.colab import output\n", + "\n", + "print('Starting.')\n", + "\n", + "with output.use_tags('some_outputs'):\n", + " sys.stdout.write('working....\\n')\n", + " sys.stdout.flush();\n", + " time.sleep(2)\n", + "\n", + " sys.stdout.write('still working...\\n')\n", + " sys.stdout.flush();\n", + " time.sleep(2)\n", + "\n", + "# Now clear the previous outputs.\n", + "output.clear(output_tags='some_outputs')\n", + "print('All done!')\n" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "VoblcmpyvPF5", + "outputId": "429fe3a9-e5d4-433d-cd2b-f86b3320c090" + }, + "execution_count": 35, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Starting.\n", + "All done!\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "Support for third party widgets will remain active for the duration of the session. To disable support:" + ], + "metadata": { + "id": "em2abCypvNop" + } + }, + { + "cell_type": "code", + "source": [ + "from google.colab import output\n", + "output.disable_custom_widget_manager()" + ], + "metadata": { + "id": "2CPY_udkvNop" + }, + "execution_count": 36, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "project_id = '[your project ID]'" + ], + "metadata": { + "id": "yrElKJx3vNTQ" + }, + "execution_count": 37, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "import bigframes.pandas as bpd\n", + "from google.cloud import bigquery\n", + "\n", + "# Set BigQuery DataFrames options\n", + "bpd.options.bigquery.project = project_id\n", + "bpd.options.bigquery.location = \"US\"" + ], + "metadata": { + "id": "adSrR635vNTQ" + }, + "execution_count": 38, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "df.describe()" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 300 + }, + "id": "MC8P2TfBvNTQ", + "outputId": "db5961a5-27e4-4a3a-df85-010297ad8325" + }, + "execution_count": 42, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " Issue Date Ticket Number\n", + "count 1000000 1.000000e+06\n", + "mean 2022-07-01 23:32:43.411199744 5.499237e+09\n", + "min 2022-01-01 00:00:00 1.000005e+09\n", + "25% 2022-04-02 00:00:00 3.249061e+09\n", + "50% 2022-07-02 00:00:00 5.499907e+09\n", + "75% 2022-10-01 00:00:00 7.748794e+09\n", + "max 2022-12-31 00:00:00 9.999998e+09\n", + "std NaN 2.597215e+09" + ], + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Issue DateTicket Number
count10000001.000000e+06
mean2022-07-01 23:32:43.4111997445.499237e+09
min2022-01-01 00:00:001.000005e+09
25%2022-04-02 00:00:003.249061e+09
50%2022-07-02 00:00:005.499907e+09
75%2022-10-01 00:00:007.748794e+09
max2022-12-31 00:00:009.999998e+09
stdNaN2.597215e+09
\n", + "
" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"df\",\n \"rows\": 8,\n \"fields\": [\n {\n \"column\": \"Issue Date\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": \"1970-01-01 00:00:00.001000\",\n \"max\": \"2022-12-31 00:00:00\",\n \"num_unique_values\": 7,\n \"samples\": [\n \"1000000\",\n \"2022-07-01 23:32:43.411199744\",\n \"2022-10-01 00:00:00\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Ticket Number\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3390298193.6777215,\n \"min\": 1000000.0,\n \"max\": 9999997850.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 5499236759.115837,\n 7748793835.0,\n 1000000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {}, + "execution_count": 42 + } + ] + }, + { + "cell_type": "code", + "source": [ + "df.head(10)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 363 + }, + "id": "lpFT7CA1vNTQ", + "outputId": "ce13216b-40d9-4977-952e-ae9250ea4fda" + }, + "execution_count": 43, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " Registration State Violation Description Vehicle Body Type Issue Date \\\n", + "0 TX Bus Stop SDN 2022-02-20 \n", + "1 NJ No Parking SUBN 2022-12-30 \n", + "2 CA Fire Hydrant SUBN 2022-02-16 \n", + "3 NJ Expired Meter SDN 2022-07-11 \n", + "4 CA Double Parking SDN 2022-09-02 \n", + "5 CA Fire Hydrant SDN 2022-09-24 \n", + "6 CA No Parking SDN 2022-03-25 \n", + "7 CA Bus Stop SDN 2022-01-28 \n", + "8 NJ Bus Stop SDN 2022-06-09 \n", + "9 NJ Bus Stop SUBN 2022-08-20 \n", + "\n", + " Ticket Number \n", + "0 2366568410 \n", + "1 1858496929 \n", + "2 7980797083 \n", + "3 2267392504 \n", + "4 1711350626 \n", + "5 9937878556 \n", + "6 2006476931 \n", + "7 1905610278 \n", + "8 3630351468 \n", + "9 6807852590 " + ], + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Registration StateViolation DescriptionVehicle Body TypeIssue DateTicket Number
0TXBus StopSDN2022-02-202366568410
1NJNo ParkingSUBN2022-12-301858496929
2CAFire HydrantSUBN2022-02-167980797083
3NJExpired MeterSDN2022-07-112267392504
4CADouble ParkingSDN2022-09-021711350626
5CAFire HydrantSDN2022-09-249937878556
6CANo ParkingSDN2022-03-252006476931
7CABus StopSDN2022-01-281905610278
8NJBus StopSDN2022-06-093630351468
9NJBus StopSUBN2022-08-206807852590
\n", + "
" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "variable_name": "df" + } + }, + "metadata": {}, + "execution_count": 43 + } + ] + }, + { + "cell_type": "code", + "source": [ + "import pandas as pd\n", + "import bigframes.pandas as bpd\n", + "from google.cloud import bigquery\n", + "\n", + "# https://cloud.google.com/resource-manager/docs/creating-managing-projects\n", + "# project_id = '[your Cloud Platform project ID]' # Using project_id from cell yrElKJx3vNTQ\n", + "sample_count = 2000\n", + "\n", + "# Set BigQuery DataFrames options (using location from cell adSrR635vNTQ)\n", + "bpd.close_session()\n", + "bpd.options.bigquery.project = project_id\n", + "bpd.options.bigquery.location = \"US\"\n", + "\n", + "\n", + "row_count = pd.io.gbq.read_gbq('''\n", + " SELECT\n", + " COUNT(*) as total\n", + " FROM `bigquery-public-data.samples.gsod`\n", + "''', project_id=project_id, location=bpd.options.bigquery.location).total[0]\n", + "\n", + "df = pd.io.gbq.read_gbq(f'''\n", + " SELECT\n", + " *\n", + " FROM\n", + " `bigquery-public-data.samples.gsod`\n", + " WHERE RAND() < {sample_count}/{row_count}\n", + "''', project_id=project_id, location=bpd.options.bigquery.location)\n", + "\n", + "print(f'Full dataset has {row_count} rows')" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 628 + }, + "id": "rfbBILTXvMg4", + "outputId": "526f4f0d-4609-47ea-b8e7-b20d012cecb4" + }, + "execution_count": 50, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "/usr/local/lib/python3.12/dist-packages/cudf/pandas/fast_slow_proxy.py:28: FutureWarning: read_gbq is deprecated and will be removed in a future version. Please use pandas_gbq.read_gbq instead: https://pandas-gbq.readthedocs.io/en/latest/api.html#pandas_gbq.read_gbq\n", + " return fn(*args, **kwargs)\n" + ] + }, + { + "output_type": "error", + "ename": "GenericGBQException", + "evalue": "Reason: 400 POST https://bigquery.googleapis.com/bigquery/v2/projects/%5Byour%20Cloud%20Platform%20project%20ID%5D/queries?prettyPrint=false: Invalid project ID '[your Cloud Platform project ID]'. Project IDs must contain 6-63 lowercase letters, digits, or dashes. Some project IDs also include domain name separated by a colon. IDs must start with a letter and may not end with a dash.", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mBadRequest\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas_gbq/query.py\u001b[0m in \u001b[0;36mtry_query\u001b[0;34m(connector, query_fn)\u001b[0m\n\u001b[1;32m 84\u001b[0m \u001b[0mlogger\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdebug\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Requesting query... \"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 85\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mquery_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 86\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mconcurrent\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfutures\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTimeoutError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mex\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/cloud/bigquery/client.py\u001b[0m in \u001b[0;36mquery_and_wait\u001b[0;34m(self, query, job_config, location, project, api_timeout, wait_timeout, retry, job_retry, page_size, max_results)\u001b[0m\n\u001b[1;32m 3660\u001b[0m \"\"\"\n\u001b[0;32m-> 3661\u001b[0;31m return self._query_and_wait_bigframes(\n\u001b[0m\u001b[1;32m 3662\u001b[0m \u001b[0mquery\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/cloud/bigquery/client.py\u001b[0m in \u001b[0;36m_query_and_wait_bigframes\u001b[0;34m(self, query, job_config, location, project, api_timeout, wait_timeout, retry, job_retry, page_size, max_results, callback)\u001b[0m\n\u001b[1;32m 3706\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3707\u001b[0;31m return _job_helpers.query_and_wait(\n\u001b[0m\u001b[1;32m 3708\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/cloud/bigquery/_job_helpers.py\u001b[0m in \u001b[0;36mquery_and_wait\u001b[0;34m(client, query, job_config, location, project, api_timeout, wait_timeout, retry, job_retry, page_size, max_results, callback)\u001b[0m\n\u001b[1;32m 626\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mjob_retry\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 627\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mjob_retry\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdo_query\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 628\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_unary.py\u001b[0m in \u001b[0;36mretry_wrapped_func\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 293\u001b[0m )\n\u001b[0;32m--> 294\u001b[0;31m return retry_target(\n\u001b[0m\u001b[1;32m 295\u001b[0m \u001b[0mtarget\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_unary.py\u001b[0m in \u001b[0;36mretry_target\u001b[0;34m(target, predicate, sleep_generator, timeout, on_error, exception_factory, **kwargs)\u001b[0m\n\u001b[1;32m 155\u001b[0m \u001b[0;31m# defer to shared logic for handling errors\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 156\u001b[0;31m next_sleep = _retry_error_helper(\n\u001b[0m\u001b[1;32m 157\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_base.py\u001b[0m in \u001b[0;36m_retry_error_helper\u001b[0;34m(exc, deadline, sleep_iterator, error_list, predicate_fn, on_error_fn, exc_factory_fn, original_timeout)\u001b[0m\n\u001b[1;32m 213\u001b[0m )\n\u001b[0;32m--> 214\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mfinal_exc\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msource_exc\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 215\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mon_error_fn\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_unary.py\u001b[0m in \u001b[0;36mretry_target\u001b[0;34m(target, predicate, sleep_generator, timeout, on_error, exception_factory, **kwargs)\u001b[0m\n\u001b[1;32m 146\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 147\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtarget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 148\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0minspect\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misawaitable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/cloud/bigquery/_job_helpers.py\u001b[0m in \u001b[0;36mdo_query\u001b[0;34m()\u001b[0m\n\u001b[1;32m 544\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mretry\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 545\u001b[0;31m response = retry(client._call_api)(\n\u001b[0m\u001b[1;32m 546\u001b[0m \u001b[0mretry\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;31m# We're calling the retry decorator ourselves.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_unary.py\u001b[0m in \u001b[0;36mretry_wrapped_func\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 293\u001b[0m )\n\u001b[0;32m--> 294\u001b[0;31m return retry_target(\n\u001b[0m\u001b[1;32m 295\u001b[0m \u001b[0mtarget\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_unary.py\u001b[0m in \u001b[0;36mretry_target\u001b[0;34m(target, predicate, sleep_generator, timeout, on_error, exception_factory, **kwargs)\u001b[0m\n\u001b[1;32m 155\u001b[0m \u001b[0;31m# defer to shared logic for handling errors\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 156\u001b[0;31m next_sleep = _retry_error_helper(\n\u001b[0m\u001b[1;32m 157\u001b[0m \u001b[0mexc\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_base.py\u001b[0m in \u001b[0;36m_retry_error_helper\u001b[0;34m(exc, deadline, sleep_iterator, error_list, predicate_fn, on_error_fn, exc_factory_fn, original_timeout)\u001b[0m\n\u001b[1;32m 213\u001b[0m )\n\u001b[0;32m--> 214\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mfinal_exc\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msource_exc\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 215\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mon_error_fn\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/api_core/retry/retry_unary.py\u001b[0m in \u001b[0;36mretry_target\u001b[0;34m(target, predicate, sleep_generator, timeout, on_error, exception_factory, **kwargs)\u001b[0m\n\u001b[1;32m 146\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 147\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtarget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 148\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0minspect\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misawaitable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/cloud/bigquery/client.py\u001b[0m in \u001b[0;36m_call_api\u001b[0;34m(self, retry, span_name, span_attributes, job_ref, headers, **kwargs)\u001b[0m\n\u001b[1;32m 860\u001b[0m ):\n\u001b[0;32m--> 861\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mcall\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 862\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/cloud/_http/__init__.py\u001b[0m in \u001b[0;36mapi_request\u001b[0;34m(self, method, path, query_params, data, content_type, headers, api_base_url, api_version, expect_json, _target_object, timeout, extra_api_info)\u001b[0m\n\u001b[1;32m 493\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;36m200\u001b[0m \u001b[0;34m<=\u001b[0m \u001b[0mresponse\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstatus_code\u001b[0m \u001b[0;34m<\u001b[0m \u001b[0;36m300\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 494\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mexceptions\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_http_response\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 495\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mBadRequest\u001b[0m: 400 POST https://bigquery.googleapis.com/bigquery/v2/projects/%5Byour%20Cloud%20Platform%20project%20ID%5D/queries?prettyPrint=false: Invalid project ID '[your Cloud Platform project ID]'. Project IDs must contain 6-63 lowercase letters, digits, or dashes. Some project IDs also include domain name separated by a colon. IDs must start with a letter and may not end with a dash.", + "\nThe above exception was the direct cause of the following exception:\n", + "\u001b[0;31mGenericGBQException\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m/tmp/ipython-input-401414200.py\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 14\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 15\u001b[0;31m row_count = pd.io.gbq.read_gbq('''\n\u001b[0m\u001b[1;32m 16\u001b[0m \u001b[0mSELECT\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 17\u001b[0m \u001b[0mCOUNT\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mtotal\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/cudf/pandas/fast_slow_proxy.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 720\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 721\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__call__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mAny\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 722\u001b[0;31m result, _ = _fast_slow_function_call(\n\u001b[0m\u001b[1;32m 723\u001b[0m \u001b[0;31m# We cannot directly call self here because we need it to be\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 724\u001b[0m \u001b[0;31m# converted into either the fast or slow object (by\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/cudf/pandas/fast_slow_proxy.py\u001b[0m in \u001b[0;36m_fast_slow_function_call\u001b[0;34m(func, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1047\u001b[0m \u001b[0m_slow_function_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1048\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mdisable_module_accelerator\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1049\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0mslow_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mslow_kwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1050\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0m_maybe_wrap_result\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfast\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1051\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/cudf/pandas/fast_slow_proxy.py\u001b[0m in \u001b[0;36mcall_operator\u001b[0;34m(fn, args, kwargs)\u001b[0m\n\u001b[1;32m 26\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 27\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mcall_operator\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 28\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 29\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 30\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas/io/gbq.py\u001b[0m in \u001b[0;36mread_gbq\u001b[0;34m(query, project_id, index_col, col_order, reauth, auth_local_webserver, dialect, location, configuration, credentials, use_bqstorage_api, max_results, progress_bar_type)\u001b[0m\n\u001b[1;32m 205\u001b[0m \u001b[0;31m# END: new kwargs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 206\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 207\u001b[0;31m return pandas_gbq.read_gbq(\n\u001b[0m\u001b[1;32m 208\u001b[0m \u001b[0mquery\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 209\u001b[0m \u001b[0mproject_id\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mproject_id\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas_gbq/gbq.py\u001b[0m in \u001b[0;36mread_gbq\u001b[0;34m(query_or_table, project_id, index_col, columns, reauth, auth_local_webserver, dialect, location, configuration, credentials, use_bqstorage_api, max_results, verbose, private_key, progress_bar_type, dtypes, auth_redirect_uri, client_id, client_secret, col_order, bigquery_client)\u001b[0m\n\u001b[1;32m 320\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 321\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0m_is_query\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mquery_or_table\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 322\u001b[0;31m final_df = connector.run_query(\n\u001b[0m\u001b[1;32m 323\u001b[0m \u001b[0mquery_or_table\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 324\u001b[0m \u001b[0mconfiguration\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mconfiguration\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas_gbq/gbq_connector.py\u001b[0m in \u001b[0;36mrun_query\u001b[0;34m(self, query, max_results, progress_bar_type, **kwargs)\u001b[0m\n\u001b[1;32m 238\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 239\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mFEATURES\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbigquery_has_query_and_wait\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 240\u001b[0;31m rows_iter = pandas_gbq.query.query_and_wait_via_client_library(\n\u001b[0m\u001b[1;32m 241\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 242\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclient\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas_gbq/query.py\u001b[0m in \u001b[0;36mquery_and_wait_via_client_library\u001b[0;34m(connector, client, query, job_config, location, project_id, max_results, timeout_ms)\u001b[0m\n\u001b[1;32m 196\u001b[0m \u001b[0mtimeout_ms\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mOptional\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mint\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 197\u001b[0m ):\n\u001b[0;32m--> 198\u001b[0;31m rows_iter = try_query(\n\u001b[0m\u001b[1;32m 199\u001b[0m \u001b[0mconnector\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 200\u001b[0m functools.partial(\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas_gbq/query.py\u001b[0m in \u001b[0;36mtry_query\u001b[0;34m(connector, query_fn)\u001b[0m\n\u001b[1;32m 97\u001b[0m )\n\u001b[1;32m 98\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mconnector\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhttp_error\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mex\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 99\u001b[0;31m \u001b[0mconnector\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprocess_http_error\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mex\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 100\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 101\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas_gbq/gbq_connector.py\u001b[0m in \u001b[0;36mprocess_http_error\u001b[0;34m(ex)\u001b[0m\n\u001b[1;32m 172\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mTableCreationError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"Reason: {error_message}\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 173\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 174\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mGenericGBQException\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Reason: {0}\"\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mex\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mex\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 175\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 176\u001b[0m def download_table(\n", + "\u001b[0;31mGenericGBQException\u001b[0m: Reason: 400 POST https://bigquery.googleapis.com/bigquery/v2/projects/%5Byour%20Cloud%20Platform%20project%20ID%5D/queries?prettyPrint=false: Invalid project ID '[your Cloud Platform project ID]'. Project IDs must contain 6-63 lowercase letters, digits, or dashes. Some project IDs also include domain name separated by a colon. IDs must start with a letter and may not end with a dash." + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "df.describe()" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 300 + }, + "id": "EqHm2LAMvMg4", + "outputId": "057a1a37-1fc9-47cd-e6cc-200e5c729814" + }, + "execution_count": 49, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " Issue Date Ticket Number\n", + "count 1000000 1.000000e+06\n", + "mean 2022-07-01 23:32:43.411199744 5.499237e+09\n", + "min 2022-01-01 00:00:00 1.000005e+09\n", + "25% 2022-04-02 00:00:00 3.249061e+09\n", + "50% 2022-07-02 00:00:00 5.499907e+09\n", + "75% 2022-10-01 00:00:00 7.748794e+09\n", + "max 2022-12-31 00:00:00 9.999998e+09\n", + "std NaN 2.597215e+09" + ], + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Issue DateTicket Number
count10000001.000000e+06
mean2022-07-01 23:32:43.4111997445.499237e+09
min2022-01-01 00:00:001.000005e+09
25%2022-04-02 00:00:003.249061e+09
50%2022-07-02 00:00:005.499907e+09
75%2022-10-01 00:00:007.748794e+09
max2022-12-31 00:00:009.999998e+09
stdNaN2.597215e+09
\n", + "
" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"df\",\n \"rows\": 8,\n \"fields\": [\n {\n \"column\": \"Issue Date\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": \"1970-01-01 00:00:00.001000\",\n \"max\": \"2022-12-31 00:00:00\",\n \"num_unique_values\": 7,\n \"samples\": [\n \"1000000\",\n \"2022-07-01 23:32:43.411199744\",\n \"2022-10-01 00:00:00\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Ticket Number\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3390298193.6777215,\n \"min\": 1000000.0,\n \"max\": 9999997850.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 5499236759.115837,\n 7748793835.0,\n 1000000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {}, + "execution_count": 49 } ] }, @@ -261,7 +1535,7 @@ "metadata": { "id": "xERdbQehOc9t" }, - "execution_count": 540, + "execution_count": 49, "outputs": [] }, { @@ -281,7 +1555,7 @@ "metadata": { "id": "oomPQ7gAOhak" }, - "execution_count": 541, + "execution_count": 50, "outputs": [] }, { @@ -296,6 +1570,15 @@ "Load the galaxy images and potentially extract features or create textures from them.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "nxhXLYbswFru" + }, + "execution_count": 50, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -314,7 +1597,7 @@ "metadata": { "id": "nC-EQN2iOgDE" }, - "execution_count": 542, + "execution_count": 50, "outputs": [] }, { @@ -323,7 +1606,7 @@ "metadata": { "id": "VPtTWBADOfu9" }, - "execution_count": 543, + "execution_count": 50, "outputs": [] }, { @@ -346,6 +1629,15 @@ "* To proceed with the task, a Python environment with necessary image processing libraries like OpenCV would be required.\n" ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "tRST2G45wJ1B" + }, + "execution_count": 50, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -362,7 +1654,7 @@ "metadata": { "id": "6QWGZk0xOrQG" }, - "execution_count": 544, + "execution_count": 50, "outputs": [] }, { @@ -383,7 +1675,7 @@ "metadata": { "id": "HQq0lOvdOsEu" }, - "execution_count": 545, + "execution_count": 50, "outputs": [] }, { @@ -404,7 +1696,7 @@ "metadata": { "id": "Sw3XV9tKOs_O" }, - "execution_count": 546, + "execution_count": 50, "outputs": [] }, { @@ -442,7 +1734,7 @@ "metadata": { "id": "j5Up4iogOuTm" }, - "execution_count": 547, + "execution_count": 50, "outputs": [] }, { @@ -463,7 +1755,7 @@ "metadata": { "id": "cW5EIi4EOvCu" }, - "execution_count": 548, + "execution_count": 50, "outputs": [] }, { @@ -484,7 +1776,7 @@ "metadata": { "id": "Kn2-TSJ2Ov6v" }, - "execution_count": 549, + "execution_count": 50, "outputs": [] }, { @@ -505,7 +1797,7 @@ "metadata": { "id": "1xIVpO6lOwg3" }, - "execution_count": 550, + "execution_count": 50, "outputs": [] }, { @@ -538,7 +1830,7 @@ "metadata": { "id": "yUdzcWyCOyE3" }, - "execution_count": 551, + "execution_count": 50, "outputs": [] }, { @@ -559,7 +1851,7 @@ "metadata": { "id": "EAiDBHcpOyyH" }, - "execution_count": 552, + "execution_count": 50, "outputs": [] }, { @@ -580,7 +1872,7 @@ "metadata": { "id": "JyXLd_uoOz6f" }, - "execution_count": 553, + "execution_count": 50, "outputs": [] }, { @@ -601,7 +1893,7 @@ "metadata": { "id": "S6fzvdD5O1gH" }, - "execution_count": 554, + "execution_count": 50, "outputs": [] }, { @@ -610,7 +1902,7 @@ "metadata": { "id": "7Lj0S65PO2nQ" }, - "execution_count": 555, + "execution_count": 50, "outputs": [] }, { @@ -635,7 +1927,7 @@ "metadata": { "id": "v_NK4W7EO334" }, - "execution_count": 556, + "execution_count": 50, "outputs": [] }, { @@ -656,7 +1948,7 @@ "metadata": { "id": "1-j61bg7O5FI" }, - "execution_count": 557, + "execution_count": 50, "outputs": [] }, { @@ -677,7 +1969,7 @@ "metadata": { "id": "dUojeklHO56A" }, - "execution_count": 558, + "execution_count": 50, "outputs": [] }, { @@ -709,7 +2001,7 @@ "metadata": { "id": "_TIs_lY3O6xf" }, - "execution_count": 559, + "execution_count": 50, "outputs": [] }, { @@ -861,7 +2153,7 @@ "# The implementation was not possible in the current Julia environment due to the lack of necessary libraries for 3D graphics, audio processing, and user interaction.\n", "# The descriptions provided are based on how this project would be approached in a suitable Python environment with access to relevant libraries." ], - "execution_count": 560, + "execution_count": 51, "outputs": [] }, { @@ -870,7 +2162,7 @@ "metadata": { "id": "pa7fx_3IO9yJ" }, - "execution_count": 561, + "execution_count": 51, "outputs": [] }, { @@ -900,7 +2192,7 @@ "metadata": { "id": "mWy7fGpuO_TA" }, - "execution_count": 562, + "execution_count": 51, "outputs": [] }, { @@ -930,7 +2222,23 @@ "metadata": { "id": "yYKbRNvXPAug" }, - "execution_count": 563, + "execution_count": 51, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [], + "metadata": { + "id": "TdB06AzNwNjG" + } + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "6_TmfNYqwO8v" + }, + "execution_count": 51, "outputs": [] } ] From cb7f75a094c0aa123fab96b69a33c3cc5676672c Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Fri, 29 Aug 2025 09:06:21 -0700 Subject: [PATCH 12/28] Created using Colab --- quickstarts/Get_started_LiveAPI.ipynb | 1039 +++++++++++++++++++++++++ 1 file changed, 1039 insertions(+) create mode 100644 quickstarts/Get_started_LiveAPI.ipynb diff --git a/quickstarts/Get_started_LiveAPI.ipynb b/quickstarts/Get_started_LiveAPI.ipynb new file mode 100644 index 0000000..157e32b --- /dev/null +++ b/quickstarts/Get_started_LiveAPI.ipynb @@ -0,0 +1,1039 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Tce3stUlHN0L" + }, + "source": [ + "##### Copyright 2025 Google LLC." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "cellView": "form", + "id": "tuOe1ymfHZPu" + }, + "outputs": [], + "source": [ + "#@title Licensed under the Apache License, Version 2.0 (the \"License\");\n", + "# you may not use this file except in compliance with the License.\n", + "# You may obtain a copy of the License at\n", + "#\n", + "# https://www.apache.org/licenses/LICENSE-2.0\n", + "#\n", + "# Unless required by applicable law or agreed to in writing, software\n", + "# distributed under the License is distributed on an \"AS IS\" BASIS,\n", + "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n", + "# See the License for the specific language governing permissions and\n", + "# limitations under the License." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "R5DkeFMP75as" + }, + "source": [ + "# Multimodal Live API - Quickstart" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "tqktCVDm1yFo" + }, + "source": [ + "" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "iS0rHk3RBrtA" + }, + "source": [ + "**Preview**: The Live API is in preview.\n", + "\n", + "This notebook demonstrates simple usage of the Gemini Multimodal Live API. For an overview of new capabilities refer to the [Gemini Live API docs](https://ai.google.dev/gemini-api/docs/live).\n", + "\n", + "This notebook implements a simple turn-based chat where you send messages as text, and the model replies with audio. The API is capable of much more than that. The goal here is to demonstrate with **simple code**.\n", + "\n", + "Some features of the API are not working in Colab, to try them it is recommended to have a look at this [Python script](./Get_started_LiveAPI.py) and run it locally.\n", + "\n", + "If you aren't looking for code, and just want to try multimedia streaming use [Live API in Google AI Studio](https://aistudio.google.com/app/live).\n", + "\n", + "The [Next steps](#next_steps) section at the end of this tutorial provides links to additional resources.\n", + "\n", + "#### Native audio output\n", + "\n", + "**Info**: Gemini 2.5 introduces [native audio generation](https://ai.google.dev/gemini-api/docs/live#native-audio-output), which directly generates audio output, providing a more natural sounding audio, more expressive voices, more awareness of additional context, e.g., tone, and more proactive responses. You can try a native audio example in this [script](./Get_started_LiveAPI_NativeAudio.py)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Mfk6YY3G5kqp" + }, + "source": [ + "## Setup" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "d5027929de8f" + }, + "source": [ + "### Install SDK\n", + "\n", + "The new **[Google Gen AI SDK](https://ai.google.dev/gemini-api/docs/sdks)** provides programmatic access to Gemini 2.5 (and previous models) using both the [Google AI for Developers](https://ai.google.dev/gemini-api/docs) and [Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/docs/overview) APIs. With a few exceptions, code that runs on one platform will run on both.\n", + "\n", + "More details about this new SDK on the [documentation](https://ai.google.dev/gemini-api/docs/sdks) or in the [Getting started](../quickstarts/Get_started.ipynb) notebook." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "46zEFO2a9FFd", + "outputId": "444618bd-a432-428b-b15a-d3bfcef91065" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Note: you may need to restart the kernel to use updated packages.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "\n", + "[notice] A new release of pip is available: 25.1.1 -> 25.2\n", + "[notice] To update, run: python.exe -m pip install --upgrade pip\n" + ] + } + ], + "source": [ + "%pip install -U -q google-genai" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "CTIfnvCn9HvH" + }, + "source": [ + "### Set up your API key\n", + "\n", + "To run the following cell, your API key must be stored in a Colab Secret named `GOOGLE_API_KEY`. If you don't already have an API key, or you're not sure how to create a Colab Secret, see [Authentication](../quickstarts/Authentication.ipynb) for an example." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "A1pkoyZb9Jm3" + }, + "outputs": [], + "source": [ + "from google.colab import userdata\n", + "import os\n", + "\n", + "os.environ['GOOGLE_API_KEY'] = userdata.get('GOOGLE_API_KEY')\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "3Hx_Gw9i0Yuv" + }, + "source": [ + "### Initialize SDK client\n", + "\n", + "The client will pick up your API key from the environment variable." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "HghvVpbU0Uap" + }, + "outputs": [], + "source": [ + "from google import genai\n", + "from google.genai import types\n", + "client = genai.Client(api_key=GOOGLE_API_KEY)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "QOov6dpG99rY" + }, + "source": [ + "### Select a model\n", + "\n", + "The [Gemini 2.5 Flash Live](https://ai.google.dev/gemini-api/docs/models#live-api) model works with the Live API to enable low-latency bidirectional voice and video interactions with Gemini. The model can process text, audio, and video input, and it can provide text and audio output." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "27Fikag0xSaB" + }, + "outputs": [], + "source": [ + "MODEL = \"gemini-2.0-flash-live-001\" # @param [\"gemini-2.0-flash-live-001\", \"gemini-live-2.5-flash-preview\",\"gemini-2.5-flash-preview-native-audio-dialog\"] {\"allow-input\":true, isTemplate: true}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "GOOZsm7i9io6" + }, + "source": [ + "### Import\n", + "\n", + "Import all the necessary modules." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "Yd1vs3cP8EmS" + }, + "outputs": [], + "source": [ + "import asyncio\n", + "import base64\n", + "import contextlib\n", + "import datetime\n", + "import os\n", + "import json\n", + "import wave\n", + "import itertools\n", + "\n", + "from IPython.display import display, Audio\n", + "\n", + "from google import genai\n", + "from google.genai import types" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "jj7gDzfDOq4h" + }, + "source": [ + "## Text to Text\n", + "\n", + "The simplest way to use the Live API is as a text-to-text chat interface, but it can do **a lot** more than this." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "dDfslcyIOqgI", + "outputId": "ae08f423-be20-4e05-876e-479485cf7004" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "> Hello? Gemini are you there? \n", + "\n", + "- Hello\n", + "- there! I am indeed here. How can I help you today?\n" + ] + } + ], + "source": [ + "config={\n", + " \"response_modalities\": [\"TEXT\"]\n", + "}\n", + "\n", + "async with client.aio.live.connect(model=MODEL, config=config) as session:\n", + " message = \"Hello? Gemini are you there?\"\n", + " print(\"> \", message, \"\\n\")\n", + " await session.send_client_content(\n", + " turns={\"role\": \"user\", \"parts\": [{\"text\": message}]}, turn_complete=True\n", + " )\n", + "\n", + " # For text responses, When the model's turn is complete it breaks out of the loop.\n", + " turn = session.receive()\n", + " async for chunk in turn:\n", + " if chunk.text is not None:\n", + " print(f'- {chunk.text}')" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "rvpmur4lKfOv" + }, + "source": [ + "## Simple text to audio" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "jjkzgogvG1q0" + }, + "source": [ + "The simplest way to playback the audio in Colab, is to write it out to a `.wav` file. So here is a simple wave file writer:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "7mEDGwJfLRrm" + }, + "outputs": [], + "source": [ + "@contextlib.contextmanager\n", + "def wave_file(filename, channels=1, rate=24000, sample_width=2):\n", + " with wave.open(filename, \"wb\") as wf:\n", + " wf.setnchannels(channels)\n", + " wf.setsampwidth(sample_width)\n", + " wf.setframerate(rate)\n", + " yield wf" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "DGuKQSurN7F4" + }, + "source": [ + "The next step is to tell the model to return audio by setting `\"response_modalities\": [\"AUDIO\"]` in the `LiveConnectConfig`. \n", + "\n", + "When you get a response from the model, then you write out the data to a `.wav` file." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "VFD4VleVKj1-", + "outputId": "6d5420ae-8d9b-4ab4-c048-7c176aa4c5f4" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "> Hello? Gemini are you there? \n", + "\n", + "audio/pcm;rate=24000\n", + "................" + ] + }, + { + "data": { + "text/html": [ + "\n", + " \n", + " " + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "config={\n", + " \"response_modalities\": [\"AUDIO\"]\n", + "}\n", + "\n", + "async def async_enumerate(aiterable):\n", + " n=0\n", + " async for item in aiterable:\n", + " yield n, item\n", + " n+=1\n", + "\n", + "\n", + "async with client.aio.live.connect(model=MODEL, config=config) as session:\n", + " file_name = 'audio.wav'\n", + " with wave_file(file_name) as wav:\n", + " message = \"Hello? Gemini are you there?\"\n", + " print(\"> \", message, \"\\n\")\n", + " await session.send_client_content(\n", + " turns={\"role\": \"user\", \"parts\": [{\"text\": message}]}, turn_complete=True\n", + " )\n", + "\n", + " turn = session.receive()\n", + " async for n,response in async_enumerate(turn):\n", + " if response.data is not None:\n", + " wav.writeframes(response.data)\n", + "\n", + " if n==0:\n", + " print(response.server_content.model_turn.parts[0].inline_data.mime_type)\n", + " print('.', end='')\n", + "\n", + "\n", + "display(Audio(file_name, autoplay=True))\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "QutDG7r78Zf-" + }, + "source": [ + "## Towards Async Tasks\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "YfEQZrtZY_90" + }, + "source": [ + "The real power of the Live API is that it's real time, and interruptable. You can't get that full power in a simple sequence of steps. To really use the functionality you will move the `send` and `recieve` operations (and others) into their own [async tasks](https://docs.python.org/3/library/asyncio-task.html).\n", + "\n", + "Because of the limitations of Colab this tutorial doesn't totally implement the interactive async tasks, but it does implement the next step in that direction:\n", + "\n", + "- It separates the `send` and `receive`, but still runs them sequentially. \n", + "- In the next tutorial you'll run these in separate `async` tasks.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "QUBet__tZF0o" + }, + "source": [ + "Setup a quick logger to make debugging easier (switch to `setLevel('DEBUG')` to see debugging messages)." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "bWTaU8j-X3AJ" + }, + "outputs": [], + "source": [ + "import logging\n", + "\n", + "logger = logging.getLogger('Live')\n", + "logger.setLevel('INFO')" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ERqyY0IFN8G9" + }, + "source": [ + "The class below implements the interaction with the Live API." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "3zAjMOZXFuxI" + }, + "outputs": [], + "source": [ + "class AudioLoop:\n", + " def __init__(self, turns=None, config=None):\n", + " self.session = None\n", + " self.index = 0\n", + " self.turns = turns\n", + " if config is None:\n", + " config={\n", + " \"response_modalities\": [\"AUDIO\"]}\n", + " self.config = config\n", + "\n", + " async def run(self):\n", + " logger.debug('connect')\n", + " async with client.aio.live.connect(model=MODEL, config=self.config) as session:\n", + " self.session = session\n", + "\n", + " async for sent in self.send():\n", + " # Ideally send and recv would be separate tasks.\n", + " await self.recv()\n", + "\n", + " async def _iter(self):\n", + " if self.turns:\n", + " for text in self.turns:\n", + " print(\"message >\", text)\n", + " yield text\n", + " else:\n", + " print(\"Type 'q' to quit\")\n", + " while True:\n", + " text = await asyncio.to_thread(input, \"message > \")\n", + "\n", + " # If the input returns 'q' quit.\n", + " if text.lower() == 'q':\n", + " break\n", + "\n", + " yield text\n", + "\n", + " async def send(self):\n", + " async for text in self._iter():\n", + " logger.debug('send')\n", + "\n", + " # Send the message to the model.\n", + " await self.session.send_client_content(\n", + " turns={\"role\": \"user\", \"parts\": [{\"text\": text}]}, turn_complete=True\n", + " )\n", + " logger.debug('sent')\n", + " yield text\n", + "\n", + " async def recv(self):\n", + " # Start a new `.wav` file.\n", + " file_name = f\"audio_{self.index}.wav\"\n", + " with wave_file(file_name) as wav:\n", + " self.index += 1\n", + "\n", + " logger.debug('receive')\n", + "\n", + " # Read chunks from the socket.\n", + " turn = self.session.receive()\n", + " async for n, response in async_enumerate(turn):\n", + " logger.debug(f'got chunk: {str(response)}')\n", + "\n", + " if response.data is None:\n", + " logger.debug(f'Unhandled server message! - {response}')\n", + " else:\n", + " wav.writeframes(response.data)\n", + " if n == 0:\n", + " print(response.server_content.model_turn.parts[0].inline_data.mime_type)\n", + " print('.', end='')\n", + "\n", + " print('\\n')\n", + "\n", + " display(Audio(file_name, autoplay=True))\n", + " await asyncio.sleep(2)\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "AwNPuC_rAHAc" + }, + "source": [ + "There are 3 methods worth describing here:" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "tXPhEdHIPBif" + }, + "source": [ + "**`run` - The main loop**\n", + "\n", + "This method:\n", + "\n", + "- Opens a `websocket` connecting to the Live API.\n", + "- Calls the initial `setup` method.\n", + "- Then enters the main loop where it alternates between `send` and `recv` until send returns `False`.\n", + "- The next tutorial will demonstrate how to stream media and run these asynchronously." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "oCg1qFf0PV44" + }, + "source": [ + "**`send` - Sends input text to the api**\n", + "\n", + "The `send` method collects input text from the user, wraps it in a `client_content` message (an instance of `BidiGenerateContentClientContent`), and sends it to the model.\n", + "\n", + "If the user sends a `q` this method returns `False` to signal that it's time to quit." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "tLukmBhPPib4" + }, + "source": [ + "**`recv` - Collects audio from the API and plays it**\n", + "\n", + "The `recv` method collects audio chunks in a loop and writes them to a `.wav` file. It breaks out of the loop once the model sends a `turn_complete` method, and then plays the audio.\n", + "\n", + "To keep things simple in Colab it collects **all** the audio before playing it. [Other examples](#next_steps) demonstrate how to play audio as soon as you start to receive it (using `PyAudio`), and how to interrupt the model (implement input and audio playback on separate tasks)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "gGYtiV2N8b2o" + }, + "source": [ + "### Run\n", + "\n", + "Run it:\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "WxdwgTKIGIlY", + "outputId": "dfc710c3-f0f3-4ff0-9e10-75edaedf63d7" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "message > Hello\n", + "audio/pcm;rate=24000\n", + "....................\n", + "\n" + ] + }, + { + "data": { + "text/html": [ + "\n", + " \n", + " " + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "message > What's your name?\n", + "audio/pcm;rate=24000\n", + "..........\n", + "\n" + ] + }, + { + "data": { + "text/html": [ + "\n", + " \n", + " " + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "await AudioLoop(['Hello', \"What's your name?\"]).run()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "uZD24TXrcsfk" + }, + "source": [ + "## Working with resumable sessions\n", + "\n", + "Session resumption allows you to return to a previous interaction with the Live API by sending the last session handle you got from the previous session.\n", + "\n", + "When you set your session to be resumable, the session information keeps stored on the Live API for up to 24 hours. In this time window, you can resume the conversation and refer to previous information you have shared with the model.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "qveK8jxae_x0" + }, + "source": [ + "### Helper functions\n", + "\n", + "Start by creating the helper functions for your resumable interaction with the Live API. It will include:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "cbkoDa1ve_C5" + }, + "outputs": [], + "source": [ + "import asyncio\n", + "import traceback\n", + "from asyncio.exceptions import CancelledError\n", + "\n", + "last_handle = None\n", + "\n", + "MODEL = \"gemini-live-2.5-flash-preview\"\n", + "\n", + "client = genai.Client(api_key=GOOGLE_API_KEY)\n", + "\n", + "async def async_enumerate(aiterable):\n", + " n=0\n", + " async for item in aiterable:\n", + " yield n, item\n", + " n+=1\n", + "\n", + "\n", + "def show_response(response):\n", + " new_handle = None\n", + " if text := response.text:\n", + " print(text, end=\"\")\n", + " else:\n", + " print(response.model_dump_json(indent=2, exclude_none=True))\n", + " if response.session_resumption_update:\n", + " new_handle = response.session_resumption_update.new_handle\n", + " return new_handle\n", + "\n", + "\n", + "async def clock():\n", + " time = 0\n", + " while True:\n", + " await asyncio.sleep(60)\n", + " time += 1\n", + " print(f\"{time}:00\")\n", + "\n", + "\n", + "async def recv(session):\n", + " global last_handle\n", + " try:\n", + " while True:\n", + " async for response in session.receive():\n", + " new_handle = show_response(response)\n", + " if new_handle:\n", + " last_handle = new_handle\n", + " except asyncio.CancelledError:\n", + " pass\n", + "\n", + "\n", + "async def send(session):\n", + " while True:\n", + " message = await asyncio.to_thread(input, \"message > \")\n", + " if message.lower() == \"q\":\n", + " break\n", + " await session.send_client_content(turns={\n", + " 'role': 'user',\n", + " 'parts': [{'text': message}]\n", + " })\n", + "\n", + "\n", + "async def async_main(last_handle=None):\n", + " config = types.LiveConnectConfig.model_validate({\n", + " \"response_modalities\": [\"TEXT\"],\n", + " \"session_resumption\": {\n", + " 'handle': last_handle,\n", + " }\n", + " })\n", + " try:\n", + " async with (\n", + " client.aio.live.connect(model=MODEL, config=config) as session,\n", + " asyncio.TaskGroup() as tg\n", + " ):\n", + " clock_task = tg.create_task(clock())\n", + " recv_task = tg.create_task(recv(session))\n", + " send_task = tg.create_task(send(session))\n", + " await send_task\n", + " raise asyncio.CancelledError()\n", + " except asyncio.CancelledError:\n", + " pass\n", + " except ExceptionGroup as EG:\n", + " traceback.print_exception(EG)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "xsPClQxUkO9V" + }, + "source": [ + "Now you can start interacting with the Live API (type `q` to finish the conversation):" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "yqBTtKvGmKI4", + "outputId": "fda0516a-7ea2-4e6e-9371-bb3a8a3280bf" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{\n", + " \"session_resumption_update\": {}\n", + "}\n", + "Hello there! How can I help you today?{\n", + " \"server_content\": {\n", + " \"generation_complete\": true\n", + " }\n", + "}\n", + "{\n", + " \"server_content\": {\n", + " \"turn_complete\": true\n", + " },\n", + " \"usage_metadata\": {\n", + " \"prompt_token_count\": 9,\n", + " \"response_token_count\": 10,\n", + " \"total_token_count\": 19,\n", + " \"prompt_tokens_details\": [\n", + " {\n", + " \"modality\": \"TEXT\",\n", + " \"token_count\": 9\n", + " }\n", + " ],\n", + " \"response_tokens_details\": [\n", + " {\n", + " \"modality\": \"TEXT\",\n", + " \"token_count\": 10\n", + " }\n", + " ]\n", + " }\n", + "}\n", + "{\n", + " \"session_resumption_update\": {\n", + " \"new_handle\": \"Cig2N3lqa3d3MXd4eHFoeDk3cnhmeHUydjlhdHN2cms1bDRnc3c0N2Zq\",\n", + " \"resumable\": true\n", + " }\n", + "}\n", + "1:00\n", + "{\n", + " \"session_resumption_update\": {}\n", + "}\n", + "The capital of Brazil is **Brasília**.{\n", + " \"server_content\": {\n", + " \"generation_complete\": true\n", + " }\n", + "}\n", + "{\n", + " \"server_content\": {\n", + " \"turn_complete\": true\n", + " },\n", + " \"usage_metadata\": {\n", + " \"prompt_token_count\": 36,\n", + " \"response_token_count\": 9,\n", + " \"total_token_count\": 45,\n", + " \"prompt_tokens_details\": [\n", + " {\n", + " \"modality\": \"TEXT\",\n", + " \"token_count\": 36\n", + " }\n", + " ],\n", + " \"response_tokens_details\": [\n", + " {\n", + " \"modality\": \"TEXT\",\n", + " \"token_count\": 9\n", + " }\n", + " ]\n", + " }\n", + "}\n", + "{\n", + " \"session_resumption_update\": {\n", + " \"new_handle\": \"Cig0ZDR1OTViNHVjOWh6aGJvMmhwdWk3NzJiZWRwYW91bnNtajgxZHN1\",\n", + " \"resumable\": true\n", + " }\n", + "}\n" + ] + } + ], + "source": [ + "await async_main()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "NdUy9WsrJwxi" + }, + "source": [ + "With the session resumption you have the session handle to refer to your previous sessions. In this example, the handle is saved at the `last_handle` variable as below:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "Y5ZVUQ5vJrEJ", + "outputId": "49994add-7cc3-44cc-ba9b-8692a7c2654a" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "'Cig0ZDR1OTViNHVjOWh6aGJvMmhwdWk3NzJiZWRwYW91bnNtajgxZHN1'" + ] + }, + "execution_count": 39, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "last_handle" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "xEIhRZBYJ_8V" + }, + "source": [ + "Now you can start a new Live API session, but this time pointing to a handle from a previous session. Also, to test you could gather information from the previous session, you will ask the model what was the second question you asked before (in this example, it was \"what is the capital of Brazil?\"). You can see the Live API recovering that information:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "xH_iZhTxKFtF", + "outputId": "22f4d1ab-362c-401a-ce40-8d386cf209e4" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{\n", + " \"session_resumption_update\": {}\n", + "}\n", + "The last question you asked was: \"what is the capital of brazil?\"{\n", + " \"server_content\": {\n", + " \"generation_complete\": true\n", + " }\n", + "}\n", + "{\n", + " \"server_content\": {\n", + " \"turn_complete\": true\n", + " },\n", + " \"usage_metadata\": {\n", + " \"prompt_token_count\": 63,\n", + " \"response_token_count\": 15,\n", + " \"total_token_count\": 78,\n", + " \"prompt_tokens_details\": [\n", + " {\n", + " \"modality\": \"TEXT\",\n", + " \"token_count\": 63\n", + " }\n", + " ],\n", + " \"response_tokens_details\": [\n", + " {\n", + " \"modality\": \"TEXT\",\n", + " \"token_count\": 15\n", + " }\n", + " ]\n", + " }\n", + "}\n", + "{\n", + " \"session_resumption_update\": {\n", + " \"new_handle\": \"CihyNDg4YTkxanl5cThzYmo4a29lMHRveDJlY3U1amRyNHlqeWF0bWU2\",\n", + " \"resumable\": true\n", + " }\n", + "}\n" + ] + } + ], + "source": [ + "await async_main(last_handle)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ietchD8GbcXt" + }, + "source": [ + "## Next steps\n", + "\n", + "\n", + "\n", + "This tutorial just shows basic usage of the Live API, using the Python GenAI SDK.\n", + "\n", + "- If you aren't looking for code, and just want to try multimedia streaming use [Live API in Google AI Studio](https://aistudio.google.com/app/live).\n", + "- If you want to see how to setup streaming interruptible audio and video using the Live API see the [Audio and Video input Tutorial](../quickstarts/Get_started_LiveAPI.py).\n", + "- If you're interested in the low level details of using the websockets directly, see the [websocket version of this tutorial](../quickstarts/websockets/Get_started_LiveAPI.ipynb).\n", + "- Try the [Tool use in the live API tutorial](../quickstarts/Get_started_LiveAPI_tools.ipynb) for an walkthrough of Gemini-2.5's new use capabilities.\n", + "- There is a [Streaming audio in Colab example](../quickstarts/websockets/LiveAPI_streaming_in_colab.ipynb), but this is more of a **demo**, it's **not optimized for readability**.\n", + "- Other nice Gemini 2.5 examples can also be found in the [Cookbook's example\n", + " directory](https://github.com/google-gemini/cookbook/tree/main/examples/), in particular the [video understanding](../quickstarts/Video_understanding.ipynb) and the [spatial understanding](../quickstarts/Spatial_understanding.ipynb) ones." + ] + }, + { + "cell_type": "markdown", + "source": [ + "# New Section" + ], + "metadata": { + "id": "TKJvxpqBlBEl" + } + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "bNlAkeqHlCkN" + }, + "execution_count": null, + "outputs": [] + } + ], + "metadata": { + "colab": { + "collapsed_sections": [ + "Tce3stUlHN0L" + ], + "name": "Get_started_LiveAPI.ipynb", + "toc_visible": true, + "provenance": [], + "include_colab_link": true + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file From a004805d7811440fbd3d833ee56158257932c058 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 30 Aug 2025 19:12:11 -0700 Subject: [PATCH 13/28] Created using Colab --- .../vertex_ai_prompt_optimizer_ui.ipynb | 498 ++++++++++++++++++ 1 file changed, 498 insertions(+) create mode 100644 gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb diff --git a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb new file mode 100644 index 0000000..4e6a675 --- /dev/null +++ b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb @@ -0,0 +1,498 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "hlI1rYKa2IGx" + }, + "outputs": [], + "source": [ + "# Copyright 2024 Google LLC\n", + "#\n", + "# Licensed under the Apache License, Version 2.0 (the \"License\");\n", + "# you may not use this file except in compliance with the License.\n", + "# You may obtain a copy of the License at\n", + "#\n", + "# https://www.apache.org/licenses/LICENSE-2.0\n", + "#\n", + "# Unless required by applicable law or agreed to in writing, software\n", + "# distributed under the License is distributed on an \"AS IS\" BASIS,\n", + "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n", + "# See the License for the specific language governing permissions and\n", + "# limitations under the License." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "RN8N3O43QDT5" + }, + "source": [ + "# Vertex Prompt Optimizer Notebook UI (Preview)\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + "
\n", + " \n", + " \"Google
Open in Colab\n", + " \n", + " 		\n", + " \n", + " \"Google
Open in Colab Enterprise\n", + " \n", + " 		\n", + " \n", + " \"Vertex
Open in Vertex AI Workbench\n", + " \n", + " 		\n", + " \n", + " \"GitHub
View on GitHub\n", + " \n", + "
\n", + "\n", + "
\n", + "\n", + "Share to:\n", + "\n", + "\n", + " \"LinkedIn\n", + "\n", + "\n", + "\n", + " \"Bluesky\n", + "\n", + "\n", + "\n", + " \"X\n", + "\n", + "\n", + "\n", + " \"Reddit\n", + "\n", + "\n", + "\n", + " \"Facebook\n", + " " + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "pHyuJTFr2IGx" + }, + "source": [ + "# Overview\n", + "This Notebook showcases the Vertex AI prompt optimizer, a tool that iteratively optimizes prompts to suit a target model (e.g., `gemini-2.0-flash`) using target-specific metric(s).\n", + "\n", + "Key Use Cases:\n", + "\n", + "* Prompt Optimization: Enhance the quality of an initial prompt by refining its structure and content to match the target model's optimal input characteristics.\n", + "\n", + "* Prompt Translation: Adapt prompts optimized for one model to work effectively with a different target model.\n", + "\n", + "For the detailed documentation please see [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "61RBz8LLbxCR" + }, + "source": [ + "## Getting Started" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "dmWOrTJ3gx13" + }, + "source": [ + "### Authenticate your notebook environment (Colab only)\n", + "\n", + "Authenticate your environment on Google Colab.\n" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "id": "NyKGtVQjgx13" + }, + "outputs": [], + "source": [ + "import sys\n", + "\n", + "if \"google.colab\" in sys.modules:\n", + " from google.colab import auth\n", + "\n", + " auth.authenticate_user()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "tTtKHedrO1Rx" + }, + "source": [ + "# Step 0: Install packages and libraries" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "8-Zw72vFORz_", + "outputId": "98b34e63-ec34-4799-adf8-fce2af428b25", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "--2025-08-31 02:12:00-- https://raw.githubusercontent.com/GoogleCloudPlatform/generative-ai/main/gemini/prompts/prompt_optimizer/vapo_lib.py\n", + "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n", + "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n", + "HTTP request sent, awaiting response... 200 OK\n", + "Length: 37206 (36K) [text/plain]\n", + "Saving to: ‘vapo_lib.py’\n", + "\n", + "\rvapo_lib.py 0%[ ] 0 --.-KB/s \rvapo_lib.py 100%[===================>] 36.33K --.-KB/s in 0.006s \n", + "\n", + "2025-08-31 02:12:00 (5.64 MB/s) - ‘vapo_lib.py’ saved [37206/37206]\n", + "\n" + ] + } + ], + "source": [ + "!wget https://raw.githubusercontent.com/GoogleCloudPlatform/generative-ai/main/gemini/prompts/prompt_optimizer/vapo_lib.py\n", + "import vapo_lib" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "-p59jd5rOp4q" + }, + "source": [ + "# Step 1: Create a prompt template and system instructions\n", + "Provide your system intruction and prompt template below. Refer to [here]( https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#template-si) for instructions.\n", + "\n", + "Prompts consist of two key components:\n", + "\n", + "- System Instruction: System instruction is the instruction that get passed to the model before any user input in the prompt. This is the fixed part of the prompt template shared across all queries for a given task.\n", + "- Prompt template: A task is the text in the prompt that you want the model to provide a response for. Context is information that you include in the prompt that the model uses or references when generating a response. These are the dynamic parts of the prompt template that changes based on the task.\n", + "\n", + "Prompt Optimizer enables the optimization or translation of the System Instruction template, while the prompt template remains essential for evaluating and selecting the best System Instruction template." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "rJG1pVZO317x" + }, + "outputs": [], + "source": [ + "SYSTEM_INSTRUCTION = (\n", + " \"Answer the following question. Let's think step by step.\\n\" # @param\n", + ")\n", + "PROMPT_TEMPLATE = \"Question: {question}\\n\\nAnswer: {target}\" # @param" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "5y-cmg0TQP6v" + }, + "source": [ + "# Step 2: Configure project settings\n", + "To optimize the prompt for your target Google model, provide a CSV or JSONL file containing labeled validation samples (input, ground truth output pairs). Refer to [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#prepare-sample-prompts) for instructions.\n", + "\n", + "Focus on examples that specifically demonstrate the issues you want to address.\n", + "Recommendation: Use 50-100 distinct samples for reliable results. However, the tool can still be effective with as few as 5 samples.\n", + "For prompt translation (e.g. 3P model to Google model, PaLM 2 to Gemini):\n", + "\n", + "Consider using the source model to label examples that the target model struggles with, helping to identify areas for improvement.\n", + "When you select a source model, you don't need to provide labels for the input examples.\n", + "While the source model selection is limited to Google models, it still supports labeled inputs from non-Google models. If you wish to select a non-Google source model, you will need to provide labels for your input examples.\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "mfgi_oR6tTIB" + }, + "outputs": [], + "source": [ + "# @markdown **Project setup**:
\n", + "PROJECT_ID = \"[YOUR_PROJECT]\" # @param {type:\"string\"}\n", + "LOCATION = \"us-central1\" # @param {type:\"string\"}\n", + "OUTPUT_PATH = \"[OUTPUT_PATH]\" # @param {type:\"string\"}\n", + "INPUT_DATA_PATH = \"[INPUT_DATA_PATH]\" # @param {type:\"string\"}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ucebZHkHRxKH" + }, + "source": [ + "# Step 3: Configure optimization settings\n", + "The optimization configurations are defaulted to the values that are most commonly used, which we recommend using as the initial set-up.\n", + "\n", + "The most important settings are:\n", + "\n", + "* Target Model: Which model you are trying to optimize your prompts to.\n", + "* Thinking Budget: The thinking budget for thinking models like Gemini-2.5. Default to -1, which means no thinking for non-thinking models and auto thinking for thinking models. Refer [here](https://cloud.google.com/vertex-ai/generative-ai/docs/thinking) to learn more about manual budget settings.\n", + "* Optimization Mode: The mode in which you are trying to optimize your prompt with.\n", + "* Evaluation Metrics: The evaluation metrics in which you are trying to optimize your prompts against.\n", + "* Translation Source Field Name: fill in with the corresponding field name of the source text in the data if translation metrics like Comet or MetricX are selected. Otherwise, leave it as empty.\n", + "\n", + "Note that all evaluation metrics are expected to have the larger-the-better property. Therefore, we have modified the MetricX value to between 0 (worst) and 25 (best).\n", + "Refer [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#configuration) to learn more about the different configuration settings and how to best utilize them." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "B2R3P8mMvK9q" + }, + "outputs": [], + "source": [ + "TARGET_MODEL = \"gemini-2.0-flash-001\" # @param [\"gemini-2.5-flash-lite\", \"gemini-2.5-flash\", \"gemini-2.5-pro\", \"gemini-2.0-flash-lite-001\", \"gemini-2.0-flash-001\"]\n", + "THINKING_BUDGET = -1 # @param {type:\"integer\"}\n", + "OPTIMIZATION_MODE = \"instruction_and_demo\" # @param [\"instruction\", \"demonstration\", \"instruction_and_demo\"]\n", + "EVAL_METRIC = \"question_answering_correctness\" # @param [\"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "TRANSLATION_SOURCE_FIELD_NAME = \"\" # @param {type:\"string\"}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "kO7fO0qTSNLs" + }, + "source": [ + "# Step 4: Configure advanced optimization settings [Optional]\n", + "Refer [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#configuration) to learn more about the different configuration settings and how to best utilize them." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "fRHHTpaV4Xyo" + }, + "outputs": [], + "source": [ + "# @markdown **Instruction Optimization Configs**:
\n", + "NUM_INST_OPTIMIZATION_STEPS = 10 # @param {type:\"integer\"}\n", + "\n", + "# @markdown **Demonstration Optimization Configs**:
\n", + "NUM_DEMO_OPTIMIZATION_STEPS = 10 # @param {type:\"integer\"}\n", + "NUM_DEMO_PER_PROMPT = 3 # @param {type:\"integer\"}\n", + "\n", + "# @markdown **Model Configs**:
\n", + "TARGET_MODEL_QPS = 3.0 # @param {type:\"number\"}\n", + "EVAL_QPS = 3.0 # @param {type:\"number\"}\n", + "\n", + "# @markdown **Multi-metric Configs**:
\n", + "# @markdown Use this section only if you need more than one metric for optimization. This will override the metric you picked above.\n", + "EVAL_METRIC_1 = \"NA\" # @param [\"NA\", \"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "EVAL_METRIC_1_WEIGHT = 0.0 # @param {type:\"number\"}\n", + "EVAL_METRIC_2 = \"NA\" # @param [\"NA\", \"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "EVAL_METRIC_2_WEIGHT = 0.0 # @param {type:\"number\"}\n", + "EVAL_METRIC_3 = \"NA\" # @param [\"NA\", \"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "EVAL_METRIC_3_WEIGHT = 0.0 # @param {type:\"number\"}\n", + "METRIC_AGGREGATION_TYPE = \"weighted_sum\" # @param [\"weighted_sum\", \"weighted_average\"]\n", + "\n", + "# @markdown **Misc Configs**:
\n", + "PLACEHOLDER_TO_VALUE = \"{}\" # @param\n", + "RESPONSE_MIME_TYPE = \"text/plain\" # @param [\"text/plain\", \"application/json\", \"text/x.enum\"] {type:\"string\"}\n", + "RESPONSE_SCHEMA = \"\"\n", + "TARGET_LANGUAGE = \"English\" # @param [\"English\", \"French\", \"German\", \"Hebrew\", \"Hindi\", \"Italian\", \"Japanese\", \"Korean\", \"Portuguese\", \"Simplified Chinese\", \"Spanish\", \"Traditional Chinese\"] {type:\"string\"}\n", + "TOOLS = \"\" # @param\n", + "TOOL_CONFIG = \"\" # @param" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "X7Mgb0EHSSFk" + }, + "source": [ + "# Step 5: Run Prompt Optimizer\n", + "A progress bar will appear to let you know how long the job takes." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "Z8NvNLTfxPTf" + }, + "outputs": [], + "source": [ + "import datetime\n", + "import json\n", + "import time\n", + "\n", + "timestamp = datetime.datetime.now().strftime(\"%Y-%m-%dT%H:%M:%S\")\n", + "display_name = f\"pt_{timestamp}\"\n", + "\n", + "label_enforced = vapo_lib.is_run_target_required(\n", + " [\n", + " EVAL_METRIC,\n", + " EVAL_METRIC_1,\n", + " EVAL_METRIC_2,\n", + " EVAL_METRIC_3,\n", + " ],\n", + " \"\",\n", + ")\n", + "input_data_path = f\"{INPUT_DATA_PATH}\"\n", + "vapo_lib.validate_prompt_and_data(\n", + " \"\\n\".join([SYSTEM_INSTRUCTION, PROMPT_TEMPLATE]),\n", + " input_data_path,\n", + " PLACEHOLDER_TO_VALUE,\n", + " label_enforced,\n", + ")\n", + "\n", + "output_path = f\"{OUTPUT_PATH}/{display_name}\"\n", + "\n", + "params = {\n", + " \"project\": PROJECT_ID,\n", + " \"num_steps\": NUM_INST_OPTIMIZATION_STEPS,\n", + " \"system_instruction\": SYSTEM_INSTRUCTION,\n", + " \"prompt_template\": PROMPT_TEMPLATE,\n", + " \"target_model\": TARGET_MODEL,\n", + " \"target_model_qps\": TARGET_MODEL_QPS,\n", + " \"target_model_location\": LOCATION,\n", + " \"optimizer_model_location\": LOCATION,\n", + " \"eval_qps\": EVAL_QPS,\n", + " \"optimization_mode\": OPTIMIZATION_MODE,\n", + " \"num_demo_set_candidates\": NUM_DEMO_OPTIMIZATION_STEPS,\n", + " \"demo_set_size\": NUM_DEMO_PER_PROMPT,\n", + " \"aggregation_type\": METRIC_AGGREGATION_TYPE,\n", + " \"data_limit\": 50,\n", + " \"input_data_path\": input_data_path,\n", + " \"output_path\": output_path,\n", + " \"response_mime_type\": RESPONSE_MIME_TYPE,\n", + " \"response_schema\": RESPONSE_SCHEMA,\n", + " \"language\": TARGET_LANGUAGE,\n", + " \"placeholder_to_content\": json.loads(PLACEHOLDER_TO_VALUE),\n", + " \"tools\": TOOLS,\n", + " \"tool_config\": TOOL_CONFIG,\n", + " \"translation_source_field_name\": TRANSLATION_SOURCE_FIELD_NAME,\n", + " \"thinking_budget\": THINKING_BUDGET,\n", + "}\n", + "\n", + "if EVAL_METRIC_1 == \"NA\":\n", + " params[\"eval_metrics_types\"] = [EVAL_METRIC]\n", + " params[\"eval_metrics_weights\"] = [1.0]\n", + "else:\n", + " metrics = []\n", + " weights = []\n", + " for metric, weight in zip(\n", + " [EVAL_METRIC_1, EVAL_METRIC_2, EVAL_METRIC_3],\n", + " [EVAL_METRIC_1_WEIGHT, EVAL_METRIC_2_WEIGHT, EVAL_METRIC_3_WEIGHT],\n", + " ):\n", + " if metric == \"NA\":\n", + " break\n", + " metrics.append(metric)\n", + " weights.append(weight)\n", + " params[\"eval_metrics_types\"] = metrics\n", + " params[\"eval_metrics_weights\"] = weights\n", + "\n", + "job = vapo_lib.run_apd(params, OUTPUT_PATH, display_name)\n", + "print(f\"Job ID: {job.name}\")\n", + "\n", + "progress_form = vapo_lib.ProgressForm(params)\n", + "while progress_form.monitor_progress(job):\n", + " time.sleep(5)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "lo5mcTzwSgBP" + }, + "source": [ + "# Step 6: Inspect the results\n", + "For a clearer look at the specific responses generated by each prompt template during the optimization process, use the cell below.\n", + "This will allow you to inspect all the predictions made by all the\n", + "generated templates during one or multiple vertex prompt optimizer runs.\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "1x6HSty759jY" + }, + "outputs": [], + "source": [ + "from IPython.display import HTML, display\n", + "\n", + "RESULT_PATH = \"[OUTPUT_PATH]\" # @param {type:\"string\"}\n", + "\n", + "results_ui = vapo_lib.ResultsUI(RESULT_PATH)\n", + "\n", + "results_df_html = \"\"\"\n", + "\n", + "\"\"\"\n", + "\n", + "display(HTML(results_df_html))\n", + "display(results_ui.get_container())" + ] + } + ], + "metadata": { + "colab": { + "name": "vertex_ai_prompt_optimizer_ui.ipynb", + "toc_visible": true, + "provenance": [], + "include_colab_link": true + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file From 58d01bdef4e5d439eadb8ee676af9188f7e0cd19 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 30 Aug 2025 19:14:31 -0700 Subject: [PATCH 14/28] Created using Colab --- .../vertex_ai_prompt_optimizer_ui.ipynb | 40 ++++++++++++++----- 1 file changed, 30 insertions(+), 10 deletions(-) diff --git a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb index 4e6a675..f45ebd3 100644 --- a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb +++ b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb @@ -154,13 +154,13 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": { "id": "8-Zw72vFORz_", - "outputId": "98b34e63-ec34-4799-adf8-fce2af428b25", "colab": { "base_uri": "https://localhost:8080/" - } + }, + "outputId": "98b34e63-ec34-4799-adf8-fce2af428b25" }, "outputs": [ { @@ -205,7 +205,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": { "id": "rJG1pVZO317x" }, @@ -237,7 +237,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": { "id": "mfgi_oR6tTIB" }, @@ -273,7 +273,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": { "id": "B2R3P8mMvK9q" }, @@ -298,7 +298,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": { "id": "fRHHTpaV4Xyo" }, @@ -346,11 +346,31 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "metadata": { - "id": "Z8NvNLTfxPTf" + "id": "Z8NvNLTfxPTf", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 356 + }, + "outputId": "f61609e6-408a-404f-eb7f-af7a992723a0" }, - "outputs": [], + "outputs": [ + { + "output_type": "error", + "ename": "ValueError", + "evalue": "Unsupported file location. Only GCS paths starting with 'gs://' are supported.", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m/tmp/ipython-input-3874795059.py\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 16\u001b[0m )\n\u001b[1;32m 17\u001b[0m \u001b[0minput_data_path\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34mf\"{INPUT_DATA_PATH}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 18\u001b[0;31m vapo_lib.validate_prompt_and_data(\n\u001b[0m\u001b[1;32m 19\u001b[0m \u001b[0;34m\"\\n\"\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mSYSTEM_INSTRUCTION\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mPROMPT_TEMPLATE\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[0minput_data_path\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/content/vapo_lib.py\u001b[0m in \u001b[0;36mvalidate_prompt_and_data\u001b[0;34m(template, dataset_path, placeholder_to_content, label_enforced)\u001b[0m\n\u001b[1;32m 159\u001b[0m ) -> None:\n\u001b[1;32m 160\u001b[0m \u001b[0;34m\"\"\"Validates the prompt template and the dataset.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 161\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_dataset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataset_path\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 162\u001b[0m \u001b[0mplaceholder_to_content_json\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mjson\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mloads\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mplaceholder_to_content\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 163\u001b[0m \u001b[0mtemplate\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mre\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mr\"(? 139\u001b[0;31m \u001b[0mdata_str\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_file_from_gcs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataset\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 140\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 141\u001b[0m \u001b[0;31m# Parse based on file type\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/content/vapo_lib.py\u001b[0m in \u001b[0;36mload_file_from_gcs\u001b[0;34m(dataset)\u001b[0m\n\u001b[1;32m 86\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 87\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 88\u001b[0;31m raise ValueError(\n\u001b[0m\u001b[1;32m 89\u001b[0m \u001b[0;34m\"Unsupported file location. Only GCS paths starting with 'gs://' are\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 90\u001b[0m \u001b[0;34m\" supported.\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mValueError\u001b[0m: Unsupported file location. Only GCS paths starting with 'gs://' are supported." + ] + } + ], "source": [ "import datetime\n", "import json\n", From 6721823b18b29bfd7bf309d7512d7c175beb907b Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Mon, 1 Sep 2025 16:33:14 -0700 Subject: [PATCH 15/28] Created using Colab --- .../vertex_ai_prompt_optimizer_ui.ipynb | 67 ++++--------------- 1 file changed, 13 insertions(+), 54 deletions(-) diff --git a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb index f45ebd3..ff4350c 100644 --- a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb +++ b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb @@ -12,7 +12,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": null, "metadata": { "id": "hlI1rYKa2IGx" }, @@ -129,7 +129,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": null, "metadata": { "id": "NyKGtVQjgx13" }, @@ -154,33 +154,11 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": null, "metadata": { - "id": "8-Zw72vFORz_", - "colab": { - "base_uri": "https://localhost:8080/" - }, - "outputId": "98b34e63-ec34-4799-adf8-fce2af428b25" + "id": "8-Zw72vFORz_" }, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "--2025-08-31 02:12:00-- https://raw.githubusercontent.com/GoogleCloudPlatform/generative-ai/main/gemini/prompts/prompt_optimizer/vapo_lib.py\n", - "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n", - "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n", - "HTTP request sent, awaiting response... 200 OK\n", - "Length: 37206 (36K) [text/plain]\n", - "Saving to: ‘vapo_lib.py’\n", - "\n", - "\rvapo_lib.py 0%[ ] 0 --.-KB/s \rvapo_lib.py 100%[===================>] 36.33K --.-KB/s in 0.006s \n", - "\n", - "2025-08-31 02:12:00 (5.64 MB/s) - ‘vapo_lib.py’ saved [37206/37206]\n", - "\n" - ] - } - ], + "outputs": [], "source": [ "!wget https://raw.githubusercontent.com/GoogleCloudPlatform/generative-ai/main/gemini/prompts/prompt_optimizer/vapo_lib.py\n", "import vapo_lib" @@ -205,7 +183,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": null, "metadata": { "id": "rJG1pVZO317x" }, @@ -237,7 +215,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": null, "metadata": { "id": "mfgi_oR6tTIB" }, @@ -273,7 +251,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": null, "metadata": { "id": "B2R3P8mMvK9q" }, @@ -298,7 +276,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": null, "metadata": { "id": "fRHHTpaV4Xyo" }, @@ -346,31 +324,11 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": null, "metadata": { - "id": "Z8NvNLTfxPTf", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 356 - }, - "outputId": "f61609e6-408a-404f-eb7f-af7a992723a0" + "id": "Z8NvNLTfxPTf" }, - "outputs": [ - { - "output_type": "error", - "ename": "ValueError", - "evalue": "Unsupported file location. Only GCS paths starting with 'gs://' are supported.", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m/tmp/ipython-input-3874795059.py\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 16\u001b[0m )\n\u001b[1;32m 17\u001b[0m \u001b[0minput_data_path\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34mf\"{INPUT_DATA_PATH}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 18\u001b[0;31m vapo_lib.validate_prompt_and_data(\n\u001b[0m\u001b[1;32m 19\u001b[0m \u001b[0;34m\"\\n\"\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mSYSTEM_INSTRUCTION\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mPROMPT_TEMPLATE\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[0minput_data_path\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/content/vapo_lib.py\u001b[0m in \u001b[0;36mvalidate_prompt_and_data\u001b[0;34m(template, dataset_path, placeholder_to_content, label_enforced)\u001b[0m\n\u001b[1;32m 159\u001b[0m ) -> None:\n\u001b[1;32m 160\u001b[0m \u001b[0;34m\"\"\"Validates the prompt template and the dataset.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 161\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_dataset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataset_path\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 162\u001b[0m \u001b[0mplaceholder_to_content_json\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mjson\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mloads\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mplaceholder_to_content\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 163\u001b[0m \u001b[0mtemplate\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mre\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msub\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mr\"(? 139\u001b[0;31m \u001b[0mdata_str\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_file_from_gcs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataset\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 140\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 141\u001b[0m \u001b[0;31m# Parse based on file type\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/content/vapo_lib.py\u001b[0m in \u001b[0;36mload_file_from_gcs\u001b[0;34m(dataset)\u001b[0m\n\u001b[1;32m 86\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 87\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 88\u001b[0;31m raise ValueError(\n\u001b[0m\u001b[1;32m 89\u001b[0m \u001b[0;34m\"Unsupported file location. Only GCS paths starting with 'gs://' are\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 90\u001b[0m \u001b[0;34m\" supported.\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mValueError\u001b[0m: Unsupported file location. Only GCS paths starting with 'gs://' are supported." - ] - } - ], + "outputs": [], "source": [ "import datetime\n", "import json\n", @@ -506,6 +464,7 @@ "name": "vertex_ai_prompt_optimizer_ui.ipynb", "toc_visible": true, "provenance": [], + "private_outputs": true, "include_colab_link": true }, "kernelspec": { From fb8ba12b43cd3faa4af00f08e5844d50cf2a5593 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Tue, 2 Sep 2025 05:36:47 +0600 Subject: [PATCH 16/28] Rename gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb to gemini/prompts/AXEE (#5) --- .../vertex_ai_prompt_optimizer_ui.ipynb => AXEE} | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) rename gemini/prompts/{prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb => AXEE} (99%) diff --git a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb b/gemini/prompts/AXEE similarity index 99% rename from gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb rename to gemini/prompts/AXEE index ff4350c..a58a21f 100644 --- a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb +++ b/gemini/prompts/AXEE @@ -474,4 +474,4 @@ }, "nbformat": 4, "nbformat_minor": 0 -} \ No newline at end of file +} From 71b7e65979e4746178940d0bd2b1e9615726068d Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Tue, 2 Sep 2025 05:37:35 +0600 Subject: [PATCH 17/28] Created using Colab --- .../vertex_ai_prompt_optimizer_ui.ipynb | 477 ++++++++++++++++++ 1 file changed, 477 insertions(+) create mode 100644 gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb diff --git a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb new file mode 100644 index 0000000..ff4350c --- /dev/null +++ b/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb @@ -0,0 +1,477 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "hlI1rYKa2IGx" + }, + "outputs": [], + "source": [ + "# Copyright 2024 Google LLC\n", + "#\n", + "# Licensed under the Apache License, Version 2.0 (the \"License\");\n", + "# you may not use this file except in compliance with the License.\n", + "# You may obtain a copy of the License at\n", + "#\n", + "# https://www.apache.org/licenses/LICENSE-2.0\n", + "#\n", + "# Unless required by applicable law or agreed to in writing, software\n", + "# distributed under the License is distributed on an \"AS IS\" BASIS,\n", + "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n", + "# See the License for the specific language governing permissions and\n", + "# limitations under the License." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "RN8N3O43QDT5" + }, + "source": [ + "# Vertex Prompt Optimizer Notebook UI (Preview)\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + "
\n", + " \n", + " \"Google
Open in Colab\n", + " \n", + " 		\n", + " \n", + " \"Google
Open in Colab Enterprise\n", + " \n", + " 		\n", + " \n", + " \"Vertex
Open in Vertex AI Workbench\n", + " \n", + " 		\n", + " \n", + " \"GitHub
View on GitHub\n", + " \n", + "
\n", + "\n", + "
\n", + "\n", + "Share to:\n", + "\n", + "\n", + " \"LinkedIn\n", + "\n", + "\n", + "\n", + " \"Bluesky\n", + "\n", + "\n", + "\n", + " \"X\n", + "\n", + "\n", + "\n", + " \"Reddit\n", + "\n", + "\n", + "\n", + " \"Facebook\n", + " " + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "pHyuJTFr2IGx" + }, + "source": [ + "# Overview\n", + "This Notebook showcases the Vertex AI prompt optimizer, a tool that iteratively optimizes prompts to suit a target model (e.g., `gemini-2.0-flash`) using target-specific metric(s).\n", + "\n", + "Key Use Cases:\n", + "\n", + "* Prompt Optimization: Enhance the quality of an initial prompt by refining its structure and content to match the target model's optimal input characteristics.\n", + "\n", + "* Prompt Translation: Adapt prompts optimized for one model to work effectively with a different target model.\n", + "\n", + "For the detailed documentation please see [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "61RBz8LLbxCR" + }, + "source": [ + "## Getting Started" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "dmWOrTJ3gx13" + }, + "source": [ + "### Authenticate your notebook environment (Colab only)\n", + "\n", + "Authenticate your environment on Google Colab.\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "NyKGtVQjgx13" + }, + "outputs": [], + "source": [ + "import sys\n", + "\n", + "if \"google.colab\" in sys.modules:\n", + " from google.colab import auth\n", + "\n", + " auth.authenticate_user()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "tTtKHedrO1Rx" + }, + "source": [ + "# Step 0: Install packages and libraries" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "8-Zw72vFORz_" + }, + "outputs": [], + "source": [ + "!wget https://raw.githubusercontent.com/GoogleCloudPlatform/generative-ai/main/gemini/prompts/prompt_optimizer/vapo_lib.py\n", + "import vapo_lib" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "-p59jd5rOp4q" + }, + "source": [ + "# Step 1: Create a prompt template and system instructions\n", + "Provide your system intruction and prompt template below. Refer to [here]( https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#template-si) for instructions.\n", + "\n", + "Prompts consist of two key components:\n", + "\n", + "- System Instruction: System instruction is the instruction that get passed to the model before any user input in the prompt. This is the fixed part of the prompt template shared across all queries for a given task.\n", + "- Prompt template: A task is the text in the prompt that you want the model to provide a response for. Context is information that you include in the prompt that the model uses or references when generating a response. These are the dynamic parts of the prompt template that changes based on the task.\n", + "\n", + "Prompt Optimizer enables the optimization or translation of the System Instruction template, while the prompt template remains essential for evaluating and selecting the best System Instruction template." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "rJG1pVZO317x" + }, + "outputs": [], + "source": [ + "SYSTEM_INSTRUCTION = (\n", + " \"Answer the following question. Let's think step by step.\\n\" # @param\n", + ")\n", + "PROMPT_TEMPLATE = \"Question: {question}\\n\\nAnswer: {target}\" # @param" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "5y-cmg0TQP6v" + }, + "source": [ + "# Step 2: Configure project settings\n", + "To optimize the prompt for your target Google model, provide a CSV or JSONL file containing labeled validation samples (input, ground truth output pairs). Refer to [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#prepare-sample-prompts) for instructions.\n", + "\n", + "Focus on examples that specifically demonstrate the issues you want to address.\n", + "Recommendation: Use 50-100 distinct samples for reliable results. However, the tool can still be effective with as few as 5 samples.\n", + "For prompt translation (e.g. 3P model to Google model, PaLM 2 to Gemini):\n", + "\n", + "Consider using the source model to label examples that the target model struggles with, helping to identify areas for improvement.\n", + "When you select a source model, you don't need to provide labels for the input examples.\n", + "While the source model selection is limited to Google models, it still supports labeled inputs from non-Google models. If you wish to select a non-Google source model, you will need to provide labels for your input examples.\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "mfgi_oR6tTIB" + }, + "outputs": [], + "source": [ + "# @markdown **Project setup**:
\n", + "PROJECT_ID = \"[YOUR_PROJECT]\" # @param {type:\"string\"}\n", + "LOCATION = \"us-central1\" # @param {type:\"string\"}\n", + "OUTPUT_PATH = \"[OUTPUT_PATH]\" # @param {type:\"string\"}\n", + "INPUT_DATA_PATH = \"[INPUT_DATA_PATH]\" # @param {type:\"string\"}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ucebZHkHRxKH" + }, + "source": [ + "# Step 3: Configure optimization settings\n", + "The optimization configurations are defaulted to the values that are most commonly used, which we recommend using as the initial set-up.\n", + "\n", + "The most important settings are:\n", + "\n", + "* Target Model: Which model you are trying to optimize your prompts to.\n", + "* Thinking Budget: The thinking budget for thinking models like Gemini-2.5. Default to -1, which means no thinking for non-thinking models and auto thinking for thinking models. Refer [here](https://cloud.google.com/vertex-ai/generative-ai/docs/thinking) to learn more about manual budget settings.\n", + "* Optimization Mode: The mode in which you are trying to optimize your prompt with.\n", + "* Evaluation Metrics: The evaluation metrics in which you are trying to optimize your prompts against.\n", + "* Translation Source Field Name: fill in with the corresponding field name of the source text in the data if translation metrics like Comet or MetricX are selected. Otherwise, leave it as empty.\n", + "\n", + "Note that all evaluation metrics are expected to have the larger-the-better property. Therefore, we have modified the MetricX value to between 0 (worst) and 25 (best).\n", + "Refer [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#configuration) to learn more about the different configuration settings and how to best utilize them." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "B2R3P8mMvK9q" + }, + "outputs": [], + "source": [ + "TARGET_MODEL = \"gemini-2.0-flash-001\" # @param [\"gemini-2.5-flash-lite\", \"gemini-2.5-flash\", \"gemini-2.5-pro\", \"gemini-2.0-flash-lite-001\", \"gemini-2.0-flash-001\"]\n", + "THINKING_BUDGET = -1 # @param {type:\"integer\"}\n", + "OPTIMIZATION_MODE = \"instruction_and_demo\" # @param [\"instruction\", \"demonstration\", \"instruction_and_demo\"]\n", + "EVAL_METRIC = \"question_answering_correctness\" # @param [\"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "TRANSLATION_SOURCE_FIELD_NAME = \"\" # @param {type:\"string\"}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "kO7fO0qTSNLs" + }, + "source": [ + "# Step 4: Configure advanced optimization settings [Optional]\n", + "Refer [here](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer#configuration) to learn more about the different configuration settings and how to best utilize them." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "fRHHTpaV4Xyo" + }, + "outputs": [], + "source": [ + "# @markdown **Instruction Optimization Configs**:
\n", + "NUM_INST_OPTIMIZATION_STEPS = 10 # @param {type:\"integer\"}\n", + "\n", + "# @markdown **Demonstration Optimization Configs**:
\n", + "NUM_DEMO_OPTIMIZATION_STEPS = 10 # @param {type:\"integer\"}\n", + "NUM_DEMO_PER_PROMPT = 3 # @param {type:\"integer\"}\n", + "\n", + "# @markdown **Model Configs**:
\n", + "TARGET_MODEL_QPS = 3.0 # @param {type:\"number\"}\n", + "EVAL_QPS = 3.0 # @param {type:\"number\"}\n", + "\n", + "# @markdown **Multi-metric Configs**:
\n", + "# @markdown Use this section only if you need more than one metric for optimization. This will override the metric you picked above.\n", + "EVAL_METRIC_1 = \"NA\" # @param [\"NA\", \"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "EVAL_METRIC_1_WEIGHT = 0.0 # @param {type:\"number\"}\n", + "EVAL_METRIC_2 = \"NA\" # @param [\"NA\", \"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "EVAL_METRIC_2_WEIGHT = 0.0 # @param {type:\"number\"}\n", + "EVAL_METRIC_3 = \"NA\" # @param [\"NA\", \"bleu\", \"coherence\", \"comet\", \"exact_match\", \"fluency\", \"groundedness\", \"metricx\", \"text_quality\", \"verbosity\", \"rouge_1\", \"rouge_2\", \"rouge_l\", \"rouge_l_sum\", \"safety\", \"question_answering_correctness\", \"question_answering_quality\", \"summarization_quality\", \"tool_name_match\", \"tool_parameter_key_match\", \"tool_parameter_kv_match\", \"tool_call_valid\"] {type:\"string\"}\n", + "EVAL_METRIC_3_WEIGHT = 0.0 # @param {type:\"number\"}\n", + "METRIC_AGGREGATION_TYPE = \"weighted_sum\" # @param [\"weighted_sum\", \"weighted_average\"]\n", + "\n", + "# @markdown **Misc Configs**:
\n", + "PLACEHOLDER_TO_VALUE = \"{}\" # @param\n", + "RESPONSE_MIME_TYPE = \"text/plain\" # @param [\"text/plain\", \"application/json\", \"text/x.enum\"] {type:\"string\"}\n", + "RESPONSE_SCHEMA = \"\"\n", + "TARGET_LANGUAGE = \"English\" # @param [\"English\", \"French\", \"German\", \"Hebrew\", \"Hindi\", \"Italian\", \"Japanese\", \"Korean\", \"Portuguese\", \"Simplified Chinese\", \"Spanish\", \"Traditional Chinese\"] {type:\"string\"}\n", + "TOOLS = \"\" # @param\n", + "TOOL_CONFIG = \"\" # @param" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "X7Mgb0EHSSFk" + }, + "source": [ + "# Step 5: Run Prompt Optimizer\n", + "A progress bar will appear to let you know how long the job takes." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "Z8NvNLTfxPTf" + }, + "outputs": [], + "source": [ + "import datetime\n", + "import json\n", + "import time\n", + "\n", + "timestamp = datetime.datetime.now().strftime(\"%Y-%m-%dT%H:%M:%S\")\n", + "display_name = f\"pt_{timestamp}\"\n", + "\n", + "label_enforced = vapo_lib.is_run_target_required(\n", + " [\n", + " EVAL_METRIC,\n", + " EVAL_METRIC_1,\n", + " EVAL_METRIC_2,\n", + " EVAL_METRIC_3,\n", + " ],\n", + " \"\",\n", + ")\n", + "input_data_path = f\"{INPUT_DATA_PATH}\"\n", + "vapo_lib.validate_prompt_and_data(\n", + " \"\\n\".join([SYSTEM_INSTRUCTION, PROMPT_TEMPLATE]),\n", + " input_data_path,\n", + " PLACEHOLDER_TO_VALUE,\n", + " label_enforced,\n", + ")\n", + "\n", + "output_path = f\"{OUTPUT_PATH}/{display_name}\"\n", + "\n", + "params = {\n", + " \"project\": PROJECT_ID,\n", + " \"num_steps\": NUM_INST_OPTIMIZATION_STEPS,\n", + " \"system_instruction\": SYSTEM_INSTRUCTION,\n", + " \"prompt_template\": PROMPT_TEMPLATE,\n", + " \"target_model\": TARGET_MODEL,\n", + " \"target_model_qps\": TARGET_MODEL_QPS,\n", + " \"target_model_location\": LOCATION,\n", + " \"optimizer_model_location\": LOCATION,\n", + " \"eval_qps\": EVAL_QPS,\n", + " \"optimization_mode\": OPTIMIZATION_MODE,\n", + " \"num_demo_set_candidates\": NUM_DEMO_OPTIMIZATION_STEPS,\n", + " \"demo_set_size\": NUM_DEMO_PER_PROMPT,\n", + " \"aggregation_type\": METRIC_AGGREGATION_TYPE,\n", + " \"data_limit\": 50,\n", + " \"input_data_path\": input_data_path,\n", + " \"output_path\": output_path,\n", + " \"response_mime_type\": RESPONSE_MIME_TYPE,\n", + " \"response_schema\": RESPONSE_SCHEMA,\n", + " \"language\": TARGET_LANGUAGE,\n", + " \"placeholder_to_content\": json.loads(PLACEHOLDER_TO_VALUE),\n", + " \"tools\": TOOLS,\n", + " \"tool_config\": TOOL_CONFIG,\n", + " \"translation_source_field_name\": TRANSLATION_SOURCE_FIELD_NAME,\n", + " \"thinking_budget\": THINKING_BUDGET,\n", + "}\n", + "\n", + "if EVAL_METRIC_1 == \"NA\":\n", + " params[\"eval_metrics_types\"] = [EVAL_METRIC]\n", + " params[\"eval_metrics_weights\"] = [1.0]\n", + "else:\n", + " metrics = []\n", + " weights = []\n", + " for metric, weight in zip(\n", + " [EVAL_METRIC_1, EVAL_METRIC_2, EVAL_METRIC_3],\n", + " [EVAL_METRIC_1_WEIGHT, EVAL_METRIC_2_WEIGHT, EVAL_METRIC_3_WEIGHT],\n", + " ):\n", + " if metric == \"NA\":\n", + " break\n", + " metrics.append(metric)\n", + " weights.append(weight)\n", + " params[\"eval_metrics_types\"] = metrics\n", + " params[\"eval_metrics_weights\"] = weights\n", + "\n", + "job = vapo_lib.run_apd(params, OUTPUT_PATH, display_name)\n", + "print(f\"Job ID: {job.name}\")\n", + "\n", + "progress_form = vapo_lib.ProgressForm(params)\n", + "while progress_form.monitor_progress(job):\n", + " time.sleep(5)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "lo5mcTzwSgBP" + }, + "source": [ + "# Step 6: Inspect the results\n", + "For a clearer look at the specific responses generated by each prompt template during the optimization process, use the cell below.\n", + "This will allow you to inspect all the predictions made by all the\n", + "generated templates during one or multiple vertex prompt optimizer runs.\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "1x6HSty759jY" + }, + "outputs": [], + "source": [ + "from IPython.display import HTML, display\n", + "\n", + "RESULT_PATH = \"[OUTPUT_PATH]\" # @param {type:\"string\"}\n", + "\n", + "results_ui = vapo_lib.ResultsUI(RESULT_PATH)\n", + "\n", + "results_df_html = \"\"\"\n", + "\n", + "\"\"\"\n", + "\n", + "display(HTML(results_df_html))\n", + "display(results_ui.get_container())" + ] + } + ], + "metadata": { + "colab": { + "name": "vertex_ai_prompt_optimizer_ui.ipynb", + "toc_visible": true, + "provenance": [], + "private_outputs": true, + "include_colab_link": true + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file From 06379fe5aefddc1f6ab9aeca16f00912d462742a Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Tue, 2 Sep 2025 05:38:38 +0600 Subject: [PATCH 18/28] Rename vertex_ai_prompt_optimizer_ui.ipynb to AXEE.ipynb --- .../{vertex_ai_prompt_optimizer_ui.ipynb => AXEE.ipynb} | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) rename gemini/prompts/prompt_optimizer/{vertex_ai_prompt_optimizer_ui.ipynb => AXEE.ipynb} (99%) diff --git a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb b/gemini/prompts/prompt_optimizer/AXEE.ipynb similarity index 99% rename from gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb rename to gemini/prompts/prompt_optimizer/AXEE.ipynb index ff4350c..a58a21f 100644 --- a/gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb +++ b/gemini/prompts/prompt_optimizer/AXEE.ipynb @@ -474,4 +474,4 @@ }, "nbformat": 4, "nbformat_minor": 0 -} \ No newline at end of file +} From 84acde6cd01e3744d16a39b0d264f36ed71d5d39 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 27 Sep 2025 20:18:08 +0600 Subject: [PATCH 19/28] Rename AXEE to AXEE Synthesis --- gemini/prompts/{AXEE => AXEE Synthesis} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename gemini/prompts/{AXEE => AXEE Synthesis} (100%) diff --git a/gemini/prompts/AXEE b/gemini/prompts/AXEE Synthesis similarity index 100% rename from gemini/prompts/AXEE rename to gemini/prompts/AXEE Synthesis From 813fa14e6a5a019dcc38a187d95dfe7a3801cf98 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 4 Oct 2025 05:31:25 +0600 Subject: [PATCH 20/28] Created using Colab --- ...Getting_started_with_google_colab_ai.ipynb | 5305 ++++++++++++++++- 1 file changed, 5202 insertions(+), 103 deletions(-) diff --git a/notebooks/Getting_started_with_google_colab_ai.ipynb b/notebooks/Getting_started_with_google_colab_ai.ipynb index ea523ac..239f507 100644 --- a/notebooks/Getting_started_with_google_colab_ai.ipynb +++ b/notebooks/Getting_started_with_google_colab_ai.ipynb @@ -1,5 +1,15 @@ { "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, { "metadata": { "id": "wdj9RMfoGPC2" @@ -21,7 +31,7 @@ { "metadata": { "id": "Ucchuu5vV3Jp", - "outputId": "a3004031-0e0c-4f8d-842d-a79421f51e11", + "outputId": "64e293b1-b525-4f83-e7ec-1881a7acc2ec", "colab": { "base_uri": "https://localhost:8080/" } @@ -38,31 +48,14 @@ "output_type": "execute_result", "data": { "text/plain": [ - "['google/gemini-2.0-flash',\n", - " 'google/gemini-2.0-flash-lite',\n", - " 'google/gemini-2.5-flash',\n", - " 'google/gemini-2.5-flash-lite',\n", - " 'google/gemini-2.5-pro',\n", - " 'google/gemma-3-12b',\n", - " 'google/gemma-3-1b',\n", - " 'google/gemma-3-27b',\n", - " 'google/gemma-3-4b']" + "['google/gemini-2.5-flash', 'google/gemini-2.5-flash-lite']" ] }, "metadata": {}, - "execution_count": 27 + "execution_count": 39 } ], - "execution_count": 27 - }, - { - "cell_type": "code", - "source": [], - "metadata": { - "id": "9D74LOIiggIt" - }, - "execution_count": 27, - "outputs": [] + "execution_count": 39 }, { "metadata": { @@ -81,125 +74,5231 @@ ] }, { + "metadata": { + "id": "R7taibpc7x2l", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 339 + }, + "outputId": "7e953657-296f-4311-ba72-2ea8aea67d38" + }, "cell_type": "code", - "source": [], + "source": [ + "# @title Simple batch generation example\n", + "# Only text-to-text input/output is supported\n", + "from google.colab import ai\n", + "\n", + "response = ai.generate_text(\"What is the capital of France?\")\n", + "print(response)" + ], + "outputs": [ + { + "output_type": "error", + "ename": "APIStatusError", + "evalue": "Error code: 402 - {'message': 'Colab Models is only available to Colab Pro and Pro+ subscribers.', 'type': 'invalid_request_error'}", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mAPIStatusError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m/tmp/ipython-input-1782392906.py\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mgoogle\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolab\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mai\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m \u001b[0mresponse\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mai\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgenerate_text\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"What is the capital of France?\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 6\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/colab/ai.py\u001b[0m in \u001b[0;36mgenerate_text\u001b[0;34m(prompt, model_name, stream)\u001b[0m\n\u001b[1;32m 83\u001b[0m )\n\u001b[1;32m 84\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 85\u001b[0;31m response = client.chat.completions.create(\n\u001b[0m\u001b[1;32m 86\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmodel_name\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 87\u001b[0m \u001b[0mmessages\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m{\u001b[0m\u001b[0;34m'role'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'user'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'content'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mprompt\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/_utils/_utils.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 284\u001b[0m \u001b[0mmsg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34mf\"Missing required argument: {quote(missing[0])}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 285\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmsg\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 286\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 287\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 288\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mwrapper\u001b[0m \u001b[0;31m# type: ignore\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/resources/chat/completions/completions.py\u001b[0m in \u001b[0;36mcreate\u001b[0;34m(self, messages, model, audio, frequency_penalty, function_call, functions, logit_bias, logprobs, max_completion_tokens, max_tokens, metadata, modalities, n, parallel_tool_calls, prediction, presence_penalty, prompt_cache_key, reasoning_effort, response_format, safety_identifier, seed, service_tier, stop, store, stream, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, verbosity, web_search_options, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m 1145\u001b[0m ) -> ChatCompletion | Stream[ChatCompletionChunk]:\n\u001b[1;32m 1146\u001b[0m \u001b[0mvalidate_response_format\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponse_format\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1147\u001b[0;31m return self._post(\n\u001b[0m\u001b[1;32m 1148\u001b[0m \u001b[0;34m\"/chat/completions\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1149\u001b[0m body=maybe_transform(\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/_base_client.py\u001b[0m in \u001b[0;36mpost\u001b[0;34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1257\u001b[0m \u001b[0mmethod\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"post\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0murl\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mjson_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mbody\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfiles\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mto_httpx_files\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfiles\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0moptions\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1258\u001b[0m )\n\u001b[0;32m-> 1259\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mcast\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mResponseT\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcast_to\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mopts\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstream\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstream\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstream_cls\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstream_cls\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1260\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1261\u001b[0m def patch(\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/_base_client.py\u001b[0m in \u001b[0;36mrequest\u001b[0;34m(self, cast_to, options, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1045\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1046\u001b[0m \u001b[0mlog\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdebug\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Re-raising status error\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1047\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_make_status_error_from_response\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0merr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresponse\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1048\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1049\u001b[0m \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mAPIStatusError\u001b[0m: Error code: 402 - {'message': 'Colab Models is only available to Colab Pro and Pro+ subscribers.', 'type': 'invalid_request_error'}" + ] + } + ], + "execution_count": 42 + }, + { + "cell_type": "markdown", "metadata": { - "id": "8fjql8kzgin1" + "id": "c3867202" }, - "execution_count": 27, - "outputs": [] + "source": [ + "## Update features for modeling\n", + "\n", + "### Subtask:\n", + "Select the updated set of features (including the new ones) for training the model." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "33d4932e" + }, + "source": [ + "## Apply Transformations to Skewed Features\n", + "\n", + "### Subtask:\n", + "Apply log transformation to skewed numerical features identified during exploration." + ] }, { "cell_type": "markdown", - "source": [], "metadata": { - "id": "cNSefuDZgjqV" - } + "id": "50c1cff1" + }, + "source": [ + "**Reasoning**:\n", + "Apply log transformation to 'total_rooms' and 'median_income' to reduce skewness and display the head of the DataFrame to show the transformed columns." + ] }, { "cell_type": "code", - "source": [], "metadata": { - "id": "0_KsQAqsgkW9" + "colab": { + "base_uri": "https://localhost:8080/", + "height": 226 + }, + "id": "37e75b8c", + "outputId": "ca5da018-ff44-449b-d4a4-e9f45908ebfb" }, - "execution_count": 27, - "outputs": [] + "source": [ + "import numpy as np\n", + "\n", + "# Apply log transformation to 'total_rooms' and 'median_income'\n", + "# Add a small constant (e.g., 1) before taking the log to handle potential zero values,\n", + "# although based on describe() output, these columns don't have zeros.\n", + "# Using np.log1p which calculates log(1+x) is a robust way to handle this.\n", + "df['total_rooms_log'] = np.log1p(df['total_rooms'])\n", + "df['median_income_log'] = np.log1p(df['median_income'])\n", + "\n", + "# Display the head of the DataFrame to verify the new transformed columns\n", + "display(df.head())" + ], + "execution_count": 76, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", + "0 -114.31 34.19 15.0 5612.0 1283.0 \n", + "1 -114.47 34.40 19.0 7650.0 1901.0 \n", + "2 -114.56 33.69 17.0 720.0 174.0 \n", + "3 -114.57 33.64 14.0 1501.0 337.0 \n", + "4 -114.57 33.57 20.0 1454.0 326.0 \n", + "\n", + " population households median_income median_house_value \\\n", + "0 1015.0 472.0 1.4936 66900.0 \n", + "1 1129.0 463.0 1.8200 80100.0 \n", + "2 333.0 117.0 1.6509 85700.0 \n", + "3 515.0 226.0 3.1917 73400.0 \n", + "4 624.0 262.0 1.9250 65500.0 \n", + "\n", + " rooms_per_household bedrooms_per_room population_per_household \\\n", + "0 11.889831 0.228617 2.150424 \n", + "1 16.522678 0.248497 2.438445 \n", + "2 6.153846 0.241667 2.846154 \n", + "3 6.641593 0.224517 2.278761 \n", + "4 5.549618 0.224209 2.381679 \n", + "\n", + " total_rooms_log median_income_log \n", + "0 8.632841 0.913727 \n", + "1 8.942592 1.036737 \n", + "2 6.580639 0.974899 \n", + "3 7.314553 1.433106 \n", + "4 7.282761 1.073294 " + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_incomemedian_house_valuerooms_per_householdbedrooms_per_roompopulation_per_householdtotal_rooms_logmedian_income_log
0-114.3134.1915.05612.01283.01015.0472.01.493666900.011.8898310.2286172.1504248.6328410.913727
1-114.4734.4019.07650.01901.01129.0463.01.820080100.016.5226780.2484972.4384458.9425921.036737
2-114.5633.6917.0720.0174.0333.0117.01.650985700.06.1538460.2416672.8461546.5806390.974899
3-114.5733.6414.01501.0337.0515.0226.03.191773400.06.6415930.2245172.2787617.3145531.433106
4-114.5733.5720.01454.0326.0624.0262.01.925065500.05.5496180.2242092.3816797.2827611.073294
\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"display(df\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.11216059914247682,\n \"min\": -114.57,\n \"max\": -114.31,\n \"num_unique_values\": 4,\n \"samples\": [\n -114.47,\n -114.57,\n -114.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3723842101915701,\n \"min\": 33.57,\n \"max\": 34.4,\n \"num_unique_values\": 5,\n \"samples\": [\n 34.4,\n 33.57,\n 33.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.5495097567963922,\n \"min\": 14.0,\n \"max\": 20.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 19.0,\n 20.0,\n 17.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3063.09350167441,\n \"min\": 720.0,\n \"max\": 7650.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 7650.0,\n 1454.0,\n 720.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 754.3743765531807,\n \"min\": 174.0,\n \"max\": 1901.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1901.0,\n 326.0,\n 174.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 337.36656621544466,\n \"min\": 333.0,\n \"max\": 1129.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1129.0,\n 624.0,\n 333.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 155.11447385721294,\n \"min\": 117.0,\n \"max\": 472.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 463.0,\n 262.0,\n 117.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6773416737511431,\n \"min\": 1.4936,\n \"max\": 3.1917,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.82,\n 1.925,\n 1.6509\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_house_value\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 8611.15555544086,\n \"min\": 65500.0,\n \"max\": 85700.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 80100.0,\n 65500.0,\n 85700.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rooms_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 4.740564553544767,\n \"min\": 5.549618320610687,\n \"max\": 16.52267818574514,\n \"num_unique_values\": 5,\n \"samples\": [\n 16.52267818574514,\n 5.549618320610687,\n 6.153846153846154\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"bedrooms_per_room\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.010982410746386893,\n \"min\": 0.22420907840440166,\n \"max\": 0.24849673202614378,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.24849673202614378,\n 0.22420907840440166,\n 0.24166666666666667\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.26269348663282854,\n \"min\": 2.1504237288135593,\n \"max\": 2.8461538461538463,\n \"num_unique_values\": 5,\n \"samples\": [\n 2.4384449244060473,\n 2.381679389312977,\n 2.8461538461538463\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms_log\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.9971222656686318,\n \"min\": 6.580639137284949,\n \"max\": 8.942591637231851,\n \"num_unique_values\": 5,\n \"samples\": [\n 8.942591637231851,\n 7.282761179605593,\n 6.580639137284949\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income_log\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.20315740151650868,\n \"min\": 0.9137274494709903,\n \"max\": 1.4331063795723562,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.0367368849500223,\n 1.0732944806838198,\n 0.9748992049809254\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {} + } + ] }, { + "cell_type": "code", "metadata": { - "id": "ysDdFbH_Dgtz" + "colab": { + "base_uri": "https://localhost:8080/", + "height": 934 + }, + "id": "c4b589c8", + "outputId": "9359a55d-7785-481d-a161-6de7aad9e729" + }, + "source": [ + "import matplotlib.pyplot as plt\n", + "import pandas as pd\n", + "\n", + "# Select a few numerical features to visualize\n", + "features_to_visualize = ['housing_median_age', 'total_rooms', 'median_income', 'median_house_value']\n", + "\n", + "# Create histograms for each selected feature\n", + "df[features_to_visualize].hist(bins=50, figsize=(15, 10))\n", + "plt.tight_layout() # Adjust layout to prevent overlap\n", + "plt.show()" + ], + "execution_count": 75, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": {} + } + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 564 + }, + "id": "2e38b388", + "outputId": "f8b512f9-7578-4ccf-aec4-68da6c19621b" }, + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "# Create a scatter plot of median_income vs. median_house_value\n", + "plt.figure(figsize=(10, 6))\n", + "plt.scatter(df['median_income'], df['median_house_value'], alpha=0.5)\n", + "\n", + "# Add labels and title\n", + "plt.xlabel('Median Income')\n", + "plt.ylabel('Median House Value')\n", + "plt.title('Relationship between Median Income and Median House Value')\n", + "\n", + "# Add a grid for better readability\n", + "plt.grid(True)\n", + "\n", + "# Show the plot\n", + "plt.show()" + ], + "execution_count": 74, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "iVBORw0KGgoAAAANSUhEUgAAA2wAAAIjCAYAAAB/FZhcAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQABAABJREFUeJzsvXeYZFWZ+P+5uXJX5zQ9eYYZYAgOQbJIGDAigl/FVUDdBeNvVcy6iKyyhlVcxbS7oquAitmVJaNkFMkzAzM9eTrHynXj+f1xq2q6uqvDBGYauZ/nmQf63lP3nnNuet/zJkkIIQgICAgICAgICAgICAiYd8iHugMBAQEBAQEBAQEBAQEBtQkUtoCAgICAgICAgICAgHlKoLAFBAQEBAQEBAQEBATMUwKFLSAgICAgICAgICAgYJ4SKGwBAQEBAQEBAQEBAQHzlEBhCwgICAgICAgICAgImKcECltAQEBAQEBAQEBAQMA8JVDYAgICAgICAgICAgIC5imBwhYQEBAQEBAQEBAQEDBPCRS2gICXOH/605+QJIk//elPB/S4kiTx+c9//oAec2/Zvn07kiTxta99bda2n//855Ek6YCduzyvv/zlLw/YMQNePGpd/8WLF3PZZZcdmg4FHFQO9PN/oCm/y370ox9Vts33PgdU86Mf/QhJkti+ffuh7krAy5BAYQsIOIiUX/jlf6qq0tnZyWWXXUZPT89B789tt912yJWylxMPP/wwn//85xkfHz/UXXnRKN/b73nPe2ru/8xnPlNpMzw8fJB7d3AoP+ePP/74oe5KwCQuu+wyJEkikUhQKBSm7N+8eXPl/pzLQtFLFUmS+MAHPlBz30v9/rVtm6amJk499dRp2wgh6Orq4hWveMVB7FlAwL4TKGwBAYeAL3zhC/zkJz/he9/7Hueffz4//elPOeOMMygWiwe1H7fddhvXXHNNzX2FQoHPfvazB7U/+8NnP/vZmgLYfOLhhx/mmmuu+btW2ABCoRC/+tWvsCxryr5bbrmFUCh0UPrxwgsv8J//+Z8H5VwBLx1UVSWfz/OHP/xhyr6bbrrpoN2fL4V31ksRTdO4+OKLefjhh9mxY0fNNvfffz+7d+/mH/7hHw5y7wIC9o1AYQsIOAScf/75/MM//APvec97+K//+i+uuuoqtmzZwu9///tD3bUKoVAIVVUPdTfmjKqqB03QCpiZ8847j3Q6zf/93/9VbX/44YfZtm0br33taw9KPwzDQNO0g3KugJcOhmFw1llnccstt0zZd/PNNx+0+zN4Z714vP3tb0cIUfMag3+dZVnmrW9960HuWUDAvhEobAEB84DTTjsNgC1btlRtf/7557noootoaGggFApx3HHHzUmpe+CBB7j44otZuHAhhmHQ1dXFhz/84arV3Msuu4wbbrgBoMpNs0ytGLYnn3yS888/n0QiQSwW46yzzuLRRx+talN2p3nooYf4yEc+QnNzM9FolDe96U0MDQ1VtX388cdZt24dTU1NhMNhlixZwrve9a6aY/rBD37AsmXLMAyD448/nr/+9a9V+2vFg5Tdfm666SYOO+wwQqEQa9eu5f777591Dsu4rsunP/1p2traiEajvOENb2DXrl1T2j322GOcd9551NXVEYlEOOOMM3jooYeq+vexj30MgCVLllTme/v27Vx44YVTXHNe//rXI0lS1fV+7LHHkCSpShEaHx/nn//5n+nq6sIwDJYvX86Xv/xlPM+rOp7neVx//fUcccQRhEIhWltbueKKKxgbG6tqt3jxYl73utfx4IMPcsIJJxAKhVi6dCn/8z//M+c56+zs5PTTT+fmm2+u2n7TTTexZs0ajjzyyJq/m20Oyzz44IMcf/zxhEIhli1bxve///2ax5scwzY6OspVV13FmjVriMViJBIJzj//fJ5++umq35XjF3/xi1/wxS9+kQULFhAKhTjrrLPo7u6e8zxM5LLLLiMWi9HT08MFF1xALBajubmZq666Ctd1q9p6nsc3v/lN1qxZQygUorm5mfPOO6/KRc1xHK699trKM7F48WI+/elPY5rmlDl43etex5/+9CeOO+44wuEwa9asqcS8/vrXv66cZ+3atTz55JNT+r6v7yGAr33ta5x88sk0NjYSDodZu3ZtzbjQ8rP629/+liOPPBLDMDjiiCO4/fbbp7Sd6/WfiUsuuYT/+7//q7J2//Wvf2Xz5s1ccsklNX8z12dtfHycyy67jLq6OpLJJJdeemlNq3qtd9aNN97Iq1/9alpaWjAMg8MPP5zvfve7U357IJ7TveXee+/ltNNOIxqNkkwmeeMb38jGjRur2lx22WUsXrx4ym9rjfWuu+7i1FNPJZlMEovFOOyww/j0pz9d1cY0Ta6++mqWL19e+ZZ9/OMfn3KfT+aUU05h8eLFU95B4LtM/vKXv+TMM8+ko6ODZ555hssuu4ylS5cSCoVoa2vjXe96FyMjI7POyXSx3rXiZ+d6/wQE1OKls3weEPB3TDmIub6+vrJt/fr1nHLKKXR2dvLJT36SaDTKL37xCy644AJ+9atf8aY3vWna4916663k83ne+9730tjYyF/+8he+9a1vsXv3bm699VYArrjiCnp7e7nrrrv4yU9+Mmsf169fz2mnnUYikeDjH/84mqbx/e9/n1e96lX8+c9/5sQTT6xq/8EPfpD6+nquvvpqtm/fzvXXX88HPvABfv7znwMwODjIueeeS3NzM5/85CdJJpNs376dX//611POffPNN5PJZLjiiiuQJImvfOUrXHjhhWzdunVWC8qf//xnfv7zn/OhD30IwzD4zne+w3nnncdf/vKXaRWHiXzxi19EkiQ+8YlPMDg4yPXXX8/ZZ5/NU089RTgcBnxB5vzzz2ft2rVcffXVyLJcEbweeOABTjjhBC688EI2bdrELbfcwje+8Q2ampoAaG5u5rTTTuN3v/sd6XSaRCKBEIKHHnoIWZZ54IEHeMMb3gD4irgsy5xyyikA5PN5zjjjDHp6erjiiitYuHAhDz/8MJ/61Kfo6+vj+uuvr4zjiiuu4Ec/+hGXX345H/rQh9i2bRvf/va3efLJJ3nooYeq5rG7u5uLLrqId7/73Vx66aX88Ic/5LLLLmPt2rUcccQRs84Z+ALx//f//X9ks1lisRiO43DrrbfykY98pKbr71zmEODZZ5+t3Def//zncRyHq6++mtbW1ln7tHXrVn77299y8cUXs2TJEgYGBvj+97/PGWecwYYNG+jo6Khq/2//9m/IssxVV11FKpXiK1/5Cm9/+9t57LHH5jQHk3Fdl3Xr1nHiiSfyta99jbvvvpt///d/Z9myZbz3ve+ttHv3u9/Nj370I84//3ze85734DgODzzwAI8++ijHHXccAO95z3v48Y9/zEUXXcRHP/pRHnvsMa677jo2btzIb37zm6rzdnd3c8kll3DFFVfwD//wD3zta1/j9a9/Pd/73vf49Kc/zfve9z4ArrvuOt7ylrfwwgsvIMv+eu7+vIcAvvnNb/KGN7yBt7/97ViWxc9+9jMuvvhi/vd//3eKJevBBx/k17/+Ne973/uIx+P8x3/8B29+85vZuXMnjY2NwP5d/4lceOGFXHnllfz617+uLBLdfPPNrFq1qmZc01yfNSEEb3zjG3nwwQe58sorWb16Nb/5zW+49NJL59Sv7373uxxxxBG84Q1vQFVV/vCHP/C+970Pz/N4//vfX9V2f5/TYrFYM440m81O2Xb33Xdz/vnns3TpUj7/+c9TKBT41re+xSmnnMITTzxRU0mbifXr1/O6172Oo446ii984QsYhkF3d3fVAo3nebzhDW/gwQcf5J/+6Z9YvXo1zz77LN/4xjfYtGkTv/3tb6c9viRJXHLJJXzpS19i/fr1VfNx++23Mzo6ytvf/nbAVxy3bt3K5ZdfTltbG+vXr+cHP/gB69ev59FHHz0giWH25l0dEFATERAQcNC48cYbBSDuvvtuMTQ0JHbt2iV++ctfiubmZmEYhti1a1el7VlnnSXWrFkjisViZZvneeLkk08WK1asqGy77777BCDuu+++yrZ8Pj/l3Nddd52QJEns2LGjsu3973+/mO41AIirr7668vcFF1wgdF0XW7ZsqWzr7e0V8XhcnH766VPGePbZZwvP8yrbP/zhDwtFUcT4+LgQQojf/OY3AhB//etfp52vbdu2CUA0NjaK0dHRyvbf/e53AhB/+MMfKtuuvvrqKWMBBCAef/zxyrYdO3aIUCgk3vSmN017XiH2zGtnZ6dIp9OV7b/4xS8EIL75zW8KIfxrsmLFCrFu3bqq8ebzebFkyRJxzjnnVLZ99atfFYDYtm1b1bn++te/CkDcdtttQgghnnnmGQGIiy++WJx44omVdm94wxvEscceW/n72muvFdFoVGzatKnqeJ/85CeFoihi586dQgghHnjgAQGIm266qard7bffPmX7okWLBCDuv//+yrbBwUFhGIb46Ec/OuOcCeHP+fvf/34xOjoqdF0XP/nJT4QQQvzxj38UkiSJ7du3V67V0NDQXs/hBRdcIEKhUNV9vGHDBqEoypTrv2jRInHppZdW/i4Wi8J13ao227ZtE4ZhiC984QuVbeVrv3r1amGaZmX7N7/5TQGIZ599dsY5KD8DE+/tSy+9VABV5xFCiGOPPVasXbu28ve9994rAPGhD31oynHLc/PUU08JQLznPe+p2n/VVVcJQNx7771VcwCIhx9+uLLtjjvuEIAIh8NV8/j9739/yrtkru+h6Zj8LrIsSxx55JHi1a9+ddV2QOi6Lrq7uyvbnn76aQGIb33rW5Vte3P9a3HppZeKaDQqhBDioosuEmeddZYQQgjXdUVbW5u45pprKu+dr371q5XfzfVZ++1vfysA8ZWvfKXSxnEccdpppwlA3HjjjZXttd5Ztd7d69atE0uXLq3adiCe09n+Tbx/jznmGNHS0iJGRkYq255++mkhy7J45zvfWdl26aWXikWLFk053+SxfuMb36h6B9TiJz/5iZBlWTzwwANV27/3ve8JQDz00EMzjnH9+vUCEJ/61Keqtr/1rW8VoVBIpFIpIUTtOb/lllumzG/5uZ74/p78nSwz+d0z1/snIGA6ApfIgIBDwNlnn01zczNdXV1cdNFFRKNRfv/737NgwQLAd9269957ectb3kImk2F4eJjh4WFGRkZYt24dmzdvnjGrZNnyA5DL5RgeHubkk09GCFHT5Wk2XNflzjvv5IILLmDp0qWV7e3t7VxyySU8+OCDpNPpqt/80z/9U9XK5GmnnYbrupUg8GQyCcD//u//Ytv2jOf/f//v/1VZH8supFu3bp217yeddBJr166t/L1w4ULe+MY3cscdd0xxRavFO9/5TuLxeOXviy66iPb2dm677TYAnnrqqYob1cjISOVa5XI5zjrrLO6///5ZXV6OPfZYYrFYxVXzgQceYMGCBbzzne/kiSeeIJ/PI4TgwQcfrIwdfEvqaaedRn19feW8w8PDnH322biuWznerbfeSl1dHeecc05Vu7Vr1xKLxbjvvvuq+nP44YdXnae5uZnDDjtsTvNdpr6+nvPOO68SQ3LzzTdz8skns2jRoilt5zqHrutyxx13cMEFF7Bw4cLK71evXs26detm7ZNhGBXLkeu6jIyMVFyxnnjiiSntL7/8cnRdr/y9N/fddFx55ZVVf5922mlVx/vVr36FJElcffXVU35bfp7K995HPvKRqv0f/ehHAfjjH/9Ytf3www/npJNOqvxdtoa/+tWvrprH8vZyf/b3PQTV76KxsTFSqRSnnXZazfk+++yzWbZsWeXvo446ikQiUenP/l7/yVxyySX86U9/or+/n3vvvZf+/v5p3SHn+qzddtttqKpaZTFVFIUPfvCDc+rTxPlKpVIMDw9zxhlnsHXrVlKpVFXb/X1O3/jGN3LXXXdN+Vd23S7T19fHU089xWWXXUZDQ0Nl+1FHHcU555xTuR/3hvL7/3e/+92078dbb72V1atXs2rVqqo5f/WrXw0w5b01mcMPP5xjjz2Wn/3sZ5VtuVyO3//+97zuda8jkUgA1XNetjq+8pWvBKh5n+4Lc71/AgKmI3CJDAg4BNxwww2sXLmSVCrFD3/4Q+6//34Mw6js7+7uRgjB5z73OT73uc/VPMbg4CCdnZ019+3cuZN/+Zd/4fe///2UGKXJH/25MDQ0RD6f57DDDpuyb/Xq1Xiex65du6rcTiYKVLDH3bPcnzPOOIM3v/nNXHPNNXzjG9/gVa96FRdccAGXXHJJ1VzM5VgzsWLFiinbVq5cST6fZ2hoiLa2tr36vSRJLF++vOLGunnzZoAZXZ5SqVSVwjkZRVE46aSTeOCBBwBfYTvttNM49dRTcV2XRx99lNbWVkZHR6sEtM2bN/PMM8/Q3Nxc87iDg4OVdqlUipaWlhnblZk83+DP+VzmeyKXXHIJ73jHO9i5cye//e1v+cpXvlKz3Vzn0DRNCoVCzWt62GGHzSo4lmPDvvOd77Bt27Yqhb3scjeR/bnvalGOR5t8zInH27JlCx0dHVWC8WR27NiBLMssX768antbWxvJZHJKZrzJ46irqwOgq6ur5vZyf/b3PQT+gsy//uu/8tRTT1XFHdVyM5vtvhsaGtqv6z+Z17zmNcTjcX7+85/z1FNPcfzxx1c92xOZ67O2Y8cO2tvbicViU/o3Fx566CGuvvpqHnnkEfL5fNW+VCpVuUaw/8/pggULOPvss6ds3717d9Xf5ftpuvf/HXfcQS6XIxqNzum84C/C/dd//Rfvec97+OQnP8lZZ53FhRdeyEUXXVRZVNm8eTMbN26cdc5n4u1vfztXXXUVDz/8MCeffDK//e1vyefzFXdI8BcmrrnmGn72s59NOea+fC9rMdf7JyBgOgKFLSDgEHDCCSdUYlEuuOACTj31VC655BJeeOEFYrFYZcXxqquumnbleLKwVsZ1Xc455xxGR0f5xCc+wapVq4hGo/T09HDZZZcdtABnRVFqbhdCAFSKUj/66KP84Q9/4I477uBd73oX//7v/86jjz5aJfDMdqxDSXk+v/rVr3LMMcfUbDNZeKvFqaeeyhe/+EWKxSIPPPAAn/nMZ0gmkxx55JE88MADlRidiQqb53mcc845fPzjH695zJUrV1batbS0cNNNN9VsN1mIOFDz/YY3vAHDMLj00ksxTZO3vOUtNdvNdQ5nSzQwG1/60pf43Oc+x7ve9S6uvfZaGhoakGWZf/7nf675XBzo+2664+0rc42tme68s41vf95DQCX+8vTTT+c73/kO7e3taJrGjTfeWDMZxMF+zg3D4MILL+THP/4xW7dunbEm5Vyftf1hy5YtnHXWWaxatYqvf/3rdHV1oes6t912G9/4xjem3KPz8b043T052ZshHA5z//33c9999/HHP/6R22+/nZ///Oe8+tWv5s4770RRFDzPY82aNXz961+veczJCw61eNvb3sbHP/7xioX/5ptvpr6+nte85jWVNm95y1t4+OGH+djHPsYxxxxT+Qafd955+/y9rJVI6MW+fwL+vgkUtoCAQ4yiKFx33XWceeaZfPvb3+aTn/xkxe1Q07SaK6Az8eyzz7Jp0yZ+/OMf8853vrOy/a677prSdq4CX3NzM5FIhBdeeGHKvueffx5Zluf08azFK1/5Sl75ylfyxS9+kZtvvpm3v/3t/OxnP5u28PLeUrbeTGTTpk1EIpFpVztn+r0Qgu7ubo466iiAigtXIpGY9VrNNN+nnXYalmVxyy230NPTU1HMTj/99IrCtnLlyqrkCsuWLSObzc563mXLlnH33XdzyimnVLn/vNiEw2EuuOACfvrTn3L++edXEq3U6h/MPofNzc2Ew+Ga17TWvTmZcma4//7v/67aPj4+Pm3fDjbLli3jjjvuYHR0dFor26JFi/A8j82bN7N69erK9oGBAcbHx2u6ne4L+/MeAt+9MxQKcccdd1RZzW+88cZ96s/+Xv9aXHLJJfzwhz+cNcX7XJ+1RYsWcc8991SS7exN//7whz9gmia///3vq6xns7n+vdiU76fp3v9NTU0V61p9fX3NjJi16qHJssxZZ53FWWedxde//nW+9KUv8ZnPfIb77ruv4h779NNPc9ZZZ+1z4o+Ojg7OPPNMbr31Vj73uc9x1113cdlll1VcncfGxrjnnnu45ppr+Jd/+ZfK72rdY7WoNV7Lsujr66vaNtf7JyBgOoIYtoCAecCrXvUqTjjhBK6//nqKxSItLS286lWv4vvf//6UFz8wJT3+RMqrrhNXWYUQfPOb35zStvyRna2Qs6IonHvuufzud7+rchcaGBjg5ptv5tRTT63EA8yVsbGxKSvBZevK/lpSJvLII49UxSHs2rWL3/3ud5x77rlzsnj8z//8D5lMpvL3L3/5S/r6+jj//PMBWLt2LcuWLeNrX/tazexqE6/VTPN94oknomkaX/7yl2loaKi4l5522mk8+uij/PnPf66yroG/MvzII49wxx13TDne+Pg4juNU2rmuy7XXXjulneM4L2oh76uuuoqrr756Wpc6mPscKorCunXr+O1vf8vOnTsr+zdu3FhzDiajKMqUe+7WW2+dNQ7rYPLmN78ZIUTNgvblvpetA5Mzy5UtEQeqjtj+vIfAn29JkqqsDdu3b58xu99sx9uf61+LM888k2uvvZZvf/vbM7pHz/VZe81rXoPjOFWp+F3X5Vvf+tasfan17k6lUvus4B4o2tvbOeaYY/jxj39c9a547rnnuPPOO6usVcuWLSOVSvHMM89UtvX19U3JXDo6OjrlPJPf/295y1vo6enhP//zP6e0LRQK5HK5OfX/7W9/O4ODg1xxxRXYtl3lDllrzmHqszUdy5YtmxJ/9oMf/GCKhW2u909AwHQEFraAgHnCxz72MS6++GJ+9KMfceWVV3LDDTdw6qmnsmbNGv7xH/+RpUuXMjAwwCOPPMLu3bun1I4qs2rVKpYtW8ZVV11FT08PiUSCX/3qVzXjGsrJOD70oQ+xbt06FEWZdpX5X//1Xyt1c973vvehqirf//73MU1z2tikmfjxj3/Md77zHd70pjexbNkyMpkM//mf/0kikagSAPaXI488knXr1lWl9QdqCsS1aGho4NRTT+Xyyy9nYGCA66+/nuXLl/OP//iPgL9K/F//9V+cf/75HHHEEVx++eV0dnbS09PDfffdRyKR4A9/+AOwZ74/85nP8Na3vhVN03j9619PNBolEomwdu1aHn300UoNNvAtbLlcjlwuN0Vh+9jHPlYJoC+n887lcjz77LP88pe/ZPv27TQ1NXHGGWdwxRVXcN111/HUU09x7rnnomkamzdv5tZbb+Wb3/wmF1100QGZ78kcffTRHH300TO22Zs5vOaaa7j99ts57bTTeN/73ofjOHzrW9/iiCOOqBISa/G6172OL3zhC1x++eWcfPLJPPvss9x0001ViXQONWeeeSbveMc7+I//+A82b95ccct64IEHOPPMM/nABz7A0UcfzaWXXsoPfvADxsfHOeOMM/jLX/7Cj3/8Yy644ALOPPPMA9affX0Pga84fv3rX+e8887jkksuYXBwkBtuuIHly5fPeq2mY3+ufy1kWeazn/3srO3m+qy9/vWv55RTTuGTn/wk27dv5/DDD+fXv/71nGKhzj33XHRd5/Wvfz1XXHEF2WyW//zP/6SlpaWmwnww+epXv8r555/PSSedxLvf/e5KWv+6uroqV9K3vvWtfOITn+BNb3oTH/rQh8jn83z3u99l5cqVVQtnX/jCF7j//vt57Wtfy6JFixgcHOQ73/kOCxYs4NRTTwXgHe94B7/4xS+48sorue+++zjllFNwXZfnn3+eX/ziF9xxxx2V0IKZePOb38z73vc+fve739HV1cXpp59e2ZdIJDj99NP5yle+gm3bdHZ2cuedd7Jt27Y5zct73vMerrzySt785jdzzjnn8PTTT3PHHXdMsdjP9f4JCJiWg5uUMiDg5U2tdN9lXNcVy5YtE8uWLROO4wghhNiyZYt45zvfKdra2oSmaaKzs1O87nWvE7/85S8rv6uV1n/Dhg3i7LPPFrFYTDQ1NYl//Md/rKTInphW2nEc8cEPflA0NzcLSZKq0i5TI13xE088IdatWydisZiIRCLizDPPrEoXPtMYJ/fziSeeEG9729vEwoULhWEYoqWlRbzuda+rSsFfK732dP2bLq3/+9//fvHTn/5UrFixQhiGIY499tiquZqOcn9vueUW8alPfUq0tLSIcDgsXvva11alFC/z5JNPigsvvFA0NjYKwzDEokWLxFve8hZxzz33VLW79tprRWdnp5BleUqK6I997GMCEF/+8perfrN8+XIBVJVUKJPJZMSnPvUpsXz5cqHrumhqahInn3yy+NrXviYsy6pq+4Mf/ECsXbtWhMNhEY/HxZo1a8THP/5x0dvbW2mzaNEi8drXvnbKec444wxxxhlnzDpv5Tmficlp/cvMdQ7//Oc/i7Vr1wpd18XSpUvF9773vZrXv1Za/49+9KOivb1dhMNhccopp4hHHnlkytjK1/7WW2+tOl75fpz4DNViurT+5XTyteZiIo7jiK9+9ati1apVQtd10dzcLM4//3zxt7/9rdLGtm1xzTXXiCVLlghN00RXV5f41Kc+VZV+vzwHta5nres03fM2l/fQdPz3f/935dlbtWqVuPHGG2d8Vicz+RoKMffrX4vprsNEppuHuT5rIyMj4h3veIdIJBKirq5OvOMd7xBPPvnknNL6//73vxdHHXWUCIVCYvHixeLLX/6y+OEPfzjlXfFiPqfTvcPvvvtuccopp4hwOCwSiYR4/etfLzZs2DDl93feeac48sgjha7r4rDDDhM//elPp4z1nnvuEW984xtFR0eH0HVddHR0iLe97W1T0t5bliW+/OUviyOOOEIYhiHq6+vF2rVrxTXXXFNJyz8XLr74YgGIj3/841P27d69W7zpTW8SyWRS1NXViYsvvlj09vZO+cbUSuvvuq74xCc+IZqamkQkEhHr1q0T3d3dNe/bvXlXBwRMRhJiHkTtBwQEBLwISJLE+9//fr797W8f6q4EBAQEBAQEBOwTQQxbQEBAQEBAQEBAQEDAPCVQ2AICAgICAgICAgICAuYpgcIWEBAQEBAQEBAQEBAwTwmyRAYEBPzdEoToBgQEBAQEBLzUCSxsAQEBAQEBAQEBAQEB85RAYQsICAgICAgICAgICJinBC6RBxHP8+jt7SUej1eK4gYEBAQEBAQEBAQEvPwQQpDJZOjo6ECWp7ejBQrbQaS3t5eurq5D3Y2AgICAgICAgICAgHnCrl27WLBgwbT7A4XtIBKPxwH/oiQSiRnb2rbNnXfeybnnnoumaQejewGTCK7BoSe4Boee4BrMD4LrcOgJrsGhJ7gGh57gGhxY0uk0XV1dFR1hOgKF7SBSdoNMJBJzUtgikQiJRCJ4IA4RwTU49ATX4NATXIP5QXAdDj3BNTj0BNfg0BNcgxeH2UKlgqQjAQEBAQEBAQEBAQEB85RAYQsICAgICAgICAgICJinBApbQEBAQEBAQEBAQEDAPCVQ2AICAgICAgICAgICAuYpgcIWEBAQEBAQEBAQEBAwTwkUtoCAgICAgICAgICAgHlKoLAFBAQEBAQEBAQEBATMUwKFLSAgICAgICAgICAgYJ4SKGwBAQEBAQEBAQEBAQHzlEBhCwgICAgICAgICAgImKcECltAQEBAQEBAQEBAQMA8JVDYAgICAgICAgICAgIC5imBwhYQEBAQEBAQEBAQEDBPUQ91BwIOPp4n6BkvkLMcorpKZzKMLEt71W7ivoimIICC7c54vIk4jscTu8YYyVk0RnWO6UwykDVn7dOBGNvENmFNQQjB9pE8AIsbIngIHt8+xkAqx0Jg50iOJS11M/anfMxM0SZVsNgxkmcgU0RXZOrDGpIs0xw3WNYco7MuTF+6WOljeyLErvE8j28fI285eELQFDdojhm0JUJkLYftwzkkJBpjOi0xgx2jeUayFo1xncWNUSTYM4bGCLIkkTUdRvMmz+waZ/NADlWROXZRHSctbaIzEeapnnGGsiau5xFSFLYM5xhMF5EkWNEao6suSm+mQN508ISHIsuEdZWuZIRoSGH7UJ5tIzlA0Jo06O5N8/iuFJbt0hQzOKqrjkWNUbYM5hjJWmRMi5a4gSxLLGiI4HqwpD5KwXUZyZh0D+eQEXTWRzljZSMPdo9w/8Z+Lm6D115/H5ph0BLTaIgYaKrEWM4hY9rkTZdkVCOkqUR1hbihomsKIV2maHmM5ExcF5a3xmhPhNg+mqN7MIfluOiKTEvCoDFm0DdWoC9dRAhBY0QlbwsMTaEpapC3HFJFG1WROboryeq2BI7w+Nv2UTYP5NBkaE+GWbu4gZWtCTrrwvSmCnQPZNg4kGbrcI503iERkqkP64wXHWxP0BbXaE9GeXLHKCOl+z8eMohqCtGQQn+qiAsc3h6jrS7CaM7GEx4xQ2Us75AIqyxpirK4Icr20Rxbh7Nkiy7LWqJ0JsNs7MnQk8oT1VWO7EowkDLpHszSO15AkQSGqtKaMEjGNAbGTYQn0Zo0OGVlIxt7MhRtD10SNAAf/fmTZGxY3hJhZVucVN7mqd0phtMmqiRx4tIk7fVRdo8VkRAsaogSMmSe3DHOQLpIfVinvU6jN22Syrs0RTRSlsNQ2iSky6xujtKXtUgVbGQkTNti60gR2/EIGwoJQyVsqCxpjNAaDyMrEmFdJaJLPLEjxWjeJqpJtNeFKDigymA5LtmiQ7ZoY3keOdPD0GSSEZUjWhNsHs5hOR7jeZuorhAL6yxrjaJJEt0DGXaOFihYLkuaorxyaSOeBKbjkQhrhFSJJ3eO05sqkCk4dCZDLGmMUXBctg7nqQupdNaHyZoOmbyDqkjYjkPW8ogbGo0xHVmRMFSZgXSBx7YMs2O0iCZLtNUZxHQVVVMIKRKxkEa+UOT8BvjAT/+KZuhIQpA1PRpjKgMpk4FMgbwlaI1paJqCrigggSQgEvLvY4FgIG1RF9Y5sjPOlsEsG/szZIoOK5ojLGyMIiPTPZwhW3QJaQpLWiIsaYrRGg8R1hS2DWd5cPMwY3mbBQ1hXrm4EcvzGMwUyZsutuvieQLbg7ihEdIlFjZFSecdJCFhOi6GIbGpL4fjebTGddoSYYazJgVboCowmrNJhGR0VaYuYmC7HjFDYcdwjm3DeVJFi/ZkhDNWNrOmLclTveP0p4o0RjWKtsdIzqIuonHWilY0XSZnOWSLDhFdIWs6FCwXAF2V2TaY5cEtw/SnCsiyxOKGCF3NEUxTIMsSq9rjnLe6HVWV2TqUAeCKn/yVnnETAUR1BV2G0YKDJyQ6kgZrOutQFZmIrhLSFDqSYUZyFgOZAk9vH2cwU6Rgu7TFdeJhg4aoTlhXaU8aKIpM0fbncCxnkwhpLGyMUHQ8esfzbB/OYtseGdMlZiil/8q4SLTFDDrqI7Qnw6QLDv2pAgXLZjBroysyh7XFOKorSTKiky065IsOA1mTHcM5JAma4yEWJMOM521G8kUsV9CaCLEgEWHneI7uoSwgsaolzvFLG+hKRuhNFdg6nANgSVO08n3LmHZlzvOWS1RTSZkWO0fy9KULWLZHW12Iw9oSvGJBPQNZk4xpky7YFCwXSZJY2hRlQX0EgJ7xAum8zdbhFAC3r+9jcWOCguMSM1RihopX+pbbrsvusQKm41K0XZY2xWirC1fkjFTR8r+pnoSDR8F2sR3BitYYxy1sQJalKhlBArKmQ9Z0iIVU4oZGeyJU+Y5PloHaEyF6UgW2leZlaVOUlqjB3ZsG6E+ZtNUZnL2ylaG8NUVW8TzBrrF81W8X1EewLJefP7GTnrEi7ckQpy1rwhKCTMEmZ7lIgKHJFGyX0axNU0xnSWMUSZamyGbTyUkT5ZiJY+1MhivXIGc5hPbB1DPTOWuNt5asuS+yYa3f3/58N+/7n02VNt9550pec/iKvR/UQUYSQohDdfLPf/7zXHPNNVXbDjvsMJ5//nkAisUiH/3oR/nZz36GaZqsW7eO73znO7S2tlba79y5k/e+973cd999xGIxLr30Uq677jpUdY8u+qc//YmPfOQjrF+/nq6uLj772c9y2WWXVZ33hhtu4Ktf/Sr9/f0cffTRfOtb3+KEE06o7J9LX2YjnU5TV1dHKpUikUjM2Na2bW677TZe85rXoGnanM8xG92DGe54boAtQ1mKjktIVVjWHGPdka0sb4nPqR1Q2TecNRnOmoBEU0ynKWbUPN5E7tk4wI8e2s72kRy26wFgqAodyRD1UX3aPh2IsU1sM5w16RkrkC7aSKXnv2h7mLaL4wl0RfBvx7tc92yIk1e08L4zl9fsT/mYT+4aY0NvmqFMEceDiQ+WLEFIlWmMGrQkDOqjOroqYzkeveMF+lJFcqaD7QoEoEhgqDKqIiOEwPX2HM0DpMpxJVRJQlYkNEUC4Z83pPmCyXjeZvIDbigSibCKQCJvOhRtD2+aOZWYOg5F8vvgTRrji4GhCL5ygsvH/6JgunuvwB9sJKAxqtESDzGatxjKmLiH7A17YHipXYMXm8nPxMHiUF+HQzXuuVCrbxKgyhJ1YY1oSMW0XQq2h+t5CAGO52E5YtYxKRI0RDWihspAKs+/Hf/SfhZ8wV7yF0Ucb5/eTxIQNRRa4wbgfzeFBGFNIRnW0FWZkZxFumBjuwJJAtP2lSd70sfGUGUaozrNcYPxgs14zsITgrCu0BQzOKwtTn1YZ2N/mk0DWRzb5gtrbT77uIKDQtRQiekqrhAUbZeC5ZK3XSZ8MpElX7FuiBqENJnhrFX63np4wh+PIkuEdYUFyTCr2uOAVJJvLEzbxS19h8O6QmNUR5VlDM3/hk+UgXRVZixnMV6wKdgukgBXiAnfd4GEhKEqLG6K0Fkfrsgqq9rjPLR5mEe3jTJesJAE1EU0NEVm61CWvLVnXIoEUUNFAK4n8ITALR1fliW/f6pMfVSnMxmuyGar2uM835eZIieVtz+5a4ydI3kKtktYV1jYEGFhfQQkGM/bFB2XqCpxamgXq44/ncM66me9X6aTzaYb7yuXNnLJiQsB5iSv7s15f/1kz7Ttt//ba2c95ovBXHWDQ25hO+KII7j77rsrf09UtD784Q/zxz/+kVtvvZW6ujo+8IEPcOGFF/LQQw8B4Lour33ta2lra+Phhx+mr6+Pd77znWiaxpe+9CUAtm3bxmtf+1quvPJKbrrpJu655x7e85730N7ezrp16wD4+c9/zkc+8hG+973vceKJJ3L99dezbt06XnjhBVpaWubUl5cC3YMZbnxoO6M5i/a6EBE9TN5yeK43RW+qwOWnLGZ5S3zGdhv704D/gghrMiM5k7zp+K8gCZpi+pTjTeSejQNc93/PkynaNEZ1AHrHC4zlLVIFi1OWN5GMaDMeY1/HBlTahDWZ3vECAxkTz/PQFBnLdSnY/ttQAtTS9zhdtPm/5/oZyVl87nWHT1Fsb3xoOztH82wZzDKYLuKKqcKDJ/yV+d5UgcFskfa6MEd0JNjQm2YgU0QI/H+l9q6AvO2B7SEBYU3CdkWVIhjRZEzbJS/8D1JYU1AU/yM8nLWmFURMVzCUtZEBqaR8TUetcXjzVWqbBwhgOGczkpuqKAf8ffByva7zedy1+iYA2xMM5yzSRRtNkTEdDxC4e7HY5AoYytoMZW0M5cD1+VAhgKIt2J8rKoCs6ZI184RUiYWNESR8q9TusQK6IhE1VEzHo2i7WLaHO82xTMejL1VkMF1EU2VUWUKWwHF9RWjHhjy6ImM7Ho7nW/wBHAGm62E7FpmCjSsEIOHU+EB5AjKmS87yvVAUGYRHRVkVpUam7fLCQIZtIzmO6aojXXQZz/v3jwS0JAwKlsvGdBpFlkiENBQZHNdXwyzHVxhH8xaqLNGRDJMt2gykfWusJvuKY952SZseG/vS1IU12lpCPLp1hJ8/vgvL9TAUmeaYbxHfPpwnXXQAXyaRJb/fjoBU0UH112lxxZ6FXFUIiq6vIBdtD6mkTD66dYTfPNVDe12IFS2xipxU3l4XVsmZDq7nEQ+pmLbHlsEsz/Wk0BSZ4xfXs7QpRtG0QMBPH9vJpaeoM8po08lmj24rjddxMVSlMt503uauDb6SFQ9puJ6YUV7dm/N++77uadsDLP7kHw+Z0jYXDnkMm6qqtLW1Vf41NTUBkEql+O///m++/vWv8+pXv5q1a9dy44038vDDD/Poo48CcOedd7JhwwZ++tOfcswxx3D++edz7bXXcsMNN2BZFgDf+973WLJkCf/+7//O6tWr+cAHPsBFF13EN77xjUofvv71r/OP//iPXH755Rx++OF873vfIxKJ8MMf/nDOfZnveJ7gjucGGM1ZrGiJEQ9pKLJEPKSxoiXGaM7izvUDOI43bbvlzVE2DWTY1J9hWVOU/pSJaXu0JEK0JgxM26U/bbK8OVo5njfh5ek4Hj96aDuZos3C+jAxQyVdcJAkiYaIhu0Knu1JEdWVqj55s2gIcxnbHc/1c/tz/YzmLJY3R+kdLzKas9AUfwXW/7DUPo8q+R+B53rS3P5sf6U/5fOOZC0s22EkZ86ozLglZUd4glTe4umdo4zmLSQkfzv+C32ytd93tRCVNuA/uKbjVZ2vYLuYtovkeXP6FHvwkrf+zFeCaQ0ImD9Yrm99kaW9U9YCZsd2BdmC7/6oSiDhz3WuaAMgI6ZV1soIfAXEsn3X16ihIQQV19BM0cZ0XNRJH0elpLxYrihZTWeRFUrfYMf1z1emfFSn9JF1XI8NvWkKpoMEaIqvSJq2wPM8bFcQUmXGCxajOZvmuEFLXGckazKStzBUBUWWyBZthrNW5RwCfyFWkiQiqoTrCZ7ePU5YlbBdl5GcieW4tMR1QpqCLkvkTGdP//EXdicK7k5psbc8j7K0Z5sqS7jCYzRv0jdexHZdMkUbx/Xd6hVZImaoOJ5HpmAzmCpiu4LGmEE8pNEQ1UgVbSzHQ5OhP20iSxAL+YaVsVlktOlks5ihYjsuozkTy/Eq4w1rKi2JEJoMz/Wk2dSfYXlzdFp5dW/Ou3XLzMpamds2bJ5Tu0PBIbewbd68mY6ODkKhECeddBLXXXcdCxcu5G9/+xu2bXP22WdX2q5atYqFCxfyyCOP8MpXvpJHHnmENWvWVLklrlu3jve+972sX7+eY489lkceeaTqGOU2//zP/wyAZVn87W9/41Of+lRlvyzLnH322TzyyCMAc+pLLUzTxDTNyt/ptG+dsm0b27ZnnJfy/tnazZWesQLbh9J0JnRkqr9YEtCZ0Nk2mObx7UPTtssXHRTh22OGMnkyBZP6sIwm+43qwzKZvEm+aFeOt3M4Q2e97//8tx2j9I5laYtp6ApYtoPrOsR0CVWWkEIyhaLFYCpPezJc8xj7OrYNu8dAgs66MPmizXiuiC4LdNV3OdQkD6Hssa4JQC2t5EU0CWyB59g8sWOYncOtdNaHK+etD8l0DxRRJQ9ZmdliJQGaLCELj0zBQUGgKxJm6VyqzBSBotwfmT3ukOVVNhmQ5T3uiZok8ODvYiUYwCjdW+X/Bhx8gmswPwiuw/5jKBIys7tBTvv74BpMQQJMyynF7Ml4nosngRAuhiTjIDCUuc+XJASGKkCTyBQcoqpMxhP+YiYe4ZLUGpYFRXyrk4f/7XRm+vhO0/fK97X0TdVlCYHAdhwUScPzXGK639J2bBBQF5JxHRdF+DGXeL5KqkoCFY+IqqAoMvmijVTqsyxJeEIghMAoKYCKJHAcm+f7UoznTCKKr+DiuX4sZ95ElUWVoK5IVC3eTh7PRNnAUP3FYNXzGErnURWZtphGtmCRK1jEwyrZgkO2YNEYURjKmDRE1JJMJ7A8Fw2BJOPHS+ZNcgWLRMhXcTviM8to08lm2YJDqjxeec94y4OIGQqpvInw/DmMh/fMwER5dW/Oe0+PmJNc9OGbXuCczy+eveEBZK5y/iFV2E488UR+9KMfcdhhh9HX18c111zDaaedxnPPPUd/fz+6rpNMJqt+09raSn9/PwD9/f1TYsjKf8/WJp1OUygUGBsbw3Xdmm3KsXRz6UstrrvuuikxeuBbBiORyLS/m8hdd901p3Zz4dQQJXPNNA1CMLB+14ztjlpW/r80Jy+e7kzjpUAqePqRXTw9Yc+HVk5quqDW73ftOXeNY9RitrGtqSv9T+mFsWccs/Opoyc+TIM8/chgpT+nhvz/vnL+x6u+pLn2uL38EgcccIJrMD8IrsOhJ7gGk5nOhjabba0W0wko1Vy99mBcg+wc2xX9/1TkGWe6hiUmz8sgNNY43txTJMzhPOakfeOVqT5qMdO3q4ypuOd3pf89gu2zymjTyWbVMliRKSwCsIBs7VtiL8/7lROmaViD2267be6NDwD5fH5O7Q6pwnb++edX/v+oo47ixBNPZNGiRfziF78gHJ7eovJS4VOf+hQf+chHKn+n02m6uro499xz55R05K677uKcc845IElHesYK3HBfN3VhrWLOnki26JAq2Lx5bSe/+ltPzXaZgsPDW4YBOKqrjg29GUKahF5aGrEcl6ItOGFxA5IEqYLN+89cXmVh+8xvnvMzOoVULNtl93gRVfEtbKbjYTser17VQnsyXOnTxGPs69j6xgsgQXtdGCHgoS3DjOetkoUNxvMWlldtYYsogs+v9bjuaY28LVBkiWMX1fMvrzuiYmG74b5uVFnirztG6UsV8Ly5Wdh0RcbxPBwhUJAwvQNkYZNLLh9/JwvAhiy49jiPzz0uY3ovzSD/lzrBNZgfBNdh/zEUyXef29ffB9dgChIQ1RRURUZRfDdA/3MmiOkaOcupfFvnQmNEx9D8eMNMwcZQZTKWWwoXkAgr8OljHK75m0zRkxDixbGweQI6k2Gypouq+NfaLgWRy4qE5wocT6AqEl0l+WR7KVlHIqShKBL5okPOdpGliRa2UkIxWcJyPVwheOWSRnrGi4xkTWRJYmFDGF1TGEwX2TlWra3snYVNxhMQUmQSEQ1VkSvbTljcQDyskik4/GX7KK7nMZQx6UiGK3KUZbvsHC0gSdCSCCFKv0uEJBYXt7CexYwV3WlltOlks7IsOZI1kWV//nRtj/krU3ToGcvTENU5fUVLlYUNmFU2rHXe7/55y8w3wwSe+/y6Obc9EJS972bjkLtETiSZTLJy5Uq6u7s555xzsCyL8fHxKsvWwMAAbW1tALS1tfGXv/yl6hgDAwOVfeX/lrdNbJNIJAiHwyiKgqIoNdtMPMZsfamFYRgYhjFlu6Zpc1bC9qbtTCxsUlncnOC53hQrQjqStOdjI4SgJ22xprOO4xY387edmZrtIiEJV5JBQHM8QjxsMZgp0hAt+TMX/Hi2SEijeyjHms46FjbFKylYj1vcTEd9jE2DGRZqKpKioigqWcshpEK66Plp6+sieEiVPk08xr6O7cgF9QhgfW+a5c1RktEQg1kb0/J90W0hY7l7Yr8kQC85iudtQcGTSOgar1jUVOlP+bzP9qRojIXYNW5WsjxO93mS8F+2qioTD6sM5x3MUjIRSvvKsW6Tf1d+EQOVhCFCgHAnxL1JEpIQmPuysDmPMT3pJZuV7e+F4BrMD4LrsG+Ukuhiu9J+x7AF12APigSGriJJMjnTxvL82KyQqmAKCQ9pzt8jBRCSP7cFWyApCjlH4AoJz/UVkELpY1nwJBxPqnw7HW/uMdmTs4qWFTdJ8uPbZFkioiu4QkaWIWu5IEQpts5jvOCQDPuZRz1PAtlXNhwh4SCTd/wORQ2NrC0olFZQFVlCliQKLqieoOhALKSxqr2OnC3YlTIxVP94jvBLWjgjxT3ffT86A6heGJYn/F1W6KTyNglUTaY5EUEg2DaSZ2lTlGhYR0gS0bBMLKyzdShHSPf7a+iSL0fJYOP7nGZNl7ZkxP9d6Wy9GYvDO+unldGmk82iYZm6qMGulInOnvGCL7NlTRdkFUlWiYQ0hLQnam+ivLo35z2rU+K2nbPfG99558oDmpl9Lsz1fIc86chEstksW7Zsob29nbVr16JpGvfcc09l/wsvvMDOnTs56aSTADjppJN49tlnGRwcrLS56667SCQSHH744ZU2E49RblM+hq7rrF27tqqN53ncc889lTZz6ct8R5Yl1h3ZSkNUZ/Ng1g889TwyRZvNg1kaojrnHtGKqsrTtuseyrGyNc7KtjhbhnO01RkYmsxAushA2sTQFNoSBt1DucrxJj5Mqipz2SmLiYc0do4VyJp+HSkhBKN5G1WRWNNZR85yq/o0W82NuYxt3ZFtnHdkGw1Rne6hHB3JEA1RHdsVjJdW8UJa7fM4QqDKEkd2JjhvTVulP+XzNsZ0dE2lMWpMSRgyEaWU4UmSJeoiOkcvbKAhovtpeCX/BWt7tZU1Q6XSBvwXsaHKlfMJ/CyRhqYgJIm5iBJyqU8BB55gWgMC5g+6IhHSFDwhVb1HA/YfTZGIlUonOAIEEoamEA35QqiHxGyhQ+WszLomkzX9hCWS5JenkUvJJgxVmZJUxBX+N0xX/CzVk5OSTEYufYNVZU8WaNijvKmlm0NVZA7vSBAupc23XQ/HE345BFlGVSSKjkcyrNMQ1RjMmAxmLBpjBo0RHdPxSwNFQxpNMb1yDgk/u7MQgrwjUGSZoxckKTgCTVFojBroqsJgxqJgu1ieIGrssavUyuysSlTKElUWhEvbHE+gSDINUZ32ZAhNUYiHfEtb1nRwPI+s6aDKMvGwRktdCFWWGMmaZIo2ozmbupBfpsH2oC1h4ApBtpS1sn4WGW062SxrOmhqebxyZbwF22EgXcT24MjOBCvb4nQP5aaVV/fmvEuWzS0OZj7XYzukFrarrrqK17/+9SxatIje3l6uvvpqFEXhbW97G3V1dbz73e/mIx/5CA0NDSQSCT74wQ9y0kknVZJ8nHvuuRx++OG84x3v4Ctf+Qr9/f189rOf5f3vf3/FsnXllVfy7W9/m49//OO8613v4t577+UXv/gFf/zjHyv9+MhHPsKll17KcccdxwknnMD1119PLpfj8ssvB5hTX14KLG+Jc/kpiyt1KQbSRQxVYU1nHecesaeuxWztYE9tjMaoUcpQJJXS9EtTjjeRs1b7v59Yhy2kKdRFdDrq/ICw8bw94zH2Z2wT23QkfffITNEGyS86qSl76rCV3QoTIW3aOmwTz2uo/vpHzTps+HXYGibUYQM4vCNBMqXRN15dh03GTz0M/gvYLlnRDM1fCyyvEBqagipJKIpUcdswFBljL+qwFey5ZZWcyOQVygAfCb8OW2sixEju76MOW0AAzO9nvlbfJPbUYYuFVIq2i2b7qeH3tg5bY1QjUqrD9veAWvLW2NfrKVGqw5YwQECuZEJrTYRIRjR0RWY0Z5Eq2CiSRNSYWx22VMFmrFSHrZza/tS2BMmwxsb+NJsHspUEDaoEkioTKRXNdj2B6bjkzdnrsI1kLbKmg5hUh83QFJbXhzmsza/DpikmQkBE95VFyxFEdIUF9eGZ67DlLcbztp/hUZJoTRiV73vB8ZAlmURIYXFjhHhIZTxvc9KyRi47ZXGlLtlI1o8l66oPo06qwyYxex02fUIdto66MCBx0rJGDmvbU4etLCdN3P7krjF2jubJlIqedzVEWdQQQeDLZtuHc0RUCULwDycunFVGm042O2lpI5edPHW8ybDGiTXqsE0n0+3NeS88tnNe1mGbK4e0cPZb3/pW7r//fkZGRmhububUU0/li1/8IstKmnC5WPUtt9xSVax6ohvijh07eO9738uf/vQnotEol156Kf/2b/82pXD2hz/8YTZs2MCCBQv43Oc+N6Vw9re//e1K4exjjjmG//iP/+DEE0+s7J9LX2ZjPhTOhrlXjp+p3cR9EU0ppZ5351yJ3nE8ntg1xkjOojGqc0xnkoGsuc/V7PdmbBPbhDUFIQTbR/wP8eKGCB6Cx7ePMZDKsTC3iSNPPIMlLXUz9qd8zEzRZn1virvXD7BjLI/neUQ0hba6CKeubOK0Fc101oXpSxcrfWxPhNg1nufx7WPkLX+F6endKRzXo6s+gizDYMZkPGfTFNO55JWLkICRrEVjXGdxYxQJ9oyhMYIsSWRNh2d7xvnfp/vYNpwD/Dp5xy1u4MJjF5C1HJ7tSfHkzjGGMyZjeT/db1hXcD3BooYojhDYrocQHpIkoykymixRsF3OWNnMtuEcT+4ao2Da9I4XK771QvhxdS0JvVKDznY9FtSHMTSZmKExkrV4y3FdNMZ1RjIm3cM5ZASd9VHOWNnIg90j3L+xn4vbRrhhUxjNMGiJaTREDDRVYiznkDFt8qZLMqoR0lSiukLcUNE1BUOTeWTLCD1jBRKGRkNMJxZSGM/b9KeK9KVNIqrEoqYoUV0hXXDIWg5CgCIJirbgyAV1LGqIkrccUkUbVZE5uivJ6rYEjvD42/ZRNg/k0GRoT4ZZu7iBla0JOuvC9KYKdA9k2DiQZutwjnTeIRGSqQ/rjBcdbE/QFtdoT0Z5cof/wcpZDvGQQVRTiIYU+lNFXODw9hghTeWuDYMYqkzUUCjaHoaqkIxo1Ic1+tJFBjImixuieAiypuOXnHA9mmM65x7ZioRE92CW3vECiiSwHejPFHFsh76Mhe2CrgACFEUmGlKJKoL/b1WBLz1lsLg1zqKmCF31EUzHZftInuGMhSpJnLg0SXt9lN1jRbYOZnhs2ygSHgXbX6F2PY+oJqGoCo4rcEr9cpEQQpDKmhiGStzQkCSwLYdx06Fg+4snYQUa4yFCmkxfyqwIieXH0i2tLKuK7x6lV2JLBDnTpWg7dNZHSUQ0khGVI1oTbB7OMZIx2dCXwXJcTNcvUD1e3CPIS/hz0hBRcYRMe10IXZG44BUd7Bot0JsqkCk4dCZDLGmMUXBctg7nqQupdNaHyZoOmbyDqkjYjkPW8ogbGo0xndGCxRPbxxjJ5BlIO5hizzn9rK++YGZ5EFYEXzrB5eq/KSSifh9ylkfRcshZnr/AI8nEdNl3lwbckntXfURlVXuCurDKQNqiLqxzZGecLYNZNvZnyBQdVjRHWNgYRUamezhDtugS0hSWtERY0hSjNR4irClsG87y4OZhxvI2CxrCvHJxI5bnMZgpkjddbNdPxW57EDc0QrrEwqYo6byDJCRMx8UwJDb15XA8j9a4TlsizHDWpGD7WfdGczaJkIyu+m5htuune98xnGPbcJ5U0aI9GeGMlc2saUvyVO84/akijVGNou0xkrOoi2ictaIVTZfJWQ7ZkgCaNR0Kln/v6KrMtsEsD24Zpj9VQJYlFjdE6GqOYJq+4LuqPc55q9tRVZnN/WM8/9cH+N1IMz3jfm2tqK6gyzBacPCEREfSYE1nXSlrokpIU+hIhhnJWQxkCjy9fZzBTJGC7dIW15Fk/92Ts11USWBoCsmozvLmGLLk1/pa2Bih6Hj0jufZPpzFtj0yputn7jNdYoaMi0RbzKCjPkJ7Mky64NCfKlCwbAazNq4r2DWSY2FjGF1TeWrnOKoiI/AoWi6u59uA1nTWYTkuozmbE5f7gvyCRISd4zm6h7KAxKqWOMcvbaArGaE3VWBr6fuypCla+b5lTLsy53nLJaqppEyLnSN5+tIFLNujrS7EYW0JXrGgnoGsSca0SRdsCpaLJEksbYqyoN5P0NYzXiCdt9k6nMLb8STyomNZ3Jig4Lh+XLyh4pW+5bbrsnusgOn4SuLSphhtdeGKnJEqWmwfziF5Eg4eBdvFdgQrWmMct7ABWZaqZAQJyJoOWdMhFvLfUe2JUOU7PlkGak+E6EkVKt/dpU1RWqIGd28aoD9l0lZncPbKVoby1hRZxfMEu8byVb9dUB/Bslx+/sROesaKtCdDnLasCUsIMgWbnOWWCqLLFGyX0awvKyxpjCKVvteTz1FLTpoox0wca2cyXLkGOcshJMPTj9y3V/LpTOesNd5asua+yIa1fn/789287382Vdp8550rD6llba66wSFV2F5uzBeFLWBu7Ms1mFqsUSVvOfSlijRE9VmLPXqe4Lt/2uL7XrfEpsTjbR7MsqazjivPWDbrS2u2vrx6VQv3Pj84Zf+mgQw7R/KcuqKJ5nhoynEdz2P7cI4PnrWCVW0Jugcz3P5cP7c928doziIZ9lejx/K+YKgrEqM5i5ZEiLUL68maDmN53wXiM69ZzcLG6LRjmO0aTFa+JSBf+jgJIbj+7s0kIxrxUPVvhRA81D1MX6rIuYe3UhfR93meDxZzuTc66kIUbI+x/Oz338TjtcYN/rx5iHTBwRMCXZH9ukeKjCp5fOrIItc9GyIeMdAUmaaYQVPMYFlzjHVHTl3t3DWa5+t3vuAr+KrvfrO+J0V9VEeWpJIg5XHS0kYSYQ3H83h2d4pYSEUIaK8LEdYVCpbL5oEsfelipdir7Xr86YUhhrMmYU2hMea7Ig9mioQ1FVf4ymAspHLq8maaYsaUe7bWnLbGDR7dNgoIBtImmiJRtD2iukJXQwTL9SjaHscvrmc0Z0051v5ez7G8zVO7xslbDjnTIV2wSYQ1orpK1nSI6xIfXJnle1sS1MfDHLeoHoBNAxkWNUZ54zEdxENThav9WQALqObF+i7vr1A613OU77dkWOWRLaNEQwqa7CvG5Xf0cYvqcYWo+bzMB/6eZaODcR8cCP6er8GhYK66wbxKOhIQ8FJmcrHGskAdD2nEDJXNg1nuXD/A0qbYtC/hnvECW4aytNeFqgRyAEmSaK8L0T2YpWe8QFfD9KUhZuvLpoEMP3p4O1FdZWVr9f7lzTG2DuV4YSBDU8yY0o+C5WKoClHdf30sb4nzvlfFOKYryc1/2UnOdFjSGGFjf4b+lIkqQ8RQaYrp/G3HGCM5k1TBpiFq8PunejlvTducXV8n0j2Yqbg7DGfNUoFSUVEmEiGN4ayf9WoykiRxWFucoaxJ91CWla3xioJQVm7mEj95oPA8we6xfNVKddeEVUbY45ffmyqweTBbpdT0pYrURzQEMJaf2/1XvtfaEiFG8xauJ2iM6uQt303W8QQ506Y+7EeguJ5vqdIVjxHJt9Y+15uiN1WYshDRmQyzvCXuKyN1MXRFRlVkbNdDV2SyRYeWRIh4KYNXwXJpihlc+IpOnt6VmtZdZ8tQlqLtENJkVFmmOa6TjOiYtoss+ZlXbVdgaDIhVUEv+RVPvGcnCkXpgk33YIb2uhAxQ6U+otM7XiglIJAI6wqWKzBtl5zl0pLwYzwm3v/7yuRnvSGqc0xXkvW9KYYyJooskbdcOpJhjuhMsHvETzGuqzLDWZO+VIGs6dIYM7j4uAVTnqHy++GlIgS+nJFlacb3+YE6x7ojW9nYn+bRbaMM50zG8hKy7Md/NUYNljVHkSSJgukckHs8YO5M/J4VHZeQqky7IBbw8iR4GgMCDhAHQtnKWQ5FxyWi1y5jENYVBkpuGPvTl3hIZX1vmpOWNk7ZnwhrtNeF6Bsvki7Y1EV0hBBkig6m49IzXuCExY2VlXzwhYFTVzTTVheqfHQMVUGWQJFl2hIhtgxlS8HKEk0xg5WtMdb3pelLF2e1PE5movUwrMmM5CxypoOEqCgT20ay7BrN0xTT6WqYasULaQorW+MsbYoxnDX32kd+MvsqGHcPZrj5sZ08unWEVN5GSFAX0jiyI8E5R7Sxuj1ROdZMsZpHLajj10/00F6KBU0XbKySghQPqVPuv5zlMJw16R0vMJQxGc1ZaIpMWJWpCymMFzw/0DyuAUWEEDTHdAxNYTRn0Z82WbswSfdQbspCxGTlsi1hkAxr9KUKFVexZc2+UimEoC9VZE1nHScva+LkZU015/HMw1oq2wfTRf79zk30p4uENBVNkdAUqRJ3ocsyjTGDeEitOn7Bcvnun7ZUhCLTdtk1VuC4RQ3EQxLLW2JkijYZ06ZouYR1Gcf1GM3bJCM6S5ui9KdN1nTWVd3/+0KtZ70hqrOqLc5I1iRq+NbRVW1xmuOhkuI8RtFxGck59IwVOWV5I+uOnH7BIxACDw4vNaVYlSQ0xY+/0qRyVLTPxOdlf+/xgLkx1RsmTN5ypl0QC3h5EihsAQEHiAOhbEV1lZCqkLecKW58MNW6ta99UWQJ2/VqChWSJLFygvWpJW7QO15kKGuSMx3CmsqyJpOtw9maSViWvipWEV6GMiZP7Rzn/57b4y7ZUHKla4jqFVe+yQJ/WQBK54uVv8tMtB4ub47y+I5xTNv1A+Choky8oquOvlSR53rSJQGqOjVwX6rIKxbW80+nLa2KKdwXYWtfBePuwQzX372Zp3eN+8kN4jqm7dE7XmTHSI4Huoc5srOOY7vqK8eaPMflPm8azFB0XIq2zPN9GUbzFo7nocoyDRGdxU1+3Fn5/hvOmOwazSOEIBnRKToaqbxNwXLwhD/PkiQxnPfbR0IahqYgSRKxkMpoziJrutMuRExULrsHM3hC4LgCWRYsb46QCKukCxZbh3NEDZWjFvjV7aezNkzcvqotge0K/uOezQxlTHRVJqT5sXGeEIQNlUWNEbLmHnfQw9ri/PiRaqFoMF1kY1+Gv+0Y5YQljTREdY5dWI/aI7F9OE+q4KDIfjKBJU1RRnIWDRGdNQvq2DSY2S/hfLpn3VAVwqXnO6SpGGo5x55/DtcTyJKEIsN4wWbrUA5DVab040AJgS8lZeRQ9PXFUIoP9DjKcUI/fXQHmaLNuiPa6Bkv8GxvGtvxSEY0skWbDX1pmmMhGmMH18Pg5cyB8MwJeHkQKGwBAQeIA6FsdSbDLGuO8VxvipihTolTmuvK52x9cT2BpshVitBEwiXrU31E5/Hto37QsqGyuDFKR9IPtr7xoe01hb5qwRoWNkR4ridVOV48tGdctSyPEwUg27E5Owb//eA2zl3TwfKWeJX1MGu6jOUtYiGtcsyyMpGzPI7sSPDkznGe6UmxrDlW7fZYEry7h7O+a2jLzPX+pmNfBWPPE9z+XD+b+jPoikRjzKBoe4zlbWQZNPw4srGcxbM91ceqpdREdRXL8Xhi5xiOK4iFVDRFxXb9hBAjOZOuhkjFLfCpneNoqozrCXRVJqqrjOQsP3ucJ3AFhFTIl1I4x3SlMseaIpMzHSzXF/amW4hY3hLHOxzGCxYDGZP6mE7RcnmhP8uusQJ5y0PCLyb76yd6eHpXas6C7lmrW+lqCPPLx3voHsyQtx1E3MATlJRBG9P2WNNZx9mHt3DX+sEpQlFbXYhFDRG2juToHsxw/OKGUrHWZhY35nly5xi64luIwb9XEfCbJ3r2Wzif7lmPh1TqIxpbh3MsbYoSL93P63eP84ouP4NsRzJMznL54zN93PFcPyvb4lVK/YESAl9KFrpD0dcXwzJyoMdRPt4zu8d5tjdFWFOwHcGylignLW2kezDLWN5/7gfTJmsX1fOW47rm3fX9e+VAhUEE/P0TKGwBAQeIA6FszRanNNfYqtn6kik6LG6Kki46tAlRs6/HdtXjeR6DmQidyTCGqlSUreksY7Uo2C6KIrGgPoJSo91Ey+NkASim6WDChr40PWmLy09ZjOOJivVwLG/huB5aaM+rbKIy0Z4MM5y1WNIUZTxvV1wID5TgvT+Ccc94gWd7UrhCEA/7SvVozsR2PcKajCvAcrxKmYuBjDnjfLcnQpglhW9h/R6LoqEqaBGJnWMFWh3Pz2A27md2O7IjwebBnJ+h0nbRFRkHD0v46T4VWSYekgGbrOUSC/v3iu16KLKMrsgzLkRs6s/wb7dvZMtgDuF5IPllKrJFh9E8LKgPs6YzWXH/myjoLm2aakWcPO6VrQkuWivxy7/tYstQFlf4aaFb4gbHLWlgdZvvTjqdUCRJEstbY4zmLXaM5FlQH6YlEaJguZiOxynLm3jNmnaa4gbDGZPbnu1jLG/vtWJeaxwzPeuqLFfqJWWKNpsG0mRKirOqyOQtFyEELXGDTNFmLF+t1Buqst9C4EvJTetQ9HXysw+QKfrvnda4QX+6uNeWkQM9jirXcV0hrClEDYXBjJ/F8ZiuJMcvridTdCo1sC44tnPeXNeXAwcqDCLg759AYQsIOEAcKGVrrjXl9qcvjTGDi0tZIqfr61FddfzmiR6WNcemWOn2ZuVvrpbHsKbwv0/3VSk/kvDTby9rjrJpqMCd6wd47VHtlePtSWYhMEqVUCcrE00xg8tPWYIsSX7c1j4K3rXYl9XRsgD/XG+K0ZwFQlTiSQq2h6HKSNKeYrOW6zFWKu7+9O5xdo/la2bW7EsXMTSZZFhjLG+XLGx+oo9s0SEZ8WsEld0/i46f7jpqaDzXk2Iom0XCFxDiskrOcomHVLrqDaBAvmhjRlwMTWEsZ1Ef0fGEx0DK4qgFUxciNg2k+dSvn2VjXwZPeFAq6K7IEmapTlKoVERWlqqV3Fse20l9VGfrUG5Ghbp7MFNxc1zUGK1kxdw1ViBnDbG0KYosSzMKRQ1Rg7WL6nl8xxijOZt86X6c+Lx5nuCeDYOM5e29Usxns5ZMW6NoQqKVZ3aPs3usQEL3FfCooTBW8GiI6n4/JL8O1poOo6LUv2pV834JgS8lN61D1deJz/5Y3q5YqhzXQ1VkorrCEzvH5mwZOdDjmHy8TNFBU2RkSaYh6sehbhnKcdwinUTYL6VRHzGIG0HWv4PJgQqDCPj7J7gDAgIOIAdC2Sofp1ac0t4IHHPpy6LGyLT7J1qyajHXlb+5Wh4lmJPyI0HleMubo9RHdIYyRfRSMfJyBsKYodA9lGNNZ10l4+JMgndUV3imJ8VNj+7k8lMWV9X/me4a7O3q6EQBfjRvsns0T9Hx0FS/xp0n/PgkAFcIXM+vp/bc7hRIgqLt8cMHt/MPJ00tWJqzHHRVZu2iBrYN5xjL+8VhVVmmJRFiUWOEdMGujKUsJDREdVa3xxnLWZU03wCpoo2uyIyVYtgkSaI3XcRyPCjV57trg0lz3M9SOFlR+fa9W9g0kIFSIVfX810fXc/DLRWW3zla4O6NA3Q1RFne4sc1hjWZe58fZGFjhGXNsWkV6r0RcGcTikKawhHtCd524sJKKv2J13pfFPO5WktmetbPPKyF+zcP8d8PbmVZYwRIU7RFlQtw2aJse6LSj+MW1++XEDjX8e4eyyOVFkIOVXzboXIpKz/7RVvh2Z4UBcshFtLQQiq2KxjP2wxlTTb2p+d03gM9jsnH811t/XdlQ1SvuI5nig7xkBokGjlEHKgwiIC/fwKFLSDgAHMglC04MKmeZ+vLTPt3jeYPyMrfXC2PedutKD9lt03HdVgi+x+usvKTt93K8bqHcrTXGaSLNgNpE/Bjt9oSBt1DuSlWzemEotGcRfdglsFMke6BLL2pgv+BFH5ih+msPHuzOjpZgG+vC5Eu2GwayNIzVqAjGUaWJDzhxykVLD+LYdRQiYdUPAActo1ka8YPlvsS0uSKm9PELJFZ08G0vco1nigkGKpCSPeVNVGaj5a4waq2BLtGMgCVNPMCP5NozFCJhVQimsq9zw+yqDFSpUj1jOfxhECS/KLWmuyPrWgLPPwxCuFbhwbTBbKmw9EL6ugZL1CwXTqT4cqc1lLC9kbAnatQdNyihpqFZTOmvVeK+d5aSyY/654n2DWa94vy6gpNUQNV9qthm7aLJkkg/NjDiRblcj9ihrpfQuBcFiK6B7P88MHtpIvTPx8Hg0PlUhbVVXRZ4pndY6QKDg0RDV2RkCQJQ5UQIYWhjMvj20c5e1UrcGAXf2Zj8vEkyc+CmjUdRnMWEUPFdv0Y4P70wS9lEuBzoDxzAv7+CRS2gIAXgYNRV2euzNaX6fbPVchtT4QqwuV0yulcrH1lBbF3PE9/ymQ0byEJl+OWwpM7x2lKhCvKT1dDpOp4jVEdIUBC0Bg1AKmmVbOWUDSas3hq17i/Qm6oSPjZDO/aMADA8YvrWdoUq2kdmcscHdmRwHU9fvrITnaP5Tmqs64SX3Z4ex2jOZu+VIGesTwRQyVvu+AJTMd3reqsD1cK27YmQhzVWVczlf7EvqxoiZEIa1P6UhbSa6Xd11WZ7SN5bNdFkWVURWLbcI5lzf69sagxjK5pLG2K4QgqiiBQU5FqjOgIwPVAlQFJwnH9ODYElHQOHM8jZqjkLIcNfWnG8xZRY2J2RJ/JStjeCLh7IxTVcmNsiulYjjfnxYu9tZZMVBAH00Ue2DTM1uEcrvBIhjRGcjZ941nWtPt19qysjarIhDUZWfbjQ8tKuR9rqu2XEDjbQkTfeIFdo3kkiRmtoAeDQ+VSVrBcesaLbBnKoZfiCsOaTEPUIKTJ5EyX9mSIobTJw1uGK/UFD8Tiz1yodbxyrb/y4lTR9ijYLkcvSO5TKZOAA8OB8swJ+PsmUNgCXnbMxzTV+9unF2NMcxFyD2uL8/37t04riEzu1xWnT59CvzMZJhnRuGvDALoiEQ9rRFRfsRnKFNk2WuScw1srVoHJ1sGwpiABeduddg4mCzFCCLoHsxRKroGW66fBH8tb6IoEkkR/2iwJxLWtIzPNkSJLjOQsrrv9eZ7bnSKkK1iOYHkpScGWoRyS5Cs/BdvFFQ4C35oVUhVakwaKLJWSBvhWE1mWa7pH7e1K7UQh4cldYwxliiWLnEJLwhc6e8bzDKRyHLfSj2/paJgazwjUVKRaEyG/SLbju2UKQcnl00884gmQJXyrIkwoFeCwvCVWUQYnMlEJ2xsB1/MEhqpwxspmHt/uj3Ug7U0RiqZzY9w56teqM22PYxcmZ7VY7Y0yOVFB3Dmao3swh+t5xEMa8ZBKxnAoOC5D43lo9wtn2zaAYCzvxzY2xXx34MlK+b4KgTMtRHiex3M9aTRVrlp8OFTxbYfCpWzrUJb/eWw3rhAosoSEb0nOWi4Fu0BUV6iLaBzWGmf3WIGb/7ITIZjRNfZAj6N8vGd7xmlLCGxPoCsy9RGN4xYleaYnxdKmWMX9+1B/A1/uHCjPnIC/XwKFLeBlxXxMU72/fXoxxzS5lta2YRtZgmUtMU5Y3MC9zw9OG6Pz6lUtPN+XqdmvVW2J2icsVxmQJn+kfLPM5K17a8mcLBRlik6lLAD48W91YY2c6UzI3OjHeZQtVjFD4W87xnh8xyjHLWqYdnW0oy7EQMakL1UkoimEdJmYoTKUKTKcNf3hCkFdWKc+ojGQNqmLaMR0lURYZUNvGteDou3RkghVatfB9O5Rs63ULm2KVVlDlzbFuOL0KF+543mKtktT1GAgU2Qsb5csBgqK5F+UcsHrWtRSpFRFpr0uzObBTKn+mm9RQyq5QwJKSWGT8JW5rOlgKDIdNSxTUK2EzVXAnVws21BkmidlkSy7QU7nxriy1bcA+i6sGTqS4RmV4YnKZPk+K7unxgyFgVSBsZzN3RsG2DSQxXL8ud45ksd03IqroyRJjBdsskWn8kjEDJWMZeM6gnhIRZMlesYLWI6YUj9rX4XAmZT/LUNZbFdw7MI9ylqZQ5GG/FC4lN2z0X/vHdVZx1jeomi5WK5AEgLL9YgaCkcvqENTZIazJpIERy9IzuoaeyDHIcsSq9rj3Lmhn2d2p9BVGV2ViRsqEV1lYWOEt79yYc0ERgGHhvnkmRMw/wgUtoCXDfMxTfX+9ulgjGl5SxzvCEGqYJMuOrjCYzBV5McP7wCosjiUBZEnd47zH/dspr0uTEdybv3qGS8wXrA5fnE9fSmTsbyFaflZIpsTBqvjYcby9n4JgpOFIqMkGOuqxGjOJawrtCfDPN+fRlN8YTRbKhFQjnMbyZmkCzbf//MW/rpwrKIYT7b2/eHpXnpTxQkZ2pRSJjaNLUM5kGBZUxRZ9uutxUMaJyxqYCBjsqA+jIxExFCn1K6Dmd2jphPStw5nqxSXsgJ9VFcdw1mLla1x4iGNhY2RKgVDFi6QIm857B7LoSq+4Gcoe8o8lPsT0RSEECRCGluHsxzblWAwUyRddPBcDyF8pU2RIaIpSLKEokjkLQeBREvc4IiOBJmiQypvVawCZWvbTG6d01mAJxfLrpVFsnz/zeTGuKIlxs7RPAsbogxnzRktVmVl8tGtIzieX2rBcT1cIShYDumigyJJPNszDsDS5hiW65G3XRIhFUWWKNh+ds/6sEK/aRPX/T4dvaCOFa5E73iBnOmQMx16xgqsbI1z6Ukz10XcG0v8dMr/kqYoQkBHsvYzeCjSkB9sl7Jtwzm/7Iih0p4IM5Ap0mKoeELgloq3q7LM1uEcILG0KTon19gDOY7uwQz3Pj9IIqyhypIfw+q49BUdmuMGr17VErjaBQS8hAgUtoCXBfMxTfX+9ulgjWnTQJob7tvCSNakvS5ESzzEUMZky9AY8ZDKWN6uWH7K5C2HoYzJsV3JGRNH1Aq6X9oUY0F9pJJ0BNIc25XEQWb7cG6/BcGJQtEzu8cp2r5S2JoIsaw5iirLdMu+IgegyjJ506F7KEehlImxLqzRGDWmKKBlwXjXaJ6tQ7mqDG0NEZ3BTJGoriAA4YHtCnRJ+Jkt4yGQwFBldozkWdQUZfdYYYqyNhf3qMkrtTMp9uv7UmSLDh3JPckJJsa/jWRsUGDHSI6BHSkkQCvNQXsizNLmCCM5v0TC75/qZetwjuGsya7RPH2pIitbY2wZzJExHT+9f6lWWsRQSYQ0VrT4Bc17xgucsLiRw9pifOve7mmtAtO5dU4WcKcrlj3dfTgXN0ZDlbng2A7iIW1Gpads3fjNUz1kijaNUR1dk9k96idXkSWJtoRO1nRwPcGWoWzFRVSRZd9NVpXJmA5F28VyPLIl6/PW4RyrOxuoC6k8uWsctxTv2D+e564NA8gyNQXx7sEMtz/Xz7M9vvId0VWO7KjjmIVJmuNGzbHUUv49Ifjm3ZvnXRryg+lSVnRcWnX/uVzWEiVj2uRMh1hIRVdlRrIW3UNZ6sIaQkB0mlT5tZTbAzGOid+GY7uSwJ4acZrsu3m/0J/hzMNaApe7gICXCIHCFvCy4FClfn4x+3QwxrSpP8O1/7uRLUNZIrrCcNaiPlKkMaYT1mUc1xc26yP1lT5kig4Z00FXJWxPVB1vpn5NjklKhDUkIUPB/13BrI5J2t+SB0tfFWPXWJ4bH9rGtuFcJR5HCEFDRGcgXQDJt/r0p4sULIf6iF/jrCVuEDEUVEVi91ieO54bYOmr9iigtTK0lQW70byN6/mxXAXbJWs6SJJvZXp0y4ifLdNyAYGmKPvtHjWbYv/07nGGsxY50yYRrla8R3MWT+0c5/glvmVMLhVNdx3BaNYiW3TYPpxjRVucwZL7Z3tdiI5kmKaYznM9afpTJgsbIqSKNkXbo2i7aCW3xJWtccKaQl+qyIL6CKva43ttFZhOwN3b52OuMXHxkDbr8+R5guf7MrTXhWiO6ozmLYYyRYq2i65Ipfp4fhHyWEghW3SwHQ9VkXA8zy/x4Plz5SpSqdSDv4CQKjjcv2moMjflkQ1lbR7dOlLTgt09mOH6uzezqT+D43k4nofpeDy2dZSILrO8JU5TzKjpSl0rg+V8TUN+sFzKJt4nDVGDY7qSbBnMMZq3KNoOrgdHdNRx6oomfvNEz14rt/s7jlr3/sRFGD+5zsH93gUEBOwfgcIW8LLgUKV+fjH79GKPqXswww33dbNlKEsyohE1/PpCQ5kiozkTT0BYk6fEeFmuh+X4CR10RZ5y3On6ta8xSfsasyfLEosao/zDKxdx40PbSyUCfMWorc5g11geECRCKttG8uiqzFje9pUr2+XRraM4nu/mN5Tp5eiuOk5d0QxMl6HNF+ye60kxkjXxEBQsl4aoTs5yGc1b2I6ftc12PZ7aNU59ROfwjgTjeXuf3aN6xgt0D2aIGQojOaviYihJfgrypU1RhjImW4dzHL1gT30vPyFLhlTBBsBQFdrrNIazFlnTxnEFii2hKxKbBzIsa4lybNcexb2rIUpnMswzPSmWNEW59OTFKJLE8/2ZSuKPdMHGtL0pFrG9tQrUEnBnez5CmsJYPsdzvSkA2ktxggciK2pZYF7REiNmqPSOF3h0q4PjQVhTQALTLtez8xNXiJI7XdH2UCSJvO3hCUFEU8gJP9kH+DGUGwb8kgn1YQ3L9QjpKgXbhbwFUGU59DzBzY/t5Old4/75hH/f5S0XzxPkLYl4qMiy5uicXKmDNOSwpCnKs33Zyn3SEDWoX6yTLth0D2U5vCPBx849DFmWeGZX6qArt/PxexcQELB/BApbwMuCQ5X6+cXs04s5prJVZiRnEtZlooaKXKovpEd1RnKWL1wKB1mWsUrug+DX27Icj8aYXjPT30yrymVBcNNAhnhIRZcFS1TYMpilPhqiMaZz/T2byJkOS5uidBj7H7M3nVvdOYe3goAdo3nSBZu6sFZKne6SLfruT5qiYjoug2mTm/+yk7a60KwZ38q1mqRSLNdIzvKtHq5fjFoAyYhOY1RjIGOxZTDLVesOoyUR2idr4sb+NOv70kiA6wlURaY+olcKVUcMlaaYQbTkJlgWwAfTRXaM5EkYfnr9vOWQMj1ypp/JUitZiuojGkNZi54xmcWNURqixoRrKrOsOcZ43kaVZboaIixsjHL26tY5WcT2xyow0/MxmjPZ0JtmMGPy87/u5K6Ib11a1R7fr6yoZSYKzJIkYWgKkiShyBL+GoaEJ/wC4rmCXZU50/M8UgV/0UNX/UylnhAYigy4DGZMXE8g4btCGppMS0wnpCmM5izytsPmgUxlnnaP5Xl06wiu52G7Asfzy1bIgKbJWI5gx0ie1W0JVrTE5uRK/XJPQ37W6hZ60taU+2QgY7KoMcpbjutCLWW4PRTK7Xz83gUEBOwfwdMa8LLgUKR+frH79GKOqSw8d9SFGc5a2K5XqYtVjskqW17ylovluDieR8Fy6U8XaY4bNTMKztav5S1xXr2qhR89tJ31vWkk4XLCahjOmWiaxo8f3s5IzvItC6X0+A1Rfb9j9qZzqwN4fMco3//zFhqiOrvHCmSKfgmA8nzLkkSylFlypoxvRdvlbzvGGC/YNCcMVEmmaLuM5k28kiKlKX4B5Mao4Vv6EjJDGZOHukf4xHmr9npc3YMZ/vh0H9miQzLiu5mWraRZ0+GYriSaItEUM7jwFZ2VWlEDab9GUzyk0lGnARmKtovjUlI6ZBzXd6sT+C57luOxZShHfUSvuhfDukJ/yr+fJs7t3lrEZrMKTHaTnc5iNpozeXLnGENZiwX1YY5or6NguzWzm05URA5ri8+YFXXiYsFkgVmTpZLC7GE5EkJ4mI5AV3wlznM9pJLSlrf9xQ9PgOT68Y2JkMZRHTFggILlIoRAkiVCmkJrwiBcetZiIT8j5XjBqszT1uEc4zkLF3A8gSZLFIV/vwEokq/IvdCfYWFjZM6u1C/nNORLm2NzVlgPhXI7H793AdMzH0sNBcw/AoUt4GXBfHTj2d8+HYgxTfehKAvPSxqjlWQZelSufPg1RUYpJaeI6iqOK9g+nMNQFY5akOTi43zhtma/IjprFtSxaTAz5eNUzmwWNVROWtqIJgtgB0MZi52joygyNEQ0BNA7XiBTtDl2YT0NUX2/Y/amixs5blEDf104xl+2jzCas4hNSAIiRClhSCLE0qbotBnfugczrO9Lky36lsGykPbM7nFG8ya2K/DwiOoq9RGNkOYL0+WkG/syrrKV1HQ8FjVEGMqaxAw/qYke1UtZLzPUhTWOWpDk5GVNnLysqXI/pAs2Nz+2kx1DGWj0k2G4wi+qLUugKBK2K8haDorkK1QT3WOFEGSKDjtHc+wYyfPfD24FIKKrrOms47wj26qE1f2xCkxX2mKyxSykKWzoTTOUtWiOGRzeXoeqyMQVuaL0v9CfmVIvsD0R4vv3b51zApP2RIimmM6GvjRNUYP+tD+nBcsjj4sQoCoSMUPDFYLxvFXJnilBKWZNIMsyEUPlhCUNLGsKQ2GAuoiG7dnIskxbaUzle9Hz/PvRtD3f9bKEIwSWIwhpsp/J0BO4+NkMy5a9npRfDLujPjxnd7mXcxryvVFYD7ZyOx+/dwG1mY+lhgLmJ4HCFvCyYT668exvn/bn9zN9KMrCc8F29yTLKCkrmiKTMx3ylssRnXW8/1XLCevKFEFkUWNkSr/a60Ig4DdP9Ew559KmWCU5xsrWklDsOVD0C0tnLYexnEPO9gVeCciYNmqPxOkrml+0uIyy8LO+L0WqYGNoCp7w3RezRadS0DpiqAxmzJoZ33wr3VYaohptiRBZ08VyPZY3R+kbL2A5FsLzU747nl+PrCFqIMu+0uYJb6/HVbGSJkM0x3WyllN1DfVSNsrjlzRUCW8TU8DfvWGAp3aMAGC7fkxVOd7KE757p2U5JCI6rgdCuFUlEPpTBXpTRYQQjGQtYiEFXVXYNpTj+f4M/3z2iso9uq9WgdlKW0y0mI3lcwxmTDqTIRY1RPGEIF2wKzF9ZaW/L12kqyFSWdB4cMswz+wepyM5ewIT03G547kBtg7n2DKU5Ymd4+iKTDKi+de26OAKUDyB6Xo4joeEREiV6UiG0FXf8mqoCjnTRlP82MOljSHAV2zHZBdZkTBKbncFyy0VHbcp2B5R3S8rcd6RbSxpihIzNPqKBcKa7CtrpWRAklRWEP3r+1xvCkkicJebI3ujsB5s5XY+fu8CqpmPpYYC5i/BGzngZcV8dOPZ3z7tze/LAujGvjR/fLYP03bpSIanfCguPXlRRXhe0RKryoKWLdrkLY/lLTHef+YyVrbGpxy/3I+JlorhjMltz/YxlrdrfpzOP7JtSgxTtuin3FcVGdPxlaSwUAhrCq4QFC2X7cN5ljQWqI9qL5qgubwlzttOWMj24XxJWfXT/U8saJ0p2tPG5iXCGoYmoykKj+8YZyxv+XW5PN9C5XmgymBoMkopO2Le8gsoN8V16kLaXo9roouhIktV1zBXykwZD6m8dk17TaFAliWOW9LAvRv7/L8l//raeEj4ioosy0jAytY4/akimaLLcMZk93iBTMFmLG/heQJd9eOwirbnJ69xPJ7eNc7Nj+3ks689HFmW9skqMJfSFhMtZs/1prjxwW1IwMb+DI7rVcX0JcJqRemfmAZ/KGPSM5ZnvBBlZWtiShmL8mLBxr40f940xGjOoqs+zFDGpGDlsV2X0dyeQtfjBaeivEUNlYgi05owqAvrlcWAZS0xdozkSBf8hDPjhTBIfsHxkK4QM1RGcxaqIjGStTBtF8cT1IVVjuxMsL43TV+qyKUnLWbtwiR/fLZA3vLblBHCP56hykQ0BdN2ea4nzRuP6aQzGQ5ctV7izMfvXYDPfCw1FDC/CRS2gJcd89GNZ3/7NJffly1q3YMZ1vemyZoOixojNMdDKLJU9aG4e8Mg5xxeLTwfszDJUMakL1WgMWbw/lctr1LWZrLYrWyJc8+GQcby9rQfp3s2DlKwXTomxDBZngcyZIt+vJwqSxWBU5UlIrpCuuiwZThDhx3mqAXJGeMy9kcAPWVZE685so2/7hilMxkupXj3LTOzxYVEdRXL8fjbjlFcTxALaaiGwu6xom8tlMDxQAgJ1/MF9qLtocr+3/URg0KpiPhcmexiWM5kV868aDkejuuxuj0x7TFWtyVY3hwDsiQjOmnL9LM2KjK6qhDWZcKawpLGKJ4HzXHBrtE8o3mLiCbjCoGhySRKLo5+GQOXjroQA+kij20dYfdYnoWNUWDvrQJzTd1ftphtH8kxlPEznNZHdbSQWhXTt6IliqEqDGVMfvaXXWzoTVUKXucslxf6s4zmbF65tLFKaStYLroi8/j2sYoAlik6mI7H4sYIAr9EQkvc4Ij2BA9uGcZxPTwBq9oTbB/OVdxAbddDkWWaYwb1EY3NA1l2jeXZOZrjFY1w8tJG+rI2qYJNzrTZMZInb7n+MxzWOHFJAwsbYwgh/Gd54wDvPn0Jz/Sk2DVawHJd5NJ9Rck1U1NkNE0GfDfXo7rq2DqcDVy19pH5pOjOx+9dwPwsNRQwvwkUtoCAvxNmEhImul7EDRVJgmREYyhjkjVdjulKVhJplD8Urz+6o0p4Nh1feD55WdMU4Xk2146J1jOAdMHGcr1Kivn2uhA9YwWQqIph0mXf5StvuaiKTAgFRZYo2L71CeEnwehPFVnSFJsxLmN/YwVkWeK8NW30pYulcfpWvoLpzBoX0p4IYdoe4wWbhfV+5sBM0aFgO0RKLpaeBznTxi1ZPTTVzyRZzrT540e2z8lFpnwfZEybppjOztECK1v3pPEvx5dtHszOmnigM+krwWT7OWV5E8uzFhv7MliOn5DEtD3qozr96SILGyOsO6KVmx7byWFtcbKWw2DWIqIrlOURXZUpWH4h6LqIxkjWYutwrqKwwd5ZBfYmUYnnCZ7eNY6myLieV8nWOTHz6XO9ad5wVDu//ttuHugewi1Z4NTSAIq2w0Ba8GzPOKevaK5S1rsawgylixUBzHJ9hVgL+RlWG2N++QZZlmhNhBlMF5EkQdRQUUt12XSFSkxkeTFgdbtEXUTjrWs7SG8e4qp1h7ErZVYKv/eMF2mKqTTHDQ5vT9AY87N0Tn6WP37eKr58+/PsGM6hqjISomRh88cW1hRa4iEMVaZgu3vlqnUgFZT5pOzsC9O9Z845ooWwpr5kxxVwYAlKLwTsLYHCFhDwd8BMysjE2LAVLTE/Jb8QJAyNmOGv/JeLX4O/wj+ULbJlKMvpK5p57yzC81xcO8rWs5At83xfhtG8n8pelWUaIjqLmyIoMrQkQvSlipUYpqghgwmm4+LiURc2qI9qjOVs8paD6XqEVIVkWJvWta88PxMF0LAWYjBT5JGtw2wazJRcO6e3NJXZWwtQWfjcMpTFE4JkWGUgbWK7Hnnb9V0TkVAVibqoigByRRdV8V0uJQkO76hjaVN0Ti4yk+8Dy/EYKsXVrWiJ7XXiAVmWOGt1C8//9XkGMyatdRHqwjov9GfoSxVRFYn6iM5RC5Kce0QrjufHuHXWR0p17EBCwnEFAt8y6gmBK8SUVeXJ593f1P1QnaikZ7zA1qEcR3Ym2DyYrYrns0vKlef5rpn3vTCE7XgkQmop2YrA9vwRmI7LzpE8ox0muqpU5vK4xQ389smeSnZUXZEripihSpXYT9vzs5uO5kwyRRdNlqgLq/SnTFQZIobKsuZoRRnsT5scXUoKc/tmf27KSu39m4fI2Q5LG2MkI9qUOZ0o9J21uhVVkfjXP2yg6Hgosh8DFzVUOpJhmmMGIBjP2zy+bXTOrloHMmnCSz0Bw3QLV49uHeHODf00xw10VX7JjSvgwBOUXgjYW4I7ISDgJc5s1q3zJsWG6YqMKsuVVP2xkB8Ls2s0T3/aZDBTpGi53PKXnazvSc8qVMzFtaNnrEDWctg2nMVxRaWGme16DGaKjORMuhoinLW6lduf62fzYJawJjOYyrOstVSM25MxVBchVBpjOkpeolGVWdoUJaIr07r2TVYox/I2G/v2xJFtHcpxbc7ic689nJVts1sN5moBmih8DmWLbBvJETdUcqavaJazAaqK5BdKtlzqQhrNjQaK4ruseZ6gOWbMyUVmuvvAtD3SBZudo3kMVd7rxANLm2M8DxzenqB72E+qsbAhwtrF9Ry3uIHVbYnK+HeN5itCSH1YQ1VkxgtWyYYjIfBj4SzbpegI6sI6S5qiM56/1vUsz31YU1jaHGV9b3rWRCWbBjMUHZelTTGihloVz6fIMu3JMLoi88SOcYq2SyKkVlLfq5JEzPA/l67nFzd/YSBDV320MpeGqnC72l8RwOIhlfqIzlCmiB7VK66OZatySzxES8KvjWeoip95U5ZZ0RIjEdbIFO0ZFWtZlljWHKMlFkItWQsnM1noO215M288ppO/bB+lPqyBLFEf1ir17jYPZlnYEGEwXaQtEaq4z04stj45wcqBSprwUk/AMN3Cle0KxvIWQ1kTVZF45ZLGqjIS831cAS8OQemFgL0lUNgCAubIfHTVmZt1a4CC7VRiw+IhtSpVv6bIjOYsnu1NI4TAdT26GiN01IWnCBW1al1tGcoymPWtYqKG5SSs+8Jo3nQZy/sugXLJ1dFQFbSIxM6xAq2Ox0lLGmmvC3HTozu4a+MgrmNDKzRGdcaLHkXbZcdInrqIRmPUYElTlKLtsqI1Pu2HbaJCOZa3eWrXOAXLIRbS0EIquuqwZTDLDfd188GzlrO8JT7rSv9sFqDJwmfMUOkdKzCQNvGEoDMZQiAxWqpxF9JkMkWHrOnQngwhS5If81RyjSvP43QuMjPdB8cuTLJpIMOixihvPKaDeEiree/Odn+/+9QlDOacGe//iUJIQ1RDAVwPFMlPWe94Hp6Q6E0ViYY0zl7aQFd9ZM79qHVdkmENRZZmTVQycUV7cjyfrsiAoDdVZChdRJGnKkBSqXRB0QJNlXnjMZ2csbKl0j/PE1MEsOUtMbKm4xdHdz3ak2HAd0dd2Bjh0pMXVdzkhjImT+8aZ+tQrlIiY6Jibdv2lOu+t0KfLEus7khw18YBugezlbIRcUMloqssbIywdlE9P310B32pIuMFu8oSvqwlSiKsMZAukina3Pf80AFJmvD3kICh1sKVEILuwSxF26UtYZAzXfKWSyL80hlXwItDUHohYG8JFLaAgDkwX1115mTdGi+A2BMbJklSVap+TZHImS6eJzBUmXhYq6zyx0N7hApPCO5aP1jlbmfaHh6C7UM5+saLtMRDlWLWZQqWiwdEdF+4HsvbVa5oflFnHV2V6UsX8TzYPJDFclziJctAazyEofup7TNFh5zpokgWf9lm0hw3uPi4+LQftnKsQFgLsbHPV9YmFr6OGiqW4zKSM/1xevCjh7fTM57HUBUMVUaR4dmePcrr0qbpLWy1hE8hBHURP9ZLkiT6xv3VdscTFG2HvC35STo8j/G8L5iHdaXiGleeR12RSRdsnu9PV5134n0AU2MEO5J+xsJ4SJvWOjfd/b2o3j/mXNwUy0JIz3iBv24bxdBkYsIXQmzX8y28qowHJEMq/+/4hVXXbaZ+ADUtMH0pX8FqrwsxnrfpTxVwPehIhjlrdQtLm2JAbeWmbFkqx/S114UolCx3RccjKstVz5WM7zLcFNM5dXkTQFU9wckCWCKssqIlynO9aTzPt26nCk5NC+eqNj+xzd4sCu2t0Feuc5gIa6ilbKSm49JXdGiOG7x6VQuGKrNrNI8QgmRUr7KEZ0w/aZChKmRN54AlTZhvCRj2ZXGuVkxSpugwlrf8xSFFIm9ZWK5fGD1ILBEQlF4I2BsChS0gYBa2DmX5n8d2z0tXnbkELsuSRNRQ2TSQYXmzr4g1RA2O6UrSPZBly7CvHCXDKq11YZY1R2mIVicueGLnGC8M+Mkm2utCFG2ZJ3aOMZa3SYY1mmIGqYLFYCnbXjmJSXmVv70uxIBUZFFjlG3DOcbyFlnTqaTGX9QYIV2w2dif5o9P97F1OEdTzCAZkoEsOcvFdsFy/EQJluOiyBpNcYOIrnLv84MsaozUvA5ly8pgplgRniYKhbbroSoK7XVhNg9k2Dac4y/bRkgXbEzH8y0rmkpnMkTOcrj5sZ00RHS2DucoOi6GItMcNzhuie8eKISoKXwmIxqeANt2QYI6VSOsKQghsFxRivOCVMFmeUuspPj616GsUCDglsd2VmL3ysqM4wmKjkvRVtjYN1Zx9yynrF/cFMF03JrWudlc0d554oK9uieXt8Q5f00bT+0aJ6z7boWKLOGJUvp4XSUZUWmIGoT1PcWdZ+pHz3iekKbMaIFpjOqcvrKJPzzdR1+qwNZhl/G/WTy9K1VZWJlNuTlrdSupvE1LwmL3WIGC7aGrMooErvCzXCJJLG+N87+l+3SyYllLAHvj0R0c3ZWkKW5UFACAXaP5KUrB3grucxX6Ji4kHNuVBKhYGDVZoj9t8nxfBs/z0FS/XpuuyKXELAp6VGYka1bS/sdC6gFLmjCfEjDMZfGiFrVikiYmnpnoEnsoxhUwPwlKLwTMlUBhCwiYhXs2Ds5bV53ZApf7xgvsGMlRH9HZNZpn61CO9roQK9vihDWFuojO4e11DGdNljRFaYzplRTsZUKaws7RPC1xg1cs9BOTPN+XwXEFC+vDjOVtJBliIZWC5ZIu2GwayHB4e5z+tFkRhH/zRA8hTeb4xfVTYmOypkPRcnl82ygjOZOw7idDkCQ/UUV9RGVg0M8iuaQpQrrosGZBkkUl4Xam61C2rDyydbgiPJURQlSy8jXHDR7fPkr3YJaMaSOEH2MmSZAxHbqHciTDJluHsixvibGsOUbRlnmhP8Nj20b5wzN9LGoIs6A+wlDWpKMklI/mTLYM5hhIF0sp4v1ixabtgSZRF9apj2iM5kxkWeawthiqrKApMo7nUbBcNg9m6U/5cUX1UZ2Irk6JU5xcNmBiyvrRUozg5AD2ubii3fv8IB17eV82xw0WNYZpjoVwhUArXRO7pASEdb9od1lQna0fT+8eZzhjcsKSxmktMA92D/OHZ/pIF2x0VcZQZbJFh+GsVbWwMpNys7QpxjO7UgxnLSzHLwBuOV7pXvHjzVoTBqoss74vPe0CzntftWxGAWxvLfaeJ/wsqkDPWIGFTWrV8eYi9NWyYpUtjOBb657pGQcBR3Yk2DyYm5qYxfOTxhzVVUfc0A5Y0oT5koBhXxYvZsrKWkk843hkTafKxflgjitgfhOUXgiYC8FbIiBgFrYN5+aNq85kZophGckW+ev2McK6wsrWGIsaI5XsfkNZkxUl10XX8xjJmmSLNiFdrcSqlK07fvFftzIH6YLNaN4X5GRZ9lfabY/VbXEG0iYDmSK7x/IkwxpHdyWrBOFyIe6JgmLZCldOdtBRF2a4FNullwX9kvVJeOAJiJT6WR7vTNeh7Da2aTDD1qEcuuoXKy67Y5ZdDwuWQ+94kVTBd0kMaX46eiH82Ctf+bHQVZmOuhC26/FsT4pUwcbzPLKWy/P9DluGctiuIKTKtNWFSjFzfhkC39IkkCS/X80xvTIXalEhaqi846TFPLc7XVEodMUvX9CWCHHswmRNpeqpneMULbdSNmBPjKCEFtEqMYLtiWoLwVxc0bYO5eiY3rBQ030sqquENdXPIhnSp/xmcpHx2fpRH9HpHsj6tcNqkLccNvSlUWWJrvoImupnZ0yVrKRARaGfTbkpW+EAEiGVsYKNaXs4nsfCRJTlLTEKtjfjAs6VZ8SmfR+UlYKRrEUipJIIaXieqHK5nWgVe3jLMHdvGGQolePcOrjhvm4WNyemKHezCX1zsWLlLReBYEVrnKih0T2YrbKGt9X5af+b48YBTZowHxIw7MvixexZWWWiusLu8QLNMb3KxVkIQe94kYWNYTKmza7RfGBZCQgImJZAYQsImIWi49I6zQrooXZpmS6GJW86/GXbGAAnLG4gEfaF5qaYQbpg80xPioG0SfdgloLtYrsC0/EwNLkSq3JMV5L6iE5fqkBE92s0QcnNx/PQFH9ONEUmazpEDJW1i8L0jBXZPprj7MNbedMxnaiqrzxM7GdbwsD1IF20GctbLEj6yQ5++1QPHclwJSlKRC1l5qvI6YJM0aGrIVK1Uj3bdVjeEuf9Zy7j2qxfwsAsubbFDJWlzVGSYY1nelJkizYCX9Epy02S5I/Rsj1sT6CWXBh3jORIFWwKlovjCUIl98bGqMau8SKPbRtlSWOEguUS1hUG0ya2K/AESMKv6TWWtzE0mZzpEgupNEZ1WhMhTntVc0WhSBdsbnlsJ/UT4u7KlJWq53pTCKA+Mk2MYFirxAhOFOrnIsQPp/2C3Z4nprjwTVdc+ZwjWqYVwD3PY8tQliVN0VL9OTFrP+IhFSRf0auPViuAQgie60ljOR4djREMzXezLNdXG81Z5G2HzQOZikI/k3Iz0QrXPZihrmAhSzLLW2KcsryR3z7Zu88LOGWlYOdoHsfx2D6SqyT1qA9r5CynolhuHc5y82M7ue/5QfK2S0NIgToAsVfu2GWFuj9VxHUFOdOuvA8mUrBcIrpSiXdtiOpTrOEgSBX8638gkybMhwQMe7t4MdesrPVRHccTJMLaFKt5upTU5dv3ds+buOiAgID5SaCwBQTMwnxw1ZmJWm5ejidQFZnjO/cU0gVf8HCFIGs69I0XSIRUFjZEyJouveMF+lIm7XUh8qZvsWiOhWiMGYQ0hYLtElfkKWUBbNcXOPOmy9ahXKUswN0bBxhMmxUBpNzPmx/byaNbR0gVfOUoGdZZ1hQjoiuEVP885aQoYznf2iXhu6M5nkdkUjIOmNt1WNma4HOvO5x/u30jWwZzIDyy4v9n78+DJLvO6170t8+cY1XWXF09TxiIgQTnSeIoUKLlQZYdluRnSr72tWXLkxy+L/yeb8R7oReW49qWZdn0Fa0r0b5PkqVn+YqWLYmjKFIECRIgZjQaPXdX11yV88kz7/3+2CdPVXVVN7pBgADo/CJAgEB25jn7nJP5rb3Wt1bCM9c7PL/UpVGxQYBtCJQSuxwvBSCEZvkMAzoDLbMbgrWSbQKKMFHYlsnB8RJXmwMubPrM1VxWOwFhIjEMgSU0GEwyyZYfYVuCwxMV5uouIIpmeNjwn13tEmWyyPe6sYbMiDDgocMNLm/4rPWiAgjM1rWbZidI9gDa25WiAfzq1y5zYTMogNlYyebqlk+cSQ6MlTg2WdllV/6hu2f2NOAr7YBnr3cIEg0k/+nvv8D9C2M8eHj8lsdhGVo62hzEHGyU6EdZASKklLm00aDq7v6zQgiqnkUvTGkH8W1vrAxZuMXWgMubPgDHpyr0v8NZq6V2wJOLLTZ64Z54i41+hGkInrjW4pGLm/zhs6s8fqWJUopDjRJCaabwwrrPkakaV7d8/n+PL/K//MDdxabIjbWTAQqSjMXWgEubfe6drwMCBDRyc6GVTsh9B8aKWdLhvOuNxiw7ma4bwe3lzW1w++ffunBHwOO1NmC4082LO3FlDeKML5zZPq8o1aCu7tkcnijvkTiPrP5HNapR3VgjwDaq76heC6t7KRXXWwMu5Y3UsakKhxrlm37unRzjztd6eQ90bKrCsyv9XUyBUopukHBho8+9B+pMlx2+dXmLLT9msuLw0KHGnibqTteqmI0IE3phgh9nGELsOV+Z5zh98O5p3n6sQdWzWO9G/PZj1zgwvnuXXynFxXWfME5RQNWzMQ2DuidQdTfPYYuo5+/x1iMNfvShQ3zhzFrBluyMBbDLgn6YUnUtnl/uMEgylJQcnCgzX/P4k/MbPHp5iz/3lgX+1H3zrHRCVjoBNc/i1EyNsZKNIRQXN/usfDPQ+VgbfQ6MecyPeWz1tDTNj2KUUpRsi7vnakilnRBrnlWYfBydqrDUHtALk5ta1xuGllO6trFbXif0bI5paBfDVOqgZEMoUMP/PrwucHatx1Y/LowZbFOHXAuhM9XqJVtnrsUpzUFCnGrrfpE3yVXXJM0kvSij5to8dGiMi5uDfWVftwOqhsxImBuaCIB8Vg70v98P0A6laM8udZirq2LGbMhernRCFuoOKDiz0mVmrEzJ1izSH51dJ0wzpio2m/24kNKemqlyfr3Pi6s9PvHuo0WjemG9z8X1PmGqQXc7SGgPYl5c6/Gty01m6y7L7e35n5337Go34t3HJ1jtRnzuzNqua5fmrnvjZZtESlzD3HWOtmkQpwmGMG57Y0VKxSMXN/nSC2usdEIMISjZJlNVhziVL2sDR0rF+fUe59d6KKWYGysV57nT1OPals8Xzqyx1B4gBIxXHEzDwMqXZKUbsNiJKOdzgCjBX3z7wT0N/o0M0AGnRJpJvnFpiyubA53/Z+hA77pnc2yqQsuPudYacG1r77zrzZiukzM15L3QCWI6od4UOL/e43cev86PvvXQrmzDnWvxnWQcvhp1J5sXK53wlmzcfq6sJ2eqxff5Z55cxjIEp2drr7u56FGNalSvzxoBtlG97HotrO4vrPe2GZpBghKaoXnXsQl+/F2H921abvcYb3xtxRK8z4PTs1WWunHBFIRJVsyCWaagF6Y8/NyfEKV699U2DY5OVvjJ9x7lw/fMvqy1Gr7+ycUWF9b7NP0YlMJ1TKarXnG+wL7v+8ChMUq2taf56IUpzUGMbQ5nnAyCOKPpRwSJRKFIUi3vGyvZ/Nm3LHB6roZhsIstOTpVZsuPuNYKKNsmK52AXpQhUNimwXov4trWKv1Iy6mevNbiFz//IgpBIiVjJRtTGCj0XFjLj9joR/m8mOKxTLNRVVvAQciU4NhUlSjNeOxKC9vSznWWEPhxRiolV7YG/NEL65Rsk8OTZd5yqLFrfYe74plUPHzv7C6WpuqaPH29jSEEpmGQyQylIMq2ARs78F3VsehZacGw9cKkaHwdyyDOJFXPQio9hzdTK1GyTTIpWevptTYNfQ5+nPLscpeDjfK+sq/bme95YGGczV7IF8+u61ytkrYRTzLFei/ieivgB+6d3QMGDUNw93yNz59Z5Znr7WJda65F2bU43CgX531iukIzyHjiWouLGz5+mGIYgm6gZwJ3SmmH0sAffvAAf+P7jvPta00+9ceXSKRkvGRTK9mkmWSzH+NHCWvdkKmqy0TFwY8yTs1W90ji3nNyit99cqk4HoFCITDyqICyY9EPU5zKbiv+OJXEqeTkTPW2ZqAurPf4zUev8eUX1wmSjIprMV11KY17XGsGbPQiokTumifceS32A93D5/mbl7ZY70WaGVQhExWbUg7uhBC4tknLj7my6TNZcVhqB8WzGsY5u5MpMrTErh9mnFnp8OlH0j2zbzcyQE0/4srWAJmDXakUNoI4lWz52m4+k4pTs1Vmau6uedfTszUeOtzYl+m6sN7jP37jCteaAwaRzhJc7WScXdFmPH/3w6eK78Gda/FyMw5frbqt5+xAFXovz9VyeF6LzQGbuSnR63EuelSjGtXrs0aAbVQvq17KTevVkHRcWO/xi188z9OLbUwBkzUHgaA9SPjCC2us9yP+/kdOFZ97J8e432vDKAYFXzm/yYfunuPsSo8nF1ucW9MOifPjHhVHO9iFSUbJNgtnwHPrPX7+D88CcGSyfEdrNTyWa80Bi80BW/0IAGEIpIT2IOYLL6xxcbNPzbPJpNrHBj1gvGSz0gl3NR9xJkmyjCSfuYrSjNYgzeWNBo5pMYgzPbeSSrb6MbBXrhSlGYcmylT9mOvtgE6Y4pqGtswHrrcClNLOkeUc1C7Hem5sYVzL4663Bpxd7erXOBYKbZuuzUUUhiH0rBnadCQKEqarDlVXu0r2o5SWH2MYgjHPxhIC1zOJkozrrQFRKnet784ZFcMwqJd2M6AnpqsstUKag5hEKpRUOKYo3AFTwDL0HOCQiRqoFASkEgyhaJQ1OO6HKY2yXotumFLzLEzDAEzmhGCrH9EOUixDs1/HJqv85Xfv3XCA25vv+eibZvitby3qP6AUu1Cm0g36fnYdw1yummeRZop2EBPGMe1BzPxYiQceGOPxS5vgQTtIePJal+V2gFIK29JgKUglm/2EA2MeQZxxccPnzYfGidKQF1a7/N5Tyzx9vcXjV5tkCmzDwDT1c5tkUodRpxI/Spmru3TD7fmfoSTuI/fO8IXn1zXYftNusF1xDD7/wjqDKKPimrucDeM0Y7UbMVf3+PNvXXhJxuLCeo9f+9plHr/aQio42CiRSsVmXxtJPHhwrJgrPLfW48B46SVnrXZ+tzQqNp5t5rLkhCDRId4Vx8Q2BVGin0OpFDXPLqTHjmnQ2pHPl8bbGysnp6us9aJdrMyN81jDAOetfqSzFj2TOJXM1F1cy+B6K6AbJiRZlrPodjHvemGjz/HpCv/z+4/vqxoYzuS1/Igw0RsV9ZKdr33IL33pPIcmSpyerb8mvxu3W7fznH3o7hnOPnb2O3K1fD1FGIxqVKN649QIsI3qjut23LReaUmHlIrPPrfKudUejimYrLrF587WDbb8mHNrPT733CrHP6CDcm/3GG/22qpnQQAtP+bF1R5//X3H+BdfSAiTjJPTVaquyX99eoU0U0yUbcJU0Q1TDox5VByTa62A//DIFd5xtHHbazVc261+TJJqi3zLEPkuvCJIJIbQwOG5pS6TFYeH3zRbuALufN/5MY9G2d7VfMSpJIglNc+mUbK51hyQKW3QoJRCApYpsAzNFD6z2OG9J6b2lSuVbZP/+tQSXzm3gWMKGmXd/L241kNJhWUKkjQjSrSVvSk0e7baCam6JlJpoxMvk/TDhEwqlFI4lolhKjzHYr5mA20MocGcYxm87Yg2QnhiUf/7XpgSpBkHxjUQq7oWTV/nkG3142J992uUlFKFqYIh4MCYS6YUYSKR6OMmn2WzhaJRcZioOniWiZRaFptkOnDcMgSZVDT9GM82qTg2J2dqfOtyk42ebtYtQ+jw7yhDALZlYAqBbd76OXmp+R7XMmkPEt5+tMFqJ6I5iPGjFNMwmB0rMVd3aQ+SXbv2RbO9NaAXpqx2Aw2YpcI2TdY6IV88s4ZrKPDg8oZPL0wQQjtoZlIh0Nc1ySStQcJk1abpx5qFSiW///SKDgpWIIGSrRnFLT9GCB2mbhkGJUswiFPmx0vEqeLwZIk/+5YFaq6Wtt4KbCulODZZ5qnrHWzLwLO16U6cSeJUMV/3+DsfPsXp2Xpx3kNpWj9KqXoWNddmvu7xuefWWGoHGEAjlyKaBjgVg6Yfc2lzwOmZKuc3+lRci6V2gCkEnr3/rNWN35W9MGW8bNPyE6JUh4n7UYpnm8XGw0KjTMW1MA1RSI8rrqUz4NDrKPLnYarqajbXNXeZqtx4r/fClPVehAIc28QU+j0cy8AQOiPPFIL1XkwvTKmXdFbhWNnh9GyNzV68x7AG9EzehfUegyglTOSuQHrPtpirCzZ6Ef/l20v8ox+oftd/N+60Xuo5O9LwOIt2pX25rpavlwiDUY1qVG+sGn0jjOqO63bctF5pScdSO+DZpQ6ZUtRKu4OPhRDUcmOBZ65rdgm47WO81WtB26lfWO/z1FKbzVweVPNslloDOkGiw6kNA8dSBLG2dnZtk8mKw4WNHgI4OVu9rbUarm3dszi/3isaLP1HtfQrSCSubROlMVGS0Y+yXQ3s8H3bg4QfeWiBpxc7uyziT0xrkOpYehZLSkWUCr0TLxWeY1IvOZyerXJxY/d13ClXWmwOuLw54PhUlX6UYRhoU4Ykw7aMnDGTSIUGmaYgS7XD4rVmiGGI3DBDIqBoHB1TMzBJprDyxq0XpoxXPVqDhH6UIYSWclU9m36UIaVm4Vxj22iiNUg42CgX63tjo9T048K2PM1kzkkJxss2VceiHcS7suL8KGO84hAmkjcfHOee+TqXN/s8t9wliDRL6ScpU1WXsm1xeLLMJ95zhKpj8bWLm3QGOg5hEKWAwLMNpIRG1eHFtS7/8vMv8gP3znHXXG3fGbxbzfecXe0SphnHp6ocbJT35NxlSnFl09+1az80wLjeGmgAhTbYiVJJkKT4ccpXz29waNzlo3VoDRJKtkk3TClZBpGhGSzDGN6XGUrZpFnGcnuAYRhYhuT0bFXPWgFJljGIMxI9dkaUSiwjpWQbxfofGHfZ7MXU3O35n5uxEk0/4tnrHRZbGnT2wwTTENQ9m4ONMg8cGuNHH9qeo9opNb62NSBItIPn4Ykyx6cqXNrUmYVLrWAXiB7eUyudgEGcstGLECgqjs1M3eMj987wnnxjY2fd+F1Z8yzGSjbr3QipFIYQZErPRxp5MPfp2SqTVZfnl7scny7TixKafkwm9aJFSUYqBWGc0RrEfOtyU3+uUvzJhQ0eOtygGyS4plHc65pZl4DCzI2HhvOWWc7IGgISKTXA3lG3Ynz8OKUVbAPfG7/jHMvAsQwurPd5YrH1Xf/deDl1q+csSTTL+Z24Wr4eIgxGNapRvfFqBNhGdcf1Wkg6/DhlEKeQz0jdWMN/N8gbTeCOjvHWrzWIejFbfrzrdYMkI5PbocCmECRK5g0QuZW7ohcnt3T423kcw7Wte/auBivNFAo9TyWHEjcFErWnwdr5vlM1d0+Ib5Ck/NKXLvD4lSYCgW0JskyRZhIhBJZhcHy6wvx4aU+Tv7OGx3psslIwAcPjMoUgSrOhGg/L0AYHlqFIpDaKUBJKlkU8PJ9cBmmbGjzqtdR/XrNv2m686cdUctOOoYW7QBXrDvp+0AyTZm78OOX0TK1olOJU8vT1DkGcUvVsLNdksxcRpTpoulGxMU2DiqltuQ9PlDm72gO0U2UiFVNVhwcPNTjYKPHUYpuNvpZ5zddLnJqtFWzLj7/rMGu9kCeutshyNq7kmESpIkwzltoBW35EL0p55Pwmk1WX2brHAwfH+dG3LRTMENw8a+tGMLoz5w4giNI9u/a9SEsPO0GCkUcX+HGmZ5ssgzRTZJlmEQEGcULF83KQofBsDdhUsf7oAPREFhLXA+NenqNmYwDdMNtz7EmmSLKMmmfSKNv7fn/sPL+qqzdnNvoRzy11aPrakKbsWMzWHfphSiIVZdfkR996kNOzu2XP15oDNnohmZTUXIt+nHJhvc9KJ6AbJLzl8IQOO84UrrVtMjSIMta7Ef0opeZaHJ+qYZmClU7IHz63ytyYt0fOt/O7cmhUFMR6w8GzzEK2OVV1irUwhOAH7p1jpROylbNRlzZ9Fje1NFoq/TzpOVMH2xQ0+9os6N/90UWOT1eYrDhs9mM2/Zi3HBovjHFAFJmCFcfS85apBHQ+oG1oF9idzHOcDqWne7/DyrZm7bv5/bXTWVWfj8SxDKSSe74/b6zXkxTwduboXq6r5eshwmBUoxrVG69GgG1Ud1yvhaSj4lg56BGFnfzOSnLQUrat4nPv5Bhv/Vr9eZMVZ9fryraJaQgSqXCN3bvWw8+wLUHNsW/7OIZrK6UGplkuu8uUBiwK3dBFiQ64TTOl//mGRmnn+97YfEipmKm5lGwL30y1aYMpsAxBxdXrutGLmKw4t7yOFcfCNXVu20TV1qAjTPKZLskQRxoCTEPPOxmGwMiDyDIJYR5qnErdFJqGQEEeLi0YkhxJJlntakD47FKHumviRylBopktSwhSqRjEabH+2jxE7VqHh++bZak94FtXmkSJZLqmM5LagxTbMkBImgPJIM44MlEhkdp++8J6H88yaA1iSraZZ1Lpmqi4HGxUeM/JqV0yvmHDdXyqymzNw7VN+lGKYRjEGWRKkWSKMEnpRblkFMFaVxs9XNzs883LW3tMG/arW+3a75d7Zhja3bOXS1Fd2yDMwZqVu10qndeNl88tdQYJjmXjWUZ+HoKKZ2MbgijV2Xz9KOXuuTo/+tZD/Nenl4qNiqprsXdbYdt5U98DiqqrZyhvvO+G5/fo5S3SVNIaxKz3NHgSgGtrKexYyWGs5LDVj7jeDPjC8+ucnNaN81BqnKaSJJVYppZSh4mWJrq2SZJmnF/v0ig7bPQinJxRbfpREeauUJQsM58zc24p5xs+z8vtASudiLVuyHovRKBnI+Ms0xJHBLNjHnN1VzOZjrkLDMyPlYijFIg5MObhJ6qQhQ+ilI1+rOW1hp5THS9rwLbSCYE2J6crTFUdNnsRfpLhOSYlR4M1yyBn1xQzNYcky3j8Sk/PcmYZQSw5MV0lSHYDqQvrPT777CobvZBWPyaIUqquzUTFoeRo8NYPU8bKNuMlZ8/35431RpQCvlxXy9c6wmBUoxrVG6/eON+Mo3rd1Gsh6VgYL3H/wpieowkSnOq2E9xwN9g0BA8c3P7cOznGm70WYLUbcu9Cg4cONXjscqt43fyYx1hJS+tsA+JUUXH1rrWUekf59EyNtx9tcGa1d1vHsdNmveqYLKaysO1HKFKpwc16N0ShzTyeXeqw1A45OVNlouK85DVYage0BwkfOD3N00ttlnNZaJJJumGKUuBHfVKp+OBdM3veYzgD9Pxyh+utgKX2gLKjZXemoUFWlOpO3DY1gFU5MygVlFyTumOyNdAW4HXXYrzkotCg1I81AK169i7QF0s9KyiV4oW1Hkmqc9GG9hrplo9tmeTqMA5NlOiF6a574uRMjR+6f56nFttkpqATJAi0dGsQaaOV8ZIGDXGa4TlWMb9UcU1kDjKb/jDnTLDajZisOvzFtx3at9Faage0g4Q3HxzjyettbMOg5cdEmUL7ZEK+XBoMmCYiZ1MXWwP+xedfZGGsxN0H6nvee1g327VfaQc8t9QlyfTa/usvni8c+aquhWMadLIExzZIpMpnm7ZBsymEBrKAa5tsDfR8nsijA2ZqDhXHZK0bYRoWDx4a52c+dJKSbfG551eL5ny1F6KUlsWmmdp17MMnIk4k59Z6mKax594duln+7lNL9MKEumeRSZnPXQriTFF2tr8TaiVbS6SX2rtkz3XP4sW1Lr0wpRemBXi1DM0yC6Gt8scPOiAE11sBUarlhEmmnT09ywQBT1/v8OZD40xUnJvK+RbGS4yXbL7wwhqOpVku/ZeW9KaZNjZ51/FJ6iV7l3T17rn6LjCw3vZpvfgtumFK2XNQQJSkxfktjHkYhmC9GzFbizkxXcnvLmgPElzL1MA8yfDjtGDWlALbEkyWHRKpeOxKa5u9VoJaztb+x69fLUxBdpqH3HdgjE6g5ag9pWfzJisuqZR4tknZtjg1W9vz/fm9IgV8ua6Wr0WEwWsRwzOqUY3qlakRYBvVHddrIekwDMHH7pvj7GqPpxfbrHVDxso2IOgMEqRSPHhonIfvmys+906Ocb/XRpHeUW7kr7UsY8/r7j84xiMXNmnm8z11TzsYbvkxdc/mJ997lCOTZVZ70W0dxzYLFPDCSlczTlKRpFpGhQClNJtXcQ1may5RokOvu2HCXbNVgnz4/2bXYCjTOuCVONgocXnTJ061W59n6Uayl1ut3zVX2+N4N5wBOrfW0+YcUmGKjFrJJkQwXna06YdUudOfQS9KCRMd5j1f93BMgyjTsrqDjTIL4yXOrfdp+ZrFEEIboSy3B3AYxssOvUSblGz6CVJqECdz130F+LGkKgQCbcyw1o04NFHZsw5TNZcjkxWmqy5Xmz7n1nr0gpQgyXKLeN3ENgcJk3lOlWMZrHQi3WiiePxKCwSMlRzefXyCH3vn/g6PO9d7quLimgbNICHKJFLJfG5vW+Kq0IDQMmAQJDim4Mqmz//6X5/lZz58iumaW+TeVVwLgZbmVhyL41PVXbv2F9b7LDYH2JbBWw6PcWC8vMuR7wfvm+PgRJnWICaIsmKmSuaumIbIz93UrOtdczWU0EHpFUebnGz6MUvtkJJt8aG7p4t1kFLt2gQJckt6OzfWGV43AzAN/VecaiOdD949s+eaSak4u9Jjvu4xXXVY7YTEmQIhKFkaqA0SyfjQIMY0AMUgznbJnpWCrX6cG6EonFzymElJiqBRttjsZzx9vU3dteiEKalUCBRCQKPsMFv38GwN4i9u9GmUG7eW8w1PQykMY/u+FfnzrmdG9VzujdLVnWDgxGSJP3hRs3aaFY7JpH7NgbqLEAab/YhukPDkNUnZtag4JuNlmx9752Hag4TfeuwaF9b6tIOEME4LybEhTE7N1mgPtOlI2TGRCmZzc43xksUzSx1+49FrfOLdR/jss6u7zEMypfjm5SZ+qN1bpYIjkyUqjs3hyfJNvz//R5cCfjcjDF6LGJ5RjWpUr1yNANuoXla9FpKOkzM1/v5HThU5bEPL+Zs1zXdyjPu9tmwJ8OAv73jfG18ngHvn6yx3QqIk02ybaXDXbI1PvGc7h+1O1urkTI0fvH+OpxbbTCltcx7kcjWUNucYK+k5pfsPjrPWidjyI7b6EWcVfPz+OR6+b+6m12Ao0/KjNDd3sJCOdqAME4lS2rlttubx4mqPD941g2GIYld9qx/R8mNsw6AxZtMaJESJJEgyTKGP7+RMlZYf0w4SZJJhGQaepY0bQNEOEu5bGOP/9u4jnFvtc3Gjz2TFQSko2wapgkGckSsmOTJVoV5y+JPzW6SZBjTC0MYkjqHt65NMs3M116Lh2XiOBrRDJ9Cd51+yTZY7A5693iVKM2zTwMokwtDsoAAcUxAmWuaXZooozTjY8HjwYIMsz15rDmKCZD+x39717oUJvWEUAYJMgmmoQio45J2iVJLmMlLP0Vl6z690+V/+89OUHKsAU5YpcC2DqarLVNUtmq+f/sAJrrcG/NrXriAEPLAwtq+L6NOLbd51bJLrzYCWHyGlIpZKG+jkc4SWKZiu6fmqyYrLn3noUGFiYxoG4zm79OF7Znn3sUlWuiFnV7tUHIuP3rvdnAuhYXWaSe26aGimSUpJKvX8mxBaKvvQkXFs0yjeZ6dL5KnZKlXXYrkd8OilJt0woWQbIMQuwx8tkRaUnW3w45oG59f7eh5S6s2DITZQQs+PtQYJpqFdMm1Lh6GbBniWhWebzNW9Ym6y6lk0+xHL7YBUKlKpKNu7pdpDNnvo3rnl6zm0KMl0uLpnESaSXh79cDss0z3zNQzTwrYM+mHK88sdLMNgtRsSpZm+LmUbwzBoDxI2+to19OKaj2uZvP/UFI9dbdEPUzzboOKadIOUS5t9lIL7F+pM1bzCsKY1SHj8aouldsCZ5S7PL3fohyl3z2+HPh+bqlL3LM4s91jvRyT5BsWbb8huG0kBX5t6PccpjGpUo7q9GgG2Ub3sei0kHSdnavyTj9/L9daAS5s+AMemKhxqlPf93Ds5xhtf6xnw9DcWOT5dvenrelFSND7XmgMEgumay0OHGrsyi+50raZrLkcmS0xXG6RSEiWSThBzdq1PLWdXOkFM2bF421HtCtgaxARJxg8/eIDDk5Vd77dTClOyTY5PV3jsSpMtP2Ki6uCYep4llZJeqC3y756rFTKvhfFSYck9V/e4sjWgVrJxLYO5usmWHzNWsrl7vkaS6sb8z7xlgd949Cqb/Yj5sRJHJsps+jErnYDJqsvf/sBJTs/V+PDdu49NoN0mn1/q8vtPXwMi3nJonKWONpeoe7Y2SpE6RqHqmghh0Atj0gwcU9vl11yLq83BvjK1Y5Nl/sM3NojSjLpnIRVEqZ6zUyLTMrtU8b6TDRKpeOZ6mygxeWBhnHrJRuXyz5JjstQeFHESN3OFG8rilNKs0hCepTdgvTw5Tc92SZXL5rQZTDfMSDKd9bbR12uhHVNhqursar5cy6QbJpyYrhZgrfiM3JHv4obPn3togcevtmgOIg0cFSAlMdp8ZrbucXSqAmwyVXWYqDj88IPzRWbe8D6+tNnnU1+9xMWNPkGSIiU6x+3gGBvdiAsbfWzTIIglZVeHXNu5uUWQ5/5ZpiBMMj755Yt49hWmqk4BRE/NVgvDCiEEB8Y1O3xuLSXOFF4eS5FKhYxT1rshpmlwqFFmvq6lgtM1j29ebuLZBt1UMlTkDddbKUWSwkTFZqxsc7hRQdBnrGwziDISKelFKU7O6KWZZKMX8fiVJmEqmai4/N5Ty3zs/rmCZby40WejH3Jssspbj5TpR9os5fxaj1TqCAs/SmgNYla7t8cyHZ+u8uxKn1Nj1WLuc9OPNDONBpJatipQnslGL+MrL24QxhlzdZezq32kVBxsbAc3m4ZB24/pxxmdIOWuOScP24715tgQ0KeSa80B/UiveyWfWQOYrHq875SOj7i85fPj7zrC952a3nMur8Xvxv/I9VrE8IxqVKN65WsE2Eb1HdV3U9Kx8zMPT1b2gJJbvf52j3Hna5Mk4elbvC5KM778wsYeicldc7U9AbN3ehyaBbKwTEGj4gHg9U2ubA2oelY+T6Md3YQQ1Es2ZdfkyqbPINntxLefFGa8ZKOATpDg2qaGDwLCRFIv6fywsmux3tOBwTvtyaMcRNie/voY2pUP4gzXNGmU9XHMjXn833/w7uKzr7UGuJbJe05M7dpNv9m61Fybb13cKD7Dj7X7n20ppNTmM9qGUhQZVYYB9bJLzbPpBFqy98Jqd9f7G4bg4ESZMMm0PC3/c4YhiBOJbRqULINOmODHWZ7rlnCgUaJe2j8OYKO3ygOHxnn/qen9L2jeBzmmKFiyMMl2mW6IHX8fggltoqJZS8vQoMKPMy2VzcFfmEhWuxFvPTzOhQ2fzz+/xgfunr4tR74gzqh5FhMVF4O4cIlEKlxHcHSyzLVmwFun4NnlDi+sD2jk98fD981yaKK8a/e+ZBu0fM3qPHW9zVfOrfOBu6b58289yNGpCr/y1UukmZZESqkIUqljGgxBo+wwyN1gwyQjzSSTFQ1Ez633iFNZzMQJITg1W2PLj1nrhvRz+fL11gA/0lI/xzT48tl1pFL8pbcf5uhUOZd96vWNUz2Tlkml/8plikEe8G5PGZRdHXheK+l5R8vQIMYy9axYmGZ4mclU1eX0bJXnV7qsdEMdsLzS45nrbS5u+Cy3Q2ZrHidmKpyYrtIoO1xY77PeCwlzdvrBg+O3xTJ9+J4Zlrox59f7zNVdSrbBYivFNvSc4UTZLsKy/ShjftxjrRsWYdytQawD7nfMkNmmUchLN/pRwfg9u6Tl5zqWQ4PDqmfRCxNWuwHPLrX5vlPTxXsVrGwOtG8GAF6t343RjNbeei1ieEY1qlG98jUCbKMa1cuoV1tisp+xi2Ma2m481TK9mbpHzdt+hPdzWbvZca50QiwhqLgWfpQyiLTJhGuZTNccTAMGO+ZpdtuTp3tsz4c2+nEmETHFnzs0UX7Zu+kL4yWOTVWgD00/5tpWQJxKopyWUnmDrcOcdWyAyjSoIZ/x2+xnPH6lyUfu3s1aeI6p3R4tQZTqwG47TyQ387m1QR7wvNoNsUzBXbN1WoOEpxbbRRyA7VnEqWStG/KfvnWN+X2s3XfK4lY6IYOkTxBneLbO1BuGSu+04jDQIC2VCtvW4L9km4SpJEwyvBxkBznAbvox/Sgrmq+3HW3scuTbadPu5PNdjmnw+JUWmVT86Qfm6YUp15oDljshcZrhxxlnV3sIlcEULLUGKEw2PYuNfsRyJ+AT7z7KF87o3fvJilNEJdQ8WzOBvYg/PrfJajfix95xiB+4Z4avXtgiTjIGOVCyTcHCuMdGL9YW/6mOxuiFCUGS8X2nptjyY6JUstwOOT2rn4eJisO7jk/yzPU259d7xIkGz4YhmCjZTFZtokTyB8+u8MiFTaaqLlIp0my4thKVg0eEzkGzTIFhGHnjP8CzDfphwnhZh56fmq2x1Y84t9bDj1Nqrp7ROjlTKwx/nrzW5pe+dJ75sRIHxj06QcJKJ2Stqxl5bVTi8rYj4zyz1ClmDw/eRCVwYx2f3j2raBqGno8TBhMVB9c2idKMfphSckzumq2x0gkxhUE3THZttgwrySSeZeCVbVY7WlqpAsX1VoBAB5wHiaTiWkyUHcI4Y8uPud4MWGoFeI52Tq265itqHnInAGw0o7V/vRYxPKMa1ahe+RoBtlGN6g7ruyEx2d/YxaDimFxvB0xXHU5MV3Y5Zd7YKN3qOCuOyTNLHequRapkHsKbEKch11sDnl5sU3VtPnzPTDFDtA0ArNz2PMSpaOnUkPGzDbHnOF7ubrphCD549zTnHj/LF19YI0xVnj23m4VKpM4BS6S2xt/qR3SCBKVgbtxjoxsVss5h85dJiWcb1D0bxzK0w2VuntDyE3phUphv3HugjmebuJbg7GqfIE6ZyM+b/DjGSjZ+lO573YezbnN1j7vmaszWPZ5b7uBHKUKkKKUIk+3MOYGemzIMyNR2xiA5M6QZIYkQRhF/kGVZbudus9YNqbrWrsy5ixt+wQhahkACDx4aY6MXMj/mYRgGY2WH+8sO9y1ocHd1q8/jV1qU8l+JMJEMUsmmH1PpRQRJxu88schGNyqkdjvXZjhT1o9iHgsTrm4NeOexBu881tBB3UKw1Aqouiad3PTFsQwsy8AVgjjT9v2PX23zpgO1wsRmp2GFbQrm6h5hnNIaaAZsquYWksBBnLK16dOPtJHGsakKq50Qz9aZc5nUs3WuZdALM4QAzzaYq3sEeQC8Z5ts9DSrNlF2KNkGFzd85sdKvOXQOAcbJfpRxmY/wjYEfpyw0Ys4OVMhzhTzYx79SJ9fN0g4v97nnjntLnqwUeYn3nX4ttUCw9opK7y40edX/uQSQaxDyduDGNMwmKl7nJiuYJsG4yWb6ZrHi2tdrHz2c2fGXD/UG0CzdZfOIGGpHeBa2lHStfTGgm2Kgr0bL9s0/YgtP+aLZ1aplyxsy8QyDE7P1V4R85A7AWCjGa2b12sRwzOqUY3qla/REzqqUd1hfbckJjcO6EdpRqOic8PqJRvbNEilvKnL2s2Os+lHXFz3WeuFtPyYQS4/0zvk2p4/iDPCROd3Xdrsc3yqWgCAUzNVTs5U6UfDEGtLsxAV7d7nOiYnZ6sFSLrdxu3G3fQgSfmdx6/zANAOYoJEFCyUgiKUe/j/UZqFMnNpI0JbxW/lssjfe2q5aP707I/BWi/k+FQF19g2i/DyRvXQRJlPvOcIJ6ar/PenV3jsapOWH+2Sk+1sdo9PVfZc9wvrPT7z5DIX1/tc2ezj2ZqhuHe+zvVWgB/1Uehd7umqQyfQckDbNPQ5yozxkp0Hx2egKMKMhRAIQfF6x9TRBGmmWO9FPHhojDMrHb5ybgMjb7IdS9AdJGRKu2iiYKFR3sPADWWgYSqLHDbbNKgY2iylH6Vc3Rpg5XN8N0rtgjhjtRuSpFIzXhWHKM24tOlT82zeND/G1eaAJJNIqYGnaWhprZGvrWMKMqmZzqV2yGTF5uMPznM+N6kZGlYcmdKzYWluluPmx6ty8G3k69QNdMTDINbSykwpHRFi6hBz0xD5TKanpZC56czdszXOrHaxDcFmP9LPYdnmrUcmMA3B41fbBRiWSj9fmVI8cbWNaYrccEcbePTClMXmgLGSfdsSyBtrqRUQyqBgnBbGSzy/1OXZpQ5zdZdEqsIwBOD8ep/7F8b4yL0z/IdHNNvX8uMig3DIxB2fKrPlJ3zw7hkmyg5fv7hFmiksQ0dsTJRtSo5Fy49YbAUEiX4AO1FGL84o2yaTNfeOzuVmdScAbDSjdet6LWJ4RjWqUb3yNQJsoxrVHdZ3U2Ky34B+EGd84cxLu6ztd5xNP8olfRkVx6Tlk8/0CDKlHQotU0urBLDSDvncc2v89Aequxi/ubrLsakK59d6rHQ0++aYmrVIleIzTy7xWWv1tiVJ51Z7/M63F7m40SdTYAnBYmtAL4h44E1Qsc2XdGMEGKQZRqZztep5CPNSK+C/P71MkrMdw+ZvqubQGsRc2vSZrW9bjK91tZNfzbP4L08s6Zm/so1S0AoSZm0DqTSrOGx2T0xXds38AbtcNWdqbp6FJVjvhdoQZKbCIEpY7kQsjHm88/gEaaZ4/GobP05RUlJ3TRgGpKcS19S5aGkmkVKDoY1exPHpCnGa8djVFrYh+O3HFvEsg9VOiCEEnq2Bj2kYHGiUOT5VZrEVsNGPWWr5rHVjmoM4z5YzKDvaRTNXlwLk815CuybaGhxeaw64e7a2S2qnlKKZxzM4liCVAs8yGCQZC+MlWoOEyarLD9w3y6989RKubXJ2pUuUasAz7Kmz3BG16lls9iPGSzb3zNX5yN2zu56HXpRwZqUL6Ny/YcWpng3zbJM41aYhZdfizYfGubDeJ04lXRLqZW2cMVV19FxfkmGaWmIbJhmbfsTbjjT4ofvnmaq5dIOE//TNa4RJyvl1v5DHWrkcsBvo6z9d1TEAw/vEsw3edKBOaxDzY+84vK8hx63q0kYfgE9++QJ+qnYxTsNnc60XFexjP0p3beScnKnxV993DM8y+fKL61xvBVRci+may4Exjy0/YaLi8OPvPMzxqSpvO9bg//F/PUucKubrLoZh0PIjrjSDPMNNl5MzwWEqUVLRGSTfEUC6UwA2mtG6db0WMTzfSzWaixzV66VGgG1Uo7rD+m5LTPaTFJ6ceem5sBuPUynFxXWfIM6YqDj0Qx2eaxkGVccgynTQ7VzNxbVN4kzuCh8eMn7DWIVOoPPv6p7DkYkSSmijhwPjJcq5Hf3tSJK+9MIav/Sl82z0IhxL4JoG3SijPUgomRotBEmG4qV/JE1gPM+0ijNJHMWEiUknSHjw4Piu5u+9J6YA2OzFdIOEpq9jImxTsNAocc98vTiPlU6IaWhr+FY/xjR1gPJQdjZRcemFSXHddzadp2drTNc8nlps40c64H2pNWCxOSDOJEmmuNYc4McpC+NlDk14XGsGJKlgsuqy2Y+0CYYpsEwd2pykEiUEVu602A8Svnp+E4D7jjY4MF5mrRuw0gmpeRb3Hqjnzoz6/JNMMVNzud4c8OilJmXHpFaysU1taLPeDWkPkpzRzB0tM0mYamlkKiVppmj6CVv5/NxQaqeUoh+lmIZ+bc3Tu/qWYeBaJvNjJhc3+vzwg/M8dHiCb1zaLOakBnGGaWuQGqeSimNRtnXQ+IGcTbrxeVhsDqjYVnFeQ6lfphRSDcPVBXZu0lMv2bz9aIO5ussjFze5Z67G3fP13H1Ss8/NQUyYpGQS3nRgjL/wtoO7GJ1vXWrye88sk+RSvaYfMYgzuoNYm9jk91XFsSi72+HrS+2Aw43yLQ059qsL6z1+/ZvXeJuh5bezrrPn+bodu/yTMzX+yZ+6lw/eM8OXXljLZ9sEIPa89h1HJ/nA6Rm+8MIazUFCxTFZ7WjWdFiWIXBsfQ/GqWKjHzFZtTm/1mOxNcDIzYLupNHdCcAAukFSML81z9oDwEYzWi9doziFl1ejuchRvZ5qBNhGNao7rNeDxOR25sJuPM5emNIcxHkWGvSiFNPUQdOWaSAMQZqpXGq3f/gwaAnedM3l1EwVUxikMuOZpS6ZVHz/6akCxN6OJOncWpdf+tJ5Vrshc3U3tzlP6QQBqQ4qA/ba39+s0mLALTcfQbOGjbK97+77gwfHafoxH7l3BiEEXzu3QdNPuGuutgvcxankm5d7OXCEqmFSdi2OT2mwduN1v3HXf6Li8OZD4zy71ObKpq9dEKWi4lhMVSz6+exRP8woOybvPjHBn37zAjN1jzPLXX7lq5foRyl+rCWPJcdEoKV+loDVXsR01eW9JyeZqGgWaKMfkUpJZxBzZdPnnvk6z1zv0vI1qHBMwZYfYxqCstj9UzA055BAN9IOnBv9mDAT2znQgCvAFEKzc5miG4YkWYYfpYDCMARuZtAaxBxslKl5WnK71g0ZJBkP3zfLubUelzZ8So6hzU6iFAQ4lkHVM9nsx5Rskw/fM3PT2IT7F8a4vOXTC5NirtIUAkNAGGdYlsFM3S1kgsM5rKmqR5Rt31wTFZfGUYdukHBho8+9B+r8ox+4a5frq2EI3nx4nP/zG1foBAmZUmRy2zRmOIMYpBnLnZCF8RIlx6Timqy0Q956pHFH3w1D8N/yY6hp234lxJ7n629+/wl++jYMfgxD8P5T07z3xNQtX2sYgh9/12HWc5OVzX6EH2fFeZqGvkaieL3eSFjphFiGwacfuUw3SO+40R0CsDAxeWGltT17aRo0yg5Hp8pE6fZ30mhG6/ZqFKdwZzWaixzV663+x/4GG9WoXka9USQmNx6naxkkmTZ2aPo6ww2lM8+06QYkSpHlQOfG8OGicRwkHGqUCyOLIM7DoA3B88td3n/K3WXzfTNJkpSK33l8iY1exPyOQGLT0GxMgkSq20Rqw/cE2oOEsmNS9WxQqrAp7wZJwfYMq+SYJF3JyZkaFcfiS2fWWdiRTwXaofLp6x3iVOHZ2l0ySiVb/YgnF1vcNVsjSOSu677frn+jbFOyTOolG8cU9KKMhXEPxzJxw4T1nkShpY9nVnocnerwsftK3HugztGpMtNVj1TKQuq31ArohgmDOCOJUgwDrrcCvn2tzUo7xI+S3JBFg60zK11MoSWVVh4LECSS6apD1bWKkHAdOSB15IFiF0Db+XeAKNOuleNlmyDOuNaMidMMhcIxRQ7AdQD6VFXfF8EO99FDE2X+9gdP8nP//QwXN/qUHAuFBohl20Qp7Tj6vlNTvCdnRPe7zz92/xxn13o8vdhmrRsxVtbXPpWKRCpmKw4nZ2q7Zg9XuxHvPj5BkMg9z/FaL+LIZIW/+LZD+0Z0XNzo04+zPJ5A/7thhp7IJcZS6bD1LT9iSjj0wwzLFLzt6MQdfTcMwf9c3du9+Oz/fL2cCJOb1cmZGn//I6f47LOrfOGFVdZ7EUZ+ro5pYOYmOOmOaIRmP2YQaWD3wMHxO250K452Xv321SaZVIUba5IpNnohTT/i0ES5AGCvhw20V7NeSUneaxHD80as0VzkqF6PNQJsoxrVy6g3isRk53E+s9QmTCSQMluYZPR4YbVHEGe53btmTFRuyGAaBg8sjO9ijUq2Udi3Vz0b0xC0gwQpFZc3fY5OVTg8se16N5Qk9cKExVz6V3EspNLBwo5lYO9oijUzolm+VN4+YNN8oAZ8piEo2QZrnZBMKs6sdFlqh0yUHU7MaFYMdu++7weylFJcWNfuh9M1h06QcHquxlY/puVHbPVjXlQ9fuj+A7vYg/12/XthSitIqLoW3SDFNg2afkKQasdFlYPmA+MOUSp57EqTlU7Ix+6b25XJt9WPeHapwyDOqLkaSEupwdrVrXzuDO2YaQo9X5QpyFKFa0HFNBBCH8+QhSw7Jm85NE6cSV5Y7tL2YzzHwI9uvv62KTCA1V7IlNKW+SemKiihWMznnExDUHW1kchmP+LIRGlPA316rsb/+sP38MkvX2SrHzFX9yjZOvh7tRsyWXH50N0zt7z2Q2Dxm49e49HLTbb6eg5xuupqx8Sai22KPSY9P/bOwwB39BynqeS/P72MlIq6Z+LH2yHcUR4tIJXCMgQmOr/NtUwaFZtG2eGeufotz+XG2r4vHYi2//3QKCZIMlqDmF6Y3NH73m6dnKnxtz5Y5eh0mf/X750hTDKUosivSzItPQUN5DKlme4w0XJfbSZz+43ufN0jSiTtIOFwo1QEv7uWwC7bXGsFzKaS+bqWTL7WG2iv5ozTSJL32tRoLnJUr8caAbZRjepl1htFYjI8zuutAb/2tStc3urzwMIY7SAlTCVSatljHw2u/DihNdD5VA8e0AHJQ9YoSFJafrLb2j63xBeWYBBlnF3pcXB8u9EK4owolXzmyWU2+1HReNRLVj73tTvTzbEMKq65K1jaMsCSkKqbnCSaXTMF1FyLQZJxtTnANgQVx8I2jcLwY5iF1Sg7LLdDDk+W6EUJ/TDFMQ3WuyG2peedlFKF+2EqFaZhMF11OT5V0QBsEBPEGX/qwXmO7LBm32/XP8504DhAkKQYQjBQkgwNfIx8Bqw1iKl5NgvjJZp+zDOLHY5PVXh+pUuUZHz1/GZu3S7ohQmDPDRaADvUfSihnR1lKgtiJs0UfpTi2iZlxyKItTNkK7fZdy2TTpiCEHi2hZQpqN1B7MPPMoTIpZkKP0zoRRn33zPG4YkKi81BESkwXrZRCNa6Ic8sdTjYKO9poE/P1vk7HzpZNKdXmwM2+zECnQ34fz2xxNOLnVs2qsP5rMXWgMubPgDHpyqEacYXnl+/JSC7k+f4icUWq92IumcR5lpdM3+tZWpZcaqg6prM1j0GccrxqQpBknJiuloAjdutimPhmgbrvZATDvSClEgmXNoY0BzEBEmKlPCZJ5dxLONVaeQNQ/Cxe+f5rW8u8tT1dh44r4jS3UBNoOfaDjU8wiTj4kafRrlRyKxvp9Fd6Ya4tkGjbNMaJFQ9/fwOzVvGSzqKY6UbFu/xWm2gvZqAaiTJe+1qNBc5qtdjjQDbqEb1HdQbRWJiGILDkxX+8rsP8+lHrvDUYof1XkiaKWbqLhvdiCiVpKlkqR0xX3d56OgEH713Ftcykfm8lZSw0Y+o7bC2z6QizWQx37XYGvDIxS3edGCMRtnm/HqfbqAzsrQhiW48Lm70We+GlPNYgOHskRCCydzEI81/D0V+DiLTJhKF/OyG87RNg0RqV0UlFWNlh7GKQ5JK2oOU8bJNP9SugmXb0u6GUvJv/+gCUZJxYd0nSDJqnoltmriWdlesuibtwXZYuRCCesmm7Jpc2dR/5sb1vnHXvxdqg44wyUgyhYHCsI3cmVEP3lmmBlVBrKWr82MeFzf6/MhDC5xd6/FHZ9fphCll28QwoJNb9A+BgkADV0tnKe9hKKXSUtd6yWY6NzTphgml3GQGIJESpfQa1ko2MhXA7vNTgJSSKNH/rCMmVMGMHp6sUPWswsAjyVLCRHJ8qspPvOswJ2dqe5iJ41NVfvoDVR65uMl/+tY1hIDjU1Uq7l4Dm+NT+wMswxAcmazsAs8AJ6drLzmvdbvP8VbugDlVc3NXSYWQGrQJodcf9KzncjsglQo/blF1LEqOxae+eumOGno/TLneGrDc8nn3m+BrFzZoRxLXNGhUbJLUYLxuc63p8+lHrrxqjbxlGfzU+47x//5vz7PWjVCogs0dPosV16TqWdRzd8ymH9MLU+olzTLfTqPrxymOZfDQ4QZXNjUo1WY9Olvu6GSZTpDseY/v9gbafoDKjxK+dWWL51c6/Pg7DvOeE1N7Pv92GLmRJO+1rdFc5KhejzW620b1hqs3is3uq32cN3v/W33uyZkan3jPEX7uv71AL0wpOwaWaXLfwjgzdS1ru7ThU7INkiTbZc//0TfNMD9W4qnFdu7oJ0lSnXM21ISZhjalWO9G+NEW0zUNVOqezenZ3UYeDyyM6VmrXNrX9ONiN10IsE2TqmMAAYYhyPKsLANVyPy2P1NhmQaTFUdL3zKJQhDl4CdOMwZRRjuIcUyDbpgyWXGZrrkcnigTJpJvrzfpRwmZVMSpgWtBy49oDRJSqZis7A4rh1v/cO/c9X9yscWLq70iuDozAHQ0QCq35Zy2qeWgQ0Zs2OBOVBxmai6OZWAIyKQkUxqgjHt6/ixJtw0hUMOQ7cKDBYUGcq5lMlV1KLsWk2jzmUG+RiXbQgBxpijZJo2SQ2egIcjOO3fIpEilZXGdMMFAFNI42DbwKJjIJOOn3nuUw5OVmzITH713lmcWOyjFHlfPYaP6m9+8xkTZ4dKmf9usxiu5saLvMc0eHxgvkWwNCJOskAgWJhwCBrEEFGXb5IGDY8zkoen7MST7PbdffnGdX/rSeVY6IVmqQfN6LyTMhJ5BBcbKDvfOb2+OvJqN/JHJMm870uDLL27QDWQBTl1TcHCizP0LY5xd7ZFkEts06EdpsREAt9foDptlzzZ529HGrnzAmmfRjzT43+89Xuo6v1LfyfsBqqYfc2G9r78zgoSrmz4/eP88H7tvrrjOt8vIjSR5r219r89FjuqNWSPANqo3VL1RNP2v9nHe7P3vnq9xdqV3y88t2RZTVYf5salC+jdkjZp+VOyMH52qcLC+W4YzW3eJUh2obRmCOLdx1+9hYxgin10i31lPmao6HJms7Gk8DMPgvoU6T15r49kGrmXQi1LiNCFOJQcbJX7m+48yuPRt/tHDd/O55ze50vTxIx0uHWcSxzKouTZCKMJUFbN0cSYxhi6BiXYeDJIMKbWbnSGgZBscmWxQdS1eWGmRScXxqUqRwyalKhrzOJE8sDBWzL7B7f1wn5ypcfT7Kvxvn3uRMMl465Fxnl3qsNwOUUCWaZYiShWOBUIYOJahzVBysOlaOlOrPUh4+9EJnrzWxra0ach6L8K1tGNklEtIFRTW8oYgB4DayVDkUQBWLlc1DSg7FkcmyqSZYjOKqDgmvm1qq3/PJE70a3cBNkFuNDEMMVfYluB6K+DwxPa1FkKHYa92Qx48OM7BRvmmUq9nlzo8tdiiFya7ZiC3P1PPJX757DqHJ7U1/mshE3voUIOjkxXOrfc43ChxeKLEYisoGB9TgJdLRR0LZmoeCs3MHZ+ucmqmyvn1Pp97bhXnQZ1Pt9mLeOpaexcIHStZfP3iFu0gYX7MxVAOEOdRECK/NwSHJ0o5Q8ur2sgPr1uQSP7MgwdYbgc8ca2NRDFVcXnH8Qkmyg7r3Yj1XkjFtbDyKAW4/UZ3Z7N8aqZasHN38h43O/5X6jt5pRPuAlRNP87zLfVc76xt4EdZMYf6U+89CnDbEseRJO+1rdd6LnJUo9qvRoBtVG+YeqNo+l/t47zZ+z96aYvffWqJ+TGPUzM3b2b9OCXKJAuNcjF7AxQ5bWkmKTsmjmXuMgx48lqbZ6+3qXuWnnGT+UyWAmnAVNUhUzoH7a65Gkmm2OxH9OOMQayNCm50aZwfL7HZjzk+VaUTxLSDGEMYnJyp8uffusCxiRJ/cAm6gQ66Nk3N/szVXIIkZbUb4seSTCpm61ZuxJBwdSsAoR0XozQjSbellJnUgCZMJE8ttjkw5rHaCSjZprbgrzoEUcqxnE1bGE+51hpwvR0Q5yYKmdSGD5PVl/7hXumGbPYjTs/WCilpJ9gkTiVxzlAptKyxXrKpuiYgsA1RNKdVzyJMM45NVpipe2z0QiqOiSEEWQ6WDJGbjaCB2jCjzTQMwiTT/12BawssU4dCr3YjDox5/NyfuY+Kp41X1jsRn37kEi+s9ljpRJRs3XDvFFdKRTFf6Fma6VNKsNQO+frFTe5fGKPsWnsaHGBfqVeS6fiBC5s6iLrpx0y1vF0GMUoplts62HphvHRH8RHfSe3Hyvzke4/y8394lkubvr4GUpFlev0NQbGZYeds7tAgpGSbHJms4FmC3392lWeWOrm75gCAE9MVFsbLmELwxy+us9YNOTxZxrMtLKGvQMW2QKjiPZ9b6lBy/H0t71/JNbjxutVLNr0oY70XkknJpQ2fiSPa1Kcbxqx2Qw42SpQcg16Y3Haj+2o0y6/0d/JOQLXTmGg41yuVBtTDOdTPPbeKgtuWOI4kea99vVGMxUb1P06NnvZRvSHqjaLpf7WP82bvX3UtUinphUlh0y72yWo6PlWlbJtkUrHUGjBedgoQNcxpc20TqSh2xoc1DJCeqrp0woQwUbntupYwbvZjFsa1Df1ExWWjF3Jly2cQZ6x1Ajzb2telcarq8lffdxSxT8jui8stAM4sdyh5DnNjJTKpA71Nw2AQSzpBkme4aWOCTGnpX6agH6WFPNDMAU2as0JRKllqD7jeGpBkEtcyKYcWJcdgy4+JV3qYuUQxTiXr3YhLG34h9zo6WdkVqHyzunG3/FCjzKmZKsvtgJpXoh9lbPQi6q7NZMWhHyaMVxxWu1EBCF3LxLNMgiTjxHSFph/RHCQYAqI4xTJNLMvEEQIpJYlUJKnEtrQYUuTOm2XXxLMtNvsxcSqZq3v8nQ+f4u4D2rnwwnqPZ5c6mKaBa5ts9SPa/s2b/6GtO4AQiiBOudYM8KOU6ZrHVNXd1eAsNgd7pF5NP8rZiYzxkkUYp0jFLoMYHUyestGPqLgWrmXuOo6Xio94uTK4W7Eyn3j3ET755Yt0ghilFEKAZ+lw8FTqZ6Nkm0glGcSKME355uUm59b6xJlESsnp2QornYC2H5MqRdOPOVfqU83n9hQ5U+3ZBcU5lLpmUmIaOr7CNo19Le9fqdpPoieE4ORMlX6kIzPW8rB12zRoVLQ7Z6PscHVrcMeN7ivZLL8a38k7AZVSFMZEOzcgzB1B8c9c74DQ7OHtSBxHkrzXR71RjMVG9T9GjQDbqN4Q9XrT9N+sCXy1j/Nm76/nhBImKw6tQbJr0H/n53794iZPXWuz2Axo+hFjJZvJisuJmUpuSJGBEsyOaXON4S5+09c75oM4pR+ZzI+VaPkRTT/R8kMpsA2Dk7NVJiouW37Eo5e26IcpjbJDJtW+Lo3DxuNgo7zv4P2XXlhnAeiECRe2wh0BunY+/6VYGPMYJJJBHGMaBhNlhyDO2OrHO6SB2/lbQ6v74QyfYRjYpoFhCLphwkYvwzQFc3WPimvR7Ee0A200cWqmxmTVwbX0fM4fnV3nyGT5JXOldu6WDxvdXpjkwFOHOI+XbDZ6kbbvLzs8cHC7OZVScWK6yqOXtnQWWybxo1QbxWQSlUimqg4PHhrn6taAK1s+idJOn5YhmB9zmam5jJdtpFK7WMzTs9tg7de+dpmldkCj7PD+E5M8ca3NZtcHMpw8uy3eQbVJpVk7IXRu2mTFJUozXMug6pr8yEMLu4wXbgSvQ1Y3iDMmKg5SKbb6MVEqmau7tAYJFzc0exTlodpHJytFAPbO2k8m9p3I4G5kZUq2x3ov5BuXNnlxrctkxeHNB8eoeCZNP+Hiep9G2WazH9McaIv9JMsIU0UmJZYQmALaQUwmFY5lsNGLubY1QKGDzAeJZKMfsdELC0v8XpgQpS4qZ9jSTJFKnZNnGpqJdS1jX8v7V6r2u269MEUqxcnpCsudgOutgMtbPtNVl3cfn+Qj98zmrrMvr9F9pZrlV+M7eX7MKwBVo2yTZhI7vyeVUvTDbYOiTCkGib4nyzcB0jfeuyNJ3uun3ijGYqP63q8RYBvVG6JeT5r+WzWBqVSv6nHebB2GlvFjZZtukOwa9B86/l3Z8vm3f3QBM7fdFmgGaqk9oBPGHGyUCWJJrWRzYrpKa5DoIfrcpW29G+WNucFYyabmmggRFLvMhqHPb6sf8ZUX11nvRXi2ST9KiFNFnGVMVNzCpXG64uI6JidndVN2o2nKxY0+37yyxY9MwWYvxnOdHQG6Ue6+l/Ke45NYplEYEyi0FFMIMIYzXTkDMsxoCxJtmDCcUXNskzjVrEcqFa5tUnU1YN3sxygFgyjhzEqH8bLDRMXhnrkaTT9+yd35/XfL9XF0Bgn9OMUyBK4heO+JST76pjnuma/vak4NQ3D3fI3ffWqJXqiBeWPKphto1kkgODxRxhCCu2ZrvO/klJbSWSaTVYfj01UWxkqs5Pfejc2vlIrffPQaj19tYQBLrQCpoBsmTFVdICZTikTuPsehxcgwPLk1iIhSnUE2SCRfPru+K/D6RvA6ZHWrOcs7vIcd06Q1SHAsg81+xEonZL0XUrItDozvbbxhr0zsO5HB3cjKtAYJL6y0aQ1i0kxybq2HAt53YoqDjQoL44oo0YxtmGZ6DjBO6ccZRr5Qjm3mhjcJjqmv/8WNPnEqqbhajqqkRr9Vx6ITaLMbP8pYbPq4poCDOqxcSh3b4FgGlimI0myX5f1yJ9iXsR6e252CoJ3XLclk4f6pHU4NyrZmnP+n9x3jxHT1joHVzY7plWiWX43fjp2A6npLA+441Xl8/TCl5JiFQVEQpZRtCwR3JHEcSfJGNapR7awRYBvVG6JeL5r+l2oCP3bf3B0d5502TzdbB8c0sEyDIM4wdwz6N/2Ii+s+i80+q70YgW5QJioOdc+mUbEJczZKKT1DAzo4e2c4NkqH41pC0BwkuLZFyTGZqXmsdkOCWLM9G52Ii5t91nqRPg8BfpyRpJIgFUilQdJSK8BAMKbsXU6Ud8/XeGG5y7NLHdZ6AYsbPX5kShuEDMO1XUvgVBxWuyFRnNENE45OVYu1UEpR82yW2yGWqc/FMLQk0DQESSoLA40olbi2yZhnsdGLCRLt4ijQu+TtQLsb6vcRDOKMTEZs9iOWWgEPHBx7yd35G3fLPcvgiWttNvohcSq1NbqCtX7EM0sdPnb//J73klJxdqXH/JjHdMWhFWh2zjIN7p2vYxkG9xyo8WffskDNtW96H93sGB+5uMmXX1xHKmjkTpvdICWIM1pSN7JDV85hDZ0nVf7f9HnoaALLMIiSjD86u84H7p7h/aemgb3gNcoygiTFNGyU1ABnru4xW3O5vDXQOXNxRtOPeMfRSU5MRax0w1yCeHOZWJpKfvuxRV5c7XJgvJSzircvg9vJyrQGyS5DCdvToe/L7ZDnlztUPYuJnKVe74eEfUnZMTCFdgGVCmzLwLOMwknSdk0aZZu1ToRlGAxibYhjmYJM6nvGtTWjIoFemOFVrHzdNagTQrPanTzgfmh5f70V8Gtfu0I3TPZsKAEvi3EcXrdHL2/R8iPCROaOrhZxmrHUCZmrexwY9+4YYL3aBk2v1m/HEFB99tlVNnqrrHVDxko2M3WPE9Na9j28Lx84OIYCnl/u3pHEcSTJG9WoRjWsEWAb1RuiXg+afikVn31uleutAQvjJc0q3dAE7gw5fqnjfDmNys3WoeZZNMo2lzZ9jk9pydhwNmijG7I1SEgzLQf0o5Q4lYRxxmTV5Z75MRTakfAn3nWYzz63yreuNIkSyXTNKZgsyxA4liCVetbmgK1lOrM1l+ttzfCdW+/RDVOEEDimQck2MQSkpnaA9KOUUzM6xNuxNCtUdvS8zqOXt/jtxxe1ZbwpCOOMIGcKlzshM2MGpbypEjkL0R4krHZDDk+U6UdZwbKdmqlyfq2n89gApMIQOtm3MOUwtPmGaWjjjrJjEqQ6/yzNFIMk02HAApRUKHTOlpefUz9KeXqxzd3z9ZfcnR82d7/x6FU+89QynSBh6IDvWtqiPVOKa80B/9tnz3KoUebkzHaj1g0Szq91mau72KbBQqodMl3LLKzON3tx0XSeW+/ddnOXppLPPLlEN0w4MOahpCSUeo08yyBOk+K1pgEyN225McM8k5J+JjENQXMQ49kGcar40gtrvDeXRe4Er08utmn5Mc2+/gvAsUxsQ7vuBUlKnCpsU/BD98/z595ykEubfT79yJVbysQubfb51Fcu8rnn18ik5OxqD882OThe4v6D2ulzru7y9PU2Xz2/sS8jNGRlSrbHCyvt3UHx6JlRyxT0oqyQbE5U9Lxee6BdTiUKy9SgyjSGwela5tgoO3i2qc1mLEEY6k0BfW8P114wiIch5duzgll+z4yVHWbHPO6eqxX3wfXWgMXmACHY46L5wmo3v07qjhlHwxB89N5ZPn9mlY1+zFzdK8Ks/ShjuupS92y+eGadk9O1O5oRfLWNpF7qt2O5HXJ4skQvSlhsDu4IEJ2cqfG3PljlwcPj/KdvXcOPdEh62bV2Ga08fN8coN0l71TiOJLkvXL1RokEGtWo9qsRYBvVG6JeD5r+r1/c5A+eXcnNKgKsfF5qaKKxM+R4pXvrH+Zh43mnjcqt1sEytLW+ZWpXtvNrfTb7OkdMKlVkcCkgSjJaAz3j5VgG7zzW4FozYKbu8UP3z/PUYpvMFNu79zUPpSBIMtJMA7gwyTAMQZBkTFcdaiUbxxB4dsJSO8CzdaOaZJIwyZD53MszSx1s02C66hU73lXXojtI2OiFlByTw42ytvkfhIAGmWu9iCMT2slRKUWU6rknxzJ0c662I3zTTOLYJlGS6TDpPLfNUCC1IhHbMjnUKHF6tkbZtYiSjGeut5FKW9bfM1fjxdUunTxfzDJBKs3UWaag6gp6kW7Kyra551rtV5v9iCjNtDun0i6CUlHI6BQGy+2Af/8nFzg6WeXShrZ5b/Yjzq/71DwrB5ra0OFkbqJQckwurPf59COX6QbpS24ASKl0wPmFTf7k3AaPXW3iRynn1/08A8/AMnQY985staEz5DA3bidoSzI9l1V1LQxD4EcZSinO38BAnpyp8aG7Z/ilL52n6ceY+ed4+X18vRXgOQZS6vvNMgT/5zeuMl52+PA9s7eUiQH84hfP89iVJmkmqbgmhtAumZc2ffw44575GuvdiMXWgP/ja5eYqXp71mnIyqz3wj2GEkAB3E0h2OpHxczooUaZk9MVLmz4zFdLxIneAGgHiWbLlAZx7XzGzTQEZdukH6Y6+FyQy3rJHUlzQ6FMUnI0wzxTdckwmKi4DHJ2qF6ykVLy3FIX2zJ4YGEMI49uqHk2Fcfkc2fWQMHDb5rd9d9u13ij5JhM19xCyptIiW0YzNRdTs7UsE1RsM0L46XXTTj0rb4zz6/36QYJqZT82z+68LLYPcMQvP/UNPNjXnFfDuM2bpQvjiSOr129USKBRjWqm9UIsI3qDVOvpab/wnqP3/zWNbb8mNm6i2uZJJncZaJRL9msdUOmau4tj/P4VJX//Y8vvuxGpZDiPLfKs0sdBnFG2TF51/HJIoftmaU215o+/dwYoGKbOjMNCke7KFW0/JggZ9zmxjzN0NTgyGSF6apLlmesVV2Lb19tcb09IMsknTClHSSUHYvpmotlGpyYrnB500eRUHVtojRDKYmfN6pmPp+W5JljZ1a7pEoxXXWRSrLUCXSeVI4CHFPnkUFKphRtP2am6mCaBv1cDjgzDDEe6vPQQKgfZZRtg6mKQydISfMIApkbcZhCMFmxecvhBpPVbdv4pXZQsJSNikMmKd47zRSObRZRCIYAlD6nG9mmG2vYnK50NAAVKAzDKGzgs0wRJpKSY9ELY/7k3BYb8zruIPUV19sh/TAhk5KDjTJW7grYj1LefGgcP2cH9mNWbtwAuLDe4zcfvcZXzm+w0g5IpQZlGu9qQJEKzWxlSmetDUvk/3OjPBI08K/lwedD9hkh2OhF9MJtlm6nvPMth8bZ6EecWemy1Yv0DKGCOJA4pqDimEzVXFa7Ib/0pfMcapQ5Paez7Z5YbLHlx0xWHB461MAwBP/ujy9wbrWHawpSx8TM2a2KYREk2oK+E8SUbB3MfHyyimWKPes0ZGW+cWlzl6HE8D7xo4yDjRJJqtjyI1qDmLKrQYBtmTTKDlNVh6Yfs9gaIFTOCrsWVc9is6fn8mqehUDhWkY+dyqKmAAhBBXX4tBEiUEkefBgDRjwfadnePJ6V98PCoIkRQi4uNEnyRRvObwN1obVj7KCoetHGfXS9n+/XeMNP9bfE7YhCrCu2P6fkmOx1g15YaXL7z21fMfh0EMjkyFLPld3v2MjqSGjkkrFx+6b4+nFNpc2fNa6IVEq6QYJdc/exfS/XHbvduSLI4nja1NvlEigUY3qVjUCbKN6Q9Wd/OC9UvKHYbPtRymNko0hDAwhcC0Tp2LQ9GMubvjcNVstZiEOTZSL4+xFCf0wpZrbkS+29lqbD+vG5umWO9V5x6T0/6CU4shkmQ/eNcNvPX6N55Y6xQxNnEoypUgzhphGN99Kg42VTqDNOOKMimNRsk3tVug5xbGdmKnQixK6QcJExeGBg+OUbLPII/vwPbP8h0euEKeSqarNWjejF+kMKssQ29ldAoTSxhabvUjnt0k9rF92TZRSOVu2zegoBVGmuLI1YKrmMlf3ivBn2xC8+9gE7SAFAZaA55Y6RKlkvOJwYNxjvaddHgVQdkxKjsmhiTJbflwEVd/IUiaZhDxkO9WHjWNq9JZKHchtW4LJqk2QZLe8h4bNqWMaxKkklTBMNstxDVmelZZJbSxRdS3OrnQ5v9EniDNEPg+40Ys4MllmoqIBwYW1Hpt+hG3uZVZu3AC4tNnnF794nqcX23SCRJvIOAadQB+/IbRBC1ISp6CULMCoyK+DQjNs2sQF4vzUy7YO5E6l0o19DuCCONPxCjesxYHxEkkmaflJIUFNd4JDAZV8HnOu7rLeDfn01y/x/adn+PbVFle3BgRJStmx+NZCk/sPjvGty00GSUbNtcikYpBISrZRSHQ7QUKUZBqwV13GShaGYey7UfLwfbOcW+9xacPHsVIqrkWSycJU4v6FMfwo5eyqZgKvbPq4lsm7j09y11yNM8tdfufx68S5CUvNNZmquhoQZ4pukGjGO7/XPUuzVUNGcLgp1AtSDjTKHGqUIISJisObD41zZrnLei9irRvSKLscm6qgFBwY3wtuhiZEArXLkGhYt2O8sdmLWGwOUEoxnm+UJJl2tezHWuocpZLff3aFOJV3FA49nLXdaWQyNFB5uQZN+zEqx6cq/MhDC0xUHD7z5DKWITg9W3vF2L3bkS+OJI7f3XqjRAKNalQvVSPANqo3XN3OD94rKX9Y6YRc3OhzfKpCnCo2eiFOPs8ihKDqWWz1Iy6Zgncemyzm6AxDu7d9+YWNXcdRL1ls9iMO3GTebtg83Wyn+u75Gn90dp2mH7PQKBU7w8+vdFnphnzo7hm+ebFZhDwPJX6Z2rkjThG0nEnFZMWhXrL54gtr/M/vP77vzMdExeXBg2N863ILyzSQUpJJo7CfPz5V5U/ObfLCShcrjwvoRzoQeOgiOMyQ8mMtdUulRPUhiFPCVNuV2zmD5sfbIMg0wJTgWELPuBkGE1WH9W7IZj/lajMoLP9dyyBIJOMVmzCRvPngOPfMi2LnvuQYXN0a8KceOMD5tf4uFvTdJ3SzfXalx4X1HobQVvZ1z8I09WxbmMg8100wN+6xMP7SuVd+nLLZj1jvRbt0hMP2QOWSzX6YIQzdvF9Y7xMmmhkZ5ux1w5QtP6LqmkxUdfbcxU0NBN9xbGIPs7JzA+B6a8Bnn9WsbDdMCOIUwxAFSNoGZprtCHMQmivxMATFedum0MYiaYqBnjlUaBA7ZIYaJYtBrA04qjsYqmGjHiYGz1zv0AuTgqUcEqUGWnIYZ5LVbkjd06D4C8+v8cUz64RJhmXq6ADHMjm70uN3vn2dTpAQpxlBbGKZBgIIEj3vF2cZUe7k1w1TvEHM41fbnJypMlFx9rBMJ2dq/O0PnuDn+nHu5phhmWZhKtEoO2z2Yz5+/xw//OABBklWbKpc2uzz6MVN4iyj7lmkUju1dkPNSh+aKDNbcxkkGd9/eponr7V47HKTXphRcQVzYyUOjLk8v9IjiDOOT5V3be40yg7TNY+3Hm0URjNSKf71F8/va64xNCFSiD35ivDSxhtSKp661sbOjVMcU4Pg4abVVj/iuaUus3X3tkHQUHa63B5wfl1vSgyNTJJMstIJMIRgsxfB3L6HddNjfeTi5o6ZsioH3NKu78iP3TdXfAe/HmJiRvXq1estEmhUo3q5NQJso/qeq1da/jBsMA+4pSIotunHeXOhZ5A6QcLJmequObqbHcfFjT6LzQFTVYdDE5U9nxfE2U13qp9d6vD5M6vUPZu3HB7f0xSdW+vxH75+hYptcnDc4+xKrGWA7FAN5iVzlm28bPOO45M4pgYJK93wpjMfW37C249O8LH755iuuXtYvx992wLfvLzFSjdkrKQZRdOAMJFIpSWJZm74IdCyTCkTKo5FnKakEixDsd6LMA3BRMkCIozcBt+zNKMXpikPHJrmPz7SwjYMaiXt3pekese/E6RYpsAQkEjFVHWbKeyFmtm4Z77OR+6Z3ZfB/OBdMyy1A55f6fCvv3COjV6sQZsQSPQMYNW1mCi7nJqtvaTZTck287DqTBu3JLs1hWrH3zUg1eYuNc+mG6aYBlimiSEE7SCh6cc6DNvQhiUTZZuqa7PZj3BMg4pjsNqNGCQZnmkSJCmXNn2+cUm7/EmlNxRs0yikcqBBo2no441SHXGgmcyMkm0WzGecScLc4dIyyJ8DnSdXzy36/SjFsgwONUrU3G0AUXEsXNPgqWttVnthES+RSX3uZr4OaaYYK1l5MPMgZ6JEPmOnpahhokF6049IMpUDSb2REqcSgcAx9fXqRzqI2jYEC+MeZdfeJSutl7Skrxdqeenwnvh//tA9/O9fuciWHzE/VmK65hImev5paChxeHL7OR4+91e3fFzb4EDVJc0U7UGMY5ncM1fn0ESJTCmubPo8dKTBX3r7Yb5+cZMvnlnP2W4QwuD9J6dY60Vs+QlebkrSD1OWuloK+v5T00XG4MLYzc01qm4u5VX6n3fdezvMkObrXnHuJdtEAIMkoxskXNzo86b5OmdWulrO6VqUXR0SnkqIMr25UPMszVybmmEdbmztFw59fLrC7z21TCYlk1W3OOah661pCJ5ebO/K8rtVXVjv8dlnV/mD51aLnMkkVcWc8RA4fumFNYIk5cCrGBMzMrh4fdTrKRJoVKP6TmoE2Eb1PVWvhvyhZJtkmeJ6a0Cj7PDgwTEubvi0BrFuApVmn/7SOw4XQPBWx/HAwhgr7ZDnlrv5j/j2jvfQtSxKMuI042CjvMuNcq6ueOZ6u3CU21lCCGqexfPLXd59fJLJmsO5tT4yzTCMbXkhaAYDwLUNPnDXDJMVl1TK4ofr7rn6y5oXPD1b5+9++BS/9KXzrHSCPIjbQAh9fKbQ6xmnuuEfnkWUH6OS2//fMgwGkT5oyzSo2maxFiutgP/6xHXCRNIYszWrFmfaXTBOidKMxWZA3bMYRCnsmFPb6dQ5ZGuHzdVOd8VDE2WiNOOe+TornQ2uNfWMnWcbzNY9JiouhyfLu0D6zZo0/V8VYSq1+Qn7Oy1alkAgyJR2/iQ/3zhVGIaeM6s4JjXP5tiUznna8kM6g5RHLm4i0CxXL0xJ8wsu8jU/PVfjemtAJhUVx6InVb6eAtPQzKdCm4dkMsvnHSlA2nTNxQx0eHUaa7TvmHB0qkovTAmSjPZAbxAUs42GwUOHGwWglfm8nB9nXN7ysQ2BY2lgMDyGDA0Cs3zuMEozonQnpNWvKzuQZJKtfoxlGAg0wDRMgyyTeLZJmGp5ncrdQAWK8bLFeFkz5E4uK7240eeuWS3p+8yTy2z2o12s9p9+8wHOrvS4uNHXQOwmz8LO5/7kdJXNvg7J9myT2bpH049Z64UcmijtYrUMQ/C+U9O858TUnvvnwnqf3/n2Ilc3utzfgPZAbwCh4HefWNrDvt/MmOn0bD7DuOHva4Z011yNT331Ehc3tFnRZj8GFFNVF9sUXNzwGfNsHdoep3SCBNsQ1Ms2c2MevShhqROw5etz3mmMM1Fx9g2HfvDQOP/l29e1bDuThcyyH2qp66mZChc3/NtiP4ZA+XprQJRmzNY9hGDXnPHQHGqpHYC6s1y0O6mRwcXrp14vkUCjGtV3WqM7dFTfU/VqyB/+8LkVFlsDtvyYRsmmUXE5MV3BNmtEacZSO+AdRyd4746A4Fsdh2EY3LdQ58lrbZ5Z6nBiurqreYozyXI7BEGeJbbd+EilsC1BP9RW70JsS/1qnlW4MhqGwDF11pNUSs9j7VoLbRIxUXZwLb3jfuMP13Be8HprwKVNH4BjUxUONW69bh++Z5ZDjTL/+fFrfOnsOu0gQaSKmmsRZ5KyY2GIjDDVlEomyZkcDU6STMs3UymL+Z5BkiGFIlMmpoAgUfhJhikMWn7CWBnWuhFJJnEskxqCTpgQpBlnVrp4jknJNvd1FL1ZczWUngaJ5IN3TXF5c8CmHxMmGYMo5d3HJ/mxdx7eZeZxq0D1smMSJtra3bIgy3abd5gCjjRK+HGWA1ZBlEiSVBGkKQKV55xp2/xzaz38nJkyDHBtk4ptFKHidi4ZjFJJkGT8zrev4+c5fUJoSWOSyZyJFGQ5GDKEBvJl26QbJgXwa/kxiTLIJJg5k1V2Le6Zq3Nx08eP9HzYeNnm9EyNfpQyWXWLtR6uz4X1Hs8ttYkziVIiN5zQrOJQGqnyYOh+lBZgbSdDnEhFJ0xxTP1nx0o2tmXSj/SsWT9KGcTaKr8XZtrR0DRxHYFnbf/sDSXNzX7Ec5kkTnUO34Hx0h5m/hPvOcKftg/ckjHZ+dxrBtZhvRfiVIztz/JjukHCajfa105+5/fShfUeXzizxkYvKoCzZQrWuiFSsa+C4EN3zxTgcj8Xzf02Ye6a25ZZl2yDLT/Gj/Q9tyW0BHO9q/MHDzZKHJ+q4Mc6rFubEhkstbUpScWxqJfsPOB+m8G0TbGnMZ6uuRyaKBOnknaQ0I9SrDxT7sR0lXrJ4sqm/5Lsx06gvDBeYqkV4Fh61njnnHGjrIGjKQQzdY+VTviKx8SMDC5eX/V6iAQa1aheiRoBtlF9T9UrKX+4tNEH4IWVHnfP1XhxrYcfpiy3A7phwl2zVYJEu/Y9fN/cvjlONzuO+fESm/2YY5NV2oOkaJ6GgNKPU2brHo5l7Gp8Tk5XcPPG9MnFdi5bk0XEQM0ztTxNanMBzzE5Ua6y2Y8YRAlBok1IGvmueJTKvHHe/4fr0mb/JXeK92OVTs/V+Mc/dC/fd9cM//6rl3hhpctUxWG9F+k8KqkKxmM4yVV1tZNfmGyDyzwru5DImY6WAaZJipQK1zN0zEIrIJOKsmvm5iYKzzJZGNfBx1+/uMldMzUePDTOw/fN7QJZ+zVX+0lPD01U6IVpAdInKi7H88Dul2rSfuBNswxiiWcZhAmgBKbQYc5D10nPNnng4Bir3ZirzYFmWlOJToCDVOoGI8kBlJSRBqKOBrH9KGWrp81lXEs7PPZjbcAxW3dZ7mjmduhI6NlGbkSjinlG0ICt7JhUXZte3rSDZkAsy0DlTps6BF1Q8SzefGicC+t91nshW/2Y3ljKgwfHCwbqwnqPX/vaZZbaAY5pYBqGdnLMNMuhAFMYeLaWMkqlgXuynx0l2+AtzvTaZEpiohvxu+drNP2Y662AME6JM236cWKqwpGpMpc3/RskzYpWkCCB2Zp30/mrL55Z529+/4mbMvNSKi5u9NnoaxAA20Y9w88zDUGYZDyz1MnnOm9uJ3/jPXVo3IVonWevd+nGku8/PV0wBjuP88XVHn/j+46zkn/P3QgubzRtmq97fOqrl3JWsMLjV9tEScZsXbPSW37Mta0BriWIMx0oX/ds6p5NzbXY7IU8tdhlouJwcNxjsx9TdcG1jILBvLDeY6xk88DB8V3fLxXHYio3f4Hdm09CiEK+/FLsx06grBS5aZB+DnYC5V6YFpEMH7l3hj98bvUVjYkZGVy8/ur1EAk0qlG9EjUCbKP6nqpXSv4gpeJLL6yzAJyYroBhUXEtLq77bPkRW/2Iswo+fv/cLgBwJ8cxVXX5q+87qud94pSybfJ7Ty0jhGYMdICuwLW2pVur3RBTaLbDFDBRdYsh/bVuwLWmZLbu0QmSPL9JkZmKQ40SceqylrMvY56tZ9jyWZ/hPM7tzODt3CkGbgno3n9qGoCf/4OzRSZamM9/RWkGSmeKSaW07b5UhVwQtqWblgFJpufPqp5NvWRrswpFAUCMnJESQuDZJp6tf6wtAb0gYdOPaQcJUm5f45s1V/tJT4UQ1Es2YOPZJhc3tp08P/fcGlv9mLm6q0GWSql5lg7wXu/zyPktoiQlSiVmzmxp8w6DsqMDpi3TYKOf8J4Tk5yaqfLfnlnRUlGhnUCHG8Mql1SmUhIm2hBlrOQQZZI0THNHTg1pBDBZcam4NpMVyWIU4FkGg0TmoFY7EsY5i2UAJcei7Fi5TFHgGiag8/cSJZHoUGchBEmqCOMUz7G4a7bKiekyV5sDfuwdh/m+U9MYOWv2m49e4/GrLQwoZvCyXJIpcjMTy4C6Z5Nkmm0xDbHruIxcMllcD7at5cM4I7PJWUWLwxNlHjw4zkonZLMfUbFNTs5WqZccxkp24UjoRykyN5WZrrqcmq2+LGZ+yB4+c73NxQ2f5XbIbM3jxEyFNx8a15/nR/SjlDDR135+3Lupnfzxqeqee1OoLD8e/b1wadPfFeYN5PEbTZ442uBtRyZ2SXV3zuXtBHDXtnyeWWpTzhnolh/typ1zLc3aTlcd2oGO86iVNABJMkmUaoOaE9MVpmsuftzeBYgdS5v8vP3YxJ7GeCf7sfMZ1Pf57bMfOzfIDAHjJZuVTqAdXw3NSmdSy2tbg4T7F8Z4z4kp5nZkp70SMTEjg4vXZ72WkUCjGtUrVSPANqrvqXql5A9L7YDLmz4Lnv6hVeg5tcZRh16Y0hrEBEnGDz94YJfhwJ0ex8FGuWhgFpuDPAOsSpKqXVKqnbvE/TDVwcY3ur3lr2uUba42fbb6MVEqkT1F1bNwTIPpmsexqQobvZCrWwNqng7lvfGHawhmtvoRc3VvXxDym9+8RpjoBmh+zKNke6z3Qr5xaZNz6z3+9gdPcHq2zntPTPFD983x2NUmd89XubDuM4i0nFPLNTMdlWBoVsjK87+GYdd60XSjqlkmmK66ILQBg5nnWzXKDgpFnGSs9CKifKYKNBu02PRZ7YR863KTv/vhU5ye1cxPzd1rkpDIbenpMBR5Z+1kapfaAU8utmj5MVe2/F2M54mZCvNjHs9c1zb6aY4WdW62lqq2B5p5SzOJYcBH3zTLejfij19cx7MEUaqHyyxD0ItSbFPLXaNUN/8rnZBemGoAhG7aTVNTZlEqyZQkSjIdum0KGhWHWctkqR0U4edlR897HRgv8dChMTzHIkokXzm/gSGz4pzLnkt7oDcL+rk5zjcvb+FaJrZlUnFMGhWHE9PbDMIjFzf58ovrSKXfYxgxIXe4lgqljWmUSkBogOaagihVxZyjKQABqdotjzTQkQ+p0hsBZ5a7WkZcsrEsgw/fPYtSiudXutQ8e9dzPGRLj05VWO+GlG+ykTO83kP54k7gc2mzX2xsHBjXmyUrnZC1blDMTh2fqRAspWz5MalU+FFCmjm0fP2MOqZRBG5//vk1Pv6AcdPGP1OKsbJdMEb1kl3Y4m/6Ed0g4VNfucRjh1s8fN9uGeSNmyoAv/6Nazx3vYPnaLlrN0g4MC5wc3pb5LlwnmMx71gstwOCONNy2tytNUol42WHiYq7DVBzQDycrf34/fN7GuNXiv3YuUGWZIowzegEKZt9HdvhWDoeYqkdcLCxPXf6SueijQwuXr81ysAb1Ru9RoBtVN9T9Uo1AMMf3htryLKUXZMrmz6Dm+RvvZzj2OlGeaOUaijd2vJjXNPk7cca+JEsjE8sQxthKCX59rU2QmjQlWbauKHpS+olm/smSkxVHeI04+3HJvj4/fPcM1/f88O1G4QMCsv84SzdXN3l0UtbTNdcHjw4TmuQ8MJKm9YgJs0klzZ8fs6P+V8/fi+n52p87P45VrohTT/mTQfqnF/vs+HHuVOloFqysAzoBCBF3qQrDc7yf9TrD9RLFmXXYgoN2KJcRoVQJIlipRtpJisP482kQglBJmGiYhYhzH/2LQs8v9zVUQNK7QJZjmngWmYhGb2xdjK1L6x0ObfawzaFdqvMGc+h2cF9B+ostgYM8vyvIbMkATKFEuhGWpgkmeILz69zaq7K4ckK3TDh0oaPMLQ7pWnozLgozfIAcL04gjwiQWkjDtO08OM0Z14jbDPBzKVgBxtlTENwaqZCmEqa/ZirWwPSgXaxPLPaZ6LsMFG1KTsm2ZDlEkLb46eSwQ7Z6novplF2aJgG11sBgyTj+eUOAPN1L3fkyzg4XmI1nzMcsqgCDcRVfq2HcljHEji2iZ3o2cYgVUTZNuO6UyhpmSKXTiomKjZjZZsgyji/0afsmHz8gXkeOtRgpRvuehaFgNYg4WCjzEfumeV3n1i6JSMepZLPPLHEZj/elevVHMS7mLBTszX8OGMQ6znTp6+3CRNJJw9pzpTCNODcep+zq33qnr6fG2WH+TEdFn150y8a/2GgdJqlHDPAEvqip1Lfm1v9kMeutBjEWu5a9ywmKjbPLXd4YbWLUop+lOow74qLaVD8N9CsteeYVPMZ082+DvVeGBeUHAuVh94rpbAtg5may30LY7i2iWMa9MKE9kBHM8Duja04nwtMM8k98/V9vytfCfZjuEH26KUtWgM9Zzo35tELEvw4pT2IKTsWJ6aq/Pi7Du96z1cyF21kcPH6rlEG3qjeyDX61hjV91y9Eg3A8Id3v1JKsd4NCRNJN9CNyn4A8E6PY+eP/X471UPp1lTV5e65MQxB0RTpQOaML7ywziBOOTpRpl5y8GMdQZDk+VMX1/u4psEDO+aL9qsXVrucW+vttszfMUt3bKpCJ0g4PVujNUh4arFNEKdUPf1ax0q5uN7nk1++wN/58Mk9azFZcdksRZQcE88yCZKMtV6oJ9oUmENv97z0rBe5S6L+2hrazx+ZLDOIMta6EZlUWhJpaYCWKIVhGFiGZkn9SDJbc1nuBPz6N64SJCnjZYe6a+8CWQ8eGqfmWqyEIfYN1/ZGG/T/7zeukkrFRGXbwGVnqPpjV5u0B0nuZAiNsl7LIMlIpI45UChOzFQ5PVPjueUO59Z6OJbB0ckyrUFM1bWRUrHW0axYkktHbcvQc1xCUbZNBnFWmJZkSuBYgrKdR0+ECY2yw19420HOr/lc3OjTDVJWOiFl12SsXCFKJK4l9Cyar6MVxioOEBSyujgPIB9OH0qpNxI6QULZMdnqx/yrL5zj3vk60zWP8+t9Kq7FIMkIkrSQ4urrqYpogJJt0o8yHedQcbAMwcDKtMw1/7wb4ykEeo7OFIKjU2UUgo1exCDOQIEfpfzqn1zihROT3H9wjM1exKUNf8+zeHyqyjOLnZsy4ufX+nRDfQ0PjG/Lgx+72uTa1mBXxEajbHNyusLFjT6r3YS11YiSbXDXXI2pmmZb/SDLDVZEPnNosNEL6YYJkxUdQTHMKFvtRDQHMUJlvO24DukeBHqOzA9TnrjWojmIsQ1BS6rCSGiu7vF7z6zQD1Omqg5LraDYdDk+VeaxKy0Q8AP3zBT5ko2yzXjJpjVI2PJjFvJ4h/GSTZho0Dpb94r8Mv0saIayG6bMKVUoAuolW6/dev8lVQ3fKfthGIKPvmmGz59ZZaMfMVd3cSwTzzKwBoLJqsNkxWWyuj13+mrUyOBiVKMa1atVI8A2qu/J+k4bgIXxEsemKtDXP7RDXdZwgH4oJ/xP37zGY5dbN7VrvpPjuPHHfj/p1unZGpu9qNjBHUr1lFL8yfk2/UjnJ5Vyq/DhsPuWH1O2TabrLj/2zsO75ltuLCkVj19ukmaKRtkspFE7Z+nOr/WQSjs/XljvE8TprnmaimsRpxlbflQM2e9ci16Y8Jknl7nW9Dk5XeGRi00GcUaSRiRSz6uZBrg7VJ+Z1JKiimsSJhmr3YiF8RL/nz97P5v9iF/92mWeX+4wUbbY8hOSXMpn5G6GQuhmV6Hz2joy5tBEmV6Y5iYJ2yDr4nq/sKZf7YYYhtiXIV3phmz0QubHtBTOsYxiDYQQlB2DCxs+IDjUKLHRjwhTiW2KggUVuSvjwUaZesmm5lmcW+sTJRm9IEEofX0tQ5s+BDkLZRraXEWgJYFCKSq2QS+WZBkYQpFm0M2jJ8qOxUKjxIV1n7/xfcdZ7gT82teuIAQ8sDBGO0h5arGNnzst9gIt1wsj/XlDt1GRoyWDPHg9P75UKpRSLDQ8QDNfZ1Y6XNsa0KjYtPxEz1TmDpZaEqpIFFhCO4UqQAjFeMmh4ul7+Foz2CV/tEwtpTWAsmsTpRlHJku849gEnSDl+eUOAvBsg3YOSH//2VW+em6TD5ye5kceWmBqnwzBj75phnPrPZ641mJ+zMvz1mRhMlQv2Zye3T3ruDBe4uxqj+VOyMGGBtcX132uNn02+xFJqjMQpVJcbw4whKAbJGSZlilLNKsogImKw1o3Qik4OllmvGzzhTNrODlzW86fQ6W0QyYInllqa7CWr6drmSDg6esdZmpacplJhSkE9cq2c2PTjwiSDMcy8GNZ5Eu2BglVT4Pr9iABpRivOByfqnB2tQco5uoumVIEkV7byarLX7h7hj86u/4dqRq+U/ajZA+jJETOcMaYhsFCo5y7+hrF3Ol+n/NK5KaNDC5GNapRvVo1Amyj+q7XdytQ9DtpAAxD8OF7Zjj72FkubvjMjJUJkownrrZoBwmNss1Dhxt4tvmSds23exw3+7HfKd36C289xBfOrO3Zwe0GCRu9ECklrmvjWNtIZzhDMogzlIJ6yd6TG9YLtaX2UOp5ITch6UcZTu64lind+JUdLSusew6DOGWtG+b26XnAs2GgUFimyfxYadeQvWEIbbvdhrcdbbDWC3lmqctmP7eit0zSOMtdA2GIlBOpDTAqjslyOySVkvmxEn/nw6e4O5daDeKMf/G5F0nz/C6Z51+VHAvb1GxAohT9IM3t/y0aFYckUzT9mIpr5Q6IiosbPu86PslPvvfoHov0+w6M8cChMVKpuL7RJ0wld83VeeZ6m7VuiGnozC/LMIqcvrGShW0ZzNU9mr5e6ziVGEJfn7GSo+fy8lIormwOiDMd+Jx1Q4x85m9YQ1MOQ0CWaTnkMAzdENvsV6w0eHnzoTGOTVWLcHQhBN0wyefNDCYqOmPw+eUurUFMkimiJCucOlFomWkOBBXbodlJJnWGmlK0BwlVDxzL5OR0lUsbPkGsc/aiVJudaFmfKHLmdMSAYmjgn0iJIQTjJYctJ8aPMg180ODHtTV74scpcaroDBK+eUmDfnLTnrVuSJxKTEMwU3Pxo4xHLm0RZZK/+r5je+3zn1/Hj1LWuxFXtwaUHZNDE2VOTFdJpeLwRHnPPJlraSnhRi9isTXgwrrOMGv62tzGNEDm7p6rvYi1XrTtixrp67Iz604bxahtN5X8b1EqCyce2zKoOhag6EXaLdWwoOTaTJQdvNyW//nlkDSTOJbAzKMbhpsuK50QP0qxTZ2rNlV1C6fP1iCm4likaYxrm0xWXGqezUfvnQWlTWOubO7NojsyWX5NTR38OMWxDN51fJJBnO1xnNyZM3ljvZK5afspKxzT4PBEmbceaeBa5k1VGaMa1ahe/Xqjhtq/bgDbP/tn/4x//I//MX/v7/09fvEXfxGAMAz5h//wH/Jbv/VbRFHEww8/zL/7d/+O2dnZ4s9du3aNn/7pn+bLX/4y1WqVT3ziE/z8z/881o6snT/+4z/mZ3/2Z3n++ec5dOgQ/+Sf/BN+8id/ctfnf/KTn+Sf//N/zurqKg8++CD/5t/8G97xjncU//12jmVUL11vpEDR49NVzgL3ztc5vzHgzEqXXphyfKqSh8HqBvuVtGu+HRmlYbAL1AVJxlPX2qz3IqTSUrvldliE1YJuquM0xhDbksLhtXhyscW1rQHdMClmgaJEMlayCBPJZi/ac06eZXBkosTjV1ts9KLCSt8wtFmBKQSHJ8tM11yubm3nKN14/eNU0gsSmn4ECDzLoGwbhImez5F5krYpNGsHkGaSsZLNQ4fHOTK53XTfM1/nTQfqWKbguaUuV5s+JcfEzp0es7wx3vBj4lQiyLi6OaDqWVi5IUGYzyQaaCBxZLLM95+a5onFFlt+TBhnXG8OisDiLFMstgYkWUYqJRv9qDAJMQ1B1dX5b3NjHv1Qs5AHxs3cmELbjg9iyURFG6Zc3OhzaaOfh/9qI4eqZ9PsR0R5Vt3wfJJM5c0+pLHENnR2mSng6FQZ2zRJpMQSesYrTCRJqo/x4kafmbq7yyBhGCDdCfL1EToPb6HuAiFpDmZhW5ZoCA0EVAEUNYgcxBm2IXKTFcX1VpBbtw+PO9MMowA7Zy+jQaJZOwVNP6FkWznwN5isGvhRljNwEMUZgygrmLcglZQzSXMQ41o66kHbupskOZj1bA0sr7cGu57VnW6ohyfK3DVbY6MXsdwJqDgWDx1usNga7GtIUvMspqoOV7cGXFzv40cpfpgilcIxBakCU+l1LFwtlZ7RC4fHaBukUhXzqpMVlyvNAa1BzOGJEhc2fNa7EZaQcFizxCemKyy2Qk7PVbi6OaCUz6AVzo6mwVpuyCOEfh6HJYSg5lp63lQqPf+JZvjedkQ7a275MWkq+VsfOkmj4hRNDXDTRmc/NcF83WOlG3J2tfuqN0ZDSXmQZHtMguDm82OvRm7azrV4YbXL45ebrHdDPvPUEp99bvV1+5s3qlF9r9cbqQe9sV4XgO2xxx7jU5/6FA888MCuf/8P/sE/4Pd///f5z//5PzM2NsbP/MzP8CM/8iM88sgjAGRZxsc//nHm5ub4+te/zsrKCn/lr/wVbNvmn/7TfwrA5cuX+fjHP87f/Jt/k9/4jd/gS1/6En/tr/015ufnefjhhwH47d/+bX72Z3+WX/7lX+ad73wnv/iLv8jDDz/Miy++yMzMzG0dy6heut6ogaL/0/uO8fRyj0995SKTFZe5G5zbXmm75peSUe4EdU8utji31iNMJBXH1MHZEvpRQpxJ5upe7synrdtPzFRZGC8V1+Jac8BGLySIUz0blWmDAakU3TAlU4os02YDw4Z8aNLRz+elwlQWUjUlFUGcYZu6wV7tBEWTdG61xye/fIEtP+LAWIljkxWCJNNzgAqmKjaTVbdgB3tRipAZ0MW1DBYaJY5NVal5NqYhWO2GfPqRK8V9szBe4mQ+A/bQ4XHtqBmlVF2BIfQ8U5IpPfNkCKqeSc2zaA5iekFKyTaYHC8jhCJOtaHLL37xPDM1l/YgYbMfsdgcYFsG9x2oc3yqih8lnF3r8ciFrTxCQFAq2YX5Rz9KcS3NUgxlUTXPwrGMPJNLs2xJKvnKuQ22+nEOGhUl26KWW75bpkHZhljq65Hjaswd7FeWuy2SM7IL4xb1kt5U6Axizq/3WcqB4L//yiWOTJaIkqxw1nv00hZbfpTHHmiJY5hI/EiD2HrJYpCmeu4s/9g405NlQ4JoaCIC0A50WLEpBKZhYBkmB8YtrjUHpFK7XpoCSpYG6IYhij8vlQYwkxW7uOc0oydIMy0jtYS2+k9SCpdMQ+jg+CDOilw/FKz3wjzbTeJaJk9ca+2KZLgx2mF+vMTcmJ6/e+JaC9c09jWSEGLIGAcst0McUxAkeg4vy9lDQwjSXPo6lLVapoHI9KaEEIosk8zUPebqLiBYbgc8sdimPdDgWUqFMPQi+2HK2dU+UsFs3SNOtKMs7o7jMnJAbehrspNxByi7Zm5WA1VXb+pouXeflh/RGmgJ6B8+t8pH753l9Ila8f1zq++3nWqCC+s9PvXVS9+1xujlzI+9mrlphiGI0oyvvLix4zdvb4TD6/E3b1Sj+l6sN2oPOizjpV/y6la/3+cnfuIn+JVf+RUajUbx7zudDr/6q7/KL/zCL/ChD32It771rXz605/m61//Oo8++igAn//85zlz5gy//uu/zpvf/GZ+8Ad/kJ/7uZ/jk5/8JHGs7bx/+Zd/mWPHjvEv/+W/5J577uFnfuZn+NEf/VH+1b/6V8Vn/cIv/AJ//a//dX7qp36Ke++9l1/+5V+mXC7za7/2a7d9LKO6dd34wzhsumuezamZKk0/5vPPrxVOY6+nMgw9QO/aJjP1vTbbQOHc90rZNQ8bn7vn6oWUcGednKnxN77vOMenKhyeKPOD981y93ydsmPhmHroP0r0DNlw3mum5vKjDx0CKHLD0nyXXzMXgrpnaYMPoWdrstxXf9gka4M6RZQoVjtBbu+nrdajVBXvVbIN0izjueUuJ6Yr+FHKz/33Mzx2pclKJ+CZpQ5PXmuTZJIT0xVMQ9CP0mIGTB+LzXhZN8iGENwzX+fwZIVGxaFe2nvfDCWlExWH5iDhgYNjVByTXqRd7JJcHjZesqm6NqBlkmneOBuGoO6ZpJlibqzEwfESTy+2+dr5TcY8mziVhevk+XWfTpBQ87RJQ5xKwjjDysHg8O/D+b+nFltEib4/rrcCrrcG+dyXbuq7YUI/HN47ikxqiedGP6SXyydTJbScKpc+SnTMgZR6/WXutGibBkGc0fRjlFIEccqWH+GHKa1BSiZhqT3gK+c2eX65y1PXWoWcU0rN+JQcE6n0TForj0aIkkwzbEKw826MM1XIFYeB6CXL4OxKj81ehGUajJUspmsOjmUyXXMxhzNrSjFIJEkuYdWGMVoy1g0T/Fjn0HWChCiRDJKMREo9NwegBJ6jIyGCROdsCTQw83NZHEKviW1qmaofp5xb6/HCave2crPWuyHTNZeVTqjnWXeUUoqNXkzN07mCzUGcz2DqdSjbenZSQBFjoNDXdnjtLcPg6GSFtx4e//+z9+fRlmX3XSf42fuMd3zzEHNmRM6plFKzZGGwLVmGNquhcVMUFJRbUIvCy9CAay1YrEWzoBp6NfyDqbara4Ci6K62gR7sAtvYFpIlW7aUmlKpnDMiY45487vzPdMe+o99zn3vRbyYUplSROb9rpUZEffed86+Z3hnf/fv+/t+SQrDXD3gq29uszvMUNpOCHK1Z98TzlwmU3RHOWeWG9RCj91RXrqH2jJ83NKK3SLI/vcypdkaZMzUA84sNzm3NeLK7ohvX+6U/XqOlKeF4rdfXufv/epL/MNfe4Vzm4O7/v1VTYxeut5jth5weptDP24AAQAASURBVLHJbN05V/7L3794T9u6W+y//89uDhmkLkZjkBaH5kzCveWm3Sse5GfeFFO82/BuuB9/4BW2n/3Zn+Unf/In+cxnPsM//If/cPL6t771LYqi4DOf+czktSeeeIKTJ0/y1a9+lU984hN89atf5ZlnnjkgS/yJn/gJfuZnfoaXX36ZD37wg3z1q189sI3qM3/jb/wNAPI851vf+hZ/5+/8ncn7Uko+85nP8NWvfvWux3IYsiwjy7LJv/t9Z6NcFAVFUdz2uFTv3+lzDwqudRIubvU51g6RmAMOgAI41g65sNnn8vaAY3P3h4PW/nMQS2j4gjRzsqUbkWWKui+I5ffvnF3rJHSGKU8sN2jGPo8t18nygn5iyY0hyy1JmrNjNSdmYv7KH3mYU3MRXz+/yXcvbxMGHsMkoxkIxqmmGQr8sgctySzGarRxfUpSCBpBgNYuQ6swBdv9vCRnzhBkz7nPMs5yrFa0aiGLDZ//4ctnubIzYKkR0IicTK0zTHgpyzkyEzFf85zpwTBhth5M+qIGqSMLy01nulCFB7v93HzdnJqL+c8/fpwvvLrJhe0R7zvaZL2bkWs9CScXEkLpeu4u7+QYA81AopSiO0ppxwFnFiLe2OjhWY3WhrXukN4oZanhetE6o4JL232CpSbDcUbNd+Qrywty4Xq92vWQehiw2UtRyiAjycNzMbk29NPC5Y5pg9GWJDNkyvVt+cIS+EDZM9iKPKxxtu4YCEozFnVz2gAAEo0vJKMkI6v7buKqFFIYQuGs9puRZJS5np7LWwO0tYRS0IidWcw403jWEnkWrRyRVEoRexJtDZ530Fq/Oh+h58Y/SnO6oxSLpTd2Ej2vFfC+1Qa1aIZXr/d4Za2PL1z1p7Lm18YSSFdxyoxhu6exWCSW0C+rarieRoQjPK2yz7NyUsUYfGEJhcH3JY3SuSYtDPN1n/maz/Yo59sXtjjSDihUQTMID1xbFRoBbGvFh08ukeQF5zf7ZdVakuSGN7eGbA8y5uo+diZEaeP6AwEPg1YGTxjk5HhZIs8tiHjCyVu1MZzb6JMrxYm5GsIaRmlOKxQM0mLSz+mXWygKRc0TKAEXtwY8vlznQyfaXNga0RkXZFlOURiOz0YcK8O5L26P6YwL8rxACkEzkHzyzAI/9eFjfPHVTX77lU0G44w4kBhtqMeSuboLnd4eFjx3fotCFfz5T5zi9NLtXRaNsfz2i9fpjVIeW2qURMjQjiStpRpvbo34/EvXOfGph992eeSN9/9238kg33+0yY89scypufjA7+f+OL3z+VeF+1wruKfn8oP4zHsQ8G6bGz2IeBDPwf18P97tcRT2xiXD7yP+9b/+1/yjf/SP+MY3vkEcx/zIj/wIzz77LD//8z/PL/3SL/G5z33uAOEB+NjHPsaP/uiP8o//8T/mL//lv8ylS5f4rd/6rcn74/GYRqPBb/zGb/DH/tgf47HHHuNzn/vcAUL2G7/xG/zkT/4k4/GYTqfDsWPH+IM/+AM++clPTj7zt/7W3+LLX/4yzz333F2N5TD8/b//9/kH/+Af3PT6L/3SL1GvT7NApphiiimmmGKKKaaY4r2K8XjMn/tzf45er0e7fXheJfwAK2xXrlzhr//1v87nP/954jj+QQ3jHcXf+Tt/h5/7uZ+b/Lvf73PixAk++9nP3vakgGPcn//85/nxH/9xguDmBuoHDdc6Cb/4O+eYqQWHVqiGqaKXFPzsjz5y36w23ngOzm8N+V+eu0xnlB9YZV/vp8w1Qv78x0/ecfX57cStjqm1lmGq6SQZ3XHBn//4SXxP8vlXNstML4+XrvUx1jqHx3KVOww81yNkLGmmGSuFBBphgMGy2q7RjD0u7ozZGbnKV7U+ftiqTzOQpfGD5KMPzXGl61bwQ1+S5i53LS97l2ZqAbujnMBz8tOjMzGdsaI3TvnrTyT8d+caLLbrLDZDru6OudZNSQo1CaFebkWszMS0ooCHFxv8iQ8ePaBFv7o75m/8m++Q5IrFVjSRP2WFnmSLRb7HD51Z4OLOuHT6ywGLROB5klQ5owwPJ3WUQhAHHjtjZ50ucGYsQoA2diKBC6QgCjxmay40WeBc//IylPvUfB1lYL2fIIFuqpDC5ZIpbalHHsO0oPQymbgMHlbhqs5FM5BYYKEZORt5C6vtmNCXrPUSVNmXGEhBd5yTaUsz8gg8OelZ7CcFhbGE0vJ//ojh//RNiSc94sBjN3ErgpIqXsAFOmf75CQC15/WiF2lJskVQgpOztXYHmYMEkUc+SzUQ9d7qSzXemOGuat0eMJVQq2A+XpIZ5yjDTQij1w5KauQTlopnbcikSdp1Xxqgcd6LwUgCryJKYcqpYoPLTbICs3/8cce5ffObfPKmpPu3tj39ObWiKePtvmLZTXIGNcLNcoVg7Tg//PNq6UxjDPxePFqj51RxtYwo8pbr+IPJtEEZWXQve7kpZEniEKfp460UdawUI/40uubk2NhgWjfeciNIPQEZ5aafPDk3CT6I/I9Ti81+LEnXO/1//sbV/nGpQ69NHeh83HARx+a509/5Pjkd9UbGwP+u7I/91uXOsSBINyXQelksQVPHWkjhbjj7+hqew8vNA6toGljuLQz5r/8I2d4bOUH2y9ijOVffOXCXZ//e3kuP4jPvAcB77a50YOIB/Ec3M/3Y6W+uxN+YITtW9/6Fpubm3zoQx+avKa15nd/93f5hV/4BX7rt36LPM/pdrvMzs5OPrOxscHq6ioAq6urfP3rXz+w3Y2Njcl71Z/Va/s/0263qdVqeJ6H53mHfmb/Nu40lsMQRRFRFN30ehAEd32R38tn72ecXPR5aKnNS9d7PBqHNz0Yr/Vznjk2w8nF1n1nr1qdg8ePzvHTn/InDkPZICfyPZ46Nvd9s67ej1seUwGZUbx0fYTvSf7tt69zeddZfH/s4TnmGxGtTs7mICUOA7qJchbxxhAHHqmyBJ5HXoYYpwaacUgcBYwLwzDT5FrckjhU0NYyUwvoZ4rr/YJmLWRrkDFXl2wMFaMC4sB3JiUKji00iX3Jm1sj1voDGpHPidkakKCt4OJuynevDZyFvLVYY8nLSfGok7E2LJitBTx/rc8Xz+7wl/7Qw/zpD59ASoH0fQoryYxEWUnVhSU9ge8H9PMcz5Oc30nojBWj3JJqJwUNPM9Z3Ovy+FoYlVloFtdjpa0z0PCQLjcNS2ZcT18gQfiCOAoJfMkoVawNxnhSkisYazeRDgNFP1UoK8q+NGeiIRUkWuKVRFDd4oDvPxfKWBqhxzC3hGFIrjSptlzsjMkKgydBFG77wjqDjEFmEUKXGWyaTMH+brXMCPLCEmtNYcTEzCJVZt+YxOT/UoBW4GuwQoDnM84Ur22OS5t/QTcruN7LJ+6Jdt82Qk8Agiw3FEYR+gGZUgjlrpuxVuS5wVon5RUCfE+i8VidaxLHIWluSsdLGBZOculJeHFtgDHw71/a5OOn57nWz3ljKzkkNyvmx993lCgKJ8fhoWX391eu99hONH5g0Rhm6jFPH5e8fL3P5lBRGIOxZTyFcL2GVdyCtqV81HP9goU2GAXX+jlbw4zYG9PLDIXZO57VmciMQBlBYWGQGf7zT53GK3vzKoOi89vDSXP9hx6aRxvXJ9kZ54yVxfN9gsCFsY8Ky7iwZP2cRFniMGCUm0mMhwWs8KjHLoMxNdz2mdSuxwR+wLCwtA6ZGI0Kg+8H7nP3wbPts88cvafzD3f3XH6Qn3lvJ94pC/V3y9zoQcaDdA7u5/vxbo/hD4ywffrTn+bFF1888NrnPvc5nnjiCf723/7bnDhxgiAI+MIXvsBP/dRPAfD6669z+fLliXTxk5/8JP/oH/0jNjc3J26On//852m32zz11FOTz/zGb/zGgf18/vOfn2wjDEM+/OEP84UvfIE/+Sf/JADGGL7whS/wV//qXwXgwx/+8B3HMsXt8W4JFP1eA7nfTtzqmK51E75xsQPAR4+1aUYBZzdHaG144WqPZ0/MToJyC+1CnLNCYzxBmhgCTxJ5EHoSKwTGQjN0HTRJoVHGkRPt/Ce4lai66rHypWB7XPDRpSbDTLM5yEuDEde3pLTb5/G5Ogv1gEFasDnI+eTpBY7PhpDu0ogCtnYTl2vGXtWiIgbGQpIbsC68+tLOiP/rf3iN19b6/GefOIUylsVmiBBM7NOrPjnPc5WyXBnOb48ByzjTzthCgBSuYSqQgkzvUYrAg1wzsWwXpdujV87QTVlikQKOzdSIAle18EpDEmOdIcY407TjgPlGRFIYhBBInIOIFZCWhKMW+SS5Qt2Cse0/HpEvWZmNma0FjFLNm4OMnWGOLp0lpXD2gS6nzBGgwjjb/3GuUVVTYlkNAtc750wXhXOntLa8dtx+fVn2lpVjMRassfRSR6SNhXGhJ9dLVT0bF4d/H6UttUBiPOesaNH4UqANpPlev1G1r3rg8dBSg/cdbbM9LGiGActNjyMzMdtl2LsSrpI4TDWz7YDLuy5y4seeWL4pb+/GDLH9E8+tQcbvvrHFm5tDLm4PiQOf+XrImeUGTxxpsTPKCKVglGkeW20xzApeuNJzQePVfeEJGmVV0+Js5/tJQZprRFhen8ZMvuNej2hluAKpckYt+50bb+V8ONcIOTlfnzgfGmv5/MubnNsccKWT0B0X5IWmmxRlpp+rBiPg5HwdXwpCz1Veb2fT/1bcGt8J3C1RuJsolbeCd8sz73vBg2yhPsW7C++G+/EHRtharRbve9/7DrzWaDRYWFiYvP6X/tJf4ud+7ueYn5+n3W7z1/7aX+OTn/zkxOTjs5/9LE899RR/4S/8Bf7JP/knrK+v83f/7t/lZ3/2ZyeVrb/yV/4Kv/ALv8Df+lt/i7/4F/8iX/ziF/m3//bf8uu//uuT/f7cz/0cP/3TP81HPvIRPvaxj/HzP//zjEYjPve5zwEwMzNzx7FMcWe8Uw/G7ze+l0Dutxs3HtP1XsrFHZc/9rGH5lloRmwPMwSwWNrTv7k14iOn5iZBudqMGOcaXRIBazWBFzDfjJDSuSpmpc29NVAPPYw1KGVvSdYq7I4KQl8wShW10OPZE7N892qXnVGGUIJMObJmreW1NSfT3B0XBNJVmCqcWW5wcTedyAx9yYR82NI+XVtHbuqhTzt2+Wa/8/oWmTL8sWeOsNiMWGyGrPUyOmNHGn3piKK1lpeu9cgKR2CFcPJGV1mzhJ6rboGrmFSumoJSChk4iaS2FlV67lehyY3In+Th2fJ9N3G3hFIiBVzZdVlaczWfpFCkuSUOPeYaoQswTwvW+6kLyubgBP5G1EKP47M1RrliLTestCK8kmyBIzeZNnhC4JRvLuIg9AKudhLnmLmvXudyujS+lEhhKZQjmsZCP92TL97ogVI99rS2DFOFMhZjXAZZ4LnvnRTm1rLa8v3IlxirUdpde0dnY9b7GUVegHWOpCfn6zx1tM2JORduHfoel3fHxKHHej9ja+AqzM04YJQp6pHPU0dmmKsHnN0c8vr6gP/yD59mrQxW3j/BN8byB29u8x9f2WStlzDOFVd2x4AzDVHGEnmCzUHKICt4ZLlJ7HukheGhpSbH5+p892p3cuwrE5HIlwSedOHmypHkQhtmawGeJxkkhzeiexK8Mke70JqzmwMEjgw3Qr8Mfr+98+G3L3d4bb1PLymYq4c8sdrmhSsd5yyaKWZqPqHnkSqDNe78ffdqj3rk88vPXSbTZjL5/vGnVqiF3oHj9oOeGN0rUXinFuLeLc+8t4IH3UJ9incfHvT78QfuEnk7/NN/+k+RUvJTP/VTB8KqK3iex6/92q/xMz/zM3zyk5+k0Wjw0z/90/zX//V/PfnMww8/zK//+q/zN//m3+Sf/bN/xvHjx/nn//yfTzLYAP7Mn/kzbG1t8ff+3t9jfX2dZ599lt/8zd884D55p7FMcXe4nypU7xbsP6Zvbg355ecuc3Q2pl1zMp7Qk/ieRBloxj47w4zr3YQo8Fhph6z3xszUAt53tM1SO2KYaXrjwtm7Bx7aOGmTV2ZgfePiLsNc4ZXByneCMZZca85uDnnm2AzvPzbjpFmZJvBdlMBM3TnsrfdSBkmBEIJvX+ywO4g5vQy10Hf27akjZ67apCc9YRVZsKUcMfQ8/DK36lo34btXepxebPDyWp+PnJotZZ2G0JM0Qslvv7LJQjNyBEwIOiNXqcu1oTcuUNr1pEncRNuXkoVWyPVugtaOXAlguRU7O3ygO8oY5ZqFZuh6/qxlkLm8uyQ3aGMpPEsxdNEKeugkaALLbD3goYUGZ5YbLDYjvvzGlrOohwmJuPHQV26eR2ZiGpHP1W7CQiPkfUfbrPdTdoY5mXKZadaClJbAc5WcOPB4bLlJLykYZmpCWoWoAsuL0hrfkCjHOqRwuW8GJrlwFaqKY1V9LLRBGUdw4sBnpR2y0c8ptJ5U8PZfS36pAVTGUpfOjj8tDBb48Kl5NgcpX7+wy0wt4IMn5zg5Xz9ATmqhR+RLfvKZI3zz4i4vX+/hSbdAsNyOObPUZL7h7o/Kun2tn960EHNuc8AvPXeZ33ltk3GhaYYeo1wzTF1Wni3PxzBTLDUjxpni8s54EiS/0Ah54WqPfqKIA59cuzxEa11FTRvItSnJrAsc1wF8YLXJKFckg/ym+0lSBqQD3XHBP/y1V6mHXrkgEdGu+WwPM47eooIVBx7nNodYa6kFHtc6CX55bGLf9WoOMuca24w8mpHH9jB3fWxHW8w1wkme2Ncu7PDbr6yz1HL5ifuJ0Q9qYvRWicI7tRD3XnzmvZP5dlNM8b3gQb4f7yvC9qUvfenAv+M45hd/8Rf5xV/8xVv+zKlTp26SPN6IH/mRH+H555+/7Wf+6l/9qxMJ5GG4m7FMcXe4nypU9wPeDo1/dUxHucLzBI1oTxPdin3m6iFbg5QokGwPM751qYMnBd1xQaI0jyw1eeb47OTBaq3l7OaQlXbMfD3k/PaIca4IPcliMyJThkFSMC4n0Yeh6rvxyipd5Es6I0caGqHHKNO0Y58jMzFpYdgcZBQlKfEkFMawPUhhGcapwppSfimc1M7iJr6CPVnmpKpjnbkEwFw95M2tIX/qQ8dY66ec2xpxZCZmth6Q5JoXr/cptOWDJ2ZZ72ds9lNCX7jAaimREkr1InEgSsLo0Yo8mqFPP1UUypmnSCmIyuqIJyWrMyGn5hu8fL3H9jDHWJcX53uu2pJr1+fWCF2wdKIMnpScXmrw/uOzdMcFr6712R1m1AOfodVIYRElaTsAC3EoCaRko59hLTyx2kJZR2DOLDW4tDN25inljwSey57LC8X57RHztYCk0GjryKw2tgzydp8NfEmmNI3IoxUHbA+zSfbe/uPvzsG+v1cGHGWwdeB5tGs+/VJ+d+M1pKverwm5dNl2gSe4tDuiHrj75PHVFifmGzdde0nuDDiePNLm+HyNNzYHrLZr1AIXln4judsoK2v7cW5zwP/0lYt88+Iu1lpOzNXY7KdsDXIXJxC7apZfHqeNfkYj8tgcZHzyzAKjTPH6xoCsMCw2XR9hNzH40lG9XFsyrSYB4lXItTMDynlytUVvvIvW1kUfiMqARCCFKM1eBHnhbowdAYvNkAvbI67sjllshocemze3hmwNMmZrAXHDJ/BcBXyUKWeOUw8YZqoMeHd3ceS7BZ8zZXA9OBLeGWVsDXN8T/CJhxdICn2AGP3Mj5z5vk6M7lei8F575t1Lvt176bhMcX/gQb0f7yvCNsUU7zW83Rr/RugT+x7jXE0mVkIIHllusj3MuLSTYK1lqeW5vLRCIYUL4u2Mi0nVoXqodkY5P/H0Cu87PgM46d+/+foVTi3UeW19wBsbg1vmgVX9VFIKTi40WGyE/NmPn6RdC3j1ep9/9oWzUIb87owyssK5MMaBy9UqtKERuvF852qXUVa4gGYDOtdg91XWyj+ldD1zuTJEgST2Ja3YZ3eUs9iKDl31f3ixgbVwbK6OtpY3Nwd0kxzXJnUw961QFukJklxzrZu6ClDkI7AoYxmmBb4n8aTkQ6fahL7kmxc7pIUmDlyl0xhn3FIRGgsMc4MvDe3YpxEF9JICT8CHT83yO69tUZgqowysdb1PuXaVOdc758KrK1mmMXrSH5XmGk84svXwYoPLnYQkdw6bg1TRHRcYC4KcMHCET1tXaUS4EGhwhC1P3HabkY825qYg6eoaKfYZkVTFNw9HwgrtnFWXGiGePJjhtx960g/nCMvJuTon5uv82Y+f5OHFBv/+heu8fL2PLcdqrZ24JV7rJnzsoQWOzda41oX5ekQ99Cb3xH5U5K4R7j0Oq4n/te7YXZOhc53cGubO8AaX+9aIPKyFE7MxvVTRrgUsNEL+D596iN1hzv/lN15Fe4J+WhCHHi27V0lLysUO51xZXmNScmy2RpJrhplkqeVCrwvtstwoz3HkOdMRKaAZe9RCn2GmWO9nfOjELGvdlJeu90uCJPd9L8Nra32EgNWZCL/ccdVXWX23hUbI08dmEEIwzhTnNoeE1lKYSjZteXNzRFoYVtsxo0wzzjXt2kFi9Ff+SPP7OjF6EInCO2XK8YPEKFekSlMPD6/y3mqRZIopprg1poRtiil+QHgnNP63avifqwfUQw9wRg5KO0leLfBYbcdkyoUAz9XnJj+TFJpX1vr8D797nijwiH1XFdkZ5bz/+CzHZusMU8WVTgLcPOnekylarnYSrvcSPra5wH/60ZOAMzLIlWFrkNFPHNFpRD710KMzyhjnhn7m+ni2BtnE8MNt8+b9OCMQSa4tvoRASuqRq+IoY6kHHicXGpz+kSZXO2POb4+APRJ6vTvm1bU+w0yxz9Nib5+AstD2JVEgycoJ91wtACyh77HSjmhEPu8/NsuPP7XCv/76ZZSxZMpihaXIFYWy7N+8J/YcEse5oR4adoaKX3n+GoHvUShDWpp11EOPYaYZ5Zp66GGtk9OBk2qenK+zM8oZZppMux6+WuiVtvqamVqAV55fY8FqOzl+XnnMPCmw2n23lXaE57qlWG7FFLbgkfL6ypQLprbFQXKmtLlJKusJd5wFAoGhO85phNKZW9x8qCfXkiegEXrMNyLmmxEfODHLH350CSkFf/R9q6z1Us5uDqkFkuvdlK1hxihT1AKfM4sZ57eHPDTfYLEZ8span0eWmrRrwYFK8mEmGNXEf77uKlZJrsmVq2RVTo+FsYwLQ+Q5F8y5RsggVRyd8WhFAVIITi00WGpGaGsZ54oLWyMu7o7JtDmwyBCHLsJBG8dem7HPKFOstGOkEPSTnFACaGqBRCNJkwJPCraGGVIUhJ5grZcwWmnxvmNtnr/c5bvXepxZak56yN7cGqKtqzpruzcB8ITAky6SYpy7hZOrnYRxrhllit1RThxIxrkCIgapYne8Z94zytVEsvuDJEYPGlF4t5pyHLZwuB+HLZJMMcUUt8f0bpliih8A3inpzq2ckJyUK+PYbI2njraphz6Z0rx0tefyuHzJ7iinX/aPbQ0zXrneJy00C42I5XbMOFe8uTWcyK2Oz9WZb4SsD1J0JYuzB7PCJG4y2E9y0sLw33zhLF8/v8sPP7ZIHHjMNwJasU+uDXP10E3qhSiNNXI6I0fYcm0wVlAPXF+ZPmSW7wibKE0q3MRzs5dyrZuw0Ij4d9+5zh99xsVw7J8kRZ5ka5BxfntEL3GSzVth/4S2Gfs0I49uolhtx/xXn32M5XY8WSW/1k3oJgWn5ms8P8xcBQy4iQuWBCCQTi641svwJXiexNcWiSVTZpLD1ox8xoV2hi1lbl4YCJc91k9JckPgS5cbpZ3zY1JatPeSAlsapQSl5tBY50op5J7RSDPyyZVmkCrakbv+js3XaDciumNFM/Kph5ZhplHKlFEGDoW56euVboNurJ6UKGW43k2xe7u8JXLlegRPztcPmFVUDeT/r69d5vOvbJAUikbkszoTs9AIeXN7yD/9/FlWWhGXO2Mu7445X8phH19tEQeeM8GohzxzfIY3NgeTc1dN/BcaIeNcUyhD6EtHUqWrirm8PUNenldfCkaZ4uhsbXL+a4GH7wmstpzbHDLOFLEvUYEjUEK4ye2RmRjfE1zeTbjWTTg2V0MZw1w9YGuQ0a6FPLwQARlzjZArXReFUA894sBHWyddHeWarWHGqYU628OchxeadEY5F7YLpIClZoQp4ya2hxlhQ5YmLa5fdZgVZIVzJe0lBa04IPBgd5ShteXsxpBm5GMsKGMIPJ9CG3wpS3Mahx8UMfp+EQVjLFd2x99TVezdbMpxvziFTjHFuwlTwjbFFD8A3Eq6U8m6Il/ywtUuVztjTi7c3IdyOxzmhJQWhlbs8+FTcyy14sm+rndSNgYp9dCjl+Q8d2EXYwybw5wk1yw1Q8LAVV2akc9DC3Uubo/49uUuzci5yB2frbHWS0lumKlbXC9SVckJfUk/VfzWK+v8zusbSCnxhDMdSQpNQ2tqoeecFI1lqRmx2XNVME+6AG/fkyS5nvS6ATRDz1XVPDEhalmhQUBauKrd0dmIl9f6vLYxAJxD4/5J0uXdEduDDG3txCjjMB5hLYSBcLlpvkQIyfG5GnP1kIcXm5OJ+hubA9Z7KeNckSrnPBmVBi5ZcnASa8r+OG32TFysdiS1FjoS73uS3XFBWhiMsTRiFwLdiDxWIp+ZWsAwVVzvJqTKkBR2Ml5POvt9C+TGYq2rgMWBhzHuvKSFQZYh1FHgoYxlrhHSGRdUnWmjVLE11FzpjFltRzQjn0JbRrlmd5ixOy4mRL06/55wFZeqKhV60vV9STGRc/qlOUn1s/unvaEv8TxBPfD57NMrqHKiPHFwtJazGwNyrfE9waDsxdoduT6z3bFzQfyxx5dYbsW8vt5nrecqcY+ttDg5XwcLv/LtawcqHB84MVM6Pe7RaymcEYsnxCSwvWLhubZ0k4xa4PHpJ5eRUkwmrS9e69Ebu/upGfl0E0fa8tIhVQoY5pqjMzFHZ2psjzJ6SYE2rj/us0+tYIGNjrsXdobuuzUjn9D3ymMowHdOjWvdhKVmyGIz4seeXOIrZ3fopwptDf2kYGeUT0jp/oiLZuzRGWcoY/Clz1w9QBkXcdGMA0JPkuSKN7dGPLbSxJeSXGlGmWa5HR/IXPtBVVC+X0ThX3zlAue2k7dcFbtfe+3eLrwbLNSnmOJ+w5SwTTHFDwCHSXd2Rxlvbo7YHTv3vLQw/E9fucif/+TJe15pvdEJqZ8U/PJzl4nLLDBwE+nFljPkuNZNKLSTqtUDn6zQZS+Z4IUrXR5ebLA9yMuxGXqJ4j++skGuK0t7DrWbtzAhA7H0CD3JOC/IrDNN8KRgWFYwrnUSrHXEJQ7KMOFS7let4AvhKklgCT1JLfR59sQsShseP9LiN15c51pn7IxBQp8wkIRSstHPef+xNl+/2EEZwydOz0/iAFpxwLG5Ot+92qPy8dj/HfaTN4vr6Tqz3OTobK0cg8elnRGvrvX5d9+5zptbQ5JCMUo1F3aGKG1pxi4aoWwLO+hsWf37BpmnoDRXsRAFHq0YhpmTd47KXrm5Wo2FVkTgSS5sjxgVGg8XII11xi3K2LLPy32b1XZMri3tOGBrmBF4rnJUGXwIXAWmMy5cTptwlZPrvYzr/Zx+WpAVetKv5ZdmJJEvCSSMS6t+F7vgzEIEjuTEoSRVlmNzNbaHGZHvTC62BpmTSwpHjHzPEe966HN6scH2MOWXvnbZZeaVE+QnjrT4dy9c5/z2iFbs008UxjiJZ5Jrd66Uu6Y7JXF7fLXFQwsN1vsp86XpTDcpDpD3F6/1eH29j5SCy9tjaoELOcjLKIRCmwlZrJDkisj3+EOPLvJDZxaBvUnrGxsDLu2Oma0HqLIyVcl3PekiCCrJZavmo4xhph7w/mOzfO5TD3F8rs65rQH/369fAgNJobBIjHGurbXQ3Re5cosyw7Tg/PaIM0tNfvOldTrjglMLdeqhzygruLg75rX1Ac+emGFnWLA7zhllrpd1ru4qis3Id32UUrIyU+PpZsiF7TH9pGCjn3JmqUEj9LjaTVhqRpxZat5RZvr9wDtNFM5vDQF4Za3P8kz9rqpih/WovZO9dvdLT9yDbqE+xRT3G6aEbYopfgC4UbqzO8r4zpWuW4WPfUJfAooLO0P+5e9ffEvymP1OSMZYvnGhw0vXezTKPqitYcbZjYGTxlmLhyCQknGhMday1AqZq4es91KeO79LM/ZpxT6NqEZajNgeFeT7mpWiMoB6kKkDzn/uT+F6m0p7d1+A0hrPEyjjHAlzZbneTXh0pcnxuQYvXO5MJjOR76poudIoYzDWlrb+kCs3sR9nhtV2NAnirgVeeRxhZ+Sqhxv9FG0tv39um3oYTMKOB6maZGTtR0Wu9r+ujWVr4CakQggGaUGmDL/+4hq5MtQCSWdUsDVI2R7kZNrQCCWUpAVu3o+94UVPULoAOvLhxz6NsvroSRd0Xgt8TszXef/xWd7YGDAujVhsaexhLVRzQV0yQE9UNvLOSVMKUYZeu2qJIyLuM9IItDFsldby670ET3oEZbmsl+R0Rjm+J/Glq6J5nsTTlrl6MJGzOrrmrsFMGaRwpDHJtaugSTEh4tV4lbFI4XLKrvcSBqnixHydhxeaJIXmxWtdfvuVdTwpqJcTcmVsGUHgDEFybWhFHoNM87XzO8zWApS1+FJSDyTfutzl+FyND+xzRy20oTfOubQ7JvQlhXKErhX7SCFQaq8KOlcLaNUClLaszMSstGt84syCkzSWk+RHllv85AeO8Op63zluKndv1CKf5dinO87JlXZdgsaQZy64/OljM/xnnzjJyYUG5zYH/Ks/uMT13SFPLZaLIMpO4iPGhcYTEPiSGT+klyrOhD5Y6IyLAxWcdi3kYw/N8+U3tnh9fcgPnVko8/QKOuOcRugzSBUPLzbQ1i2KVK6aM7WQNzb6XO0kXNwZM9cIUcYR/6C8j++HCso7RRSMsXzh1U2OAWeWGiDdtXa7qtitetQeXWm+I71291tP3INsoT7FFPcbpoRtiikOgTGWa6WZxrVOwslF/219yOyX7jRCjzc3nbFB5dK4O8pZace8/9gM57ZG9yyPOWyV9Sfet8Kr631+6+UNtDHsjvNJcHXgSZZmnWGGUoYrnYRBppmru0nsKFeszsREvuuHG2YaT4JvnBFHKJ0d+TBXJQFwvUyyNNRwRMFOqkh5WZ3w7J6xRD308T3BYjOiM84pjOtrgxxPQCcpJpUJKSAzoLXh5et9PvnIIluDlIVGxPVeSrvmTB/AEZ5eUtAd5xjjTB7SwlIPLZsD1+O2O0wPzZQ7TBbpScEwVQxSZ31+vZuSFQZfahabES9c7ZHkisD3HJkYGwaZmWSTHSq13LcvKaAeSBCidILUaOOBcN/9SDtkfZDzqTML/M3PPMb6IOULr25MZHralhbx5bGvjrm0Lo7AE4LMaLYGGbWyJzAOBLly5zArNNoYMo3bp3AbqIUeo8JVAExZBc2UoR56zNUDLu+O6Zdyz3GhCXxnbmPsHrmIA+cw6XuSM8tNNvqZ6+XCEUhfCKylHIN114HWBJ7Huc0Rg1TzyHKT1XbMd6/2mG8E5MowyApCf3/12F23aeFIcj91DqhzUUChDVvDjO1hzmJpFNKKfTrjfLJoMlsPGOdOors1zNkcONONyPc43gqohR5GG3qp65sLpDPk+NXnr/EfvDWWWjEfeWiOJ4+0eWKlxdNH2mUsgeS19QG9pGAm9pGiNNQpNDvDDGMFj680+dkfPcMjy62JdO7yzphhGaQdSkm67yoyds+4pjPKWWpGfOapFb5ydvvQCs5CM+KjD83x2rrLnvOlIPI9Pv7wAs8cn+FXvn0N3xPMxeGBn5tvhDx1pM1szbm9nllqkhSKz7+8ed9VUN4JonCtm3Bhe8Sx2N0DB6rwh1TFbtej9sbmgFyZt7XX7n7tiXtQLdSnmOJ+w5SwTTHFDahWKS9u9flDMfzi75zjoaX227pKuV+6891rPTYG6cSqfZgqaqHPmaUmUsp7lsfcapX1iSPl2IVzuCu0qzZQTurroU899LGBpZkWjNKCfuKTaYNXSsC01qz1UyyW2VrAuDBuki5clpRSe9MYKcD3BLly+9rf4VZVrSoStzrjY4yrHv3Zj51ECMEvP3cZTAEMGWSKsi0NYzRCuiyqZrn6XyhDpjRLzRhfSgptiPxKCpUwSIuJBFICqdLsjqAde1zvJhO78sNwozzShQw763gpBFEgUcadp9fWh4yzAl9KNvspaeGCoSfVO+v2v/9YVGOqPhN4EllWrbR1x67QBqUNoe/RSRStyOeHHlnk119c59uXdzm/PZhUO10/3M1jt8CRmYjA8xBjJ28dpk7elxWud62S/lUumcJCXm5rlCqCIKAQkCiLEI6s5dpl6OmyoueVsQqh5ypnngBPSOqhRy30CHzX9/fpJ1f4leev8cKVLsZCmmmiQDAuzCTgW5fXROQ5k5StQcowU5xaqCOA690EpS3DXOPnGs+TrhJWVhEHmTv+UVXJA9Lc0E8VaWF4da1HLymYa4QkuZ4smoxzze4oZ6YWcHqxwZXdMVK4al4j9HhspcXuOGfFums89CRHZ2ukheH19T7PXdjlN19a47HVFs8en2WuEbLWS3l0ucbTRyVfO7/Dua0huTKkpYS0awpm6yGPLDcniw3XugnnNgeMc8WgdEzNtEHbg8RDW2j6AisER2djHltt8h9f3bhlBWd1psbuKOeHH13k+Fyd04sNjs+53y3fvdK7ZQ/Yej874NQJ8MhS676soLzdRKGSsYM7Fv20INdmUoXcXxW7U4/aGxsDstJ457GV773X7t3eEzfFFFNMCdsUUxzA/lXKY+0QLMzUgndklbKS7vwvX7vE2U3XGxF4kuV2zJml5qTadi/ymFutsr54rcdvv7JOOw74iadWuNxJ+PalDnN1t7p7fnvEziijHrq+tcVGxDhzcrCscDle41yxmSqUNtRDHyEkkS/wpJoQuqofyy9NLir3yMPoUOUpp62lnxQsNCIGmatYfOTUPL/7+hZffr0Hc44EhN4+Yw5tacUepxYaHJmJGZVyQE8K5ushm4OUsOGcL5NCU5RE0lT/aUNqYZwVtyVrFaqqITi5XmesePFal0eWWnzyzDLPXdhFG1jvJ2VFL6VQZuIAKdiTOAoOHhBrQUhnIjFXDya9Y3iSyJMopZy7owVfaYLC2ff/7htbGOus+PfHHNzu2yw0IhZbMc9f7oCFVBknZ5SC0BM044DOKJ+QCF/umYBk2pAY5SSRQC1wGWTjXBN4kvl6QKFdrl5uXDaalM5AJigNYaSQ/PAji/zZj7u+zFMLdX7pa5f58tkt1noJSWIn14bw9q4lhKAzLlhuhvSTnFeuF/TSAqU0YeAeY4WB3Dh2WRYooTzeubYMU8XmIKM7yimMc8rMlCPD17sJvaRgdcYZ8myPMqy1zNcD4tAHAdvDnMiX7IxyXt8Y8r953yq7o5y1fsqjy00644IXr7nq6nIrYlDKDF+63scvc86qCIKsUIwyPSHZnsQtekjBua3RRAatjKWT5OyMcrLy/j/scnWyRk09ZGIUciu3xN2Rc4DdHGTw6gbz9eiAbO5ee8DeKxWUSsYO8PzlLpsjVRq0SObrIasz0aQqdqcetaOzNS7vjol8+bb02j2I+XNTTDHFvWFK2KZ4V+F7abi+cZVSYiBx9u2PxuE7skrpSNvDrHVTaqHHXD2c9IxUuFt5zO1WWVfblu9e7ToDCOFITSPykVISeoJW5Jehw4a4tCJvxT65MiTl5D3bTRwJM65vbGCdw6CTVApCz8PaAm1guRVPMtZuhf3ziiTXDANFPfRoVm5z+94PPUEYuLDmXBmMhWNzNT5yag4DXNgasdyOWe+nnF6qM8icOUI/LcgLZ0AhBIRl/1WmLEK4qt3doBbIyZgj32OpFfHM0RmGueLbl7rkynCtO2Zn6Pq9rHWulYW2pZFHmbVWyRWt+07OPMWjFvmcmq+5ipQUbA9zMqVdfhv7jEqsCz++2knZHGQ8e2KG9V5WGvXfHha43kvpp8oFUS/UGaYFDy82MdZSC10G3lfObU9InzJQ+dRYIFcGLVxVcKEZkBaWpHAOh/ONkLTQ7AxzOuMcQdXXJnhstcUzx2b49JMrfOrM4gFr/r/7x5/ipztjfu/cFr/8tcusl5VJF4ZtiAKPeiAZZprLHVfVHGUu7NsAnjFEpdNlhcJA5Ds5pEBgrGFjkDrCbyxRSQJzZdgdFyw0QgrtHFoDKegnBfXAhzKQuxW7XrWnj80gcBmFH3l4jn/7jascKUneuc0hSa6YK4mr70m644L3HW2zOcg5OhMzWw/51eevsjV0tvyh54iAJyWqDDLvJwU7w5zffnmDP/7+I0gE3XFOJA/vf6zglcd0vZ+y1ctYbEZc3h0dqODsjjKev9xha5hzfK7G00dmSAp904LU1CziZhybrTFTC8DC1iAljsJJrMFGP+FKZ8yPP7XCsdkab2wO7tijFvmSn/zAEc6uD7/n4/yg5c9NMcUU944pYXsP435xk7oX3G7Mb7Xhutrmm1tDvnu1y9HZcpVy38yoWqU8uzHgm5d2adeCt+WYmXKl/8hMjQs7Q07M1Q6QNWNcoPXpxSbWWoyxzhjiHp3HcmMQwrI9zLm6O570DG31E46Uk+1BqibueYNUkRWuHlXZ5jtpn5sUm1Kqlym1Z8ignaGEFtYRLN/Hk4LdUTYhHjeick0sjDPAODFfpxUFLsNsXPDBEzPAEG2gUK4varYR0YxcdWeY6ZJEST5wYobPv5pypZPwyFKDc1sjrneTiVQv8uWk2pDkrsJx59ra3ji1sQjrKhi5NlzvOXK4PXRVyMu7Y6x11aS8dDysLqJKDhlICEq7+GbkYXC5cRZY72fOeKIw5Eof6KmTpWEIAox11c5xDr9/bpda6PLsklzdlIF2I652xiy3Yo7P1cqgY2eM0Yp9vnZ+h29c2GWQqr0x74Oxe/95AtZ6Wenk6Qh3Ghpqoc9iy5nPPH2sjS8km8OU/+KHTx+Q0e2HlC5gWgrBty50yop237lV2tJApBBlRIQtzVfK84Jz7Yx9ScrBSIDIlyhd9s9Z4fLFgCh0ix/auPD4tHB2976E3rigN1bkyuIJzdWOy1Jrxh6+5yop9cjj4vaIzriYTJIHqaIzzvE9wVovIyk0xroMvK9f6HB0NuZqJ+FHn1zif/3ONeqhR1a4xREXDwGhdREJ17oJjy43Obsx4HpvlsiXJIUmCve+XUXg7b5/x2WY+1ov5f/x9Uu0Ip+tQcYo0zy60iQOPF653mdr6Prcnjoyg+9JWp68STZ3ux6wt/LceBCfNYdiclPcMPaynFu9erd5cE+utvnMEyvf87GZBlVPMcW7H9O79z2K+81N6m5wuzEDb6nhev82t4Ypb26N6CUFj660WKh7Bz6bFpqX1/r8918+TxTI7/mY7d/39jDjyu6YtV7K+462OTJbY62b8NL1PkXZz/Pz//HspBfttbXBXTuP7Y4yXlsb0E8Umcr49W7ipHnCVYK2hzlR4GFxzosXk8JVXAKP1XbEej9HFQqsI20AhYZAGhAC35MstyJ2hxmjXONLwTjXHJ2r8fTRNt+50mWtl2DMXp+WpZz4A0hn1b7YDPnQybnJCvX2MMNoBTXXv5RqS8OXzNUC4tCjM8rZGWVc7YzxpODLb2wxTBXbw4ytQU4gBZ6UNEMPryRcviyztCKfTJkDLpe3gsSRNE8IZuoBC40I3xNsDlIGmXPh66d2ktnl+q8MFrHn1FhWg5QBUzgyNsxcr+JcI6Q3LhhmqgwtdsTc9xzhqKZulqpKZyf9eHmZ8TbKnFNmP1W3JaGur6sAagxTJ92zWM5vj7jWGTPIHFkLJJOg7sOgSymkBCcXLKWnx2ZrJIVmZSbmoYUGw0xhsdRD70Aw9WET0lGu2BnlbA1zjLUlmfEYpC5/rnK51KV1vy+ds2SmDZm2eJIJkbPWEblW7Jc9i64vzhOuciwQFBrmGiECGGfOJTQpnNFIPfRcfIRw4+qnBWeWGrRin0HqohWGqUJryyhzbqnjXDnSXFbXtHa5dxd3hlztjqkFHr0v5qz1UqR014m2lkwJaqFPUEYWjHPF1jBjvZfyP/7ueTrjAmMsw5KNV0euin6orq8k164X1ZecmqsBgt1R7gKyfSdJ3RxkHJ+r8dSRmYnkGg6XzR0mdXwrz40H8VlzGK51E3ppATEstiK2RophpvClZKUds9qO6IyLiUvo3ebBvR2S0mlQ9RRTvPsxJWzvQdyvblK3w+3GfK2bEPvynhuub9xmM3KOf2u9lFGu+dCJNg+XH98dZXzrUodhqphvBKy0v7djduO+j87WWGyGvHStz7cvd2ltDNkd54S+5NkTsxybqzPOFV87v8OvfOcaR2ZiHl1uUgtiNgcpXz2/zXeudDDWHlhlreICxrnGGkuuXc7WpNesDP3NtKIWCI61I4QQrPVSjIXLu0lpxQ6iPHYCN2HWVtAMnR18WmiUgaOzNf74+49M5JCZ0gRSIIXE89wkPCncWCqu5Atn/vHYcmvSt7E1cATWFxZW4OhsncvdjEHqJsTN2KOfKL5ydpu87KkzBh5fbXFmqcn57SHaWGbqPr5wFYTdsSMVoS8xxqLtnckauEpNFEhOzNdL63l3HKoeuTe3RnTHeRkELchLQkYpi6wIBpT9c+VuMw1FovBEwjBzlvqBFO4cSSfFq0aoS/dH2KuuSCnQ2pFQ1ycmuRuMUs16LyEKfMaF5mtv7rA5yBjnauLo6UuJNua25E8KQS2QLgxcGQap4XLHcmKuzpmlJgBnN4Yg4Jefu0ymzW0n67XAc1LQQjNbCxjlmlrggs+VcVJbXVY4Q0/ie4JG5BMZQ5IbhCcdESo0RemYGZRB62mhJ7lnhbZo44juSisi9CVbg8zJJUeW2ZqPsi4/MKzsF3HkdWeU8Y0LHXxP8oVXN7jSGXNhZ8STqy3GuSbNXdZekjsSJwQEgYfRlgzDG+sDkkLTDOVEwlhoi84UzcgHnGTzza0RxlgWGhHHZutc7yYMk2wyjur+rUg8gDV7leRzWyPGuaZQmkGm8aTgR59YxFjD+47Oupy+G3An2dxbeW48iM+aW2G/6ciHTs7Sz+wB0xFtLRe3R4xy9X0Pjp4GVU8xxbsfU8L2HsOD6CZ1pzG/cLXL1iDn4w/P3XXD9WHbtNay0orZ6CeMc8WF7SEfWnIrlOc2hnSTgtOLDY7MONniWz1mN+4bYFA6Qz55tMULl7tc7SZIAc3QY6Of0Yx95uohyhgGacFSMyRXhlfXBnTGOUo7i+jA98iU5UMnZwEmcQGxB2O1p5fzpetF2y+hM8bZ67frIde7Y1JlJ2YZvpST3K5G6DHMNZEvnbtfrhmkisdXW/z0Dz3Ep59cmUigBlnBv/zKRUb5FqMyn60R+SS5pigcIbDaYhGMCze5eGi+wQtXum6CjZsg1SOPY7M1doYZnXFBL8mJPEG77MWbbwR0k4JvXerw6EqLuXrAC1d6TvZoFb20IPZdhlhWOEdJcwf5ILjqWui5c+1JeeD6EsKFQl/YHrlJW+QzUw8Y5YqNflZKSi2344UG2Bm7CXJoLb6QBFIwyg23Gl61OWMcoatMPZL89tW1/fus6jTDsp9NCAg96Y6LdZlgCNdrdxhcS19J/IVz7NTGGY48vNgg8ATPX+6y1k85MhMz1whdVt4hk/XqWjm/NSRXGoFlrh6S68z1T4qyP8s6Qrw6ExP7Hlc640nV1JcgpWSQumpUGEjiwGOmFmCMoZ9aIt+RzLQkhPONkFrokylHaJJC8/Big5lawFovZZgq8gIakcdSPWBnmPE7r23hScFHj7U5OlunHnp842KH5y7skuaaTDvZpSqlzmFJ2LWxaDTzUYiXKjLl+j8LbfGEiyAYpgUSdy+kuZMxViYopxebrHcsoA5UXKszub/PcZgp1roJUVCS1VxzdrNge5DRiH0WGgkn5hs3ndPbyebeynPjQXzW3A77TUeEELRrB49TkqkDx+/73Qs47T2cYop3N6aE7T2GB9FN6k5jnqs7QxB9ixnuYSvHh21TCOFClLOCflKw1c9gCTb6GZd2x6XlduumSfu9HrP9++6MC85tDumMc8a5MxwwxjnrnVpoEAVyIr17ZMk50S00Qtb7KbujHG0szTggKMO2t4c5VzuuR211JmZ7lBF6kssdJ4MMPagCnPfPxSWup+1aL+VyJykt9N00UAgnIwykk+gVxtIMPWbrAacWGySZ5s9/8hTvOzZDpgxXdsccm61xYr7OlV03qf6hMwuc3x5xtZMwzirZmCAqTVDA8tU3t/nmxV2eOjrDKFM8fbTFpW3nnpkrTRT4LLZCBmmBtpIPnpxje5gRhy4SICs0G0nBej91X8oyIZhWCEaZcgHAccBKK+Tc1ujQ7LX9qAKNG5HPMC0IG+Hk/NvS3TJTmocW6jTKnqGFRsR8PeRaNyVXehIgfSfkBkyZi3cnLllJSsFJE0Hf8btUcNU5N/75RkhSZp4hxIRgVL1qh8EXEJUZbHmZteB7EoEjbBe2R/ilucuRmZgPnpgF3KJErg0rrYj1fsZvv7yBsXaS47U1dCYxADYpmG+4XspBqiiUkzxGgeThRecMujvKnaw0cETa5b25aoMsg7gDT1ILfRqhoRX7vP/EDG9ujlwwt3TB4O78WCJf8uhyE2Us/VS5nKxMkxWa7aElVYalZsgPP7rEQjMC4MR8g3ro8eXXN0kLF4AtSvZUhYIr7civ1pZm5JFrJ4F1rqqWVDlSn2uLxC2QNGOPR/aRnMVWyJWdvfNXwRPuXGpdxkOU1dbdcTGp0IaT+wy644JvXOxQD/3Jd4A7y+beynPjQXzW3A7HZms8vNiAoTte+0/ErY7f9zs4ehpUPcUU715MCdt7DA+im9SdxtyOAwTQT12e0o04bOX4Vtucb0Q8e2KWsxtDNnojADqjjFbs8+GTcwf6Pirc6zGr9p0W3sQGvBn5DBI3cbO4yVuhDe1aMJHend8eobShXfPZ6KfUQ//AZKgR+eRK0665Me4MU/pJQS3wnFmJAE+4vq7MmgM2/AZXYRumalIdUBp8z/2MtuDjMrEyZWg2wtJoxDnnXdoe88VXN+kkOZ6QnFlq8r//yLGyL0ix1Ix56kibM4sNXrreZ5AqmpHH7rggyTVSSjzpJpq/d3YLATy60uL0Qh3okBaWVOfOxt6XtGoe7XrAej9FlTlghTZEnmCYazwh8YSTXQb1gMCTzNUDBqlmph5Q890EVlpuS44qK4FKUrc7ymnGPr50NvO7o4JASk4vNWjFAcNMTT6z2IrY7CUICdK59KPN3v72m0ZU0AY8cRelv3IDgXAT9Ls1T6nQHRccna1Nohe0sYS+69saZe76vBVhM9b1zhlj8TyBsK6frB4EDDJFHEr+8GNL/O4bW8w1QjrjnDc3R+yO84kNeiP0+L2zOa9vuADh/ZLkJNeu38xzkkusPzG5wcKl7TFJrjm9VOf1tYFzvZTuuNYCJ3el7PVLC83qTI3TSw3e3BwxyjRPH21zvZuyNcwYZYpa4PP4SpOzWyO+fblbRihYGlHAsbkIg2B36OS0jy03CTzp+sJKKZwQklrkY2xG4Lu+RWVsKSl1PZ5SuDBxKSSr7Zi0dC41JTmuDrWUrproy71FgSudMa+s9ZGlijH0JPk+Uu0J1+MZBV6Z++dIoifcvaKMRQGLoUdkLbmyfP3iLp86s0C9rHbfSTb3Vp4bD+Kz5naQUvDpJ5d57Ruv8ebWiOWZ+l3JDr/fsQfvlZiFKaZ4r2FK2N5jeBDdpO40Zk+6rLTOOOfkfP2uGq5vt835RsSTR0RpOjLic3/oYf7NN68TB4f3CN3rMWuEPpEneX29T5Ir5htO3pgqQxx6qNJKv5cWzJcVnWbs00+cHKqfuApV64bm8kIbfM/1CClt+PRTy4y/epntQYayGmudnb0n9T7TkX2TRdxrhd7r2ancIUFQWOsaZSwEUpAULsh5c5BxdmPIOHdN+JkyvLrW57kLO3z6yWUu7SS8sTGcWNv3koJ2zaeXKLJC43uCQeoyjVyFx1W1Lu2MkdbASfjYQ/Okxsm9vnO5Qxx41AMPv7TAL7SZmJ3kyuJ7Bl3KXH0pWG45QwDfc/s/cqRNPRyR5ArMrUmbwOWjjXPFkZka9dBjvZ/SK/PpCm2IA5+NfkYrDvnAiVleud6nM8ox1kUQeEIQ+K4q1U/V5IAfxocs3HXUQOC56uEg1fdE2kLfEYVxrsm1wS+r1AAz9YArOwp1G85oYC8/zFisKA0vAndN1gOP717tkSpDkiu+fdn1UDZjn9laUObY5ewMczJl+EOPLAJuwaUZ+RRKUwucvLSqwsjSbdSTkCnNy9d7rkpcFjo0LjxdSjfwyHdVt0bkc3qxwUw9IC8si82I7jgnDjweWWpyZDbmiSNtXrjcRW6P6CcKKQRh4OShmwNXmSu0W+B4Za3P5U7ipJieJPIl41ISLEpTlND36Gdq0seoS1dRgTMuqknBQiMk14auKbDYiTpAlpXCjX7GNy52mKsFnN0akuSaduTu9Xbdp25keQ8VzNZC4kByYXvssvokKJiEiGtrJ719tdDjzJEWa72E693UVbnvQjb3Vp4bD+Kz5k44vdTkNeCpI23ObSdT2eEUU0zxfcOD85tyircFD6Kb1J3GvN7P+MTpBdJC33XD9Z2PQ8ZD8zVQsNJyQdYvr/XflmN2bLbGUivmuQu7LLecyYe2zn5cCoHBWXQnmSbNFVJKCmPRRjNTC7naTVxFI9pzsbTWudYtt2OWWhGXdkYE0hl8dNOCyJMYY1D21u5/QuDkW7j39xwhLVI4CZmQkgAXovz4SptTczXObY3ojHNnVR8HtGtu8nylM+Zf/cElmpGHwDmrbQ8zemlBPy0mE24pSnv/cn8WZ76RKc0wcxK5ZuzRlD5BaRqx2HLVxfPbI651EwJPMsr1hGz6wlnACwE7o5z3H5/lidU2SaHZ6Kd85sklXrradSYtmT602gWOrLlzDluDjPcdbbEtnUNo6Ek8qVhohmwNMraHOY3Qm0jjssK4SbuAVFkKo25ZtdqPu6yv0SpJvKUKpnYT/9sbhcAPnZ7ntfURzdjj/cdmiXyPQmteuNpjnGsMwvUuCu4os8z3DVblhsD3mKtHvHy9Ry/J2RkWrjpZEptaIJlvuIDhXBtyrV31eMtV4Ma5ck6XVpX9dM52n9I1stDufttvwAKuD1Lgznst8FHGMMoUW4OMF3SP5VbA9V7iiJewNAKfUwsN/tSHj/KFV7boJgVPH51hc7BZ9py5+2U30WwPc4Rw1azrvYwVA8fnaxTamUykSuOXF2+uLalyvZrVRaWMmVTR1vopgZS0Yx8pXQ+k0gIpLHEgqYfOTGeUa85uDFhohk72HPl4JRnVGqJQUgsDaqFPWhiWWjHnNkcYa1F2z4hEaYvnSWqBx7gwRIGTyEW+5D/56AlWZ+K7ks29lefGg/isuVv8pT/0MJsjNZUdTjHFFN83TAnbewwPopvU3Yz5z338JMBdN1zfbptnN4f0kwKM4slZ+G+/9CateoQnxdtyzKQUfOShOX7zpTUGaeHMHcqp5zjTRIHHQjNkrZtyaTdxRKo0LkiVJfYkhXUVkkYkSsMC5VbPlxqkhSb0JN+61KFdC1DasNazBAasNrechGsLpuyFcVIrQT30sMJVZOqBJJAS35c8e2KOP/XhY/zqt68xzhVpoSfVQGc773YyTAuWWiG+lGwOskmP3n4ZmClt7yqDEyncf5m2ZX8WdJMCz3PkfKkVUQ/cBPDobI2zGwNGhS4zA8q8uPI4R76TcL62PuBDJ2fRxjlent0YoowlK5y5x/7a6X4zh8h3vX1Pr7Z5db3PK2sDUmVYqAcsNCPGhWaYKuJAcnnXEekTczV3zJMCrRxpdOYgt78ubjST2P+6ADzPyVar8zdKlZuQl4O/k+mlBJ480uLUYoteqlnvOVlfuxYAAc+eELx0rcfVzhgpIPSdFFbcpZsmQD8p+A8vrblzjDslvoDAFxNSnakET7rKziAp+MbF3bIX06cVx9RLqdz2MCuvcZcD2Ih8xplmxD6HxH37tjhirEyBFKIMebckueKNdeWMWQrtssciV13c+FLKKFOcnK+zOUjBukr1uNCTqld1/Kt9bAxcXl47DkjL/j8jHeHKlbv2q+q1qhYkpIuwMGWWRWEMvZEq7xOXxdeIfAJP0q4JdkY52lJmx1koIx7AyT4LA71xNulbHaYKXcY9VBVabSyR75Wh7+5einzXa1g5pN4t2Tjs92UcOHfNtV7KQjPiM08tH9jOg/isuVtMZYdTTDHF9xtTwvYexIPoJnW3Y76XhuvDtpkpF6LbjoPJyq+xlje3hjQjnyPtmO64uOMxu1NQ7JNH2jy22qIzyhnl2vWclBlhK+2IQhsXUmutC1Iu3eTGmWKhETIb+XTHBbnS+J7HcjvmzFJjYsByYr7GVj/l0eUmxUKdF6/1uLg9cpW828jnLI4QeML1r83VAxJlGKWKbuJyuz795Ap/7uMnnbQtccYPzThACEGS64kZxChXWGNZ76V8+NRcadCxV8E7bN/KgBQuAy6wZtLLc3l3xFyjzvuPz/CnP3KcL762yRsbA6RwvTBZmVUlpTiQ1VVogzbw5taQ/jinMFUfnuUDJ2b4xoUO/ezmypeEkihAOso5uzkkKwy5MdR9j0YccHq5iQCev9zlejfBWtczd2l3TD9Re71qd8l3qo8FUlCUA9pPFrDgeYJQWArlztP+YyZEZR5z+PbbNWcU8rXzu4SeC3c4tzXksZUWtdAZdNQjn0bokyrt8v+AoBxANZbbfR1j9+SSkSfItTsm/UTRrolJZlwt8CaSPmOdAUWuDGnhcrpOzNW52nHZZfONkO64IPIlm/2sdKa8NUFVBiTueIwyZ2svgHro+rW0UewOM7YGPjtl5ttSM+LsxhBtLY3Qp58Wk/NXGbxI3EKAxfUADtOCsviH0KAFpZMqpbMlk/c9AbXQxxOCI7Mxg6RgW7vqcT2UNCJvEssghbuGKXsFhRQIbZiL3eN6vhlyqZMxTBWpMuXYitLp01XonXGMxZcwKpxxCriYj197cZ3ZWsC/+cZlaoF/15lo+39fPn+lw5XdMeNcUw894sDj8y9vIoU4sJ0H8VkzxRRTTHE/YkrY3qN4EN2k7mbM97ryuX+bg7TgV5+/ji8Fi82INzYHvH8ZXrnexwrJGk4e+dc/8yhJoW95zO4mKPbYbI0PnpjjxWs9nmlHFMblp53dGDJKC3bK1XeljQttli6nqh56DMoq3OOrLQptODJTY6kVTSSh842Qjzw0z68+f4166ONJwR9+dImHFxuc2xg4o4c79Ek1QomUHr1UkStnkOBLwZNH2vynHzvBI8struyO8YQkU4Z2zZG19X5aks1ygl8GBL+5NcIrA7KLO+j2rIVBppirB2V1AD79xAqPHZnlQyfm8H332v/8+xe5sO2qoYW2hB60am5SnuTOga/ajdKW3XFGHPgYK+mOc04vNVmdjRlvDin2jUcKJ4WMfTkJXF7rJZycb5ArQyPy2BlmfO38Ds8cm+GR5aZzptTOtAX2Qo2ramW13f09gxVuJEGy7IWyONLjJv2uKumXFRRnEmMnwclVFe8wElMRrUy5nceBpDPKkaVTX3dcsN5L0GWsQ+AJRrmr1vjeQWZ0L+Ymtsyhw1oX2J0WzNQCWjWfmu8IypbKmJfCmY0UTgJZtkwy34joJgWXtscI6SrJ2Z3KlCXMDYN1/ZiGZuwTC4EyhmHmXCsDCd+61GGcK5qhxzBTJQneO3eVRNgrj7G2TpoIjsj5nqAWeujMTirIpqwaz5TV2FrgZKHPnpxlmCp2xhtkhaEeygMZesZWgfSWmZpPqx6SF5rVtusD644Vu6PCSZaryrRw1bzcWFZaIcYKtkcZ3UThCUoDF/fdjIV27DNXj4gDeU+ZaI8stzBPwRsbA5ZaEUfL3z1JoW+5nQfxWTPFFFNMcb9hStjew3gQZR3vxJirbV7ZHbM9zKiHHi9c7aGKApZhrhEwVoLOKOd3Xt/kR59c5ocfXTp0W3cbFLtfLrQxyDgyEzNTqzHKNC9cSUkK5azWoextcT0vuXLmBbvjnA+cmOXkfJ3zWyMu7YwOrFxHvsdv+usHGv5nayErMzFvbA4n4dm3QqYtTd+ZWtTbEQK32p9rw7/6g0t87lMP8dB8g8VGwLcu5ZPJtNKGeug5F8HS8KMeeq4fLXWGJBJxx/3bUpq2NXSz4q+d3+HbVwZ840KHx1eb/PsX1hhmBfXIp54rMqXINGRDV7U4rBKkNRgfTs26OIXnLuzQjHyOz9W4sptMKlbGukylpBCTHjvfk5yYq3F2a8jmIKfQmnRo2B3mLDYjZ/RQkia/DLR28k6BKAlLZZBxaP8gzkTE9wS+EMTAINeTa6CanOf6IHnyZUkgzN5rh2079J2b5Fov5eGg7gwzAsGp+TrvPzHLF1/b5Ho34eL2iGGmUWXswv5eRnGP82uLqy7a8rsZ46pXzdhnlClHgKRka5gjhbPs93Ek2ZYxDePcGezM1nwEkhH6rkljVRGrUGiNtT5CukDtZiQYpAVjY+mlith3oei5tpNK837ossp2Yz6d75WC5sm14txTDVAPPR5erON77h7wPUnkeYQN18e2pXLGuXHB8tLtIy8D2EMpaUQB7zsyw7mtIZtDF5x9rTtGGTExCWpGPnEgUdrQTzXdRPHocpNcOTOUwC8JoXBOkkdnYtLCcHFnxEdOzfHocvOuM9GMsXz+lQ0yZXhkqVkuNGlasX/b7TyIz5oppphiivsJU8I2xRQlRrkiKRSdUUGSK5abjugI4XpMllohVzsJX3h1g0+dWbxpYnOvQbE3SozObQ7ZHbkQ7KKcNMa+mPS2AHiBc10zyrI1yPiTHzzKSmkT/thKkw+fnMf3nbV51fCfK835rTG745zdUeYqLXeA0s7Iogru3R3lrMzUeP+xGc5tjfil5y7TGeb8zhub9BInlwS30p8UBm0MxkBhLXnZUzfO9URadrsRlBFejFJNs3TGO73YZFi4rLb/59cukitXeVTaScJ8edBMxXUGudcRpU26df1MaaEZFYo016w0Q6zwiANn265t5ToIXtkT5HnOhr4yzhimCl+KMpBZM8iKA86OFanSBpB7wdnVmA77vr4nODJTY5xrOqMMhCMB+0099pO9ajt3KjhVx7owFl84wn+lk3JirsZjK02+c7XH2c0RuTbM1Jysdb4esNZ3weITMoIjhjeSoNtBGRAls7GlDHetnxKMBMbAUisk8gV5oRFCkhYGKQTN0GOuEXBlN8VaiAOPtDD3HF9w42etxfWwSb80Edm7z3wpShdTMyHJhx7PkiBXx8DfV4UbFy4vbkJySzKlrcCrTIFaEZ1xzoWtEeNMY43LGOyWcQehJ2mGPtY4SeZyK+LEfA1tDc9fSoA94hgFkkK7RRICSRz4KO2+43o/pTCWKJCcnG9wZDbm0vaYVuwTBR6+56TLg1TRrgV3nYl2rZvw/JUOnVHOxZ3RJKZhvh5yZrnxwGWrTTHFFFM8KJgStimmKNEIfYyBrWFWVqXcTCzJNab8eyPyWeulh05I3kpQ7CPLLczTlm9d3mWcuxDgIPYnTni5smX/jyNtoqz2JLnilbUef/dXXiZVGmGd9OrpozP8+NMrPLna5sefWuHV9T5ffmMbKdz7d6tCkhJm6856fL+hiZSSWiD5te9eZ5gqLIJm5DHOHdnRFrRyeWhR6KoVw9wwyLPJtm+nxtwv7wI4MVcHeshSErc5yNgd5a4aJeXE2fKw6tX+/i6Nk+gVxvWYVZbrG8OcWuBNeoEqGaOUgsVGwDBzwdC5slzvJo6wWEsv3fsWN4Y97O91upFQHUZ2dFnO2R5mzpRCCObrIVJY1vr5ge9Tnb6bZJSHbNuXpZlN2dOnSjMMATy63GJ1JuLl65sstSI+dHLOGV0Yy1wjpJ8p584IxJ4ENIF05DVT5o5EsRqvta6XqyI1WluMgShwQea9kugHnsWTEum5PrBBqsmVMwppxT6b/cy5qN7iGN5q//vh8uM0OvDwJIxzVwWuhy5ce5zryaLCraDM3kKAMu46rfIJBQLfc4sdpbcIrdinM8rxJUgp2R3nvLLWJ6/6A31XjdPKooUGDDo1hIGzu/c9ySAt2OxnRJ47+56ARs0n8L2J2+oo00ihyZUjnKp0zZypB3z84XkKY7m8OyYo5cSBJyeSUHB9oOu9lDe3hreVLb661ueN9YE7L7WAwPPL+zJlkBU8c2yGTOkHJlttiimmmOJBwZSwTTFFiWOzNY7M1PjO1S5xIFkfFbAK17sJhXXyuOPzNTwhDp2QvJWgWGMsv/3SBm9ujUr7fEiK4kBVptCGJDf4sauX5Mrle/XGikBKlpoRaaG43km4uD3mK+e2efpom2ePzxKWvTUS50A5PqR5rarC7J+n+gIK5T5bGZrMNyKstVztjOmOCzwpmK05qWbgSTrjYrINbS3NwCfNi3uqigQSfM/DaE0cSJ5YbQE9rLWc2xySFJrIk2TaZbZVVZdbTbItrkrkCTGpLObK5VJ5wvWc7Y5y1D6TD2Mdsdge5QQVKRSGrUFGri3KmAOE6UYCURGrOxGqqj3M4EjbMHPHOxAuk8wc0pBWTZ/NDa8dRmKsdcTbL4OYnWugZKbmU488tgbOhfHoTM1J8DxZhjwLWlEA1hlZHJmJgB5zjYhOcpchcftQyTV9CZHvjE8CKWnFAb1EOWKrLcZotHGZfJWLaKos4zxF7evVuptohEPHYcEol4kmDWUYunBuj6WctwqhNsaR+wpVH6CB0tzD2f5X1bR6KJFSYq2TDhdagxCMco0vBWlhsRiG5XkNfRfJkSk9icxQxpIriANYaET8+U+cpJ8ovnuty5XOmHbofib2PaQnJwHbiTYUhduPKKu1zchnY5AySjWXd8d45XfKlSYOHMnyhSArNNvDjO1ByuXdMb/83GU8Txzad2uM5ZsXOyhjmW+EROV3iHwn8dwduSD0k3P1BypbbYopppjiQcD0t+oUU5SQUvCZp5b5/KvrXNoZUy9jznxPkmRuctZPFHnLHDohuV1QrLWWzX5GWuiJtb2UgmvdhK+e36EzyifSS08IUqmd2QR7lYFcSbR1ky5toRFIjszEZMrQGbvJtV8G5O6OMr5+cYcruwnPnphhth6xO8oZX1AMU31ggl8ZZFQIJJxZafHoUovZekgr3stQGqSKa7uJc9ML/MkKfOCJiUlDVVnpjYvbVtMOg7YQSgiRnFlqcWyuBikMU01nnLsA8bTAKIsyLiT7TvN3oy1G7Dn9ybI6ggRVyiD3oyJbhXZkWQKELlrAWmetL8Wt3RgPe/lGQlWRZFH2Q1Xbq/btev0O3/aNRdJbfX9tnRRRW0voSWdi4nvOgVMKLvVS6qHHUisCXDVorh6yNUiZq/tk6iDBj3xJvYyRUG+BNVUywdiXZYVLu+vHunshU/YmNmZxVayyuOQiGG5B2m7VH3jj9oZpQeBJfCmYqQVlJbuU2Bonhb3RMKY67p6AxVZI6Hl0x87hFQHD3ADO1bQdB4R+yEwtoBE5l8tvXuzQSwq0tQSepOFXFNCR6MiT1GOPvLA8c7TNIFdc7ST8V595jD+4sMM//8p5HlmoA33mGiHrgwIR2APZe4V2FdQ4kGitkQL6meIr57YIfQ9jLDtDyYn5Wpl1By9e65HkjrTVQp8nVtscm6sf2nd7rZuwNUg5MhPTSwrCMpwcKEPKPda6zhH2fs1Wu5N77xRTTDHF/YopYZtiin34xMMLrLbdhESWM2ZtLK1awGzNZ2uYkyvDkXZ808/eKih2d5RxbmPIpV3XQ/LLz13mGxc6/MT7Vsi14Wp3jDaWduwhpUCW5gCmlBlWk7HCGEJPoo0z81gtpZe7I+eSWAt9tHXZYr2x4vhcndfWB1zYGfNU6JfSODMhCTfKB8FNSJdaER8+OcfmID9A1sBVBIaFRuIyzvb/vFfOcCtp5FtBHEiOz8YkuWF1xpHM0x5sDhKSXLHYDAl8iU0hLcxk3LebrBcVgwRCXzpyVPbY3dTndMh2DJDkLq+tqvAI7tzPdeOYqn/HvssgU8ZMZIeifLMiKHKfLPTG8d0TrPvqqdmrHjVin/W+y86KAxeu3vLc5PuR5SbDTJHkToZrrJ1YwmfK9ZhV3/9exuJMVSSF0tQDryTaGk8463tzhwumIvIIgcSS69IqP5AkJal2MQ4Hf07iJJn7+xuNLeMqClPeP/mBama16CBw1U7PE8SBh9LOd7QZBbRiv5T+Oalo4HuuUqoNo6ygXatzqozTcPe2TzPySoMVJ4NUZRg4lD2jUtJXOa9vDrHWcn5rxPYw41OPLLLUiMo+THj/8Vm2X9+mk6ibzHvcgoJlWDjjEidHtS4qAsso17yxMSL0BXO1EE844xVZmgOd2xrRjAPmG+FNfbejXJFpw+OrbV681mN35BZQAk+WWZAa3xN85KH5+5IE3Y177xRTTDHF/YopYZtiin1Y66fMNUKOzdYwWgMZR2diFJJRppith4S+ZK2f3tTDtt/58Y2NIa3YZ5gpXl/vM8o0s42QD5+cO2Cl/ZFTc+SFW5mvApyFoCRfkJcVoMAT1HyJMpYo8GhGPq04IFeGpNDlajd45VQ6KTTr3ZSsMJzbGNIdudX9bqImzof77ealEGWVTLDcivnAiTm+eXH3psDba92EWuBRlH1MlRu5QLjQ7HukFEHZZ2VwroqNyOeJ1Rku7474xsUOPoaPfACeO7/LoHC9OpS9WPv7qO52r8YYfN8j9AWBlKWV/J1/vtpVxSsOq3TdiP3brHK1NE7mV2g1MZIJKg9/DpKGu9luhVuRxwPSSelcKOfqIe8/PuuqyS9vHlhgmKsHPLLU4Pz2iLVewkIjKu3kh0Sex2Ds3EvfGh8XKA19fdDp8W63lRsIpCUvD762gJTUpaQV+/RThdLqwOJDVFWBlAvCruSno1whhGRn6OSwtUAipSAtdGmW4nrQqriExUbIuNC04oD3HZ3hWmeMsWXfaxliX0USSOlI5VovQWnL0dka3aSgFQT0U40n3WJDrg31wN23iTas9TO0tjRCV+3rpwVfen2Tb13qsNAI6Y4kzyzCyfkaqzOx68UsL8gqj7AduQp0Wrisu3oAo1yXTp0ehVIoY1BGEniQaYPnSVZmQtpxwO4o582tIXP1uZv6bisFQRxInj0xy7nNIZ2xy1z0pWS2ETBXD3lytf2Wro53Enfr3jvFFFNMcb9iStimmGIfRrki9CUfPjXPlZ0BMGBcaKxwvVynFur0k+KWTfWPLLf4sSeW+Z9//yIvX+/RGeVoa1lsRjy+0prIz6rV6xeudGnFLqg4VwYv8BBlJaQZevS0szhfbEU8ttykGfuc2xyWwb3K9aZYiyfc5D8rCVyuDP3UBVVb68hQWlaJEKVRhqxkXqIMPDYEUjDOFb/3xhZzjZAjbe9AUPhHT82zWA/5j69vMsoUvvDL3p29/KnKlKHqAbpdNcaXkvlmiLUwWwuYa4T00oK1Xko/LQik+8lBpki1IC1yfOnIJdibzC8OIy6BAOkJar6HtpZCW+qBx1wj4lo3mUQl3CsJudXnqypcRep8yUS2VqEyZwGwpQX8W4WrXu3Z0R/2vi9hqRnyMz/yCD/86NJECiaF4Hov4ezmkFogudZN2B7mDNKC0JMcn6/hl6PzPcFCM6CfFvc8PotzLzT7XrtV793tUJSmH7VAlkHbCnDX71wtIC00ubYTOWmVYRj6HoVy5Nzz4EMn57i8M6aXuO+irUVa9x1NmXmnYKJJPrc9JiirVd+8tMvuqKAd+1gL41y5hYvSacYYuLAzphZ6PLLcZL4R4ktX2a0Fnvsd40nSQlMYd9+MczUxaNkYOJFy5AuOzjj54vYoZ5wCi7DRT7HAQ/M1dkc5/VTRiPzSoVWTFcY5SQrwQpfdOFMLGGUa5UkK7UyKosDnyGzM5Z0xrTL4vhn7B9wj95uRLLcjFpshl3cTHltp8tGH5hikavJ7Y72f8v7js/edHPJe3XunmGKKKe5HTAnbFFPsw/5V5A+dnIV0i488NI/v+ZOKWVYc3sMGbiX3i69t0og83n9shpev9/A9R2gubI+YqTm5UbV6fa2TsNSOybVld5QzyhRR4AGWTBl8TzDbCPnTHznOtU7KS9d6XNkdMy4M28OcRiSxCLQxKG3pJc7kww8lvpT4IQwzw1o/xZeSVuQxSLWbyAKNyMOYvVX4lbYL3Y4Dj7Veylw95H/3oWMsNENeWxvwnStd1ocZgZQMlXISLwnWHJTwNUOfThkifTsitNQKCXyPWiCZrYckuebc5oBe9bPlD1eui9VEPCv2HA/3yyJvZF7Va60omJiF5MpQC90+W5HHrnavv1UZ543QN+y/cha8Vd9bVVm9F/Ky//OVZPZWw29Erm+tEfk8e2L2QGW4ipb4pa9d5nde33SB8JHvQsVbEd+52iMvCn5yzi1m+L5/oFfxbrBfiljBA2y5cHCv7XDu+1ZyWFESZMu40Mw3AnZGRVmFFWXemscoc46mnucWS+bqIRe2x9R8UVY83dbsYZpY9sxo+qmmFrj+yWHmTD60MVgr8D3Xf6qMIVUWkylWWzHtOGC+HrI5SJlrBOTaLagIAeNUkRuDNhB6rl9WGYs2Bm08EC4HMs01c2VT7e4wp58UxIFH6Lv7vJsUSEQZY+G+g9KGQWppxT6DVKGMJfAlotAI4bIcM+Uqg4U2RGWY+X73yLVuwsWd0cSMJFfOfGeUu6y3euQhcljrOYntZ59eue9Iz1tx751iiimmuN8wJWxTTLEP+/vQWktupXih4bK6rHXBw88cmzl0FXn/Su5jKy12Rjm+L5mrhy7s+ga5US109uKPLjeRQjAT+1zrpSRl9S7yJbP1mA+fmuPsxpDvXnX9MFHgnPYKY+mVrn3DfRJHX7rJWuxJDJKFhkdSGNJC0yiJSq5dH1xSmMlk1ZfQjAK80sGvWn3+0mubGGv50utbkwn9QjMgLRTD3KBv6BsSMCFrN2I/nwqk6ymbqQfUQ5/5esi3tzsMMie7CzwnLdsPi+sprEhOZa8uxB6ZMzd8vjDQHefOia+sZvWTgnGmEKWznjH33pd1N6jGEvrOpfHG3sEbP3fXEK4yWmWG3ernBYB1RjQbfcMra31acXDAdOH0YpP5ZsjJhTrHZmtEvkehDd++3OFaZ4xXZqltDjKUySfk+XuBBsLSSeRujGNuRGEqwxZLIwom1a4zS02ev9J1fVk4g56xgKSwpWOm5MR8nSjwsGWVyfct40xhStORG/sOa4HL4eulBYVy3z4rLGlRlBLISmLsqmWWvX67y7tjziw3ObPcYJAVJLlmvhHSGRfkypQVcFchrYfeZOHEl84FsjMuWG1HKGOZrTkjo089ukAv01zvZYxyTa5dP6bB3lTJBcgKQ+BLaoFHkqtJNT3JtTtOQpApw4m5unOPLPPgdoYp37jYoRZ6HJ2NaUQB49wtWPWTgsu7Y2eY4ns8c2yGzz59f/aCvRX33immmGKK+w1TwjbFFPuwvw/tza0Rp1tuBX1UGNZ6KfON8JaryDeu5IaeW/2uVq9vlBslubPY/vSTKxR6nZ3Q59GVFp1RzrhwK9+nF5vEgeT3z/WgXAk3Ftq1kCQvSAo3QawqN1FpkDDKFf20oBUHLLcixrnhei+hGTvzlF6iXO9M4UwSKhfBtDB850qXZ0/MMt8IqQWSL7y6AaKMNZirMcwU17sphbbEPljrLMmrQF9POgJ0GPbImuDJ1SYLrZjZWsCjKy3aNZ/feW3DmSUIFzhdfS+x7+crww9PgsR9diJh24egZHBFWf0TZTYV7Nnp+wLqoV9myr09uLHqV5FMy54BxveKwJNEHgyyO5OdojwZAvjvv/wmv/nSOqEvJ6YLHzgxw/mtEacXm4DLIXzpWo/1XkJhQJZuqaKsEN7rcfLgAMmr5JAgymgGPbH+vxdU5HeUFWSFKp1boBk5YlJJRHXmSJC0MFPzeWihQVaWPT0pKCrjl5ssPJjcW4NMT94v9J7TqK2+n7XY0j3UUkY24LLPLm2PmG9GfOD4DOe3xuyMMgROYq20wZOC7WHOKFdu28Idc2Msw7Sg4wl6qeLNbQMz8Ptnd7jSSdgZ5YSlWUzku3GqfZVWTzpzm3HhzECyQjPMVHWYyAtH3pRxpG6UKppxwIn5OtYavn6hA8DHHpqnXQsBJyP84MlZ3tgYcGqhwZ949iitOLiv3RZv594LLmcz8r1pFMEUU0xxX2P6G+o9jNtZHN/43pF2zFq5Crn/s9+LTfKtfvZux1UPvElvzGH7Vsrwrcu7vL4xIMkNZ5YbPLbc4vhc/bZjrGRiv/XdazCCF691Mdbn9FKDzzy1wunF5qFjHGQFO6OMQht2RjmzNZ+5esDWICNsSCc3KnO/MuUMPB5faTHXCHj2xAz/6/PX+c6VDkobQl8yW3cr669vDElzxTBzq+lx4PphmpGPMgWFdpNGgMjfq7qAIwrr/YxMOZODzUFGUq7KN0KP2ZpPXii0df01tUDQHee8dK3LM0fbnN0c0ksV7dhnrhEhhWCYalz/mC2rU3s9WIaDZO2wqpUnYLUd89M/dJq5ZsDOMGehGXJ2fUBhLLHvkRqXN+cf4m1fSfKcI6Ate4tu/lxxAwmo1G6tUGKFQGuDJ5ykzkVDvz2YTJjZZ1Zi9gwsJt+Dt1BZw5FyX8Iov3PvncVN4hGObmwNc9q1gE88vEBSaF663uPltR6bpWS2M85Z76UMMnXTMb2X+bhXkjuJ6xmrqrCu344y6Nyy0IiQScEgUXd9LCp5qbGlNFNTVmRdUHShLZ1xgbEGIdz1NMo0IOgmBV96Y8uFs2snhcyUI3T1QFDkNxPgSr4Y+ZKisEhpaUQ+/TJDbv91pm0ZWC4ESlmGRvHls1ssNF3/19GZGoHv3Dg/9cgiv3d2i5k44D++uokyBl862aKtqmCFk0bXAo+oNKmJAo9eopyJinBXtScFlRpSl/ellIJxoSm0ZZiqyeJHVZXWlBxXOAKaKoNJCrRxBii+J/nosTYLzejg8S9lhBe3R2wOskNJ0P2EW7n3AndUTbxVTOMDpphiircbU8L2HsXtLI6BA+/lypAVhiiQB1bmnzjS4rW1wVuySb7V/m+3zf3j2h5mbA8zQLDYDFlsRgf2/YVXN/hvf+ccr68PSEuzA18KVloxP/70Cn/u4yfvLN8pn6/XOinDwrI+SLnaTfjia5tgXS5XNcbZWsC1XsLzl7uTCVMceCyW/Wq7oxyLpTdWPH+lwzjTaGs5vznkV56/Ri8pyPdJE2frIUdmQt7cGvLqWp9MmckEepRrJ/8Texbz1ZzRVW9cdUpZ6KXqwKReG0OmcgAKremlBWnuJqRp4bLO3CQm4ezGkMKUVu5l6HJShoabqvp1h3LL/rcboSTwPKw1DHPF/+2Lb+BJSaI0GJcpVSiDtXs9Zf4h27nR7v5GYnYnDHJDGf+FVYfTtO9FHnnYz1r2+vEqvNVCm1vU2MttE0AcVOHMN8NaSuMZQey7RYNxrmnXnOz1q+d3OLc5pB75LmA9v5mswVurDBpgf1a7Lf/tCdDKsjFIyYp7M12pnBiFsaiqUoojEhIXhu5MaSSNyKMZeQhZoLST/2qtXN6hJx2pLpj0Nt4oh6wucWH3+uZkSfKFuPmcgjtOyrhqri+cpBJrubQzZrOf8WNPLPNnP36SwJN86bVNXrjaI/QlbeEMXbLCTCrA4IyEjs3Ee9Jlz5HvOJDO5EQbigM9e5JxofCEJLc395Fqw2T8lYTSGqhHPifmY545NssffnyRf/uNKxydvbmna3eU88ZGn6udhH/xlfMsNeP72h5/v2riRtfbO6km3gqm8QFTTDHFO4EpYXsP4nYWx6+u9wG3SntkJiYtPL51aZduUjBXD/jQyTniwONr53f4le9c48hM7JrP78Em+Vb7v90294+rFkh2Rhnj0khACFhshpN9P7Ha4n/8vQts9BNHniSEZfbRWj/l333nGpuDjL/xmUcPHWM1vuudIccXHNGbqwdkheHNzSEvXesReJKPPjTH6cUm17tjfuOl9TLPyE2G4tD1mV0vjTviQHBlN0NKlzUmpUBYJz/L9jGQqqDUHRc8d6FLLRBkhblpQlvyMqo/qsllpswkr6nCrYhHUuxjXNa5FXr73B2rfprQs4y15eJOQlBKq+517u5IhU/kS/qpoSg0a7kiDnxWWiG9VNFPCpQF9X1oJbmT0cX3Io+sfjYKnHPj2yGBrLC/V6pC4AmaUYCxxYFrqcLEnMTaMgJCsDPK3CKCsOwMUsa5q8TkSt+WAB92XMQN792NgUv1vrsG7w0GkDcwJVvKG8eFYVQ6Lsa+pFAWHcDJuTrnt0cY42zso8AjVwZjLaHnfocU+wbtoi72CE1VORbC9d7lah/pv8U4KzmlsfDsyTki37lwzjcijLX8+xeuc357xJVOQi1wPWtUVcP939fC5U7CqTmX/SiEY1ux71EYQ4D7nuAWPTLl+kpnYsFsLSZRBqPdIgm27P+TgqjMT/OkM0yRAk4vNl0geKbIlWWjn3BkprYvUzLnO1e6E9OThxea+J647+3xJ6qJkkhVrrdvd+/dND5giimmeKcwJWzvMdzO4rgRevzWyxsg4CeeWkEIwatrHbSxnJyr0RkXXNwZ8+GTsyhjGKQFS81wIjO5G5vkW+3fyfsO32Yj9PitVzbAwmefWuHbl7tkhWG5DK/eHeWs9zM+XPZW/POz2+wMM7Cued+tSIMnLbm2DHPF62t9fuulDU7/yMExVuPbGeaocqY91wjReDRCw5vbI7BQDz3W+xnHZmus9VJyrbHWUg+C0nXNVaRyZekmOTKxNGKPx1ea7I4KksxNrot9mVaBdJbisly6H+eKcX77nrAKlj37+Hxfr9bdoJLm3ShnrFBoJ18TwuJL+Zb6mMD1ikhh9yRmngQsO6MCYy3tWkA+yN82aeK9QnLrwOq3sq2i3FAg770KeCtY64hF1cdnS6ledb5vJUGt+gGHqSIvNF96fcuFh1vXvzSRKnJvUs2ql7CqIL7Va+NeYezB6lY98BBCMMoUhTI0Yp/Yl2wNc6KSDAWewCJLGaQjXD6CZi1ASNge5tQ8see6aW8+np4AKSRJofCkq3Td7twaC1uDnLMbfT5wYq40RenwxuaAXBlOLdTZGKQYY0kKgzZ2IifdT4CNtQwzF0EwWwtc4HmuKLQl8CS+53pJLZYkN2VlUDDbiPjgYoOXrvXoZWpSWTPGUuDIazNyWXK5cqTu6m5CLy24upvw6pri1EKdR5ZbzNUDzm0OGecKX8JKO2a2XsYBPAD2+I8stzj9I813TKr4dsQHTKWUU0wxxa0wJWzvMdzO4nhYyvSw7u8AnXFOMw6QUk5MM9Z6KZ1xwULpdlaZaMCdbZJvtf9Bqm65zWGmJ31Z64OU3XFOM97rRajGNcw0nhRsDNIy9FaUkyoHKUTZv+Fc4b57rXvTGKvxtWOfa7tq8p0oJ8rVKnsUeJNjsdnPMKWkSBnLUjNkmGmSwpG4TGuMhoXA5+quG3/kS0aZdkYFVKYMjqwZ64iRKQljzfdQRt92IlzVyvZbvd8tbjXftPv+9Jyqi1ybtzwhV0YzSG1pyCKIAskg02jpqqaFNtjvRYv4PcJwuMTtrSD0BVnpftgIJLYwbwsR3C+t9IW7NqvzUtzCbXHSO1cSqkRZcq0IfeFywKptWzshgXd7Djzp7qnqu1Y/+k6fxknOGo5EteOA1ZmYmVrAd650yQvDKFNkStMbF9gaE2JRKMtMPSApNKNUkSpDVgZr10NJHPgMywzDA8HjuEWVcWnWYbW9q3NqgPV+hr3S5X1HZ7i8O2a5FfGhky7H7Pz2iGGqSFUxqfzWAoEnJGkp2a1HPqlr2qQZ+RyfrfHK9R7aQjv2EMIyLgy5shNTkdCTfOD4DAvNyPWl9ZJScuze9z1JI/LxpWCcO6v/cxtDCm1ZbESstmO+fbnD+e0Ru6Ocx1dbbA5StDa0agFnlhqT38EPij2+lOIdG9v3Gh8wlVJOMcUUt8MhLf1TvJuxZ3F8M1d32Tt28vdcG5Q2ZT+Ic6bTxjAuNEq7LCttzCSzp0It9MiUPtQm+Vb7r/Z12DarvwssSa5RxhB4e5du4ElU+TPGVo587nvc8Nx0xgkWFJZxfvMYq/FJ6fKU9kPvC2mSZd6Sa+p3xy3wBNY604CjszEn5mostUKkEFgBrVpAI/YQuAb/ivwcGONhfTHCSRUj7/YrrfeaZ3UvUObmqsa9wFUtIAokrdjD91z1MVemDPlWdMeH9059v/B2rmNrs9dfluSOrFX/fjvgqi6uKmasM5W4FfGuzt2NSAuL2mcGstejdffjVMZO3BgrMxB45zm3snsmMVLAbD3g6GyNq10ngy60dhU0KUkKze6owBhLpiyhLxllirTQ+J5kdSbCl66yluSGXOnJPekLiH1XvfbLaqYn92X+3SUyZeglBS9e65HkejKpb8U+q+0akS9Ls5I9o5ikcPJUZWCUqolk83ov4aHFOlJWLrSaTDmyHXuS5VbESisi9OXk9+RyK2a1HdOMfQJPICQ0Qve7aJSpSZ/jMHMVtdWZmKVWzEcfmuf0QoNBqnjhapckU6zO1koX2YNmJLf7vf9ewO2erXD741NJKV+63mO2HnB6sclsPeCl6z3+5e9f5Nzm4J0e/hRTTHGfY1phe4/hdhbHoVf5jFV/d6uwTt4nyn4HST1wE+4k13hlZs9+3M4m+Vb7Dz15y21Wf7e47LL9VvnAgewgWfayTPpq7EFCZMqZpY/LPbpxjNX4jHFVrv3wxN6Uu6qC1QOvnBQJJ1UTAk8IV0XyJcOBxloIpcCXgkC67wmWcSl7qoxDbFkGuZFkGuNkT63IJ9dm4k7nxlS65d10pN9+VD05bxUCeGi+zjDTbA7SsgK5N8n/fnyH2+HtrAopY/GF+07VMQs9Vz3V9va9T3dCuzTS2BrmpPv7EO8Bh53Hqt/qXrD/mqhI5PcLFUkMfA9tLc9d2GGQFAgJeWHxPEkt9MAYCmPc7y8B+HJiCtKMfWZqIYNUU+gUZS29xEkHI1/gS1kurLhq2ih3YfZS2Hu6FwplGKYFw0wxUwtYakb0k4JcG+qhdDmJyk6On7JMJJlCVPeGe/OFq11atZi5Rkgr9NgqXWcpf6ctt2OstWwOsvL1wBHDmRrKVH1ulsE+oubk0JbZmmSpFU0qRPONiI8+HHJ8vs61boIvBWeWmhP1w3681+3x32p8wNshpZxiiine/ZhW2N5jqCyO13op9oZySTPynM25FDQjj1bsM1cPGaYFxhiGqWK+EXJkJmauHrAzypmru8lAhcom+ZHl5qE2ybfav9vX4dtsRh6edERotRUzXw9dbpa1blW4HFcz8tDGstKKy9wwO8m/AkeylHHVqnrk8/5jszeNsRpfP1XM1vzJdwJn7iDL1fWs0JNjsdyOkBLGmaJWOmlSfmaYKiJPMt+MyJSz668FXum6WB4zyqqGqAKcBcaYSRi0LCVfRWm40ohc4HYgYabuJE2ht2dPXwVK328QAtZ6KYEH41xPzDgyZQ81y3jHxnGL194a9TkcFijsQWJUaLtHzu9hW1Xlykny3LXbqWzd2fvve8X3SrbejkDte8EeqRJc3BmzPcidyYsG33eLN4XSFMaWSgHJTC1gkBaTKlrkCXZGOfONkCeOzBB75b3lSzJl6WeaVNlJTlwcCE7ON1hshs7c5x7GmhWut7UV+jx3YZevnt/h997Y4luXuhTaHLguq3MR+YLILxeJyvfcohacmq8hpKAdB5ycr/PIUoPjszVGmWKQKjwhuNZNGKQF2lqOzLiK2Ewt5KmjLQIpUNpMSJwACmN5dW3A7iifjEUIwXI7YrbmKj/r/ZufHXf6vf9ewO2erbc7PvcipZxiiineu7gPp3VTvJOoLI7nGyFnN4cM0mJi9nFua8Rjqy0eW2lxbmvEMFM8tFjHk4LLnQRPCh5aqDPKNb6UtOIA35MMMzXZxtnN4W1tkm+1/2GmbrnNc1sjHltp8dhqize3R6zORESBZKOfstHPiAKP1XbEua0Ri62Y/+KHH3bZQQKUcf0puTYTu+xm6PP4kTY/8b6VmwxHrnUTHl1tOolSWdnrjHIGacHuqGAmDgh9V3VcbUcY4MhMTOh5iNI0JFWuf21zkFFoSy30ODob4wk3OWyWksDKhnwygvIZr61bzY99yepMTKsWuaqhEIxKYwKBwPc8pHCmKqHvzECoJFU/6HLVDZBQOkQqNgbZZEJqeXuJ0t2gIsg3vvZOj6Gqtt1tZSbyBUHpOurMLtwYN/oZySHOod8LfoBK1LeEZugRBx6FtvRTRVa46lk9dIRLl0Hu2lpqgc/JuTrNyCcKPJRx8RFpYdga5hTKsDoTs9AMEa74TVqYQ8/TKHcS3uVWPFkguRsMc0OuNVjLKNdc7SZEnkDbckHJ2gkpn/wnnLTWGCd9DcrJ/KfOLHK0HaONixZZboXM1EJqoft+c/WAcaE5MhvzkVNzdMcFF7dHgOCzT63wmSeX6SeKwjh56Fw95ORc3S2SWctGP+XFa90DpCPJNXHg8Zmnlpmrh7xwtculnRGdUU4/ye/4e/+9gNs9W293fL4XKeUUU0zx3sF7U7vwHsedLI5hL+8sU5oT83WWlSHyJb2kIC0MnzyzwOOre5lp92KTfKv932mb+8e10IhKCaFgoREC4sC+j87WDuSwFVh8KVhtx3zmqZtz2G5s+M73MR4pHdGohx4n5hucnK+DdZOli9sjIt/jJ59ZZXec8/r6gJ1hTlESRGMtnSRncF0ReJLYl8ShRy30SlmWmPTUaOvGGPmS43N1fvpTD/Ghk7P86+eu8LULu2wPU5Ry8sjZuk8t9CaVOWtdT97bZZrxdkNKmGsEDFNXdfx+wOPWYdi3qyZVocw/KPhSlP1XgrRkDVU75X7L93fK2KNyG60kh/fb9FsChTE3RVdoXOXWk+KA42paKHLtszLj+rqGmZrIunPtlAPfvLg7mRhXxd79Biqikh5b2Bxm1MOqD1PjS4G6zQUTem5LhXZRGQbDUjOkmxSMc+3iBzSY3EUuVE6gWNBYfF/iC0noASiW2xEvrQ3xyriRzrgoe9OcVHyYKmZrAbP1kD/x7DG30LPPdfDizpAvvrZJM/RYbEYTA6dCW5exqA1XOwn9pGCmHh4Il15uR859c+BImgBmagGfOL1wd9mW73K8lfiAtyqlnGKKKd5bmP4GeI/iThbHN753pB2z1k9v+uyPPr78lmyIb7f/221z/8/UA88ZBRT6ps99+skV/sijS3zr8i6vbwxIcsOZ5QaPLbc4Plc/MMZbZedsdkcA/LVPP8J8s0Yz9mlFwUTScuMYAa52xnzl3Da/+vw1Lu+4n7fCmQFkyjDKNVHgHuDDTPH4Sov/7QeP0k8Kru0mpMrw2EqTD5+cxy91jX/3jz/Flc6YC9sjjLU0Qs/FHUQ+1lj+5e9f5POvbiApUDCp2r3VqtHdEoHbEaIboYyrDBmzJ+2qKgo35k7dLXzhQoRN6XQoYCIThD2L+tAHISS2lMQeGAM3ywl9eTDs+Z2GgLIqVO3fyfxW2hFbw4xRenju3TvFKbVx4/GEcOHc4v5aBTDg3BA5eO4mnMm4hQ8hBMa679JNCrSBY7MRkSfZKSV/eSlF9D2J1mZCjAVOAq2NRUpRyq/dMU9zzSBVVC2t4g5nQgBCSkLhwrlHmeaHTi/x0vWeG0dZZXOOm5L5RuCcZ8vXw7IXbyaSQMbWIGecaYQUfPDkHJe2x+yW2WmelCy3Yx5aqNNLCsaF5onV9mQs5zYH/N+/9Cabg4zAk2wOcwaZYr4RMd8IybUh1YYk1+yMcqQUk3Dpx1db/Ks/uMTuKOfjD8+hDfTTgs44nzhYTnHv8QGVlPKl671JnE2F/WT5vSo1nWKKKRymhO09jNtZHB/23mGf/V5skm/1s/c6rlvB9yUfP73Ix08vAnuSxzc2BwdI1q0avlvLTUjhwtaIzz597KYH7mHjOD5XZ3eU0x0XNCKfpZbPxiCj0IY4cCv4nXHO2Y0hH31onv/koyf2Vl3P3Po4nVpocGqhcej7n35qmf/f81cn/VFiUnV7a2TosM9XBpWTioMF6YO+h2KZPlgUwdi9Hr23YmairLNW9z2BtM5Z78AEvtq2EQSemzRj9E2fuRHfT7IGe4YzntwzyKlMHay9e1L8dqH0vsFUUszv8/7vBoctRlQLDdpCUmbLVWx4ru4xyhXrfUpDIPdvW940hTb0dWn4U95HVTh5JQ2s9qctbA1SRElodfn50HNOqDdeU4WxxOXqROAJxpki05oPnpgt3T2d+22mDGmh6aeuyq5M6TjbjsmNpR27M/G18zsIKUkLQ29c8Phqi8dWmxTaEnqSVuwzzBRpYQ5UZaqFqUs7I4RwkmspBaNck+uU1bZzktwYpPSTgvV+SuBJnjk2w2eeXOHzr9z8e3KuEXJyvj41xrgB9/KcqqSU13sJZzddL1st9EhyPSHL72Wp6RRTTOEwJWxTvCdwq4yb95+YuW3DN8D5rdFdZwtd6ya8eK2HtpZWLSDyPVaFYHfk+o4se7EDf/SZ/z97fx5m61XWeeOftZ5pzzXXGerMQ0ImCCEQQmQOQaAbFVFf+SkRERtauhW68X39XcqliK3iT8FWBH0bUVqxwalbZYxhkjmQEDIn55ycuebatednXOv3x3r2rrlO1Tl1knOS53NdSZ3aw9prP/vZT6173ff9/W6/oBKibgB6fLpFlGikNHYDiTLiFlKYcqxkg35R67E8oBKAihf+DecXeCm4oFRRoiFZ4811A0uFkZ5fHjA+0axlSN09Blb6u20Lrt/dRytIqHVi2kGClQYDT9T8Yw2i+2Fa6z92q7jQEs/Vnqu0CYL3DBb53ql5crZkR1+O2VZojKiFCaSUMt+fnGPRDExQ38vYrTJwGGv0osyjaxl7EaXVCvN5pY2svyUlQhgF0U6YsLPPZO0fn2lhpaXQiVKoVCgpUhqpTM+b60hqHfOFcx1JznGY73Q4NtPk7Hyb/SMlrhvro5yzqXcijkw3uWZnHzsqOTOHRUqE1+yscHy2TRArip5N3jEqlabCwJQ8VgbyvO0lBzk8WmasP3/BHmMZ63M+pZQZGRlPL7KALeMpz1olj/efrfHAeI2mH7NznXKTzTR8t8KYdhhjfNnMjnjetdjp5AljRaQ0DT9iW8VjpOytP9g53tPn7p/knlNV7js9jx+bjIK0zKLTsSSOLZAI6n5IHOk1A4blbPRx3cfYwizwe6IJAqJVBtiKYKObkdtIANrta3rCVU3WoHt8Fsvgd8s2u5khqSHvWCbroTTtMEZI0E+wo7gtwErLTbsZtou5v38xxu6qQPblbKaaftrTZpRKm0FMkmgsS2ALgXQtojgh2UDzoi0g55gMWJSYUslEA0qnwczSMQTGfzBnWzQD46dWa0fMNANjGdAtt9TQXzC+jQ0/QgqBa0mKrkU7Vog0ErSFpB0mbKvkmG0GtIKYx6dbNDoRnmMx346wpSDnWPzpV47xymu34dlWL+DqGm8fm2nRiRJc21iitMKYyYaZx4sOj/CSK0Z7WZ0FYYzVr5N512IyLZnPOD82W0qZkZHx9CIL2DIuObqZo634o7Wex03RtbjreJXpRsBo2WVnf2HF7jGwoYbv7pwnaj4ilWpc7BUnhMBzLIgTHEtSdJ3zbiLvBqAn59pMN3xIJbmBdMFpfKNc20Zr3ev3sSToDWSZuv1g6z2uq7So9ULw1NVpceTFEcQQLBUE6b5GVyTjfEsrnyhivZDxhNWPj8b0BdU7EQ0/JkoUMhWEeCLfmkoDkKJrM1iwgBaOFPgXqT5zrfd2vudRN0a3hMCPFfU5HyGg2o6wLWM4bVsiLWvUhFGS9pLpc75mzpH0Fz2KrsWJuRZxoinnHNNzpiFR8ZKg3JZGmdaSglZoAsl7T8/z+GyLesfMR2lTjplzLAqOxc7+PDlHgoZXXLONf3t0hpGi+Ry01gwWjVeaa0mmmj71dsSZeR/HElyxrcyV28vkHIv7z9Y4W+vw4itHegGXEILrdvXRChNmWwFhbILGKDHv/Zm7+/nJm/YsueZmwhhPDBfSYpCRkfHUJru6ZlxSrFW6+Mprz68sZK1SnrlWwNGpFtMNn6lGwFceizg4UuLQaJnBogss9K4cGCmyo5Lj1Fx71SBy8Zw7UcxMI2C+ExPGih39+d7raq2NP5IUPHPX+TWRdwPQ2WZIHCviRLOtL8+8H/d8vqTWJIkppZKYxbctTF9UrR1tODu1Ft0sGt2sWnpYuwHbxewBM+Hosnl079MXTzlxqwhXiSi778cSJruWcySPTjZ60vKCzQdrixUOz/d4KGX8yLaVXaCFJaDoSlrhE+cZcSGfpSXMRkmkNInWSDRaCyxpTLUdS/bUYLXWqQfiwrm92mu7FpRyDgMFh7xj0ZdzmGmGuBZsrxRoR4qJeodGGtl2+wHDRBEEZiukr2Cnaq5GBEdjes2u3VVhe8Vk/ydqPjPNkHon4rP3TVDtRPTlSgA9VUcwma2xvhx+mGBbkopnc92uPvry5hrWNV7+zvE5PEv2Aq7BosfzDwxyZKrJVD2gExkT7Vdes31pX23KjkqO4ZLHg+M1Do2U0j45Y5fiSMFEPTjva1pGRkZGxrm5oIDN931yudxWzSXjac56pYtnax3edMu+TQdtq5XyzLUCvndqnk6YUMzZ9CfGTPvYTIu5VsgNewfIOxZTtTYHynB4tMSffuXYqkEksGTOO5wcSmkmmwEz7ZBYKUYqOUBQa0corXnW7n5eee12gDWDwLXoBqCVnM3x2RalnI1rSfrzLnPtEKVSk19LEEbGqFsIKOcddlRyxt9ukw1tixf/mKF7GYy8Iwl72Z+tC5WWBxrdUkhLCoTWC2qQmiWebpcrljDBkRAw04qW3LeZ99XNQlbyDlFiRCy6qpiuBZY0/UrrUXIllpT4UUI7iHlkMoKdJnvZV3CJVUhwqRn9rUGYKCwhKLrmfUuh8WwLP056qo9SCCSamAXPu2SNc8qzjRjERM1nR1+evoJLzY9JtGC6GfSO9+JMcAI0g5icY9Hv2YwN5JlvR+wfLvLYVBNLmp64aitieznHY5PGw8uWgoJrMVRyOVXt8MCZeV5yOFWvXDSndqRQGoZLHolSxhIgpdtfNl0PGCnnOFVt95QIB4sez93n9nrert5Z4Zdve0ZPnbZLd0Pq2EyTk7NtHpls4EiBY1uAJoo1I2WPH7txV1a+l5GRkXGR2HTAppTit37rt/jwhz/M5OQkjz76KAcOHODXfu3X2LdvH29+85svxjwznuKsV7rY3SU+HxWy5aU8WmuOTrXohElPxrro2Vy1vcxEzefEXJu7T1S5ekeFa3ZWoHGWLz82w0wrXhFEnpnvkLNlb87VdsRD4/NU2yFFxyzsan5MrHxcW9KXd7n5wCA/edMeAD70paObziR2A9BKziFWCscyi69tlZzxYAoikxmRJi9TylkIoJh6vxmlys31mXT7rGyZ9lkt8ulqptkW1zKlkOeIBZawWvbHEguKiVovKBTaEgqeDUJQbUWXdXDWxUoX9aZc1XiHNYILS092e+H8KOlphXRLXAUQJ+t/QF7aA1kPjJ9ZOecQR0YCP9GaVhDj2RLXuvC5rsZWZUiNQqTAShUgW4FGaU2oIdYxjhRYlqBo2yilCeLFjY4mC9ftTVs8n3ZoSpqDRCHqHfKOxVh/nmftqvDlR2ZopsfNEtCXsym6NgqFH5lNjW2VHLHS2Jak6JnXnmmGWAJq7ZBTc23CWGFJCBJN3rGYa4WMlF2m6x0Aolgh01JrrTVNP8a2BK4lCDH9aN37Gn5MJ0qY70T84LU7aIXxCiXCyUbA3qEiP37j7lWDte6G1J7BAp4l+PrROWqhKeUcKbns6M9RcGy+8PAUe4cKmUBGRkZGxkVg0wHbe9/7Xv7yL/+S973vfbzlLW/p3X7ttdfygQ98IAvYMs6Li6VCttzjpuHHzLVDSjlz6jf9mNFKjt2DBXYPFtg1WGCuFfCTN+3huu0lPv/5h6m2Qg6PVnrzKnk228oe95+tUetE3HJwmGo7SrN2MaWcQzlnU/JsZlohB0aKvPZZO7nl0DC7Bwocm2medyaxG4AqpbGl7PXJ5V2LXQMFJusdWkFCwbOwhODFV45wYrZNtR0yWfdJEt0TCdkMCgjTkrFklXX6WmWQ3UBhtTDBTpUPu1jCiDMkiabgWiaLo80Dip5DpAXtcHVPssuNrpR/N3OZKE1rCwOgTqR6YibdnxsZPkxgrhVhScjnbPQi8RxbCCOSARQcueUG491QYSuG1BibhySV0reEQCWg0ejUUFtoiJWi4Nrs7Pd4ZKKFlAKJyUSGicJi6XdFpyWqSaKZa0UMFOGFewcYLLi4tqTfMv1d7TChEyk6UZj2tpms8Ela5Byb0bLHkakmgFGHTDShUjSbIVKa0tiCazFUdJlphgghKBrnbGZbIYNli1iZYK3gWthSUO9E7BwoUM7ZvZLvuXZIJ4pRCr57osrLnjHKw+ONDSkRLt9Em2uF3HemTqSMRUmcKMJE8YxtZYZKXibtn5GRkXER2XTA9rGPfYw/+7M/4+Uvfzlvfetbe7c/61nP4uGHH97SyWU8fbhQFbK1hEqWe9x4tiRKjDLaXCsk79ocHFnI6I1WPNphTCXvMNkIANheWQgiFy+Eah3jt3bPySpCCjphzGDR7T22mLMJkwRbCubbEbsHTKB5PpnE7vtrBBHDJZeTs2368zbjNZ9yzsGWAs8WlHLG2DvvWlw71s9/ufUK/t+vPs4XHpmk2oouOODZbAZkMwKNSoOfZuyiRJFoE1wClHM21U6Cv5kU3iXM4uOS6ntsOYt745Yrd0pMpnSxiXg3kNfpk5tBDAhsYR6Rd21yUlJthbS0Rur11UQ3G9DlHUE72toDIYUJLjuxSWVKwJESx7IYLLnkbEmtE1HvxOQdkzlDCBRLDda7dDOYQgi00jhSEsSKhycbeGmQNV7zjSJsontlvCo9VnPtGMcyvV8Fx2J7Xw4/Ukw1fFpNE1GbPjrB9nKOgmeEgybrPiXHhLRKw+lqJ/V59NhR8XhgvEEnTDgwXKDaDhdKvj2LKJb0VxxOzrVohTG3v2Avr3V2nrMUe/EmWrUdcdfxOartkJxjmWxeImn6Md85UeV5+4cyaf+MjIyMi8imA7YzZ85w6NChFbcrpYiiaJVnZGScmwtRITuXUMlij5vvn5lPF/0x2yo5Do6UeiIjy1+n3vYB06dV70RMN30em2wSJ4py3sGWHvVObBZoiWL7suxglChsy2JHX763kAE2lEk8XW0jhKAVGhGT752c59hMCz9OCGPFqbk2DT+m6UdMNwIcy5jgFj0bBAyXc/zoDbtwXYtn7Cjzie+couFfWCmhxcbk/jdCN/O2mMVBTLfUslvXZxbV6ilRCrmc5e9JrHH7RlkeVMcaHLGgptkVbun6hdnSCMZ0yzO794eJySZZ6VeuFcZoIZHS5OzWOhekAFsK4k1KdgpxPvIqa+NaxkdBI1BK9XrT/DihEyV0otiUiaaltwXPxm+FaDRqFQPsbn+gY0mkEOSlOXbNIObQSInT1TYn54y/WU8JVBvftW7gagkTGNc7EVpr/EiRcySeLSm4FkqbcslumWwnTJhrhbTCmEbbbFZdN1bBsh06UYIlBEJIXnhomMlGwEwzYrrh0w5Mpr8VxBQ8m6t39DFQcHhsqsm/PjjFW1988JxZsO4mWt7J8dD4PO3QlHu6lum1dC1BnCjaYcLR6SbX7+7blAVKRkZGRsbG2XTAdvXVV/Nv//Zv7N27d8ntf/d3f8ezn/3sLZtYxqXLVsrud8fTWlPJORyZarJ/qJBKoEvKaenieM3nurGVKmSPTtb54BePMtsM2NGXY/9QkU6UrCgv7HrcnJxt8cdfPMLx2RaHR4r0FZxer0cQJ5yZ7/C8fUOM9edJ0l6vu47PMe8rphrGN6k/71BUZkGVdy2kFEShouHHVHKOWXimY/blHaSEmWZovJWkWDWTuNBvEnO62uZ/fOVYugALmKz75F1TunRguMTZ+Ta1TkQnTCh4NmFsxCXiSJveJQE52+JPv3SU/SMF7j1dox3G2FKsq4C3HgJwHUEQa1zLvL8wMfFUsugxmxnXBATp+z/HY/0o2VR/3MVAYjJVF9s64EKHX+356x27rn7IWmWrTrqxkGhNECtcy5xHq2XQJMb7bPHtG/HOkywK0reIKNHYFoSx6knuk2bGEk1P7dK1BP1FlwPDRe4+OU8UK5btpWCJriKqYLjkAJKBgsNUw2eg4BIrRTNI6IQJjiXQaQ9moo15uy3N9QINQgpUpAhjxVTTp+jauLZFJW8Cu1aYoLVRea11IqJUiTFWXbVZKLgWr3/OLobLXu8afGymySfvOsUDZ2tYUhDEitFlm1KbyYJ1N9GmGj7VdkjZs2mHSZr5NnYIlpSUPZu5Vsh0I8ik/TMyMjIuEpu+sr773e/m9ttv58yZMyil+Id/+AceeeQRPvaxj/Ev//IvF2OOGZcQWy27v3i8k3Mtjky1uOdk1fSA5RzKnk3Bs9kzWOC2a7YtCQwfnWjwm//yEEenmxRci5lmyEDB59BoicOjpRXlhcdmmnzu/knmOxFTjYCz81P05x1sW9AKElpBTN6xOTgccGymSZQ2Zp2p+ZRyxuQ6l5oaB7ERHNg1kKcdJNT9mKYf40cKKWGuFRJEZqH4zWOzKAX/+56zvOiK4RWZxLlWyJGpJtV2SKMTMdcOeXSySdmzaYVxumttcd+ZOgXXZqIWUHRN+VV/wWVbxeX+M3WCKEFp6IQxD5yp8a3jc70sipUqB7qWJlIKtQE/ti4CKHkSIQRhbBaT3WzM4iX2RsYTwLayawLOeOP5lER1HbK2ntUUKS0B3eq8bjZQpKWFtljIVF2sOVwqxAnELGSLlDafxVDJZSDvMl73TTCdqnMICQoT0DmWJkhM0CcQqGRpVq57XMt5m0Zn67MyCtMjaUmjBKn0ggn44jlEiTEoPzxaohlEPDjeQGvwbLNBYaV9cN3Pp96JGRsoMFRymWoGlD2bo9MtbCmwpDDnql6aQRYIKjmbMDZm3WFsSn7bQcLOvjx7Bws8NNEATNYtSBTz7bDXo+rHCbm0l/DgaIlHpzt8/3RtSabs0GiZH75hjEenGmyv5Mk7FuVFFgCwOYPrbv/vN47NECeK/oJD3rdohTGWYywRip5NwTNm3eM1nxccHM6k/TMyMjIuApsO2H7oh36If/7nf+Y973kPxWKRd7/73dxwww388z//M694xSsuxhwzLhG2WnZ/8Xh5R9KJEgquRTs0u8wgaPoxI2WPlz1jdMnYR6YafPCLRzg63aS/4FD0bKJEM93waQYx1+/uX7KbHMTJErWz0XKO752qcnymhcZIYu8bKrKzP8d43efPv/o4BVtwHTBcdJlpxyRa41lGbKEVJEgpuHZnHwDtR6aYaYVU2wG2JQkihWdLKjmbpp/0ekg+fV9Ef8FhvOZT8uylYiWezVk/SqW5Bc0gRmlN3rVJlOlj+e7JKkppynkT7FVbIeO1Dg0/RgpTQhUrs8i0pAkDEkx2o9aJjE/b8lXrMhbLmoNZeLYD1cukdUVHJJsvkbSkkSHfbJZqsyIpG6UryAGp4Xe6sE9SgZW8IyjnXbSG+XZAosGzJH4aCW/VtGwBtiVMr9VF4HwDwsXP6QZYiQI/UtglQcmz0YBna1zbIohMf5YQ4Dk2IjbCHVIKEIooDdI1JpArujaeLWlcpIhViNTHLt1kiBel/ha/ZCtIOFltEScL79sSAs/CnA9p35pnSSxLcmi0RLUd0p938aOEuXbIQNE1wVacEMRqoQxSmu+c1gLbEoyW3F5A6NkWz9heZrjkMVkPmKx3KLgWri1o+TFCCmJlrAn2DOUAf10RprLnMFjwKLjWBRtcd/t/H51qcGy6ZURVCg6dKKbWSW0K8g7tMKEdJgyVvBWbahkZGRkZW8N51S688IUv5I477tjquWRcwmy17P7i8Q6NFPnuiXmCSLFrII/WmqlGSH/B4fpdfUw2Ah6ZaPDSK0eRUiyYR7cC8q6Rx5bCiG64RZe5Vrikp6LhR3zx4eneazWDBNB4tmS45KG08RF67r4BpJRorbn39Dy1ps91e+GZu/u572yTWseIdthSUs7b5B0Lx5JU8g7P3TfIXSeqbKt4+JEymYM1ekh29lkMFFwenWww3QjSfhOLuXZIkGgcyyLvSPxYESujmOhaglaYMD7vU8lbVPIO7TBmshGglDaCCVFMrBaEERwBwhIkiclNqbQUMlFLA5XlLA+m1grKunLxG82saUz5XTs0weVa5ZBPRLZpca9WF8cyvURaCzpxTH/eYXtfnrofmaA1tNBpaV3XdqB7rC8EV5p5xGplsLxVXMiQIg3whVh434nSVDsxAwWXIFa0o4RtRRfXkkw3AiJlSoeVhplmgBSkAYQmiBRBlFDybEqe2by4GEv8oitTsRW9aklo95h0vxv3nKxTztlGtj82JYtdrz/L0owUPQaKDs0gZqYZsHewyMHhEo9ONYiShIGCS8mz0jG7VgGmtDtRmjBRJsuWKPYOFWiHCU0/7gnsbO/zOFVtA3DV9jJHplt4jiSMFOWczdU7+4AqsHambLkq7uLsmtZ6zdLytTg0WuYXXnqQ32yGaSWDud4VXZMp9KOYdqg4NFriF156MJP0z8jIyLhIZMXmGRtiq2X3F4/XDJKe1L4QAiEEA0UnLS+U7OzPLxm7+9ydfXlmmgtlQ925lHJLeyqaQczR6SZ5R/KdE8YnrRPGVNsRBdemv2B6M5pBQiVvSv8GCi4npxsADBRcbjk4DMB0I2Cw6OJYgvlOZGTOtcaPFa+82uwuf/b+iXV7SKrtiB+5YYx/e3SGB87WjedSLLGlIFEKrc2uutaaOIGmjCmkmYhWkJAoi3on5My8T5Dq4idaESdLlQeDRLPYVmnxon0jC/iNBA+bCdZ6QZICxzGB42rjPxGlgUIYr7pw0QTiRKXH3QQX2yo5HEuiNQyWXGZbEVop2nGCZwmCRPdKTs8XV4JjWwRxgkaTS5UAW1vcz3UhdE+hRJvPDIygTtOPGC66DJVcdDMkSTTNOEYIyNsWDT8m56SltIkiVjFxoomVRqaiJGdrHVSabYoVJMnaYiYCk4nciJCkBPryjgmIlkVrizcEFmeJgyhhoGCy2d0A0xLGIiFRxuNQY/q2rtnZx4/duAuAP7rzCMemW3h2Qn/BpROZ95QmuAljhUjLJaUQFDyba3dWODHXYVvZ2A8cn2nh2RavuHobaHN9TJQ5v8YGChwcKTJQsKFjAq+peoAfKeqdCJUeT2CFKu5iv7Xxms9g0d10FuzQSJm3vGg/f/614zR9Y/g9Usox3QwYr3UYKnn8wksOccW2LFjLyMjIuFhsOmCTUq5YsC8mWc2kKeOy50Jl99cbr9oOeybQXRxL0gxiI/JRcJaM3X3u/qEigwWXqYaPW1w4Lx3LyE13eypKOZuZZsBsKzQ7+zkHS5qAy49iZpuKvGsRLjIVLufsJU0oUgqu2Vnhe6fmaQUxrm2U4sI44bGpJoNFl5+8aQ9honhsAz0kI2WPH372zrTfJMdMM+Cux+eIFUj0EnGLRmDKzKx0HNeSnKn6dCIjcKC07mXWFqP1QjYNYX7v3XeOz8eRaYneFsis61V+hrHGkqt7uj0hpOVxixfvKv2f0lBJxW7OVNu0woQoUanSYNqfZVv4cXzBwaWUgig97xxLojQUHIs40USLeqGerPBNCuO/16UbeIexJlZxKv0Ph0dLXDFa4r6z9dSU3mGmGRInmtGSybq1w8T4wklBzjLiOz3BE20CaNVNA68yj83YBCig2o5wLEHOFbTDhSeutXEhpSmNNOWaknwabFqWJE4UniVwLMlt12znXbdd2TOZfttLDnL2f3c4PttKxUHSAEqYoDRRGkubzRPPkQwUXGYapjT79pv3kXetJQJOAKeqbT76tcd5fKbFM8f6jDJn6kl498kqR2d8yjmbv/nWSe56vLqkh3ixKu5G/NbWY3GPsVKadqh44Gyd4VLAcMnjBQeHNz1mRkZGRsbm2XTA9o//+I9Lfo+iiHvuuYe//Mu/5Dd+4ze2bGIZlxYXIrt/rvFcSy4xgYZUEl9KXEuuGLv73E6UcHC0SCOImGuZDJ1jSVpBvKSnwrEkM82QVhCzreKZAEob42lbCvzILNIcayGwsqWgknOBFjpdNQ8WPa7f3c+RySYn5tqUczZxopcshE7NtTfVQzJYcAmihPtO19KgzCxKly9Mg1gj0Li2IE4SojS1k3ckrdBk4xbTy2Zp8160XjtzsRrJedT6bbSUsTsv/QRFIVIslC926Za6rfZYpWG+E9EKTblXJW+zoy+HUprZVmiynkG8JaWLfhq4SkwGJk4UkdIUPJuGH4EwvVRBop+QUlFjGr2gKrlCBTIVXYmUKeEcr/nsGy6yoy/HZCMkUZrhksf1u/s4XfU5OtOk6UepwqLpq3SlBLGQrQNzftty9XdnCyO5n7MFzcB48W3k1PEjhUSScyz8MF71OUvOCaVphqaP1hKCTqTMxgwmuHctCykEV+2ocGSmSdG16YQJdz40RV/BhlmYa0e4lmCsL4dlSWrtiEZa9ljrxNT9mDPVDiPlHD93eJhDo6We3UfvGEvB3qEiP/X8vXz0a8c5Mt1iR1+OMIrYb8Hx2TaVvMsNewbIOdaqPcRdVdwLUfNd3rO8sz9PK4g4NtOi6Nm87oYxXnBwOOtZy8jIyHgCOC/RkeW8/vWv55prruETn/gEb37zm7dkYhmXFlvdG7F4vEMjSzNlAE0/ZrSSo+RZHJluLRl7rD/PgeEid52YY6w/z6GREhM1n2onoulHtEPFwZESr7thjFhpZpsd0Cbg6eLaMg12jOrh4iWH1pqJesDz9g2ArnJ0usVoX4GcI/GjpJdt+9Ebd3HNjr4lC6HNHCeVqu19+r5x6n5I3rGIEoVeY1Vuygk1tU7Mrv48c60o9XjSK/rBev056UJ5s6V7SrPmPNZicdnjRh672fHPB8FSxcfV6JbFJQq6+eFaJ8aWUMo55B0LP+0jmmuFvV68LUODQhOmg9pS4NoS5RhfLj/eWoGT9ej6s0kBni17/ZiQStunWaVEm/M0ThQFRwKCPUN5YmX6tLqlx3GiUj82gWsZtUNbarodjIvPl1it9OYDeuWFkTJzSpQm2EC0rIEgHXStRy9+fcsyx31nXx4hTPmzHyUkaSa2v+DQjhI+9f1x/vWhScJYMd0IqOQdDo2UmGoERDNt4rQHd7Dk0l9welnIomsxUHTohIpqO+BPvniEu4/PIaQ8p3/kkakGj03UeO5+2DdUYN9IhcGiUa5dq4dYSnHeBtZr9SxX8i7P2mV6cb9/usYL0lLxjIyMjIyLy5b1sD3/+c/n53/+57dquIxLjK3ujVg83pHpFtv7PGp+yGTdB0wf2vaKx5Hp1oqxj800mWuHnJxt8/BEg5JnM1xy2TtYoBXGuLbF3oE8/+ees/hxQhAZUQTbkksycaWcTd2P0alstx8ppIh67+f1N+7i4buOcfWOCnefrnNqrk073YHfPVjg6GSLQyNLRVY2epy6FgMPjteZbYaEiSaM18/aSAGubYRObj4wxNGZFsdn2gihsaWRIO+EyZJMgsTIlncV/mDjC//zCRCeiKBio1jC+FX50fp1l13xlG7PnmZBIKWRbgJIIYzgjT4/dcz16H7mSaIppiI6XXNmzxacqXbWH2CLkQIKtqRccJisB70+SEcKhCWIYk3OMcI4YZzwjB0V/t0zd1DM2bzvM4/wyGSzV3rs5EymcKrhE6QKkev15612/ijMBs5QyaPoWXRif1PZ3ygxPWnLnyKg996EEOwaKKKV6WNs+mkZbKoYWnQt5tsBsTL9dvsGC3zr8Tkm6j5xojjtSOZaEYMlI7zSChP68w7TjQClTVDVDBM68745x7Sm7id8+oEJXnXNdg4Ml1ZV3O1myr5zYo6PfPkxoMYNewZALvzpPp8e4nOx1T3LGRkZGRkXxpYEbJ1Oh//+3/87Y2NjWzFcxiXKVvZGrDbeUNFLsy6CoaILiBVjLy7Tefaefs7O+0w3A07MtplyAp69p58w0Uw0gp71wGS9w0PjCmxJf96ImbSCGEtKDowUCWNjej1ZNya43dfcO5DjYeClV47yyFSbkbLHzr48I2VvVXPujR4noPceRkseAwXblJOdYw1a9iziBPxE0QhiDo2WmWtFNIIIKSWVvMCWxg6gWwLYVYmXqcKfBIIt7hu7WMqG50tXATPRpv9vI2i6QiTGe0yxoCJppVL/KDZdWrpZTN+hQilNw4+YiVWvPHG9QLFom16zCzUXt7tli45FFClTIpneFyaaMEpID0VqvQF//93TfO3ILFduK3G62iZRLJQeA2gTNG32FLGkCajCuNv3mNCXt/EsiVJ6iWDMWiSLUrmSrry+uV1isqqVnM3OgTx7h4o8eLbObMs32UQp0QgsC2p+SKyg7Nkcm24xXguY74QMFBxOVzscnW4RJcqUjFom6J6o+TT8GMc2AVwYK2xpehXDWPd6Ab9zoko57zJYdFfNlkkpjIeisyCstPydb7aH+Fxsdc9yRkZGRsaFsemAbWBgYEWZV6PRoFAo8Fd/9VdbOrmMS4+t6I1Yb7yCY6GBTpSsGHu1Mp1dAwUavjGXPjPfYboRUPRsrthW7p2nO/ry7B0qcGymxY5Kjuv39BMlGteSlDyLx6aa7B0q8kPX76Scc3qvGUURAF94ZJL5jhEJ8GwLS4pz2hmsdZwAPvSlo7330PBjbMs6Z3mgFOA5FkqbBfNE3WfvUJEb9/ZT90NqbVPCFyuT/ajkbHKOZL4Tm/4drQlTE+HNYIv1PdAcmWZFLnLAJsXGAkPHMkIm55UdTEVaFsc8ljSBskBQ96OL5gfXJYgUc62wZ8AcLwp0uvMSLIhwdAO0PSNlGp2Qs/PBeQWUggWDadc2svZaa2K9UE7a6z1c9tx2pDg52+L0fBu0KR0EU67XCRNmW+GGxUIWz0dg+hy7T5VCMFrJ0Q4TI8rjxyv8ArvzZNG/lTICOgXHItF6IeMqQGiMeIiGF10xzFTdZ7LuE2jTZGnKiY0Pm/kOmp64mWZgPicBndhk4qxUCVIpTa0dItPeUQQLwjK2NOWgIg3A037JI1MNnrtvcM3sVbdvdy0220N8Ls63Z1kpvWV/GzIyMjIyFtj01f3973//koBNSsnIyAg33XQTAwMDWzq5jEuTC+mN2Ox4SmlOzbVphTH1dGGzuExHCLP7DA5RovnmsVmef2BwyTkqhODgSInJus+R6SYDRZd9wwX8SHFkusVQyePHbty1Zobw8w9M0ozMQsSWksGCy8HRIoNFb93SoNXe16m59pJSo5Jn9xZz62EJI/+ttGag6DJUdLnn1DztwIi2IDR+bNQl+3M2o5UcrSBmtOwx2YAoNTTeTO+VAFxHImK1IpABE8ytdvvFIG/JNGA1pWRrESULC/fNinSsFowlyvwXqbV7C7eSBLA19OUcakGMjle+V5GW8EopiEOFBtp+xHDJY6IWnFdwlHckShvvsHCRdGc3qICFUtHViBelc+fbIeO2xWDRYbYV0k5FfTaCvagsVSkWzNq1EfT4/qkakUrIO2bjJFkWwXdjA8cSRInujSWATpykKp/CiKCk2dJuRvrzD0ziWIKhkkvDj9HaeKd15V5sKXp9hgMFm8m6j6/M7VIKbGn66xxLEiWm9w1t7AKUNkGjTLO1WpvPsXtgJusBDT+mkndWzV6N9efZP1yEJr0gsMv59BCfi/PpWV6sKLlaT17Gk0sWTGdkXN5sOmD7mZ/5mYswjYyMlSxfAARRwqlqhxv3DlLOrXy8lUqkW3JpGskYabdQ2mTu7j5Z5eh0k92DBW7YM7BmOeex6aZ5fjtkoJTDs40oyFTDpxFEXL+7n0reOW87A4DT822afnTOBW2kzE58ybW5cluZF185yse/dZLpRoBrS0bLOTphwnw7pBUm1P2IHX15Rksek43pDZWPLcezMSWbRZdOGFPrxAghmGkGhIm+6NkmWFiXurYkRvTMiNeju0A/X1XFJVL/2izoNyMp3+V8e91ipZlpBsSrZLO6c0qWyVx2IsWBgmuO0ybrInOOJE4tBFxLECnde68K07u2GcIEap0QpTXzbeNdttHPQq3xb9Lnt0ITXEVJjGfLtDdNo03FM1qYzKRG4FganZjNDscyqo9ROhdLAMKUEBddi4IjeXC8TicwGaV9g3miRDNe9xGOoBOZ1w1iRaw1Mo1ejaKrxhKSnCPNa6RBnpXOrbtJ4kiRnpfmeCbpnB0piJTq2Yqslr2SUvDyq0Z5+K6HeyJIF+qvth6b7VlerihZcPOr9uRlPDlkwXRGxuXPhgK273//+xse8JnPfOZ5TyYjo8tqC4Cpus9D4w2+e2KO5+0f6plRd+nubieLJBHnWiHfOzVPJ4wpuBZjfTkObitT70QUXZtbr1r9D5ZSmjsfmmIM6M85SNEVgbBwi7IXBF65rXTedgZRorjvdA0/Vhta0CptFqzj8z4PnanRl7fZO1RAIBgoOARxwtePzpIozUDB5Tl7+plthWil6RbWbUR4RApTWjhYzPHiK0cQQvDNY3Ns68vhWhKhFdPNkGgV77etxkoXhKOVHKdqQc8o/FxIYfqV1Cb69bpBmRALx0ml/U7n06N3vpnHjbxerIwYRvdhrTBmvB7QX3CIUxGb9fBsiOP0GKVKoznHMsHOsufGm41UIc2CmpJAz5YEQq1aTrmcc71Uok0ZbqJN/1fOkdhaE2pFogVojRQCW4BCUvJM+bIQggE0Z6o+ClNeKYWgr+CwrZxDo3l8ukkrVKZsMu03UxqKriRWpkw0UZp2ENMKExMo0lUMVUgs8o5FW+tUZVVhWQKVmGC4J1ijF8pc845ljq82gdt62bIDIyUeBq7eUeHITOeCe4jPxUZ7ltdSlDxX2XjGE0MWTGdkPDXY0Crz+uuvN43O56gJEkJkxtkZF8xaC4DtfTn2DhY4Ntta0vMBaS+lH7NvqNgrZwI4MtWkE8YMFByq7YjRSo5DIyUAHptq8q8PTXJodOVC4sx8h8dnWozloL/oMl4PcYsuIi2pKuVsZpsBxyzBTfuHNm1ncN+ZGrV2SCdKTE+SXOpLtRyjaCdQwLHZFqfm2vQXXTzbx7aMGe/2ikfetZEC2mFCMzBCBxrIOzbtKEYpE5Cs9VW2BYwN5hnry3Nirs0DZ+sMFj2iOMG1U5XNvIcfa6rtc2cGL5Tu5xglmnaYsJbA4PJeO5OFOb/XXBzUdse1WCjPuxTolicKIGcbEYpGJ6IdJqmM/to4ErZXPGaaEWGsCBNtrA9iZTJtyx5/voFnO4hxHUmQWlVs1bniWhI/Nn51cZCQswWOLdMyQ5NlDxOTJSp6Nq4tSZLUCiDtHevLOwyXPCp5Gz9STNaD3ndCa1Pm2IkSgljhWJK8YxGkvWqzrRCd9rQlaYCvgZofU3BtCqkRdhSDFBpHCsJEm+ycIt34kSSJopX24zlBzPfPzFN0HfYMFdbNlr35B/Yz1Ypp+BHNIKaUs/FsC9U17N5CNtKznClKXrpkwXRGxlOHDQVsjz/++MWeR0ZGj7UWAEIIDm0rMdcOOTHbZtdAntFKrlemM1Ry+bEbd/GFh6d4bKpJybOYbZmSwWo7Iu9aHBwpLhIjWXsh0S1dBLOzPe/Xl1gCKA21TsSh0dJ52Rk8OtngxFwbKRYyJasZPHdxLEHOlggBzUARoijECdsqHu0g4XS1zWwrIO9YNP0YIUz/jWsbc/BEKSwh0MIszm0plij3CYzH1VDBQSt4ZLJhDMW15ky1QzOI6U80uwcLDBQcxmudJT04FwPJQmBZ8yOj1LgGyyslZaqIuV7PniVhrC/HeM03vXjpGN14R7Dgy9YNjrr/vlTY3ufhSEmkFH6U0AziJeIksHK+kYKTc8GS22PNikCva6J9vsu4WIMKU+GOczzWXqTeeC46sTmXIe1REyYIEml5o/keSHb056jkXaJE0ehEJjtnSVzLbP4UPRutNXOtkChRxmA7NiXVYaLwbEGQQDOIyNum5DFMjBCMI831yJaanC3Ju7bxfMMEzrGi1w+XcyzOzPupZ51NX8GmFSS0NaCN+FHOtZioBYyU4WXPGF034yGlIIgTvvjwdK/EzbMkI+UcN+4b4KodlS3tTzpXz3KmKHnpkgXTGRlPHTYUsO3du/dizyMjo8d6C4DBosdz9g7wnRNV5lomo7C8TGfvUIHP3T/J3Ser1DsRfXmH0UqOgyPFntksrL+QWKzKNlBwuH53P0emmlTbYU+kYLDo8X89bw8Hhks9YZSNNHMfGi3zmmft4KGJGtONsKdWJwDbWpCV72JLIycuJbSCpCc60PRjjs+2jV+U0lRbmlLOIZeq/FVbIVKavqRarEm0TksFFwXBmEBRCHBtQbngMJMaBitlyst2D+Y5MdumFcRIoWkGMYlSKxby5xPQrBfzqUX3tfwISwg2ktMziocSrTWO1KtK3TsyNUIOkxX3dzsgl/dTuZYRwlivje4ix7BLXqfkWbiWxLUtPCShZTJA1Y45n/Wyxy/+fSNzlGJpoHo+c3RsYcoB15H1F+mENirqojRYQvf67Qqu3csYtlKT6oJn49n2QhlzSTKRbjIkCpJE0Q5j4kTTDmMcSxDECs+RlDwbS5qeN0cIAqXRwmyYuJYR/fEjRX9R9Pr0wljhWIL5doTSJlgr5myGih6WFMh+OFXziZVivh0RJZqSZ7NrIM/+kSIF18aRgol6wCMTDV565eia15Bj000+9q3TvRI3P7J4ZKLOtx6f47P3j3PF9jLP3j3whPUnna+iZMbFJwumMzKeOpz3FfTBBx/k5MmThGG45PbXvva1FzypjKc351oA5ByLa3ZU+Mmb9lDJOyuCpMVms3/65aMMFT22r7LDuN5CYrkq22DR5bn7BpZYCDxv3yDbKh4f+tJRjkw1qHZCLCE5OFLi9TeOccW2yprv8artFfYNFvHDBCkEQZrNihb1m0G66LXMjn8YaqK0xBENrUgRJEYCXgqBEFDvRAS2JO9a3HemRjuITYDVTd0J05MkWViQ21JgW0aAYaYR0gwT4rSMbaLmM9UIjMS7gq8fmcO1IYpXBgTptDbFuR7fE/9Ab7jEUQNKqbSMe+F2x4Ld/XkmGwFhrPBjhb+KT1vXSLub8XTtBaEIJdav7buYwdpyWwPHkuzsz9OJEhp+TM6xmK77sGj+58pYrRVgdm9XyvS7nQ8aCOKFc21x5nJxZlcKE3y2wgS1wfrLSJnz2LEEYaRo+Al9OZt2EJG3LWqdiDhR7Ow34hxCCPoLDlMNI+ZyqtrBssxn6ocJrm0hBOwZLGBLSSdKqOQdNDDXDPBs098XKJVuYhQ4OFIE4L7TNU7Pd2j63SweDBRd+nIO1XZIJzKBtJtmurf35dk/VGRnf55K3lmmuizOmfG486GpXolbtR1x35kandAowjb8iGo75L4zT1x/0vkoSmY8MWTBdEbGU4dNf0uPHTvGj/zIj3Dfffct6WvrXqSzHraMC2WjC4Ab9w6uuQstpeDGvYPctafK/WdrbF92/7kWEmupsgkB1XbEroECz9hR4S+/foKTs23aoQmMgljx0Hidbz0+y39++WFeftW2Nd/jzv4C956psb3PY3zep50aES9e0GpMRiFSGpGGcksW4toYOyNMSVusNFFi+m4OjhQ4WzM9bnXfZAEKrpHGl0gc28iUx2k5WBApgnih9NBKRRC6AhZWV3oRwXKh9ovfy2aCL0ee2xzakebzi1NZd0il621JlGjyroVnS6rteM15p9Vq6XNNj1jRsYmShFaolmTfnLTkbyvMw4uuJIjUiiyeIBVESedWztm86IoR+gsOX350mk6YUOtEPRXNbo9bV6lyvfe5PGjrBWvp67mW5EI6+JYJWuJaaY+h6mZDBZYlcS3Tl7ZRNCZos6Q5r6stExzlHNPPVevEINrsGyoSK021FSOlIGdZvQnFynxndJywoy/Hc/cNAnB0qsVcO8SPYlzb4gev3c5VOyr8y/fPrtgAetEVI9T9iLtPzvPQ2Rr7h4p4tsVkIyBKVKpmKYgtQbWVMNMMOTxaXrGBBBvLeDw+02JHn5HJ7fboDqb9tQiThb9up8dkI3hC+pM2qyiZ8cSRBdMZGU8dNmmjC7/4i7/I/v37mZqaolAo8MADD/CVr3yFG2+8kS996UsXYYoZTze6C4DBostjU00afkSsFA0/4rGp5oYXABc6zoFUnOTqHRXm2xHHZ1rMtyOuG+vj9pv38fB4g5OzbartkFonIu/ajJQ9RsseE3Wf/37nYzw60VhzbrdePUrBsai2FoKk1WailOr1cwkWAolueaPSmiTRRIlOgzuYbobcdaLKTDNgtOyyZ7CAJQVhrLGlRKMpejbX7+7DcyyCKMGPknQBbAyAXUv2esC68xIaHClxN33lODdCpBLsYuVxsC2BlAtByJpjYAKMrk9X7/kSCq7NRN1nrhUxv06wthw/Nv5kzTAm0qZ0VKZzdGRq1r3KYOezPI2Vppy38eylz17aa2jKVHcP5JluBEzXAxp+RBSbfrEuSq/fO9aNv5dPvRvEORbs6PMonm+KbQ3CxPQWWmmGt2sQLqXc1DHrBrFaC+ZaRsBHCkHOkZRyDlJCrRNzdr5DJ0xItKLkObzkymGu2lFhqOgxUHAop32p/QUXSwiUhiu2l7hp/wC7Bgq86rrt/PIrn8EPXT/GDXsGaQRLgykhBJWcQ8GxKKSiP9W26YvLOxJLGqGiKDbNqq0g5utHZ/jG0Rm+c7zKXCvojbWRjIcpcbNp+DHVdkgpt5Cl66rkRkov6U+62HQVJa/d2bfiWpmpED55bNXf0oyMjCefTf8l/sY3vsEXvvAFhoeHkVIipeQHfuAH+O3f/m3+83/+z9xzzz0XY54ZTzM2Kin9RIzTVWVb3KN2Zr7DkakG7TDGj5KFHW7Acyy2VzymGwF/d/cp/p8fvGrVP4gvODjMS64c4Z/uHe8t7hIFtmVk1jtpKilKZcNd20LppJeZcC2zEPRs2cvOQSoWISBOFEmiODPvMzaQZ7DoUvcjtpVzaY9OwmwrIlEm2EMsiD/YllihGJg+hGaYpP5RZuEtxOY9yhbTDRq0NnmcJH0Pi49Ykihitf6iQgBFz6LoWsx3YvOeFt071w57Aej5TDdM9fa7gU533kJIBKZUNWebe6JELci4b+I1oljT0qY8Nh0KW4CWkjgNyHK2xdl5n7+/+wx+lNBJa0W7n4+TZmDP9brdwKz7Pro9ekIKyp5NKecw1wqQemurJrrZv+6HYFTtzS/2BjKoXbpnQ5QogijBkpK8Y3zYCq6FYznUOwnlnMO1Oyp84/FZdg/m2TNYZM+gUZMN0162e05WOTZtelTt9LxGw9hAnhv2DDBe9xnrz6+bSTowXCRKFCfm2mhl7Ay614QwVjSCGNsyNgOdyKhDLvZ0HCi4G8p4dEvcwsRkx53cwp/xrg+la0lyjkW13eL+szWAi26UvBFFyYwnnq36W5qRkfHksumALUkSymXzBR8eHubs2bNceeWV7N27l0ceeWTLJ5jx9GWrFgAXOs5qKmmtMKbaCVNZbWdFeZNrW7i24Og6/ShSCl521Ta++Mg0ecfCtgT1TgQabC1wpEj9nrqZBE3OtdGLyqWU1qaETi3K0AlAgkw7r9phQrUVMlzyaIcJ7Sgh70pmWyGFyMISAtuSSGUk3hNt/lvc/6WX/TTy5BcmSgELfWKwENx0+5oWr9vzjkWgjFz7mghTHlpwLeZa4VJfNWF64LaidLMXcKS/dPsAldYkSiOlCXh1GpUkauPlkgp6MvsIcw54tpHGL7iSkZKHbVvMNAKm6n7veHXH10CUBoobCRaXBOQJ5FxzHg4UnZ5qpJWe29YWr7tVOkfbEuRsi4Zvzuu1+upWQ7PgW5ezJf15m/lORCdKsKTAsc3GxPFqG1tKrty2UIpYyZuenrlWKlKDMcZuxCYAjJRmuhkw/pmHOTRa6gl5rLf4PTHb5tf/+QGm6j4lYSOEJIoVNd+Yzu8ZLODaFifn2jQDs9HT9CMeHK8zUsoxVDp3xmP/cJH7xptsK3vYlinz9WxTvtz0Y0YrOaJE8f1j80w1Aj5x10nuKHhPiFHyuRQlM54csmA6I+PyZ9MB27XXXsu9997L/v37uemmm3jf+96H67r82Z/9GQcOHLgYc8y4TFFKc7ra5thMCzALjd0DhU39kTifBYBSetU/TKuNo5TmVLXNsekms82QobLLgeESuwcKSx+TqkDmHQuBEeMII42fihMsJ0q6GTHW7UcZKXvsGSwQRAlHZ1oEicKzJAXPwrUlohkSJQmeYzNQcDi8rcwDZ2rMtUKCNOOSaN1T5ItTk15bmsJBrU22rtaJyDkWZc8m50jG53382GT1Bksu9U5MtZ30gqe1Mma9bBhL++i6JYJSGBW+bqZkvYW3lWb0uoFUN/gw81763DBRafi5+oi2ECA0ji2oLlLqU8ocn8Vz30q6ZapJesASQCiNbUnyntULpKUQKKWMT9oGsnyJhoIFpbyRix/IG8XDmVZEoky5XTdLJeTKwc7HOy0hLcnM2QzkXebaIc/e1cd0owNE9Bdc/Hq0NGBdhc0c566JdcGTKG3RicBSpgT1XK9hW/QCeFvCYMHBsSWDUtDwY2qdCNcy34n9Q0UGCiYInWkGuJaknGamjk61iBPFSMnrmaZrrXG1OXfqfsSpuTZBpHpCHm97ycFVrzGHRsvMNAP+f597hE6U4EcqLS8VbK/kGCh6BHHCUMlloODSTjdkpuoBz9k7wI/fuPucAdXLrxrlTD1kou6bbHI7QucsWkFC3rUYLrl871SV6WbIroE81+zooxMlmVHy05wsmM7IuLzZdMD2q7/6q7RaZgH+nve8h3/37/4dL3zhCxkaGuITn/jEpsb60Ic+xIc+9CGOHz8OwDXXXMO73/1uXvWqVwHg+z7/5b/8F/7X//pfBEHAK1/5Sv7kT/6EbdsWhBxOnjzJ2972Nr74xS9SKpW4/fbb+e3f/m1se+GtfelLX+Kd73wnDzzwALt37+ZXf/VX+Zmf+Zklc/ngBz/I7/3e7zExMcGznvUs/uiP/ojnPe95vfs3MpeMBY5MNfj4t07yzWOz1NoRWkB/3uX5+wd5w/P3XLQFw5GpRm/3248Tcra15s7ykakGH//mSb782DRTdZ9YGcPc0UqOFx8e4Sdu3AnAR776OEdmOsw0A2aaIaAZKpmSx7lWSN6x6Cu4vXG7O919BYf+VMVyLYquzXDJQwqYaYYMl1zQ0Axi5tsmUxAlmlhFdMKEajtKM2pmSd5VhzT/ThfKAjwL2pERVFAaoiShM9sy/TQteuIUM82Q2VaIUisX+Wv1Ny2nGzh0Ay5LGlGMWEHdX7tXTAgTrC1+3W7GbnkizY81qwg69pBCm6ymZfrrlAZHCuMlp/T6mbkLQAhoR8r0E4qFwDOIFZFSlFwTaI1WcjiW4ORci/nOuScjMEIzXQuFIDaZGqVXfgYqzXZeSFlql939OZ53YJh2GHNqvsPZuo9IA97tlRxz7Rh/PV8D1jdmX40gVpyp+r1A1pKCoitphWrVc6erOmlJgSc0QWyyyJN1v5diFkDJsxkpeeRdi1ddu52/+PoJvnpkhrwrcSyLwYLLtj6P2bSHrKs6aYmuOqjExvSQ+ul3brZphDze+uLSmovfH3vObqbqAV87MsNg0SFKNI/PtBgour1rw46+PM/Z008zSOhEMZN1nx9+9tiGrosHRkq9LN89p6pMNwOmGwk7+nNcsa3MoxMNppshIyWPq3f0YVuSsiUzo+SMjIyMy5gNB2w33ngjP/dzP8cb3vAGKhUjV37o0CEefvhh5ubmGBgYWFX1aj127drF7/zO73D48GG01vzlX/4lP/RDP8Q999zDNddcwzve8Q4+9alP8bd/+7f09fXx9re/nde97nV87WtfA0x55mte8xq2b9/O17/+dcbHx3njG9+I4zj8t//23wBj+v2a17yGt771rfz1X/81d955Jz/3cz/Hjh07eOUrXwnAJz7xCd75znfy4Q9/mJtuuokPfOADvPKVr+SRRx5hdHQU4JxzyVjgyFSDD/zrY9x7ah5LwFDZRWA8iu54aJKpZsAv3Xp4y4O2I1MNPvq14z1/ooKbpx3Gq+4sd+f4nRNVWn6EFFBwLeJEM1n3+fT9E5yYrfPaQXhwvI7r2My2QlpBjEAjBOwdKjDZ9Dkx12YPumfS2/RjPNtI7fcXzCJNKb3qAqmr4vWNYzMIYUrrphoBUaIXhEbSrFWolXltKdCIdHEpegbfElM+ZwlBO1JL7AGMol6aCRILi/5EGyERWFraqFlQZDzX2ntxWWS3NC1MIOqKpZC+h0WvI8XaptZrBoWr0A0QSRVrY6VwLQvHEtQ7MaDPmS28IPRC/1fOdWiHsQlEI1OCWevEDJVc9g0XuPfkPJ4lzhlcCRYylFHYPUhqyf0rgrYtSh26toUUMFBwGcg7NPwIrc1r5xyjdniuo7aZuXR76NSic8O2BIleKMFcHB+mlaIooBOZPj8nDdATpbEsSRgrgthki+daIa4t+f/+430MlT2zkZAYP8LJeocztTYt35QmRspkcefSDG0Qm2ZRAVTyXXXY/Dll96UUvOq67anATUh/wUFK42MYxoq8a3NwpISUkkpeIgQMFDzK3spM/VosLnF7aKLOdx6fY7oR9Gw4dg3kuXpHH4PFhY2kzCg5IyMj4/Jlw1pvz3rWs/jlX/5lduzYwRvf+MYlipCDg4ObDtYA/v2///e8+tWv5vDhw1xxxRX81m/9FqVSiW9+85vUajU+8pGP8Ad/8Ae87GUv4znPeQ4f/ehH+frXv843v/lNAD7/+c/z4IMP8ld/9Vdcf/31vOpVr+I3f/M3+eAHP9jzh/vwhz/M/v37+f3f/32uuuoq3v72t/P617+e97///b15/MEf/AFvectbeNOb3sTVV1/Nhz/8YQqFAn/+538OsKG5ZBiU0nz2/gkenWjgWiazkHdsco7FtoqHa0senWzwufsnUFu1ykxf93P3T/b8ico5B0uaBv/DoyXmWiGff2ASpUzw9Nn7JnhkokGY9roUPYecY1H0bGwpCOOEB8/WATgwlGe8FhBECdsqHqOVHEGkaEcJLzo0jGNLzs77TNU7tMME15E0Q8VMI+DodJMP/OtjPa+25XRVvIbS/rKpekAUK9O/FiVIAX1pORyYhWretii4Fv0Fh7GBXCobDgVbcnCkSDFnlOp0snLx3BX3gIXFcvf27r+7/U+b/XQWi3H4cUIYK1xHctvVI+wZLJh+JbHST+xCcG0TtCZa4zkSiaATmlK0riG4JcBa9jyj7ihw5eo9eBu9mvXCKCEpexZaG3sFIU1QClD3I7748DTTzQA/WiVFtgzN+sIbW13WuZhHJxt85v4JZpoBA0UPqyvNCZyd79DeqCLIBrHTz6jsWQwVXTxHUvZsXEuac1dA3hFLzlOd1mSaZJrpv+wqQxYcSRQvlPbalsCxJPOdiPF5n539OUYrubS30ZwrUgp2DeRIlGauFRAnGivtQxSYzFu9E9IOYywpCOKEVhj3SqUfnqhzaq695Hq2WDUxTswxm29HjJQ9rt/d3wukutLqh0ZLS4RG1hu7S7fE7bart/P/vOoq3nnblfz4c3dzcLTI8/cPLQnWuuRdqzf/jIyMjIzLhw1n2D7ykY/wR3/0R3zyk5/kL/7iL3j5y1/O/v37+dmf/Vluv/12xsbGLmgiSZLwt3/7t7RaLW6++Wa++93vEkURt956a+8xz3jGM9izZw/f+MY3eP7zn883vvENrrvuuiVlia985St529vexgMPPMCzn/1svvGNbywZo/uYX/qlXwIgDEO++93v8iu/8iu9+6WU3HrrrXzjG98A2NBcViMIAoJgQbK5XjcBQBRFRFG07vHo3n+ux11qnKl2eOhMFQtFX8HCkYs6XgQM5iVNP+HB01VOzjQYG9ga/5cz1Q7Hp+uMVVwkS9NCAhiruDw+VefkjAmaHjpTBRXjCI3rSmy58ATLk/hBgk49BWcaPs1OwEC++35gIC9ptAOuGi1y25XDPHi2znDZJVaamWZIyZZcvbPMjr487TDhobNVJmotfuqmPewbKjJe83v9L7v7crz1hXuZnm/y4HgDxxIIDTmpyedsk22JFAXHZNC2VzxcWxBEiqt3Vtg/mOPB8ToCaHUCkijGlRpt6RWByuJj0n3HqwVQjgRXCkJlDLMFIKXJ9FlpNLc482GnWTtLGKNpTxnxj1LeoS9v40pNnwed9ElrzWs5Xnq8Pbl6mOIJY2ZtaSjY8Pz9/RyZbjPVDBjIe5yZ75h+OK0JU9VLIcAVglgpEgF52yzeY6V72a2u0MtG8aRirukj0JQdgWNZdKKE0KjF9Pzz/DjG2eibfxIQQNsP+PbRaZ5/YJC2bzHXNJtf1aaPtwHlkc1mLiUQJwk5C4o2FB3BM3eWeehsgyBRlD2b6VZgFCxFt19S9ILxbmZ6rOJwZKqJLTV5KbEsgYVACk2xYNMOE07NNnn1NdtohZpQKcIo4cGzNeotnyAIEVpRsHUqxa+JtaboCiSaOI7RSULBFkzNt/jCA+M8PtPqlV7vGy5w3VgfQyWv973+uVv2MF7zeWSyzucemCSMEjypUUlEJ1RM1H2Giy4vv3KIJIlJEjg23eTOh6aWjL1/uMhLrjAecWv9TdhedkhGi4wUHIIwWqIe2SUIYgq2ICcvv78tlwKX69/lpxLZZ/Dkk30GW8tGj6PQejPdBgscPXqUj370o/zP//k/OXv2LLfddhtvfvObed3rXrepce677z5uvvlmfN+nVCrx8Y9/nFe/+tV8/OMf501vetOSgAfgec97Hi996Uv53d/9XX7+53+eEydO8LnPfa53f7vdplgs8ulPf5pXvepVXHHFFbzpTW9aEpB9+tOf5jWveQ3tdptqtcrY2Bhf//rXufnmm3uP+eVf/mW+/OUv861vfWtDc1mNX//1X+c3fuM3Vtz+8Y9/nEIhK0fJyMjIyMjIyMjIeLrSbrd5wxveQK1W67WcrcZ5O6IePHiQ9773vfzmb/4mf//3f89/+A//gc9+9rMkyea6+6+88kq+973vUavV+Lu/+ztuv/12vvzlL5/vtC4pfuVXfoV3vvOdvd/r9Tq7d+/mtttuW/dDARNx33HHHbziFa/AcTbe2/Bkc6ba4fc+9zDHpluUchauvTSdEMYJTT/hwHCRd/3gM7Y0w/bBLx6hL+9QWmVnuZmqxv3CSw8B8HuffZhHpxrUOzGuI7EX9ZfFSuMHCZZI+JVnxXwrGOO+8RY5R+Lasvc+/EjzvH2DCAG1TsSPPmeMv//umd4cqu2IY9NN5tsRcaIIE0UriDkwUmSsP8/Z+Q6TjYBmEFNwLJ67b5CztQ5RrJjvxEzWO2kplCDWymQL0jKonCNXvP5bX3SAP//64/zrg5MEUUysF2Ttkw30ol0I3drqomuUMfOuZLDooZVGCzg91yHRi33lNoYnNb95o+LXviMJNuDD1s0Kdn+XwohHeLaFY0vCKKEdxjiWRGnTJ1jKu5TTcrpGENMJE6abwXmXbV4MNconCwGUbPi1G5INfQYARUcSqwVriM0ex7Ir8Rybph8Ra01/3iVITd1jpYhXOZelgKJj0YkT+nIOUgraQUIQJwu9k6mYyM7+HNfu7MO1LB4ar9EKE/YO5XnwTB0/TnqZY0uAJ2WamdUIBEMlj+0Vj7xr88xdfQghqLZD7jtdoxPGxAq2VTyu3FZmshEwUHT5qZv2cGCkBJhSx8XZ9R19uV5vq1Kaj3z1cR4cr3NwpLikzUBrzfHpBi8rT3DrrbfiuivLHbscm27yV986SbUVsr2SI+/KXjZv+XwuB9Y7Zk80l+vf5acS2Wfw5JN9BltLt/ruXJx3wAZGffGjH/0of//3f49t27zlLW/Z9Biu63LokFlEP+c5z+Guu+7iD//wD/mJn/gJwjBkfn6e/v7+3uMnJyfZvn07ANu3b+fb3/72kvEmJyd793V/dm9b/JhKpUI+n8eyLCzLWvUxi8c411xWw/M8PM9bcbvjOBs+yTfz2EuBPcM2V40N8Nh0h7l2wlDJ7i08tNbMdYyx69W7BtgzXN6yP7x7hm32jVS4/2yNwzl3xWLnTD3kurE+9gwb0ZGrxgZ4dKZDpBOCQFFw7d6Crh0mSCGxLQHEDJdzlOZjphs+g0UTgFY7itFKjkLO4ch0i+vG+qgUc7RizTbPZbYd8b1TdTqh8WnzXKhWO1T9hFPzAWdqkRF0wLxmI4j410dmGS65jJQ8rtxRZLoV4ycxJc8iSXvmbA0nqj6WlAyVXMJEM90KeeaufmzXoR3BYLnA8ZkWCtOvl1blnZfU+0boHmkhwErAtiTNUNMMA4quRc2PaYdmyXu+BEoQJOd+vp8snpGhk2gGLEEUapqBIlGCdmJ6yYqeRV8hRycyvYe27eD7ik4snjJB14VipeWoG/0MwkURksXS0tmNoAJNTimktLEFKCSdRBElmihZ+rksDo7jRJFoQaIThBBEsQIh0VovCRqPzwacmZ/GtU3QvmewQH8xT7kY4sUJDT+mFSYECprpWSuFwLUlw5U8J+d9yjnFro5ioODw2FSHmp9Q8hxUrDhbjzi0TXJgtMJjU03ufGSWw9v7e9e6faOrB1un5tocmekw2lcAaS89/wSMVAqgYbqVsK+49t+EK3cOcPstdk8tN2iEeLbF1WMDl51R8mZUf59ILre/y09Fss/gySf7DLaGjR7DDYuOdDl9+jTvfe97OXToEC972cs4fvw4f/Inf8L4+Dgf/vCHNz3R5SilCIKA5zznOTiOw5133tm775FHHuHkyZO90sWbb76Z++67j6mpqd5j7rjjDiqVCldffXXvMYvH6D6mO4brujznOc9Z8hilFHfeeWfvMRuZS4ZBSsEPXrudK7aXCVPFxU4U04kSJusBYay4YluZV167fUt3SbviHYNFl8emmjT8iFgpGn7EY1NNBosLhrRSCn7wuu1cub2M6xivrJYf4UcJLT8mVkYi/uqdJgt6bLbDjj4Pz7GYrAfGLNcxvWRHplu9scueQ862aAURR6Ya1DsROUeC1kSxIogVOVtSbUWM13yiRGEJgWtJHEviRwlzrZDpZsCD43U820hxh4tWm0GsqftG3v/YVItPfPc0D080GCy5PDhep9qJODxawraEUaZMjaUuZvDR7VKUQCc0WcR2ZH52IpPleDKDH6Wh2oqYa0epMbjJOHaVAM/Md7AtQSdSHBwt4sqnTobsQrHlgnH2RumeD+eTXQOTgW2m2bHBgtvLbEspWH7JWDx8lG5K+LGmEy1YAiwv+hfCWCY0goQg1pye9/n28TnOznc4WwtoBsYrT2GybJWcEfnJOxbznQhLGmGZo9NN6p2I8XqHVpRwet4oNE41fO45NU+1HbG94nHv6Xm+8tj0muIhXVphjB8nFNawAcm7sve4c3FotMzbXnKQd7ziCv7Tyw/zjldcwVtffPCyC9Y++rXj3H+2Rn/B4cBwif6Cw/1na3z0a8dXFXHKyMjIeKqy4QzbJz/5Sf78z/+cO++8k9HRUW6//XZ+9md/tpcdOx9+5Vd+hVe96lXs2bOHRqPBxz/+cb70pS/xuc99jr6+Pt785jfzzne+k8HBQSqVCv/pP/0nbr755p7Ix2233cbVV1/NT//0T/O+972PiYkJfvVXf5Vf+IVf6GW23vrWt/LHf/zH/PIv/zI/+7M/yxe+8AU++clP8qlPfao3j3e+853cfvvt3HjjjTzvec/jAx/4AK1Wize96U0AG5pLxgKHRsv80q2Hez5ss6loQV/e5eYDg/zkTRfHh62rzNbdkZ2s+3i2xXVjfSt2lntzXOTD1g4TbCnYVsnxkitG+PHn7OThu6a4ekeFIzMdhopuapSsGSp6gFgytlKagyMlvvToFI9Pt4y6nB8hhcCW0AljPFvSDhMUJmjoRKkkfypLLwU0/Ii8Y5F3LZxEoEPQOlnhwWVJI2V+utrh/Z9/lD1DeSZqAX15h6Giy9maT6TWlrXfSiwWpPuNKJ7JTLTCOP39yWXxFHoCKal4SjOIEQ2BwGww1NpZIzWYYM21JBeSmz3fU08DUaKZbPhIISh5Nlprgk3U0yaLJVFTuhm5rjuB0BqtNdV2SJSazi9+BaWNz17ZsxkbyFPvRHQiRdlzmGuFnKy2mW2GSCnI2TLNZkvm2xHfPDZLwbGYaQX8j68eY7SUWzc7VHRtcrZFO4wp51buuHZSi4f1fB0XczkbJS9X/e1WTJRzTuYnl5GR8bRkwwHbT/3UT/Ga17yGf/zHf+TVr341Um46ObeCqakp3vjGNzI+Pk5fXx/PfOYz+dznPscrXvEKAN7//vcjpeRHf/RHl5hVd7Esi3/5l3/hbW97GzfffDPFYpHbb7+d97znPb3H7N+/n0996lO84x3v4A//8A/ZtWsX/+N//I+eBxvAT/zETzA9Pc273/1uJiYmuP766/nsZz+7RH3yXHPJWMqh0TK/+pqrOV1tc2zGGK3vHy6ye6Bw0f7AKqXxbIuXPmOE5+4foJSzKXsOY/35VV/z0GiZX/13V3N7tc2x6SazzZChssuB4RK7BwokSczDwJt/YD9TrZhWGJN3LKOkFyUUXXvJ2FIKnrGjzP/6zkkaQUTJs3FtSZRo5jsRUawJk6S3IFTaeKCZQMco02k0c62Ig6Muz9kzaG4Xms8/MEk7SLClUWtUWpB3LcLIZAlqnRA/8ojimEcnfaNwlyzI9a+2cO5K929FPJfAisBMw0UzrD4X673nbulrrECiURi/rsslqybS/y32L9tqLMwxihKFEuf3It3P4HxCPon5PvlpkDJaNpYg853zl6M3Vg6SKFUDTVJPwyRRhInuWU6EiybbjfkcW5KzJYlnU+vEzHdC8q7F+LyP1hrXMh51QawoeRaeLThT62ABQyWXA0Mm673YE/LAsPFR6/VmVUxAd//ZGiXPXlHWPVH3ua4MO/py530MLhfOzHc4Ot1kR19uhWVQ5ieXkZHxdGTDAdvp06d7JtJbxUc+8pF178/lcnzwgx/kgx/84JqP2bt3L5/+9KfXHeclL3kJ99xzz7qPefvb387b3/72C5pLxlKkFOwZKrJnqHjRX2u9XgcpTXng4sVRN9CSUrB3qMjeVebY1c/Z6E61UpqHxxtsL+fohAlxovEjhdKmrCxEL9nwX7zTrzC7/ZaQdOKE6XpArR0yWPKod0KagfGLcizjdCa0Jk5MX5jnmH6dI1NN7HTAMF4/EFsc0PTMiJ/EiMVOs3NbNYXF43QDBpH+dIQ5jkGiVph3X+qCIbsHcoSx8QvbYku0Hj0j6vQ/eZ42BHrRz80eV4X549TN2jb9iEre3bCHn2dBlCwNFCMFsVp60KJEk4iFHs/lQ7uWmUMnjDk528ZPFH6UEMQw3xb05R2Krm3KFIXx/gsTxWw1JIoVWkApUiitKefcXnbob751koGiy7Hp1pLr1TN2lDlb6/DYlAlW8q5FJ0wYrxn5f+BpkVFaKA9dXZQq71pM1v3MTy4jI+Npw4YDtq0O1jIytopur8NcK2RHX46Cm6cdxr3d7Jc9Y5SHxxsXvXG9uyt87VgF2xKcnfcpeZLJeoifeoAtZ3GQFCuo+an3Wyvkjocm2VbJgYAgNkIK6IVsnEp/ghF2ULHC8Ww8IQlXqUPM24Ig1qsuTM/P3GPrsKRAK71lhtpdFhuAd3+GicZeI7V4KQdrXUPzvGuRCy3i4OL0Bm51IKhJDbIx5+lG5xwmmrQFlJofk3Nsco6kFa4/QYEJ1taaS/cx3eCve851FVW7SLGQhW0nCUHaF6e1NmluNDPNANeWhPGCkqQfJr2xhBAo4N7TtZ5hdt6RfOHhKfYMFTg4Ulr3etUt6752Zx/X7SxSfeQ4Z6od9gzbT+nA7dzloQmebW24PDQjIyPjcie72mVc1pyr1+GeU/P89zsfY0dfjp39+RWLozfdsm/LgrburvBOL8+h0TLNIGG26VP3o15/2kayWAKMMbVSnKm2jeJd2hcWJzqVqTe9cEJi1PAWHY/OGivuSOmLphR5IdjCKEtGm7QE2QirxWUCY92w2kdxKWfYFEYhVIqlgejlQKxNgDRQcGiHMf4GpCO7JZ/dXs1Ea/rzDq0wWPd5lji3MmU3u52TAj+N2DQsHFu9yDi+K3qJuUNKQdG1sKRgrh2iNewezDPdCOhESa+P03MEOdtmW9mjFcYcnW7Sn+/nzHyHTpQw1p/vBSOLe7MemWjwH150gPE0gzTTCPjeyXn++d5xfiAHH/ziEfaNVJ50pcSLyVh/ft3y0PGaz3VjfYz1b40tTEZGRsalzoU3omVkPIms1+sA0A5iphsB2ys5yjkHSwrKOYfDoyXmWiGff2ByXeU2gDhWfPvxWT5z/zjffnyWeHkdXcriXeHBosuzdvWZ0rJF41sCyp61rsB9N8hIlNnhjxalnRSmryhRCo0mjBOC7oJTQytM1sxSrTHtJx3bEgRxclGCyVWzmov+bYlFtgQX4fUvBkpvXip/s1yMY5FoqPsRfXmHvrxN2Vu91lJiAiedPkcK81+9HTLTOrcgzEaPTaLAsmRPedK2jGKrLQW2NJmxxZeGKDECPqVUgMSxBAJBrDSOZWT/+wsulZyDlZZZljwLz7Eo5WzmWiHjNZ+ZZkjRs/GWeVQu7s0ar/vsHixgS8Fn7p/ggfE6fXkT3PXln/pKiZtR/c3IyMh4OpBl2DIua9brdWj4MY0gNsIfy4KyzTSu/8eP382RmQ5RonAsyb6hIj9zyz5eftW2JY9bvCtcdC38KMESpoTNkSLNiAnKOZt4jUxYVxSj20O0+Pbuo83C12SjFr8rwYXo+T15WFJsKOOylXRfTem0h4+tE2B5KnAxjoNMg+Nu3+hjkybYWC5KopZNIEgTr6uV+V4I3d7NnC0JYoXWmjABWwocW9BapJhjAa4jsaRAph5vQawpeRatIGa2FRHFCs8xQZhMpf+LroUQAseSNIOYdhjTDGL2Dxcp51b++V3cm7W8ekCioAOlnM3hnPuUV0rcjOpvRkZGxlOd8wrY5ufn+bu/+zuOHj3Ku971LgYHB7n77rvZtm0bY2NjWz3HjIw1Wa/XIUwUQdqzZuTJl3KuxvUvP2L8/Y5MNynnvZ4AwKNTDX77Mw8DLAnaurvCD03U+dyDk3TChGo7JNFGPS5vS2xL0okUri0JIrVkobp4hssDMdsyGTKtVwYW3V6cyzFYA6h4Np0w3LL5b1SYAhaO40bLVTPOH62Nmmi1FeJISZx+SE/kebv83HAtga80ji3wLCvNZmuCWGFLk3FrRwnlnN3zR+tExgdRKYVjCRxbkncsGp3I2HQIE9RJYXrv8p7dM6+fbYUUHIudyyoCtNY0/JhqOyRONHnHWlk9sGjeTxelxEOjZQ68pLSqYFRGxlazljhZRsalwKYDtu9///vceuut9PX1cfz4cd7ylrcwODjIP/zDP3Dy5Ek+9rGPXYx5ZmSsynq9Do4URLFmuGSvupu9XuN6HCv++lsn+eFh2N2fIxHmMeWcpOhanKx2+MuvH+fFh0ew7VUqi3ulXOmOvDKL1aGCQxgp6n68pGGqW0K1mkexZqmIQi9TIQTDJYdEw0xj6wKeJxIBTDW3du7rBWvLe9S6v1+o2EnP34ssS7cavSymNsbWk/UOriXMJsQ5nmunTz7fkt7F9hVaL5TBCmECtjAR9Odcbr1qFCEEZ+c7PDRRp+TaxjOxGRArRZQoZGp0H8ZGgMSPFJ5tkbMt8q5NrBQFR/b82+JEM9+O8KOEwaLHCw8NM9eOGK8ZOwAhBHOtkCNTTaqtgGonYrjo8k/fO8tQyWWq6fc86JZfGp4uSomXs59cxuXDekrTWTY341Jg0wHbO9/5Tn7mZ36G973vfZTLCyfxq1/9at7whjds6eQyMs5FN6u1mhT2RD1gpOxRcFae5udqXL/7VJWTc20YBiHlklWllJKhosux6SaffXCcQ6Plno/S5+6fJFGaV16zjUYQc8/JeebbIeWczdl5n4Yf0593cG2BbIHnSFpBTBirXs/MqmIYqUdUrBbK+BKtmW1FKH1piolshK0Iljb7ehdz3CxYW52VSp3GE02KtXsuId30kKIXsJzP8e367nVfvxusSSmwLYuSJ6nkbKYaITv7cwyVPCwpiFKBn4JnU2tH+GGIbUlsK/VdxIjXFD2J0ordAzkmGwFRbKw8+vM2TprZv2FPPz95015uOTjMsZkmH/3acR6bapJ3JI9MNmn6MQLNcMllZ1+ef773LO0oIYwSxud9Rss5rhgtsH9R1JYpJWZkbA3nUpreSnGyjIzzZdNX+rvuuos//dM/XXH72NgYExMTWzKpjIzNsFavwzN39fFjN+7iCw9PreprtF7j+mwrJFqvZ0bAfCfif37jBEMlj5xtMVxyOTbTYs9gASklfXmXZ+7q43un5umECdsqHn6sODBSJIgVV+2wOFvzeehsfUUv1YqXE+nCM/29+zNKVlc77GJLs+iNkoXnWGLtwPDpRrd/KjsWFx+97N/tMOn54y2/v/c4DUqf38na/WwXn+tSgki/ZbYU9BUctldy+JFi92Ce2WZItR2iFHg5SZQoCo5F7Cn8WKGVphMqBDBU8ihZote7lnNtBgvG4FppExraUpBzLN5w015+4PAIsHC9+ux9E3z6/gnmWgF9eYehksdwyeXxmRaJUlhC4NkWcZww1fAJwpAbdnePS6aUmJGxFZxLafqp3iuacfmw6YDN8zzq9fqK2x999FFGRka2ZFIZGZtlvV6HvUOFTTeuDxXd3u74cjqh2fVOlGao5HFguEQ7jHlwvM7JuTaj5RzlnHnsYNHj+t39HJ1qMdMKeoba2yo5gihhrhn2eqc0a/fzqLSkcjma9Xu2YmXutyRoBVpkZXtd8o7Aj9YPeDMuHt1zvZv1Wg2NOYfP55xVLJQ/dm0F+nIOjiVItCmHjGPF8dk2fpRwaLTI624YY7Do8o/3nOFLD0+htGZ7X47+gstcK6AZxASxKY28YluJl189yse/eYpEaSbrPu0wwZaSgivwbEk571DJOQyXvSVzOzRa5rXXS+47W+PKbSX6C8ZU+7snqnTChKGSR5goap0I17KIE0XDN6WPjU7E2Ua0ZUqJWd9OxtOZ9ZSmny69ohmXB5sO2F772tfynve8h09+8pOAOaFPnjzJ//1//9/86I/+6JZPMCNjo6zV63A+jes37B5gz2ABaKKVAmGCN601s02fdhgzWvY4mO66lXMOh0ZKHJtu8chkneHSMGCUKpWGK7aV2BnkOD3fIedIvv34HM0gxo8SyjmLKNZ04gSLhQzYYuHE9Rar5yop1JhMG1JgS0kYJ0/7iM2zwJGSzqphcMYTzblOx/M9XRd/NzxbMFBwCRNFKw2s8p6D0iZ0PD7b5jP3T/CmW/bxoitG+NcHJ1HaiBd5jmSo5GJJgWtbHBguUHBtrt7RxzU7a3SihCPTTQQwUHBxbJOdq7ZCau2ImUYA25fOrR0lWFIwNlDAkoJ6J2KuHVLK2T1lSUsKDm8rMdeMqDY7AEzUfK7bPbglSolZ307G0531lKbh6dMrmnHps+mA7fd///d5/etfz+joKJ1Ohxe/+MVMTExw880381u/9VsXY44ZlxBxrLj7VJXZVshQ0eWG3QM90Y3N7tSe6/Gr3Q+s+RylNKerbY7NtADYP1xk90ABKcWSYG4j87Rtyf/npj20jk5xat7vqUTW2hEzrYi8bfHsPQMIAfVORJgoHCnYXvEYn/c5OdtmshEw1wrwowSBWaDZaE5KC7QibwuaviKKtSl3TOvDupkHmaYVBEuza5tRQYS05y1t5NHp4vTpnGUTmMznbGt9A+YMI9wjxdIzxWRsRe8cCp/IJsTzwJaLxU58Snmbkmuxvc+kwSfrEQMFl72DBU7Mtfmrb57gRVeMsGugQJQo5jsRzSDGlpKxgQIHR0pU8jbHZ1qUcjYHR0v8n3vOEMYJlbwLmHPMtYwqrCUF956a5wUHzSZO99pT70R4luwp3IaJIlYKxzJ/lqNEYUvJSCnH/qEiE1UXqPOSZ4zyIzfsWV3saBNkfTsZGesrTUPWK5px6bDpM7Cvr4877riDr33ta9x77700m01uuOEGbr311osxv4xLiDsfmuQvvnac47OtFZ5ki8sON7JTe66d3dXu7y84oE3v2PLnAHz8Wyf55rFZau0ILaA/7/L8/YO84fl7enPYzI7yi68c5dNH4dBIiSMzHeZaIRooezbPPzBIX97lruPVVIpbYVsSz5aEScI3H59FCoHSmlYQ015iaB2tHTClcna2MD04CalAgl4o8ZKbDNgA/GilLMZy/6unCwLToxhmybV1KToChETqpSdbkp6fShnRjUud/rxNKecw3QiItMIPE0YGXGaaAdPNAKU0DT/k2EwLrTX3n6lxdLLJbDvkym0lrtpRIUwUriUpp9mvhh/h2RZlz5Q7TjdDU8Lox6mPm8SVkr6Cy+HRIkenW3z96Az3nqr1rj2eJZlphsy0Qp69uz817TaZOdeSNP2Y0UqOKFF850SD+WaHHzgIX3pkiqlmfEFZsKxvJyPDsJ7SdNYrmnEpcd5bBrfccgu33HILYHzZMp7a3PnQJL/9mYdp+BFDRXeJJ9lv/POD7B8uUnCtDe3Unmtn92XPGOULD08tuf/sfJs7HpwE4Ln7Bnp9Y/efrfHQRJ2GH3FsuoUlYKjsIhDMtyPueGiSqWbAL916GOC8dpT/5A03cN9Ek9lWSKIU//rgFFKQionElHIOTs4mSjTVVkAYa6QNncSoP8aJWuHxda5lbrccUmAyZNaibNtWLZGfTsHa4uPm2MYsOUyyiG09HNsynoGrrNeDJ9jo/HwRmLnKUDFayTHbDGmFMY/PtvHDpPe9bIULj5dhwplah0TDd07M8+Irhhku5XpjLl7EdcKErzw6nYqL2On3XRPGMdqz2T9cZEd/nvtO1/j4t0+iNUuuPTPNkPGaD8xzaKRIf95hvNbBtiQF12a45HHv6RrtMMZKs+PbK/kLzoJlfTsZGYb1lKbPJU6WkfFEsumait/93d/lE5/4RO/3H//xH2doaIixsTHuvffeLZ1cxqVBHCv+4mvHafgRewbylHMOtpSUcw67+3PMtgIeOFPj4HCRcs7BSnu6Do+WmGuFfP6BSVS6Mlq+s7v88bPNgL/4+nFmmwv3SwETtQDXEri2ZKIeIAVp31iRRyYa3H+mjiNhtJIj79jkHIttFQ/Xljw62eCz943z2fsn1nzd5fNcjG1Lnrd/iFddu4NXX7uTQyMl7j9bpx3EFF2LRCmiWOFaRn5cKYVlQX/eoeRZSCFxLGOku1m6/lEq9WhL9Pn7UT1dEaQBb0qiMJ/Lkzajy4NWKrARXgZZtLWQAnKORZQowlhRcCVSSBJlPNAsa+UGSKJhuhEYH8dE8e3Hq9Q7IbFSNPyIx6aaDBZdbr16lDsenKQVxAyVXLZXcuwZLLBnqMCB4SIlz2amGdDyI/MziFdce569p58dFRMMzrcjXFsihcCSgkMjRSbrHeqdCLSmlJZrlfP2Oa9Z52Khb2f1Pdu8axHESda3k/G0oKvceu3OPubbEcdnWsy3I64b68tKgzMuGTadYfvwhz/MX//1XwNwxx13cMcdd/CZz3yGT37yk7zrXe/i85///JZPMuPJ5e5TVY7Pthgquki5dJlrVAgFfpww0fAZ61/YjV1tp/ZcO7vlnM0DZ+vcfGCod3/Dj5lrh5TzZsEy1wpp+DGVvEMzSAjjhCBO8FxvyZjd8Rp+zLcfr5L3LMb68+fcUR7rz3NmvkO97QNwaq5NqEWv3+36Pf38zV0naQUxc+1Fr4dZHHqORaMTs70vR5SkJY1CXFD5mALyluiNneWGNo5mqYBLrOBMLXzS5nO5EF3mGwOWANsyxvWuLWj6MaCRmP4wielt654a3SysJcz9UaIo52yiJOHodIuSZzaCugqznm1xdLrJgeESUayZapjd+O71RUjBXDPgIWWaUw8MF1e99hzeVqLaCvnJm/ZQyTvMNAK+d3Ke+87UOF3tpJtPOQ6P5IFq73kXkgXL+nYyMpZyPuJkGRlPJJu+Gk9MTLB7tzGD+Zd/+Rd+/Md/nNtuu419+/Zx0003bfkEM558up5keddacV+iNVJAnGg6qzQFLVdYOpcik5Xuai++SC5vxm8GMWHqkRYmCqU1WmukWHlh7UrzN8MIhSJOcsw0gyX9KIvn+dBEnX/63lmOTjeZb3X4oSF4xyfupa/oMVR0GSnnsC0IY7VIilyTKE2UaDpRQpwoEgWTdSP9r9HYQq4pXb5RLGl8nS7ffEfGZniihWGeaj2NlhS4loWVGm+HiUIIGC67jNf8NZVYLWk2V+qdmFgpPFsSJ5rRco5brx7lBQeHkVLw8EQdP07Y6eU5OFqkEUTMtYzKo2NJlNbMdyJGKh7DJYuitzIwgu61R1HJOzxjewW2wwsODvOVx6b5yFePsX+oRH/BQaKgs/x556del/XtZGSsZC2l6YyMS4FNB2wDAwOcOnWK3bt389nPfpb3vve9gLnIJ1lPyFOSridZJ0wo55Zm2CwhUNpc6FYL6Jbv1J5rZzdR2ix2FmWjFjfjA9hS4qaBmGuZEiKRCnwsp/sciWCyHjBeCxCAbUkGCi6HRksMFl06YUIQKz517zhhosg7krlWCEPQDmNakWamGfDNY7M0/ZhQaQYKDv0Fh0TBVMNHa0WsdK9ksREYdUiTYdPYliC5gN6fREMQq6fUojpjbbLA/PyQXa9BrXEsc01phzGJ1hQdi7H+AtONkHCN2uI4NaMP4wQpBSXPZmwgx2TD59P3jQMwXPaWqDwu9luca4e0AmPnMVR0+ZFn7+Krj82ses3TWjNV9/EjRb0ToZTuqdoeHCkxUsphWyJVeV06zwvJgmV9OxkZGRmXF5u+0r/uda/jDW94A4cPH2Z2dpZXvepVANxzzz0cOnRoyyeY8eRzw+4B9g0VeXSqQdG1lpRF2tJk2fK2xfZybsnzVtupPdfObsOP2TdcpO7HbNe6V9Y4WHCZrHdACLZVcpRz5tQteRaubeHZFn4Q4UqRqikKHEvQ8GNipYmUsedNkoThskesYLrh0wxinrWrj5lmQBArbKk4PFrkuyfmCdKasLJnc2S2gy0F29KFmi1NqWacKDTQDhI0mmTZGlCTSopHigtU4UZrTdG1aaeZzK5S5NNZoj9j67gcNwIEC2qqkPas2ZJCziaJTVbNjyJipck7FraUnJlvkyjVK39Ueql5d/c45ByLIFEMljx29OWZa4V8+/gc956aZ89QkZy9VOVxsOgxsM+l4ccEccKZ+Q7P2zfEa5+5k/F5f8U1b64VcmSqwYnZNuWczd986yR3PV7tqT+uuFYuet9bkQXr9u10VXMn6z6evVDymfXtZGRkZFw6bDpge//738++ffs4deoU73vf+yiVSgCMj4/zH//jf9zyCWY8+di25Gdu2cdvf+ZhTlY7S1QiZ1shw0WPfcNFjs60zrlTe66d3aGSx4+lKpGL79/e53Gq2gY02yseidZ0gpjxms+V28tM1Do8NtlkshliCQEItIacIxgsulTyDteNVbj3dI35dkQpZ9NfcJhumEXYM7aXiZVmZ3+OZpCYnrmcyRjOd6JepkylxwNtsnTNIMJfJWuWPqQXwGlMT9DiBeJm8WPNTCpnp1PlSJX+OyPj6YiGFf2cthTcsn+Qct7l2EyTRyeb2FLw/P2DTNQDTs61et/BrpiPXvad7PomVvIOV++oUG1H3Hu6RhApEkswUvKwLbFE5fHwaIm8ayEEVNsRuwYKvPLabdi2XHHN60QJd5+oMt+JGCg43LBngJxjrVB/XPy8sYrxeGv6MWfq4ZZkwbK+nYyMjIzLg00HbI7j8F//639dcfs73vGOLZlQxqXJy68yXmddH7a5VohjSa7cVub2Fyz1YTvXTu1GdnZXG+8VV2/r+bAdn2n1nnPl9jL/eM8Zphsh1XaIH8aLfMosOlHCSMllqJTj+t2iV7aUKIVtCRwpeP6BIb56ZIaCaxtftUU9c50owXNMHwuYBWGSaEqebRTcViFWZtG3WMigu0i0pQlc40Rvyk9NYLyvdPqLZwkSBQmbGycj46lMrDTfOTnPweES8+2IwaLL8/YNMlTyUAgenWr2Njm6GfDlSAEF1+am/UMMFo3fYieMGSm71DoRidYM5FyevacfTs4DUG2FTNQUidbs6Mvx8qu2cWDYbGguvuYdmWrw4Hidhh9zYLiYlmV7ACs80BY/7/h0HXJQ60RbmgXL+nYyMjIyLn02HbB97GMfW/f+N77xjec9mYxLm5dftY0XHx7h7lNVZlshQ0WXG3YPmIwTbGqn9lw7u2vdDyy5bUclx59+5RhxonnW7j7uPlHFtgQl16KSd5iqB8w2I+47U6fg2gyVPPr3uozXO3TCBNeW+JFiZ3++11vnWhJLCJqB2buPE4WQFkIIcrbEsSVhHONHMXqd9JbGlGtZEnb05VEq4dBomWaY8OxdfVy7q48Pfemo6YlLFLPNCMWC10a3NMsWRnFOCig4Rm47TIxgQs4WFFybVmRky11LECl9WflkXR4zzbjUkZiNEUuAQDBcdsk5krGBPJW8y1wr5PGZFjlb4DqSJFG9flMhTD+sa0vCOMFzLF54aJi9w0XqnYhqO6TkmXLkONEEcYJOS7a7Ko8vumKEe0/VGK91mKz7/OPdZ/j+qVqvxLF7TfvOiTn+9MtHGSp6bF+mlrua+mP3eSdnGtz7jVP8wksPsWe4nGXBMjIyMp5GbDpg+8Vf/MUlv0dRRLvdxnVdCoVCFrA9xel6kq3GZndqz/X4te5ffNupuTb3nKpyZq7NiWqbIFJIAa0gYbYdITQEccLpapsgSnjW7j5mmxFzaRZNa/BsyUwzoJK3OTrdZKwvTydMmPED2At+lBBqTX/ewbUlrpTEjkUzSFYYYi9HAY4QFD0LsDkwUkYImGtH9Bc8Do6W2T9UpB0mPD7T5L4zNVpBYsRStNnp91KrAEeazJ1jgSLBsyR7hor05R00plTKknB0umWMezf8STx5XA5zzLg8UIBW0I4USTvgO8erjFY8tvflmW74PDTeoB1ExtoDqAcJKMVw2aMdxpQ8l6t2lLj/bAPHEuweNBtEYaJohzGNjqLmx3i25P7TNc5WfQ6OFqnkHY5Mhdzx0CRaw9hAnoJr0w7jFSWOUgoqeQfPsRitrLQ2gdXVH6UUjA3kuRczfhasZWRkZDy92HTAVq1WV9z22GOP8ba3vY13vetdWzKpjIyN8tB4nfvP1Gj4kTGvtiVam0VWGINjGSl8IWCmGfDlR2fozzsMllxsaXF23me+HfHHdz7GcNljfN7neyfnTYBkLaiEJErjxwmT9YC+gsP+YpFvPz67IaEGITRhrNhWyaGUYrYVcLLa4d7TVeJE0Q5Nr8yzdg+wa6DAd09UeXymiY6NZYJrS4YKDgXXwo8Sqp3IBGSplcG2co4fevZORss53vupBy/ewc7I2AIupn1Aty9Np5L61U7EZD3AEoK5dkjBsyjGmqFSDj/u0FGaZpAQJZpm0KERxAwUXbZXPI5Mm57cuh9RbYXESlNwLXb05bEtwVTDpxFEHBotMdMMEAKetau/F4SVPJttZY8j003+9juneddtV2LbMvNAy8jIyMjYNFvyF+Hw4cP8zu/8Dj/1Uz/Fww8/vBVDZmScE6U0dz0+RyuIEQgsKZECIqV7IiGJ0tiWxLMlTT8h0QmJstAaphoBfpxQdCw0AksI+vIONT8iiGL686kVgWejQkUQKWJXcc3OCvPtiCDaWH4oUkYlstoO+T/fH6flG4nxo1NNXNvikVyTFx4eYqiUY6jkceX2MmeqbYI4QSlodCI6YYJjidRzDpQWKC2YbQZMNwKOTDd5+VWjzDVDPOsC5SgzMi4iF1uNUgNhYuRIBJKGH7GjL4dom+/hRN1nW9nDtQR+bHpUrdQaZLjoMlTyKOccRkse1VbII+N1wGS+dvblKHjmuuAWJbPNgO+dqpG35RJjbKMA2TQ9tVHCidk2Wmt+/Lm7OTBcyjzQMjIyMjI2xZZt4dm2zdmzZ7dquIzLHKX0BSuPnWuMM/MdTsy2sC0jCCKERmnzn0xti1Qq/lH2bFpBgiMl850YIQJU6su0oz9PmCimmyECODRSotoOGS3aQItXX7eDqVbM8ZkWM82Af3tshmo73PjCU8FcO2SuFRojba3xLJP164QxnTDhs/dPcN2ufsJY8ehkg1aYGEEEzP+iRBEl5t9agBSCgZzNtopHO1Qcm27x2NRRnNRcOyPjqYIjzfd4My6fiYIIza5+h/lOTL0TIaURGOqWSLu2ZLDgMFhw8WNFlGiet3+QSt7hsakmQyWP267dxv/7lYgDwyVOz3dMcGclOJbxhYwVxCphuOT2jLHnWiHfOzVPJ4wp5RyKnsVsM+DB8Tof/dpx3nTLvvU90Aou1+3qS21UMtXGjIyMjIzzCNj+6Z/+acnvWmvGx8f54z/+Y2655ZYtm1jG5cuRqUZP4dGPE3K2xcGRUq/5fqvGaIUx7Tih5Nl0wpgoNAs1pUDKVP1NGNGPMNHkHSMq0AwSwljRiRKKORs/UniOJFIKocGxJQNFFz82S8RK3qFcMN5v//rgJGGi0pKmc4dsArPQTKKFx1pp+i9RECUajWa2pfjSI9Or93SlsuO9EbRRmnQtybGZNu0wJox11g+W8ZRBYL63OpVEtSxINiiFuji0qfsxeddiqOTRrpqSR0eai4Jrm9tdS9AKE7b35ajknZ7wx9HpJteMVfAciwPDJUYquV7WrBnE2FKyvS+H1opyzk774GyOTDXphDGDRRchTICYc2wOjZSYbAR8/oFJ3vrig6sq5e7oy4GGf7z7zIrr3t6B3JrvOSMjIyPjqc2mA7Yf/uEfXvK7EIKRkRFe9rKX8fu///tbNa+My5QjUw0++rXjzLVCdvTlKLj5VZvvt2KMomtTdGxcW1L0clitgGo7RqN7QZspDhTYlkSlBtY5x6Kv4BDUVa9EarDo4EiJwARRjiUJwwXJfq01j0zU8aOEgYKDbUnm2+b+9cK25UvMbuYvjI2lALCucIlIB1n8EIkp9Txd7VyWZscZGWshMN8RKQQaTX/eRmG+kwJFojRCQpKs/r0TQM6RJMpk2cNEo1FYUlDybMJYEaWm2WGiUFox10rIuxYHRxZKGrvCH0Cv32yw6PLcfQM0UlVX15KAptoKybsWj0422FbOUW0FlHIm8NNa0/RjRismGJRS9BQglyvhzjQCPn3fONV2tOp174037XpiPoSMjIyMjEuOTQdsSmVLxIzVUUrzufsnmWuFHB4t9RY/5Zyzwl9ISrFqySOw4THG+vNcN9bH47MtokSxZ7BAfz7idM0niEx2TAhjnD1YdGn5EWGiKboWBcfCtiSWNOWGU/WAK7aZ15tuBBQ9C0su9ILVOxGnqz6OJRkouD2RgfU2/buLz8XZsa6MvdbdRejqz+sO2/1ppQqRkI6VpdMynoJ0y4ATrbEEJFrg2oI4Sci7NmMDOWrtGKUSIg2uFEzWAxJtSifLeQdbSuY7ETrt92yHMbPNgKGSR1/eYaruU/Mj4k6Eawl2DxY5MFzAlkYtthuIebbF/uHiin6zSt6UPmqtuefkvPFEDBJOzrZ5ZKJBlBibEDDB2uJgcLkCZFcJVynNnQ9OUW1Ha173vvDwFDufjA8lIyMjI+NJ54J62LoeVKtJE2c8/Tgz3+HotOnJWH5OLPcXCuJkRcnjgeEiYwN57j45x1BqJLveGLsHC/zgddt5eLLBvafmmWqEVPI2IyWH8ZpCac1IyeX63X08ON4g79qIOEGmAgM5R9L040VjF0y/SSvkdLXD3n5TgtT0Y45Mt5ASirZFJ1LMtaMNxUxSGL+0LksCPM2qAdvycTVgSUF8Lg+BjIynADlHUnAscrbETzSOlLz4mhH+/fU7Ga3kmGkE3HOiymcemGSy7uPYAldIbGky6TIN+xT0lFQreRfPtnAtTTnvMNafY7YVYlmSfYMFjk63qbZD4kRhS4ECXnhomN0DhTX7zR6bbDJe99nRl2PPUIHRisf3T89zdLrFybk2I2WPHX15Do4Ue8bYaylAbuTaeWy6xc6sKjIjIyPjacl5BWwf+9jH+L3f+z0ee+wxAK644gre9a538dM//dNbOrmMy4tWGOPHCQV3dXWz7u7yQ+N1vvzo9JKSx7Pzbf7p+2dp+TFBrBgquZyuehwcXVjsLB6ju0N9aLTML916mI9/8yRffnSaEzMtIqWxpcCzbXKuzdmaTydK2DNoFlUzjZC5doiVyv0LgZHMj2NOzrWMhHeimWkFAJyutrl6ZwUNnJxtM17z8SN1zoBNY0q7THHX2o/ZCJeLEXZGxmbI2QKtIUh3MoquZLDoUHAdip7Njr4czSBm33CJHzg0YsQ3tsMLDg5z/d4BPvLVx3nwbJ2yZ+HHxiLDGMhLLCkJ4gTXMuqxQZzQ9GMKrs21u/ppBRHfOjbHFx+dxrUk/QUH1xbU2xGJhslGwLGZJodGyyv6zVxLgoAdfTmevdtI+ZdzDi+9chTHmuHkXJv+vMNz9gz0BEPWU4DcyLVzpr4Z2ZWMjIyMjKcSmw7Y/uAP/oBf+7Vf4+1vf3tPZOSrX/0qb33rW5mZmeEd73jHlk8y4/JgI/5CriX5zvHqkpLHuVbIY1MtEpUWRAmwxILP0fW7+9fdoT40Wub/et4eZloBZ+cdBose2yoetpAcm22abJptccW2EpW8y74h3etDaYcxJ2ZbnJ33uffUPCDYM1TgitESWiVAm4Jn87pn76LsTXD/6TqtcOOm1MEGhRIynhp0i2izwvGN080cSwEjZY+Rco4wTphtBjT8iAPDRY5MNXpZ9W4p9UjZ42dv2cefffkYx2Za5B2JZ1uUczYHhksEccyXH5vBsSXtMMG2JKOVHAdHSgwWXco5C8eWaK3JOZJ2GGNJyc6BAgeGC8y2ol759fJ+s3on4m++dZKBVFiki5SSa8f6aYfGs3Gi7jNa8RYUIIsut12zbYXq40a92TIyMjIynp5sOmD7oz/6Iz70oQ/xxje+sXfba1/7Wq655hp+/dd/PQvYnsaM9efP6S+0ezDPdFpG1G3K76qqDRVdAtfiZLXDfCdiuOTSChOOTrcYKLgAS3aouwu3RhDxv+8+QxhrXnBweMnrPivfz6OTTZJEc3beN71jSuNaksGCiyMFecditJyjlLO4YrTc61FpdUIApuo+f3PXSa7dWSFRyboiIRcbWxiRkiwguDTJPpfNEaYbGhIo52z68y5BpJhrhXSiBL+pqLYjBosuD4zXODHb4l8fnGK81kFKyDs2h7eVcGxBwzfCIKNlD8eSHJsJGCm6XLm9zHA5h2tJyrmF69J0IyBRmucfGKTkOT0hke5jXNtaUn7d7TcDeHiiTpAoCquYWw8WXW7YO8DdJ6rMtQLaYYxnW1w31sdt1yyo3C7u4S04piT8gfH6mtfOZ+4sQWPlMdwKC5WMjIyMjEubTQds4+PjvOAFL1hx+wte8ALGx8e3ZFIZlydSivX9hYouN+4b5H/fc6a30Gn4MdV2SCnn4EcJs62QIEoIE0XDj8g7FolSjPfnaQZxb4f62EyzV6I01w44OtVitOwxUnaXlFAKIdjZn+Oh8Ton5wLuO1PDsQUCo9QYK0zPitbYMketE5lMXdWn6fs88xA8NP7/Z+/PoyzLzvJM/Nn7jHeMOXIeKjNLqiqpNJZUJSQkWVPRCGM3auyFm0aghm4JiTbQzDZeFsbWWrQb4V4IhMFIeEAMP8A2CIRESSpZojQWKtVcOc8Zc8Qdz7T3/v2x770ZERmZGZEZOe9HK1WZEfeeezLjnnv2u7/ve98GT5xu8sUXIrr5lS/Jl5uJXCmuM9JxOxD64AlJPfbppAWpMgRSUCjNdCsjV5rIl3hSkOaa2VbKr/zV86S5ojCGauQzUY0oDXscmm4z3UwolOHsYsLTAoZKIQ/dNcL+iSpnlxLGVlXC+iKoHNrNGn+NsPnV7dfLuVxFrBR43Letzvc9uJt6KbhASK0VWzJcDvCkuOhn51vumeS5rz234nU2I0LF4XA4HDc/GxZsBw4c4I/+6I/4hV/4hRVf/8M//EPuvvvuTTsxx63JWvMey3eXI9/jU/65wUInU5pCaQoJ082UNNdEgcdENaKR5rS6Bc204OR8hze+aIJ3vGQLwArb/9CXHJvtsNixgbXLWygBklxxerHLeCWiHFpTkdlWSq4MpcBjfCTm3GLC4ZkWB6dbaAMGQyisOgp9SSfRnFpMLukKeTlWWPP33CPXe7jNEHsOx82AjaoQGDRzrWywCTHbzmn12qZjX6J7F0imNLGUTDUTAinYP1FBGcFsK2WubavgjSRn53CJ+7aP0UoK5jsZSWF4670TfPa56TVF0Fg1Ig48urmitoZgu5hBCKyvm+D+HUM8sGf0gmrXxWJLzi4leFKwrR6z2Mkv+OzcMxLz3DqOs5EIFYfD4XDcGmxYsH3wgx/kH//jf8wXvvCFwQzbl770JR555BH+6I/+aNNP0HHrsXreY/nustZmxUIn9Ky722wrJy80Ugoqkc9wOWC4HNAsFcy2UvZNVPg/vn0fUgp+8/OHV8zAGQNxz1WulRaDFsp+y+Xz55oUyvCynUPUYp8vHZojyRV5oWgkOS+ctSYD/WWVL214dn+2xmiD1uaKXRq9Nez/NyLWwIk1x+2DzUA73wophb1Gcm1zEtNck/YyCpWxhj2l0COQtmKuNESBJCgHHJ5pg4BdwyXamcKXkt1jFXaNljk43eL5c03e/W17+MzT0xdsIL3tvkk+8/T0ZUXXaoMQWF83wVqzauuJPhmrRrz79Xvp5mrFZ2ee5xs6zvIIFYfD4XDc2mxYsL3rXe/iK1/5Ch/+8If5r//1vwJw77338tWvfpVXvvKVm31+jluU5fMeq7++fKGztR4Rhx7NhS6egDj0GF0mtnKl2T1WtguhXpDtavvrWuwzUg6ZaSZUIo/5dkYzKaiXAhrdnLNLCduGbXBtMylY6Nr5mH57o8E6Rfb1WK4BZaj49viNtCBT4opF02b7jrhqm+NWR2BF2lA5IM11bzNEk+vzgi70BRKBNqCUsW3LnkD14mRyZcWc6T1HaU2m7DW9PALk7798O+978/41N5CkEBsWXX0u102wVnVrPfb9h2daSCG4Z2v9ov9+G4lQWetz2HFr4OYTHQ5Hnyuy9X/1q1/Nf/7P/3mzz8Vxh7B6oePc7B2CAADMJUlEQVRJK4b8nhFIFMiBBXcp9HnRlhqNbj6YJVltfy2E4MBklVZa0EoKlNF0c4UQcGimhe8JXryljhCCtFAs9ubkJALhCdLcEHg250z1Kl+FMujBLv/KFkYnlhyOq0dKgScFpVDSTIpBMDzYayxXhlAKQl9isJs3vpR44nz1rf/otNB4UvZCry3LZ9AutoF0JaJr9fMv1k2wFqvt+40571gbepJS6JEWa8/NXeo4q7nU/J3j1sDNJzocjuWsW7A1Go11Pa5ev/iuoMPRZ/lC5/BMi9/+whG6eUEn0yx0Mnx53oI78KzxQH+WZK1h/9FKyCt2DfPMmSWmmylTjYSRcsh92+u2XTKwC7lMaXJlUNrge6B1Py8NQk/S7a0aNZBr+3tPgOpV4IQAcQUujaurYlcj+pxgdNzq9KvaShk7x6rXzirU2Gu2LGXPHdVurgAD4QZ2TnXHSJlafP6WdqkZtOVsVHSt5mJicC2Wm5XkSnN4us18J6PQVoxWQo+RSnjZc15vDMDljuO4OXHziQ6HYzXr/jQfHh6+oPViOcYYO1+gXLin4/Isb/XYN17hdfvGeOrMElvr8cB2v7/4OjjdWjFLcrFh/5FywEQt4oG9o/yDV2ynFgdsq8f81heOnJ+Z8yVGgNKgjekZjNgsKN8TeD1hJpfNnSnDYPffGDt303/V9YonJ7IcDntd9VuPtTG0M0Wu9Jptw/1iWaEMLWNdI4dKAQudnGrs40m74aJ6rpH7JyqDz4PLzaBdcF4bEF1XQ9+s5MtH51hopyS5phr7BJ5PVihOLXYptKGbX7oytl7Tk/X83R3rQ2vD6YUuAKcXuuwe969Je6KbT3Q4HGuxbsH2uc99bvB7Ywzf+Z3fye/8zu+wY8eOa3JijtuXi1la+55kqpkOZklaabHmLMmlhv3HqhHf+8DOFbuPyx+vtcH0jAy0OW96UBgoco3vCYQxqGUltNW3RJe15XBsHAGUQ49OZrMMlQaNvmiuodbgS2PnS7XBE7B3rEKaK2bbGa0kJw4kpcCnHPn4UlBofdEZtJthHkhKwdvv28KnnznHTCtjaz0m8CS50rRTxUQ1oh4H/M0z0xyYqF30/K7U9MRxZfTvWcdmGrwhho987hB7J+rXpD3RzSc6HI61WLdge9Ob3rTiz57n8dBDD7Fv375NPynH7cuVWlovvyludO6k//hPPXmOv3zyLEIIpLAtWZ7omYlogxEMBtVWty8KVlbdrhaBrSAo7apvjjsDKSDN1WADpC/UJBdeA/3HRL6H1JpubjdZDk41CX1JNfapxyXKkY8Ezi0lPPrCDOPViB3DpQs+C26meaBS6DFRi/CloJ0p2llxQQv4ehbkVzt/51gfy+9ZO+ohGBgqBdesPdHNJzocjrVwDe6O68bVWFqvZqNzJwcma3z3KyRPnlli23CJwzMt5topGGvhr7ShmynyZXbj/ZasSAoMArWqFCAFxL51s0yW3TvXI8CcSHPcaQhhMw3Bmo00exfN6op13zZEG+gWGqMNEhivhmgNi92c2VbGeDVkvBrRTAq0MTSSgrTQ7Bmr8Lb7JjkwWUNrw5cOz/KJr56gnRbsG6+yPbqx80DtrCD0JQ/tG6OTqYHhSC22rY2F1utekF/t/N315maocm6E1fcsiYYuVGOfu+PwmrQnuvlEh8OxFu6Kd1w3NsvSuig0Xz8xz8GpFnHg8Zq9Iyty3i62IOjkCk8KDkxUqcU+3zq1yGwrI+k5RpYCgZQgjMD3BLUQQCGkQJgLq2u1yAdhZ2xiX5Mps2YF7mLzboXrrXTcIQhsNVkZ2Dkcs2u0xN8emqMc+ZQCyXQjHVSyi2UXSq5sK6S184eRSkCuNQudgoVOxtePL1CLfUYrISOVkJlmxhOnFvn4l47x1nu38OyZBn/51Dnm2ylDpYC8MOyfrDBaiW7YPFB/Qd7NFfXS1S/Ir9f83dVyM1U518sF96xl781r1Z7o5hMdDsdaXJVgu5QJicOxms1o9Xjk2Sl+43OHODjdIis0QkA18vn2u8d558u289zZ5kUXBJXQJys0n3tumulWSpKr3hybIPAlgRQkeY4WGlUIyr7d6w8EtFYpsdATxIGHNoasKCi0sQHAUgzyofq4aprjTmdgwK81e8cr7Bwu8c1oiSRXhL5ESjEI016NNlDyJVvrMVmhSQtDJZQ9wxJFJfQIPYkQgpFKQJIpDk63ePpMg6FSQFoottRjhIDpZkIzzXnFrmFGK9EVLbivtkp0Jy7Ib1XXwxvRnujmEx0Ox1qsW7B9z/d8z4o/J0nCe9/7XiqVyoqv/+mf/unmnJnjtuNqWz0eeXaKD/75M8w0E3wpqMc+yhjaacFfPXWOx47Mc2Ciyt1bqmsuCLQxnJzvcGK+QyAFldCn0JpGUtDNFX7/Bmjszv5Sr2XL9yUy16h+u6SAyJeYnsud7vn9+xJGSiFLSU4319bMxFXRHI4BhYZnziyxpRYxUQ05PNum0c251LaG4XybpDK9AG1pnV1LgTUnaqYFtcgn8CQtXdBOCha7OXtHy5xZ7FpRKARhRTLfzjg802akHG54wb0ZVaJrvSC/2doOb2XXwxvVnujmEx0Ox2rW/SkzNDS04s/f//3fv+kn47i9uZqd5aLQfOyLR5lvp0S+pBz6CAEBNj9ttpUx10rZM1IaHHv5guCvn5pCa01SaAJP4vUWBmmukZhe7pptv6pEPt1M0a+TtVKFXia8AikoBR7dXKN0X5gZPCEZr0YUBjpZuqK1y+G4k+nnECoDU42Uv3luikroE0iJJyC9SBpM/3ntTLHUzSkFHlIIklyhtCHtVcnPLnZpRgHVyMMY6Ba2cocU+J4kV4bIFwghqMY+8+2MZlIgBOtecG9mlehaLchvxrbDW9n18IJ71rLvXetq6K02n+hwOK4t6xZsH/vYx67leTjuAK5mZ/nxkwscnmnhCUEUeCy/7/dz07QxnFlKaCbFYDakvyD41ulFuqmtom0fLtFKctqpIlUaKezsmtHGztAom+uUFwWgyLVBmfMvKKXotUIqlDFkPTGXa8OZRpdOpl0bpMOxjP710MuvZ76VseQV7ByJURqOznVWPF6y0oxEG5hrZdw1XsaXsJgpTC/I3u+Jslaa00hytg2V6OY5pcBnpBQwUg6ZaSaElRAhBIEnaacFaaFY6OTrWnBfiyrRZi/Ib9a2w1vZ9XD1PWtHPQSglRScbmTXvD3xVplPdDgc1x5nOuK4rlzpzvJcOyNTemDFvxxbCbP/nylNplb2IZZ62U+tLAegFvvUY5+lbo5aMgSeoNnNUT07/7SwlbhQ2uOEEjLVfy37/bzQFMZWAIToVQK0oZ3anf/VC06H407HRllIhIAk1whhKEd2rlT2SmlS9maje/EafaVngCQvaKWKpLCbLL7sGf4EAk8IVO95UhiKwhDEkkxpttYjmknOfDujGvtoY9DGVn52jpTXteC+VlWizVqQ38xth7e66+Hye9axmQbEsNTNXXuiw+G4rtycn5CO25or2Vkeq4SEnqSjbFXLX7ZoElY2ITCEniTs+/H36GaKcughDDS6Ra89SlIKPAJPUmgrvjQQSkE18mmmxcDxURtr8e97krzQKHNejBns2rL/uLzXO+kqbA7HhWRK40vwpc2yWurkGGOrZLkyiN7VbLBVcykh722WpIVmoZPhS8nWuj+YPVXGHrccesS+ZLadgYGpRsJXjyp8TxL1stuSTLHYzRmrhLx279i6WwVv9irRzdx2eDuYrPTvWSdmmzzx2Ene//cOsHv84sHmDofDsdk4wea4IWx0Z/lVu0bYP1Hlm6cWSXOF15thg347pF2YbB+KqcXn39b9BcHLdgyjtebckwnNJCeshIS+tJbizcyKsp6ZSOAJayW+7PilwMMAWgr0KhfI5az1dXGRrzscdxICwFh7/1pkrfjPLiXEvqASeix2bZ6a6BXXhLBizQCRD770kBgwmnIUsnO0TCXymW6mtJICIQxKQ1Zotg+XMMaQ96p3raTAkzBUCtk3WeWfvHY337Z/fN0L7uVVomrk00yKFflpl6sSXWsjkBshKNf7d7pdXA+lFOwYKfEEsGPEzZI5HI7rixNsjlsC35f80BvuGrhEKp0PbPU7mcL3BCPlkMC3rnGrFwQPv3QLAM9Pt3ji5CJTjZShckDoSwplF5NSCCJfkhaaQhnCnmLLNeSF3eY35uICrJ8jtfp7Tqw5HMtahI0VGCfnO6SFpp1C6AuksKYk/RbjvtFPIGG0HLJ9uIzvCU4tdNk7VubFW+sIIbjPGJqJnUn71qlF0tzjwb2jKGM4PN1mvpMhhKGVarYOefz42+7mwERtQwKqXyX68pE5Cq1Z6OQUSuN7kpFygC8lr9s/tmaV6HoYgVzvtsON/p2c66HD4XBcHU6wOW4Z3nqvFV39HLa+y1st9nnDgfM5bIemmxydzZBCcmCyyrtevWOwIPjxt93N73/5BF8+Os9cKyUvNKXQIw4knUyx2C0wvRmXQlup1W97HGRJ9f7rKmcOx5WRa9BG22xEbedOPSkGxj+yl1HsSUEceoxVI+7bXme4FLDQnuLoXIcXbakhhHV+rJcCljqG+XbO9pES9VJgc9n2hoNqWFZoCqWZaqR85unpDQkoKQX3bKvxZ988TTOxLZVD5YBupjgy26YWB7x464UtctfLCOR6th1e6d/JuR46HA7HlXNFgu3gwYN87nOfY3p6Gq1XWiv8i3/xLzblxByOtXjrvVt4090TfP3EPAenWsSBx2v2jrB7tGLbLEfKLHUzGkmOMobpRsJnnp5GCsGByRoHJmv88++6j5MLHY7Otpltpvzp46eY72ScnO8CerDDv9xpfC0DkdViTXDe3c4JOcedyHrNdvoV7VLksasSc3yui5SCyBeDfEOwFe+94xXu3zHEaCUC4KU76vzdiUW+dXqJ/RPVQTX90EwLXwpe3BNypld567cuDpUCnjq9xCe+egJj2JDY0Nrw3Nkm24ZiJiohC92cRjfHk5J94xV8T/L8uSZ/78WTAwFyPY1Arlfb4dX+nZzrocPhcFwZGxZsv/3bv8373vc+xsfH2bp164qdPCGEE2yOS3KxuYf+15tpTispiAPJsbkOi52MUuCxY6TEcCmkFgfsGC7x0L5xHto3vuKYT59Z4v/3jVMsdjJGKxHbahFpofjbwzN88+QC/8urd3Hf9jrb6jFGG2abKcfn25xd6nJuKcHzJJXQIyk0xRWEqBlWirzV+L2S3M1nXu1wXD0SLlp2DqSdXeuLOSmgHHkUyhB4HjtHysy204HIKEeSHUMl9k9U2DVaXnGf2TZcYraVcddYlcVOPmive8n2IeLAIw485tvpoB2y0BpfSsqBZCkp2DlS4uU7hzckNvqmHndPVtecYWulxQWmHtfbCOR6tB3ezOYmDofDcTuzYcH2y7/8y/zrf/2v+dmf/dlrcT6O25iLzT3cs63Gc2eb/N3JBU7Md5hvpTQTRWH0YPHnSzFoi3rlrpFB+1L/mI+fmOcbxxdppQUCgyclUoAvJUIYMmV4/MQiL9pSYalbcG4poZsrMqUxvYWkLNRyJ/FNxwVpO25rhDXuwVxYZdO9S9nvGbj6UhD5HoXSKGOolXwKrblnW42pRkogJS/eWqVeCjHG0OjmA4EEhvFqxHvesBchxGDzZ1s95re+cIQvH51joZ2S5Jpq7BN4PlmhOLHQpVCGl+0c2rDYWG7q0W/BXM5aph6bYQSyfIMrlhd92ICraTtcj4nIze6W6XA4HLcrGxZsCwsLfO/3fu+1OBfHbczF5h6+fHSOP/vmaYZ6u9SNTs5SUlAsc2IU2HmymWbKk6cWmW9nvDDd5Lteto3PPz/DifkOR2ZatNLcOtEJQa60tdsXdjamHEg6Wc43Ty6RFhoBVEIPpSDvvY7LTXM4rpx+gL0vGYTJD76HFWxag5DgebKXYWgz1PKegUcp8Ng5XGKiFnNyoUOuDIdn2ix0MmvyIQUa+PYD4+wcKV8gKN5+3xY+/cw5ZloZW+sxgSfJlaadKjv/1sk5u5Swa6R8gWi7lNi4ElOPqzUCWb3BVfEFb4jhyEyLF28fWfM5cGVth+s1EbnVM9UcDofjVmUde3Yr+d7v/V4+/elPX4tzcdymrJ57qMUBXi/vrCg0jW7GdDMhKxSdrED1zD4EDAwIAJQxzLQyjkw3+dqROX75L57l2GybvFDWgAQIfWl3+HuWjQZQypArjdI2sFcbm6mmjKHQbt7M4dgslL5QrAkg8Gz1Tfceg4GsUJRCj8ATtJKCkXJAMym4e0uN/+WBHXhS8OgLM5xZ7BL5knLkkeSKbqaYaqYcmW1d8Pql0GOiFrFzuDTIbUtyzWQ95v4dwwyXA2aaKc3kQlF2KbHRN/U4u5RgzMpPjL6px4HJ6gpTjyt5Tp/+BtdTZ5YYLgfsG68y1Kvq/eevnODQdPMiP4GNs9ZrDZcDnjqzxMe+dGzFa13N38nhcDgcV86Gt8EOHDjAL/7iL/LlL3+Z+++/nyBYucv2f/1f/9emnZzj9uBicw/NpGChm1OPA6abKSOlgE6mML2derVsPaCX/V5pCAPJVMMuGvrfklKiDRjM4Pm2gQo6+fkD2DMwZIWrqjkcm8nqzY9Q9mIxlBVsfm+WLSsUAokUhrNLKaEv8YRte37HS7awb7zKZC0iDjyUssIrkJLtwyX2TVSYa+drzpu1s4LQlzy0b4xOplbMmQGcWepwfK5DWijg/L3rck6KV2LqcaVGIBcz9qjGPnRhoZ1tmlnJRk1EbpdMNYfD4bjV2LBg+/f//t9TrVZ59NFHefTRR1d8TwjhBJvjAi4295ApTa5ULyBX084KVM8+f7lY6//eo9dWBXjStlSlhSYpFAJN6AmyQqP1+arcckHW90MwQK4MxpXWHI5rgsCG0PsSTKEpNINwek9au34pBLPNDNmrtgspeMs9kxyYrHFyvsOJ+Q612Gepk1MUGm00SaGBi8+b9Vv2urm6YM4MbIVoupFyerFLHHgbEhtXYupxJc+5lLEHwNb65hl7XImJiMtUczgcjuvPhgXb0aNHr8V5OG5jLjb30EkLlroFSaZIC23nzi51oJ7ikkIghG1rDCQ0Co0nhA3B1rYf8nIGH9qJNYfjmmGArNBkAgJPEErbmiwECAOR73HXRIXtwyVqsY/R0EgKPvvcNLtGS3z92AJPnV5CYDdWcm0otGGxk3F6ocsDe+0M1+p5s8vlkXVzzVvumWSkEnJkpr1hsXElph4bfc7ljT0kaTPbFGOPKzURcZlqDofDcX1xk8GOa85ai6j5dsbB6RZaG3KlCKQYBFVfDGXs7nwtkqS5NQ5Z6OQUypCjKbSmFPoUSl8gyPqtkQ6H4/qgAQyky3dPerkXeVKQ5IqxSshoJcIYQznM+dbpRf7Znz7JQidnvp0BtrWwEtrZMqU1rbTgK0fmecXuoQvmzdbTsvd9D+5m3/jFxcbl3BKvxNRjI8+5vLGH3jRjj6sxEXGZag6Hw3H9uKJP/FOnTvHf//t/58SJE2RZtuJ7v/qrv7opJ+a4fVi9iNpaj3hhqkEzKahEHkob0sI6EVwkxmlAKfAwQtBOC8qRRzcDg0YIQZJrVFJcINasG93mVtU8YY9ZuCE4h2MFHpfOI+xzar6L0vPcu63GbDPjbKPLTDMlV5rYl3jCti4LAd3cur0GnqQS2mpco1uwrR5fcNz1tuytJTbW65Z4LblUlRDgXCPhvh0jm2LscbmK5KXm+hwOh8Nx/diwYHvkkUf47u/+bvbt28dzzz3HS1/6Uo4dO4Yxhle96lXX4hwdtwHLF1HfOrXIqQU7Q7KlXiH0BN88uUihNLInrNbSVhIYLodIIIgkW+oRU83UtklKmG9ntFOFNjaoVxsr1rRZORN3tXjYtqTuajs8h+MWR3L1RjzrEWu+tBse042ERjenEtm5M19KjDEkha2Se561elVa082AEDJtCDyJFIKzjWRN4XUlLXsXix556swSZ5a6/NDr914X0XaxKmGa2rbEkU009rgeJiLryXdzOBwOx6XZsGD7+Z//eX7qp36KD37wg9RqNf7kT/6EyclJ/tf/9X/lO77jO67FOTpuE/qLqC8cnOE/fPEId41Z++hGN+fQdItM2VYfiTUkGS4HeELQLTTNbk7oS/aOlji92EUIwXQzpR4HvGLXMIEnSQvFyfkOT59p8PJdQ5xZ7HJsroNRBo+e6UGvN9KXkPRWlhK7eFSGy1b4wC5IO6m25iesb4HqcNwKRIEgK8ymbHCsdS31l+lCCCJf0koVuTaMVkKWugW+JxB4SKHp5grPs+6RmdKkhcaTkjiURCWPUigvOce1kZa9jbolXmvWqhKWfQExfP+DuzdVOF5LE5GboWLpcDgctwMbFmzPPvssn/jEJ+yTfZ9ut0u1WuWXfumX+Af/4B/wvve9b9NP0nH7IKVg/0SViWqM7wkWOjkHp5q0M0Waa/LCBuj6UjJaiQg9wXQzozLkkWQFB6dbLHZyAl8SBx7D5bDXHukT+R57xyocmW0jhSAtDEobPCnwpCDtOUgCSE/iaVvRk1KgtEEYK9y4SIVvOf0qhBNrjtsFKWxA/WYVo1cfxxNgetdWv01ZGYMvBIXWaGMw2th8Ri3p5gqlDbWST8l4JIVmshaitGG4EjJcCjctoHk9bokHp5p8/fg89VJwXSpFq6uEsYQnHjvJvonqNX+tzfj73SwVS4fD4bgd2PDdrlKpDObWtm3bxuHDh3nJS14CwOzs7OaeneO2pD838eUjc71gW8VwOaCVFBTakGuNRHN8rm1t/DVkSqF1r0VKQOxLapHHyQWbq1SPfcqRTzmUxL7kyGybQhvKoY/WelA909j2SYFA9VsltRksIH0pyC5SXhDYCp1yYduO2wwBNnBeM4i7WE+1+WL0TX76z18+R+pLKIU+3VxjtLFCTttoj8j3rAkJhkY3t+6x2hBIOdh0qcUB5cDn7i21TZutupxbYjdXPHO2wW89epgo8K5bpWh5lTDPc564Zq+0uSYiN1vF0uFwOG515Eaf8NBDD/HFL34RgO/8zu/k//6//2/+9b/+17znPe/hoYce2vQTdNx+SCl4+0smaSQ5M60UT0IrKQg8a9cvAAQ0ugXtpCAtClsp8yD0bH5TMy04u5SS5gqlNanSRJ7g9GKCEYI0VxhtjQrKkU8l8okDD18KBNDOVtbGpLDZUJdyqjScrxA4HLcLnuhlpnl2QyLwYKIa8rKddfwN3yF6x/QEobc6ENqKtqFyyK6REp4AhK1geRJGyyGVyCMOJOXQZ+tQjO9JullBMymQQjBWDRkph+weK29qQPNyt8TVzLczHj++QDMpGKtE7Bu3rdxPnVniY186xqHp5qacw+3ERvLdHA6Hw3F5Nlxh+9Vf/VVarRYAH/zgB2m1WvzhH/4hd999t3OIdKybUuAzUYvwhODYXJturoh8STXy0cawlOQo1TMg6QVhGw2Z0RhjW7eUsbvzvoSk0CSZYqIWUS8FzGvDZDXkyFyHdqaIPEk19kkyddG5Fwnkl1Fjm2le4nDcDMhea6LpCaqwdx16QlKLAowq2EjzrycAY9DCijZfQqYM2kDoC0bLAY0kpxr5jFUjhsshL9sxRKENT5xaYr6dUYl8BLB/okI3U2RKs2M4Zsdwmbu31DY9oPlibonGGA5NN1ns5uwbr7C1J0BcpejSXGm+m8PhcDjWZsOCbd++fYPfVyoVPvrRj27qCTnuDNpZQVZoNIZM2UqY6IVfVyKfQhkSYbPVjLG7soEnMUBaqBUGIf0WLtPbrZ+oRcw0U3aPVdgxUubJMw3ywoZzG9Nrf8S2PyJs+44yNtjX4biT8HsaI++996uhx47hEp4UzLQSDGZDQiSQMFmLUMYGZ+dKUw59mkmOBsqBRztTDJcCHtw3xusPjPPZ56aZaqZsG4p56Y46L5xrcnYpwfcEdw2XeOWuEV62a4iJWkQl9NlWjznbSHjuXGPTZsku5pY43Ug4PtdhpBxwYFlrH1xYKXKZZOe5mnw3h8PhcFyI+7R0XDeW2zs/e6bBiflOz/lNUA49tLGtip1MURiDMQZj6Im5nlmBOC/QvJ5hSCnwkEKwe7REO1MsdTJKoce5RsKrdo9QjQOeOr3IwakW2hhUr2I3VPaRvUy3bqav2s7c4biV6LceK22ry4EHse8x00wBMBiyQuOL9W1kSKAaB7zmrjGmGgnH59oMlwP2jlc4MFHldQfGED2fyH3jFXaOlJFSsGesPHASTAvF7tEyD+wd5dV7Rrh3W32FIDs03eS3vnDkmrgOruWWmOSaWuzzqt0jjFaiC57jKkVr4/LdHA6HY3NZl2AbHR3lhRdeYHx8nJGRkQt60pczPz+/aSfnuH1Ybu/czRXHZls0k4KoZ9ttzQgEXuDRSqzZgOR8QLUvpXVy5HwAtjK9IUwBlcgnCjyEFMy0MrYOxYxVIw5OtygFkkJplDEorRGi12LZU4DaMMh/czjuFAznDXQ8AZ6UtLIc2atmx77dCMl7JlOhFKTLOiP7ler+RkccWKv+TlZQj31ec9cY77x/2wWiazXrdSi8Hq6Dq8+l0c35xFdOEAfemo9fT6XoTswhux75bg6Hw3EnsS7B9uEPf5hazd4If+3Xfu1ano/jNmT1QquqfF6YahL5PetuY1CZslU2ACnsTrwwiN7/Ql/QSvQK2/G+C13kS0YrIUIIfGkrZgcmKrz13i386eOn+erReZvpJAVDpYhCa5a6djEW+p6t4nlQLNskF1yBI4/DcYvhS8i13fzo5BoBVCKJ0bb1WAiB50lAsW2oRL0wtBI7n6R7OxwSu/mhNCx0Mp48tcSBLTX+0Wu289Z7t1zy9VeLmRdN1tZcxC93HTwwUaGVKhY6GaEnOTBR4dBMe9NmyZa7JWpt+NrRhSuuFN3JOWTXMt/N4XA47jTWJdje/e53r/l7h+NyrGXvPNtKEQK2D8dMN1IyrelmikZSWMOD0CMQ0M41sucg10qK3izb+ZZIsIumSugTBTY4e6Gd4wlJJ9P82eOneeZMo2dYUCLXtsWrHHho3WWpm9PNFKEn1jQTkWsottiHrMC1TzpuC/JVb2QhbFtk0XNYrUU+se8DOWmhmKyViAOPSujRSAoWOxmttLAbHFJQLwW8bMcQQko++9w0e8bKF12Yb0TM9F0HS4HkG8cXme9kFFrbvMZyyNah6JrMkl1NpcjlkF2bfDeHw+G4E1mXYGs0Gus+YL1ev+KTcdx+rGXvHPaCsQttGK2GdDPFy7YPc66Z0EoKlNZ4UrJt2KeZKJa6GSCQ0rZu6V6VrRL6CAzNtMCTYmAiUos9moltyxICxisRS90Cg2197OSKyVqM0pqlRJHrnoPJKlRvMSvozcsJEEIi5fkAbofjdkIb6GQF1dgnKzSNtGDXSAVoEvhykFW40MlpJDntnliLQokvPQRwbL7LA3uGmW9nF616bVTMtLOC2VbKXDslzTXV2CfwfHKlmW4mLCUZY5XomsySXUmlyOWQnWcz890cDofjTmVdgm14ePiSc2vLUWr99s+O25+17J1rsc9oOWS6mTBcDlDGMFGPuGdbjUY359BMi5dsH+J/fuUOfuNzh/jy0TlGyyGhL9HG0EoV3VxRi3wqkUdSaPZNVEhyxVK3oF4KeNGWKnPtzLZcakM3sy6RQa+Cp33DUDkkKRJGyiFSCBqJrbitruJFnrQOlPScKd2sm+M2JleaRpITSAkIttRiAA5MVNk9XuPwTItvnlwiyVVv3k0gew3EaaE5vdihmxW8es/ImlWvKxEz5cBjtpXSSQsm6+c3fyLfI6xIphoJGPu4a8FGK0UbySFzYsbhcDgcl2Ndgu1zn/vc4PfHjh3j537u5/jBH/xBXve61wHw2GOP8Xu/93t86EMfujZn6bghbMaw/Fr2zkII9k9WaKY5M80U35NIAa20YKqZsmeswvc+sJMDkzW+6xXbeW6q2VtEFkgp2DoUsWO4zGwz5exSh/l2TigFd2+tEniSPWMVhBB0eqYBxkAcegSeJFMaKSD0PHaMRQRS2tYqT1KLPI7NddDG4EmBJ60yC32B0bI30+PMSRy3H544nzEohEBpCCXUY59SaEXQy3cN8yNvvJvHTy7w0c8fJi80L8w0yQszmCXtB9AvdDKeOtNg21B8QdVruZgBaHRzMqUJPUkt9tcUM/bUBGatUviy713LS3MjlSKXQ3Z70p/bfGGqSb0cu/ZOh8Nx3ViXr8Kb3vSmwa//+B//I7/6q7/Khz70Ib77u7+b7/7u7+ZDH/oQ//bf/ls+9rGPbejFP/ShD/Ga17yGWq3G5OQk//Af/kOef/75FY9JkoT3v//9jI2NUa1Wede73sXU1NSKx5w4cYJ3vvOdlMtlJicn+emf/mmKYuWN8POf/zyvetWriKKIAwcO8PGPf/yC8/nIRz7C3r17ieOYBx98kK9+9asbPpfbhUPTTX7z84f58Gde4P975CAf/swL/ObnD3Nourmh4/Ttnc8uJZhlpanRSsTLdw4R+R6R7zHXSlns5Ny/Y2hFO1Q58CgKzVwrY6GTsdBOOT7X4eB0k7ONhLONlFaqODLX4XPPzfKN4wtMN+xrnVtKkELYRWRvFk4A9VJIoTWnFhNetdtWj5XSIMDvzbOlygxaIrWGAxMVQk8ihV0Uulu043ZAApEviHyBJ+zv48DrGWzYmbbTix0A9k1UOLPUpZUWZFozXo1QyoZulwJ5PkvRs79vpwWzrYzSqqpXX8wkuearR+d59IUZvvDCDI++MDMwCEqLlQH33VwxXg2pxj7z7Yy0UGhjSAvFfDujGvuMV0O6+c3R4bF8o2otXA7Zrceh6Sb/4YtHAfjoo4ev+J7ocDgcV8KG7xaPPfbYmmHZDzzwAD/8wz+8oWM9+uijvP/97+c1r3kNRVHwC7/wC7zjHe/gmWeeoVKpAPATP/ETfPKTn+SP//iPGRoa4gMf+ADf8z3fw5e+9CXAtmC+853vZOvWrfzt3/4tZ8+e5Qd+4AcIgoB/82/+DQBHjx7lne98J+9973v5L//lv/DII4/wwz/8w2zbto2HH34YgD/8wz/kJ3/yJ/noRz/Kgw8+yK/92q/x8MMP8/zzzzM5Obmuc7ld2Mxh+UsN7c+1c16zd5TvuH/rIBR3debSJ756grl2Rq4MtcgHAZ1U9TLV7IIyCgS1KLA23Ini8y/M0C00C52cyXrEfK81sp/npoyhUBqtBa/aM8K5ZspsM+HkQpdCGzwhVuzVt3LFs2cbVOKAoZKPXkxIlaZwc2yOW5ygl5xdaIPvSbYPxeRK08kUSaEplCbJ7Bv99/72GNOtQ7Szgk5aUA6sILHX6/ktDNWrUPdrXqs3NyqhnY/728OztgK+7HuLnYxzjYQdwyXOLSWDz4RK6DNejRivhpxdSlnomZ34UjJZj9lajwBx0wggl0N2e9G/Jy61E3bU4K6xCq3c3FEGMg6H48ay4bvbrl27+O3f/m1+5Vd+ZcXXf+d3foddu3Zt6Fif+tSnVvz54x//OJOTk3zjG9/gjW98I0tLS/yH//Af+P3f/33e8pa3APCxj32Me++9ly9/+cs89NBDfPrTn+aZZ57hb/7mb9iyZQuveMUr+Ff/6l/xsz/7s/zLf/kvCcOQj370o9x11138v//v/wvAvffeyxe/+EU+/OEPDwTbr/7qr/IjP/Ij/NAP/RAAH/3oR/nkJz/J7/7u7/JzP/dz6zqX24FrMSx/pUP7n3ryHAenW9RLAUluzUECT2DQg/Ytr3dugSepy4BCZ3QzxVOnFqnGPqOViNCTzLUyGklu5+C0YdtwibA3mzbXSjm3lKC0IZCSzGjrSLn8fAxgDI1uQe7EmuMWRmANdJQBpfpvdMFw7DNWDcmVxjRt9ponJWeWEtgG3zq1SDu3mx4ArUSBsO2ULSEohR5SQJIpPE8wVA4Zq0Z0VlW9ttVjFtrZ4HMgDuQgB7GTFZxa6NLo5vzBV09QDn32T1R5+31bBgLogT3DtFI1aKOsRh6HZto3lQByOWS3D8vviS+aqEBif7612L/jDGQcDseNY8OC7cMf/jDvete7+Ku/+isefPBBAL761a9y8OBB/uRP/uSqTmZpaQmwQd0A3/jGN8jznLe97W2Dx9xzzz3s3r2bxx57jIceeojHHnuM+++/ny1bzuf9PPzww7zvfe/j6aef5pWvfCWPPfbYimP0H/PjP/7jAGRZxje+8Q1+/ud/fvB9KSVve9vbeOyxx9Z9LqtJ05Q0TQd/7rtt5nlOnueX/Lfof/9yj9tsTi90OTbTYEc9RKJZvv0tgB31kKPTDU7MNtkxsv7F0Z6RmB9+/W7OLiWDmbhtQzFSijX/jqcXujx7egHPaLbWArT2WehktFMFWhP1uqxCKYgk+NKmaI+WPFpJQTfJKPmglUfkQT2SjJRK7J+sMF6JADuf97VDMxRFgTCa4Qi6uaZAE0io+vYvPxyJXh6VYbGT2aretfE2cKwi6s0R9v/ruHoEEPuCXBm0gaBXefaEZrGdUPI9SgEYDUYrRkr2ze5hiLye4JPnQ7cl4GPD3FJliD3JnrGYPWMVQBDLlZ9jJ+c7dJKMig+e1ARS4Alh2xxVQSjt8bZU7UbMs2cWOLfU5k13j3Nuqc3RmSZb6zGjJUk30xyd6TBeCXnri8dQquBm8b3aMxLzAw/u5JFnpzk622a2YdsgX7a9ylvumWTPSLyhz/cbdU+407ngnggIY99kV3NPdFwZ7jq48bifweay3n/HDQu27/zO7+SFF17gN3/zN3nuuecA+Pt//+/z3ve+d8MVtuVorfnxH/9xXv/61/PSl74UgHPnzhGGIcPDwyseu2XLFs6dOzd4zHKx1v9+/3uXekyj0aDb7bKwsIBSas3H9P+O6zmX1XzoQx/igx/84AVf//SnP025vL7h9c985jPretxm8oYYuxLrXuQBMTzx2EmeuMrXudzz3zEEDK3nSBcb3C+AzqqvLQ5+97Jh+983H7j00X/h5c4Y4Ebzrx5wJc1rz6VvGr90yZ/BapWUAAvA2p8V791/uXNRwDEwcH+vAN8+fIwHJFDDfj719sL633/ua8d47nKHvQHsAHbEy77QhOe+9twVn+uNuCfc6QzuiYn9897k8MoHbNI90bF+3HVw43E/g82h01m9Tl2bK2r437Vr12A+bLN4//vfz1NPPcUXv/jFTT3ujeTnf/7n+cmf/MnBnxuNBrt27eId73jHZfPq8jznM5/5DG9/+9sJguBan+qA0wtdPvK5QwyVAqrxhW+PVlKw1M15/987cE13E08vdPl/PvWcdYjU2jrRGYPptU3l2s7GhJ6kXgrwvfOzOGmmiAPJD77+Lv7u5CKdrGDvaIVy5NHNNOcaCVmhODlvFWk3V0y3EvTKgiKRNPyrBzT/5psejcyFZd8I+j+DX/y6JNWu3WizCCRsG4pJco3ShmZSoHrXV+QLaqUQXwhGKyFnF1r87Mty/uU3JLmxPlXaGHxhDUr6LY+v2TvCS7YPkeT2GhuphHz/g7vZN1Fd8dpfPDjDL/35M4xWQyJfkheabq6ZbaUEnsRgYzjedPcEI5WITGvy3jzdB95yN9uG4jUr9Tc7R2Zag2rbXDtlrpUDhrFqyFgl4q7xCm+9d/KCf68+G7knLH+tfij55Y7vWJvl98RaJNibHOZYvB8jbOX5et0THZYbtTZynMf9DDaX9WZdX5Fg+x//43/wW7/1Wxw5coQ//uM/ZseOHfyn//SfuOuuu3jDG96w4eN94AMf4C/+4i/4whe+wM6dOwdf37p1K1mWsbi4uKKyNTU1xdatWwePWe3m2HduXP6Y1W6OU1NT1Ot1SqUSnufhed6aj1l+jMudy2qiKCKKogu+HgTBut/kG3nsZrB73GfvRJ2nzixxdxxeMCx/upFx/44hdo/Xrukiafe4z+RQmS8eXaBQhmrk43mgtCHVgqy3oe95AoW0YstAJ1MUGl68vc4PfNt+3jjf5lNPnePJ00t0MkU59NgxVObQTIuFRDFZi5jrFiSFuKhd/2IGqbr5F4S3M6kW7mewiRQaTi3lRL6073vpEXsCbQRprug07bxnZgSNzF4YHWWvO5tTKAh9Qex5mMJ+P9WSo/N2Lu2+HSMXnU/dv2WIUhwy17aZatL3ELog1QLhCTqpRkqPo/MJz0x3KLRG9j6HXpjpsHeyzt7J8Lr9W20Gh6ab/MevnGK+nVEKJFOtglaiEBgKcoYrMU+ebXG6kV3WwOJy94Tlr7VtKGZL6NPJinUf37GS5ffEF01YQWaEZ39dx3uiYyXXe23kuBD3M9gc1vtvuC5b/+X8yZ/8CQ8//DClUonHH398MKO1tLS04aqbMYYPfOAD/Nmf/Rmf/exnueuuu1Z8/9WvfjVBEPDII48Mvvb8889z4sSJQQbc6173Op588kmmp6cHj/nMZz5DvV7nvvvuGzxm+TH6j+kfIwxDXv3qV694jNaaRx55ZPCY9ZzL7UB/WH60EnJwukUzySm0ppnkHJxuXddheSEFpaBnZJBbIWbozdxg5wdyba29s8KeY1poxioRP/j6u/B7QdtLnZxmN6ebF2ileWGqSZIrhkoBudI0kwJ3n3XcCSx/m+eFdYOUWOOeOPAIfYHsxV+kuTXIyJftZBisOYgBK6J6v982VOKfvvUAP/bWu/mJt7+I975p/0VFwc6RMg/tG0MZa/iTFgrRO7N2UlAYgxTQSHLiQDJSDvGloJUUfPLJs7ecjfpy04oDExXOLqWkuWJLPWKyHpPmmnONlAMTFebbGZ9+emqQ93U1r3X3ZJVaHOBJQS0OuHuyetXHvxNZfk88PNMGQN2ge6LD4bhz2XCF7Zd/+Zf56Ec/yg/8wA/wB3/wB4Ovv/71r+eXf/mXN3Ss97///fz+7/8+/+2//TdqtdpgFmxoaIhSqcTQ0BD/+//+v/OTP/mTjI6OUq/X+bEf+zFe97rXDUw+3vGOd3Dffffxv/1v/xu/8iu/wrlz5/jn//yf8/73v39Q3Xrve9/Lr//6r/MzP/MzvOc97+Gzn/0sf/RHf8QnP/nJwbn85E/+JO9+97t54IEHeO1rX8uv/dqv0W63B66R6zmX24UrcXXcbE4vdlns5Hzb/jGOzLQ5tdClnRYYY4gDj629QN68sC2SxkDoS16yvcb73nyAt967hUeeneL/e+QgM82U0JdEviTJNFMN69JWCj2mlhIKbdCu39FxB9BfpuueOWShDL7UyFxRKN3LH9RIBHnvmlhrHSp6R2ulBb4veeXuYWql4IJojrWQUvBPHtzNdDPlhXNNmklhy+PYybVACgJPUo0DQs/uKWaFZs9YmTRXt5wj3/Kg8FaqWOhkVONg0L3Qz5ZrpWrN0PArfa3l3RFgA9Gv9vh3Kv174qefPAOtMxyf6+D7wXW9JzocjjubDQu2559/nje+8Y0XfH1oaIjFxcUNHes3f/M3AXjzm9+84usf+9jH+MEf/EHAulJKKXnXu95FmqY8/PDD/MZv/MbgsZ7n8Rd/8Re8733v43Wvex2VSoV3v/vd/NIv/dLgMXfddRef/OQn+Ymf+An+3b/7d+zcuZPf+Z3fGVj6A/zjf/yPmZmZ4V/8i3/BuXPneMUrXsGnPvWpFUYklzuX24l941W+6+WSo7N2R3HvaBkhBd1ccXK+c8GirCg0Xz8xz6HpFqEv2TVcZqgSUIuCgdX2qYUOR3rHu2u8wq6R8kUXXc0kZ76TsbUes3e8ghAw08xQRhP7ktC33nRvvH+cyVpMOfQZLgdEnuTrx+f5zDPn+NKhWdJcs324hO8JOqlitpXSzRXtJMcTduYtV2632XH7I2AQ+u7LXrVMQ640mdJ4vQV+7EtyrQdDm/4al6gBssIQB5KxcshCJ+fXP3uI2PfYP1Hl4ZdeehF7YLLGj7/t7hXtykPlghNzHZppjtKGk/Mdwt61PlQKOTBZI/DEDRMcWltn2f7s3OWEaZ9+UHgpiDm1aDeeQk9gjHWfDTxJOy3IlGa4HDDVSFaEhm+E/muVw7VnqUqhd1XHv5M5MFlj1xvu4lOfeo7/8037qZfjdb8HHA6H42rZsGDbunUrhw4dYu/evSu+/sUvfpF9+/Zt6FjGXH6hHMcxH/nIR/jIRz5y0cfs2bOHv/zLv7zkcd785jfzd3/3d5d8zAc+8AE+8IEPXNW53A4cmm4OqmtJr90wzTVRYBdPqxdljzw7xW987hCHplt0c4U2Nnx6rBpy3/Yhdo+UWehmPH+uyVInxwgYLoU8dNco/+Sh3Rcs7A5NN/mvf3eGw9MtXphq0kltOO9kLaJQkjNLXbqZxgAnF05SiXxGywFL3Zz5Tr5iFs2X4HsCKSTdXJEXim5mf51rpheE+joctyv9NmJPQuR7JIUdBDXGZrJpYYh9SRR4ZImBXuh1tkb1WWCvq/FaxM6RMrtHy5R7s1LrDRM+MFnjR99c5fRil2fPNvjkk2cxRnN01vRy4mwFr4LPXeNlRishhdY3RHCs/kxcrzCF80HhXz4yx2InH4R+V0KP0UqElDbvLvQk3cxa/19pAHgl9Il9G2hei1fORRhjmG4kJLmm0c3R2jixsUH6/14v2lJzszsOh+O6suG7wo/8yI/wT//pP+V3f/d3EUJw5swZHnvsMX7qp36KX/zFX7wW5+i4jhyabvKxLx0bDKwnueTxEwssdHKGSwGv3jNKHMjBouyerTV++38cZaaZIIVACrsALLRhppnx5KklvnlykW6uGIoDxmshAsFiJ+czz04x3Ur58bfdPVj09F9/rpUyUYs4NttGa4MQgrOLiRVdygzynySGRjdnoXPekrxfSQBrrnBmKaUcSGqlACk8WqmyxQMDkY+zf3TcEWjstaENIMxAwBWmdy0JeuHXAm3MiusIbEh9HwNIY5iohrxy9/Cg/a4WBxsKE5ZSsGO4xH//5hmyQvPynSN0Mo2UAl8KJLbafmqhSzXyyXth2VcqaK6E1Z+J5bC0IWHazRQzzZRzjYRt9ZgkD2ilBe1MkRZdSoHHztHypgSA7xguDQLGq5E/+LnMtzMOTTc5PtehFvt84isn+NrRhXUJTofD4XDceDZ81/u5n/s5tNa89a1vpdPp8MY3vpEoivipn/opfuzHfuxanKPjOrF6YB3gubNNCmXYPVJioZNzbK7NA3tGuHuyyvPnGvz2wRnmWhmRLymUXRJGgZ076WaKuXZG4FkVJwXEvocQgi11yVwr46nTS/ynx47xnjfsY8dQafD6L9pSoxR4HJlp2UWj0TQTNVh0+r0FXa70Be6OnrRCbTndXFMOta0ALvt66jqDHHcQBltNa6X2KpC9rwlhBZvBGvwsV2py2W8CYwWfMpBqepslGaOV8264G52VWj53VY18RisRM82EWiUkyTWdQjM73WKulZIrw/7JKt1sde7btWH1Z+JGhanWhs88M0W9FKC0ppUW1Eo+mdKkuSLJDULAllrIoZn2VRtY9A0yzix1OTht/027ueLx4wssdnNGygGv2j1CHHjrFpwOh8PhuPFsWLAJIfhn/+yf8dM//dMcOnSIVqvFfffdR7Xqsl1udVYPrDe6do6sGvtIKQfD8c2koF6y7mPTjYTAk/hSkhYaT4pBm2HgSZJCYzDU44BurskKTRR4JLminRW00oK/euoc55ZS9oxVODLbYndvgddIcgplyLWmk5mB0JICwt5gjV6n4DLAYidn9bja6iqCw3En0N/0AGu4ow2gIc01pcAj8CSL3Rxhzheg++LO9CpyAmglOYdn2oyUV0aAbGRWavnclRCCA5NVWmnBuaWEdqZQ2mAwKG2ol+wt6/ceO3ZdhMbVmnj0n3/3ZJVclTk83Wa+k1EKPQzg93abOpnm5buGN8XAYrlp1KHpJs+cbdBMCvaNVzgwWR2I641UQh0Oh8NxY7nivpIwDAe2+Y7bg9UD65nSFFoTePZtEniSVm84Hvo77YYAEMKG7oplQRH99Y0xtuqltEEZQzcreuHV1ugg9D1KocczZ5c4Mdch9iWPL3Y53JuJ80Tv+er88Yyx4b1woeC62GikMSsfG/aMF5R2XZGOOwdP2GvT92yemsBQGBgpB3zb/nFGqyFHZtp86dAsiPNRALpXXfOkoBRK2qlCSrliE6fPRmaxVs9djVZCXr5ziEdfmCErFEKAQDBZj3nJ9joj5XBdQuNKTUKWc7UmHsuf70nByN6QZmI/QwNPoLTh2FyH73twN2+8e2LTRNOByRr73lzl68fn+a1HDzNWidi6SnTeia6Rm/GecDgcjhvBugXbe97znnU97nd/93ev+GQcN5bVC6ewVznLlSbyPXKl8aUkkLb61k6LQX6SdTyzomi5UAP7Z6XpzbgJ5loZuTJEvkfWm0kZKYcMxT7Pnm3wxUOz9jjYBVGuTK/d0qKxLY4Xo//c1bpteROV/b5AClsucLb+jjsBwfmNC60NBoEnJVprcm1ICkWjU1hr/95CVgp7JflSUJIelchDKY0UkBYKL7P/BSvYtNYcnmlx13gFbcxlzS3WmrsKPEkl9KhGZVppwWQt4tv2jw+OczmhcTUmIcu5lIkHXF6Yrn6+EGKFsG0mORPViP0Tm1/hktK+VhR4TNYvrBDCneUauVnvCYfD4bgRrFuwffzjH2fPnj288pWvXJe7o+PWY/XCqRb7jJZDppsJQdkG11Zjn+fONVnsZMy3MzwJSW9grG+TLzy7MLACTxB4giQrGKvaVpxurgg8QaY0AthSj8iV5tB00w7i5xpPQBR6RJ6k0OqCVsZLYbh8m6PBnmvoC5Sz9XfcQfQNd1JlxVgp9vC0ICs0Xzw0h9LaOkf2zH2C3l2iEvkI6ZMVikai8DxJN9O0UsW3Ti1x/04btv3U6YY1BjLw7/7m4GUXxWvPXRUkhf0cGC4H3Le9vkLQXEpoXK1JyHIuZuIB1nXx7FJySZOQq33+1XK1gvN2YTPfEw6Hw3EjWPen9Pve9z4+8YlPcPToUX7oh36I7//+72d0dPRanpvjOrPWwmnveJm5dsqJhS7lwKOVFCyoHIFhoh6xP67yzZOLdHJF6EkMhjS3RiBSCEYrIZnSJLkiU5pOVlAoRa6tw8GWesxELeaJU0s0ujmBFBTSVgHyQqOUXTxKwQXmIv2lzwUtkev8+xrOL0qX0/NIcThuO/o5bBLbviwEJLkGDL4UlENJktvNjMATJPl5U59OWqCFoZtrhICJ3rUNgvl2xuefn0EbGw1wz9YaByZrdHO1rkXx8rmrwzMtFjopShvG6hH3bauvMDWBiwuNqzUJWc1an4ml0KObKc4uJZc1Cbna518tN1ow3gxs9nvC4XA4bgTy8g+xfOQjH+Hs2bP8zM/8DH/+53/Orl27+Ef/6B/x13/9167idhvRXzi9dPsQi52cpW7OrtEyL5qsIoWglRbEgWT7SJlX7R7htXeN8bZ7J6lGgW2x6rVb+Z5gpBJSjTxGyyEj5YAk15xZTEgKjS8E+yYqPHjXKDPNlG5WUIs9pBSUAg/fkwhBz3TEUAokwyW/Z+W/EgnUY58r2SQuVs219XOqXIek43al5y8CBjwhKJSmUIbQk4S+vfaGSwGh7zFcDuiZvpIoQytVCCD2BQudvOe+6lGPfVpJTqsXSH98vsvjJxbJleHuySrz7YxPPz2FXr3rsowDkzXe9+b9/MTbX8RPf8c9/E8v3cpENWakHK48/57QODBZvUBobMQkZL2s/kw8NttmsZNz/46hdVVmrvb5V0NfMI5W7NxfM8kptKaZ5Bycbl1zwXgzcC3eEw6Hw3G92dASN4oivu/7vo/v+77v4/jx43z84x/nR3/0RymKgqeffto5Rd4m9AfWlw9nK6350F89RznwGC6H1OLzu7X7JmqMVUIOz7R5zV2jdrgd+Oxz03Qyxb7xCuXQZ6qRcHTWuqSNVUJet2+MVqpY6GRU4wBjrBNcNfKpC2imCnzoZIpK6KEMeJ4g8iAOfNuiJewO6usPjNPNFY++MIPRdti/0JeutvXf/HHo0elZmRvgOjmGOxw3jL69f1EYuwkibcWhnSlCXyKlIPQlhTI9UdSylWcg14YitZso2+oxnhScmu/SzRWlwKMaB0gpmWkmtNKCV+waXre5hZRi8P3wNZKPfenYhipTV2oScjkzirU+EzdiWHG1z78aVlcvpxoJke9x/46hTXGlvNm5WuMYh8PhuBm44sZ1KSVCCLvIVm6Fe7uxfOEE8Ny5Bp4U7Bgp40n7c29084FpSDkKqJcC3vGSrbxossZvfv4wIHj5zvOhutuHS1Qjn2+dXqSdKQ5OtYhDa2YS+oJ2qqiEPqEnGSoH5DqxeUvGkBQ94xFjCDyP8WpE4EsKbU0N4sAnDjzGKhGzrcxmtF1iNx+gwIYBa2NcC6TjtsSXEHqCbn5h62//z14vgy3wJTot8HpWr56ARGlmmzaUvpekYSMBPNs2OdfKCHrVcIH9mjZQ8iVhJWS+nXF4psUrdg2RFmpDi+IrERpXMrO1XjOK1Z+JG+Vqn3813EjBeKNxc3wOh+N2YEOfUGma8qd/+qf87u/+Ll/84hf5ru/6Ln7913+d7/iO70DKdXdXOm5Blt/0cqUHeUKFts6RldBjpBJSCf01W1Dm2+ngOd28IM011dAnTKUN6sXOs71ke8jR2TbdTDFaCZlWKW0UzaSwC0sp6GSas40EKWxw9mg5JCsUJ+a7BL4kKRRpsT4FpoDOJRwnHY5bGg1dfV6sif4vwcDIJzfgKTszKoVAGYMvBEpDNy/Ies/uX1JSQCAlyhjamUIKWwFPC0Wh7Zyq36vQ9bMbZ5rpFS2KNyo0NjqzdSeZUdxIwXgjcXN8DofjdmDdd88f/dEf5Q/+4A/YtWsX73nPe/jEJz7B+Pj4tTw3x01E/6b35aNzLLRTklxTjX0Cz7rGnVrsUmhDNy/QhhUtKPPtlG+eXKSbKaqxTyWKmGtlhL5grBoyUYtY6GS8bMcQUkqGSgGHp9ucWbJtVpEviXyJLwWp0nQyRSdVhJ4gCjwKbXjkuRlCX7K1HjEU+0zl2Q3+F3M4rj2XC35Xq77fd1CVQLCsCm2AhW5OOZBkhUb6ctBW3N+L669z7fWt8SRgDAqbJ6Z6AdwzzZSlbkEpsDNwhdKcXUr4tv3jV7Qo3ojQ2IjJx40yo3BZYNeXG2384nA4HJvBugXbRz/6UXbv3s2+fft49NFHefTRR9d83J/+6Z9u2sk5bh6kFLz9vi18+plzzLQyttZjAs9mtLVTxXglJPQkn/jKSR5+6RYiT9LJCqqRz+Hp8xUzIQRpoYgDj7sna0w1U7YPRZRDn0MzbbYNxdRLAS/aUuHMUpehUsBD+0apRAH/44UZkk5GOZCkhcEIqEQe5cBjtp0T+oIXb6lwaKp5o/+5HI4bThwI0nxtOacNCMxA8ElphUSSKRCw1FUUemWr8CBzkV5wvep/3dBMFUIIfGEGFbx2WtBKcwJP8pJeG+PNNLO1VieAMWYQbF2NfA5ONVfM3V2t2HJZYDeGO32Oz+Fw3PqsW7D9wA/8wJrBm447h1LoMVGL8KWgndl5FF/atieA+U7Gp58+x5nFLp1MMdvK2D9RYb6TUe2ZlBhjaCUFk/WYWuzTzgqOzXV458u2cWahy5HZNlONhEIZKqHHq3YPs2u0QqObUw49qrGdoSuUIS0U9+8cJvAEXzk8RzMpePSFORYTNzzuuDO4VHUtXWNubTnK9CptnqAUSOLQp5MWRL6HFIYis23Inuw/vh8KcOE59M2CypGHLwRJoTFoktwwXA5535v3bdqieD2iaT2tlKvNKJa3bRfatocCPHu2wa7R8lWLrTup/fJm5E6e43M4HLc+GwrOdtzZtLOC0Jc8tG+MTtbLVUsLDk63SHJl5wMwlHuui2eXEtpZTjcvqEQRaaFoJQWl0Ge8GvH144vMtVMa3RwwvHL3CP/zq3YwUYs4u9jl9/72GKHv0ejmdj7GGEaiACkE2hjyjt0FX+rmLCWFbcsKnYGIwwHrzCMUUI8DxioB9+0YYqaZ8g9fsYM4lPynx47TTgumFzuAdVH1e7Nvax/bMFK27YSdVNFMC0Yrkr1jJRrdgufONa56kbwR0XS5VsrVc7nL27YDz6edFix2cj755Fk8Kfjsc9NXLLZcFtjNwZ06x+dwOG59nC2S47L0d7TPLSUoZehkBfVSiDGGIzNtklwNArJ9z9r+25viIklWoJR1k4sDj8l6zHg14uhsm06aI4Qg9iWx7/HU6SXOLiW85Z5JvnJknsMzbY7NtYkDn3LooZShnRZ4UqCUNUYIpODMYhfVC/p1Sx3Hncrl5tnWQgphZ0lrMcOlAIHgwX1jAHx2eAYwdJIMSO1rCIHEDAxL+lb/nhBM1mNAsNjN8aVk12iZ4XLA4ekWv/XoYaLAu6oWwM2uUPXncp88vcRSJ1vRtm2MISs0e8bKJFnBx//2GJXQ50VbrkxsbSQLzAkKh8PhcKzGCTbHJVm+o93NFScXOhyda/PavaMEnhxkqAErWh2FEIPA3AOTNU4udDgwUaUW+3z9+CJLnQylNUuJrdodnmkxUgmZaaU8dXqJrfWIyVrEYicn8gUzzZT5dobBBvwqbVutFjs57bQgkAKDnZu5koWrw3Grc7H3vCfsr2yVGWo/JL4S+ewbL3Ouka5wy+s76+0ZKwNtwLY+GqxTZOxLJmoRi52MTBlevKXKlnppEPWRK83Xjs3TTArGKhGT9XiFwHr3t+2hFPjrak+7FhWqvhnFC1NNjs93GC4HNodxWSfAgckaSV7wzNl5Xrdv7IrFlssCczgcDsfV4ASb46Ks3tHeHpYoBZKvHVvg0RdmeNGW6iBDbb6tKIUe+ycqg0VNKfTIG5rvvH8bj74ww1QzpZ0VnFnq0kwLskITB5JtQzG+5zHdTFnq5ggMByaqBL5HKy2Yb1tRprS2wb0YQl+CgW+eXGCxm1Mr+TSTgrTQRIEkybUTbQ4H1mAELqzA9d0it9Rj5tr5BW55D790C8+ea3Birgvj9gBC2GpaOfTYOmSNh5pJgSkUpcCnXrKbN8YYvnZsnsVuzr7xCluH4t7XYaQc8MK5Jr/0588wUY1Ilb5s5e1aVagOTNZ458u38ey5BkobFjoZvpRM1mP2T1QZrYRMNRS50hcVgusRWy4LzOFwOBxXg7s7ONbkYjvau0YrlEOPrx5d4Phcl25vkbKlHrN/osJoJRoco78IuXdbnX0TFf76qSm+cXyeuZZtrxouB4xVQkq9RYoJPc4udlHG8PXj8wSeDcZudHNyrYl8G7JdDm1rFRhmWjmF1kS+JFcG2WuXdDgcFoOdO1stNwSAEJxa6PKWe2r8kwd3rymWhLDXkzb9X7Y1+cxiFwF0C03gCc4udRgqB5RCj+lGwvG5DiPlgAOTVRY6OYemWyx0MjpZwULbxm68fv84B7bULtvauNEK1UbcHO/dWucl2+r4niD0PUJPDroEgF67tUTrtT9X1iO2XBaYw+FwOK4GJ9gca3KpHe2xaszrD4xxerFLLQ6YbaWDDLU+qxchUgr2vbnKXz5V4pmzDWqxz0g5XHHsTq7JlMYY8D3JSCWklRbMNDUewrpDaoh8CQLamQ3szbXsHcdQKMiUpvfHNatssvc9F5ftuJNYfS14ErbUInaPlhmrhOwbrw6+19+wWerkVCNbEfIF9NMNCwOtVCGwrYWBJzky28UgGK2EJLmmFvu8avcIIHqGHjbmo9k1SCEotOHQbJuJesxoJbxka+NGKlQbdXPcMVziwGSNp84scfdQ6QIx1UwK9o5XaCQFW425IrHlssAcDofDcTU4wXYHUhSax08uMNNMMRj2jlcYisMVu9DLd7SNsVWuhW4OvZamcuQReJKHX7qVR5+f4dBMm631CKWhkeTMt1OGSyHD5YAvHJzhrvEKu0bK7BuvUo8DlLZyyRhDMy3IC818O0VrCHxBKfAQMNjV7haKTGvKgddrU0popwWhJwg8D6UNSa7RF3WwswhsW5a8xGMcjlsdgRVYF4lhA0BrmG1nvHhrjcMz7RXthKcXuxyabjLXTplvJYDdKOkWZrDRYQBfwu7REtXY59xSymIn592v38toOeQTXzlB5EueO9eimxXWmKjQJIUm8CWeNuSFtvOr5ZFLtjaut0LVzRS/99jGjEkuJ6bGqhHfe88kn31u+qrElssCczgcDseV4gTbHcYjz07x8S8d4+B0k1ZSoI2h1HM/e8OBicEudH9H+8xiZ7CYS3KblBsHHpO1iO3DJe7dWmffeIXf/8oJvnxkjqVuTqY0hbIBul8+OofvSYZLIQ/dNcpb7p1k91iZUwsdTi50bEhtoVHaDGZtjIFcac4s5jSTnG5uq25aG7xY0kgK5toZWkNaGDZSK+uvX9Wm/qs6HDcXhgvFmlj2PbBXTTtVHJ1tc2CyumIGq50VnF7scnqxS9RriSxHPu28IFfnjUfKkU8tDogCj61D1hzo744v8tPveDFfO7rAV4/NsdBOqcYBQgiUMWhjeysrccBwOWC+ndFMCuql4KLzYOupUL3tvkk+8/SVGZOsR0ztGStftdhyWWAOh8PhuBKcYLuDeOTZKT70V8+x0LYOjb4EIT2SXPHM2QZZoQe70PvGqwyXAv7yqbN0MoUQgkroYzCkuebobButDd1MISUkuWKiFrG1HvH8VItmN7ViMPAYKYe004LPPDvFVDNh92iZM0td5tsZhTJ40rY76t6gTaENx+faRL6HJ8+bJWigkxYsdXOUXivC1+FwXA6JvZ76v04tdJmoxStmsEqBx2wrIys0w5WVt4kVHdIGurlCGbtBE/qCQ9MtzjYSHn7pFp4+u8RCN2dLIFFa0M0Uaa4IfclIOSD0Je2sIFN20+VS82D7xqv8Ty/dyt88M83phS6ehDjwB6Ip8r2rMia5nJjaLLHlssAcDofDsVGcYLtDKArNx790jGY3J/YFnVxQCn1Ez567kRRMN1PGqwmffnqK/+PbKxisIFPaUImkzT8zdmfdl4Jurvnrp88hgIVOzs7hEo88N81MM7WPA5paUSx0uWu8TDfXHJxuMVEJmW9lYKzxiBRQKGhlBZ4Q5EpTaENJGAotes50tvK23P3RWYs4HOun7wq53C5SALk2JLliWz0ePFZgr3MplrtMihW7JMZAWmimGimid336UtBMctpZwT1b6/yT1+7m2GybhXZGO1Pkhb1+M2VYaGdUIx9fSkJPXnIebHW8CAIm6zFvvXcLr98/jpSC5841rto6/3Jiyokth8PhcNwI3CjPHcLjJxc4NtemXvJJCmuL39+EllJQCj2WujmetDvkj59c4MxiQr0UUIsDlLZVtELZVqYdIyV8T/C1Y/M8eXqJUiD50uE5ZlpWrHkC+h4knUxxcqFLIG1+2jNnmxRaDyzAs8KgMUSetJlR0i4ORysx24ZiqpFP6Em7eGRldcDhuNO4msqywQqr/rUjgMiTxIHH2UYyeFwnV2wbiqlEPu3UChwp7HWpzPljGGMIfUHsSwyGXGumGwmzTesE+237x3nwrlGUhnLgsWu0zP6JKqVAMt/OOLXYtSZCGA5Ot9acB+vHizx1ZonhcsD+iSo7hktMNVI+9dQ5jsy2gJXGJGvhrPMdDofDcaviBNsdwlw7I1ca35NoY/BWtQwFUgzmyNJCMdfOaOc21HrnSMyukRI7RkrsGimxfSjuObUZWmlBO8s5vdhlvmOrZhIrAqUQeL3spiRTNJMMMDTTHGNgvBYS2FUgxlihprDVNoNtj4x8a9Pfb5nq47l+SMcdyuU2KiRQjySVUK4p7paLtdAX7JusMlTyV1SeKqHPRC3mZTuHqERW4Cx07GdI/xgGiAPr0JoUNlqjHgeEgccTJxcHhkGi5/AaBR6hLymFHhPVmDj00AaWujmLnZz7dwxdYAqyOl6kFgd4UlCLA+6erDLfzvj001NobQbGJGeXEoxZ+a/Ur94dmKw663yHw+Fw3HK4rcY7hLFKaHPNlEb2hv/9ZaIt13aWTAqIfI+xSkglsG+PQkMUeCuOlxUKEFQjHwycW2pjNLZtsm/VaIOeEFZ+0UwUnicZKwfMtFLOLdld+FLgDVqvdFqQ9X7fTDKWOoJcG3o+BQOMK685HBelFPoU2pArUFrTjyb0pL12hIDQk+wYKXNgogKIFZWn5a6Mr9o9DHR6gdk2G7GbW+HWyTUIRSn0CKVkqBxy92RlYFQEsNjNec3eEc4upSx0MlppgS8lL95Sox77FBq+78HdPLBn9IJ5sI0GZm+mdf5GstwcDofD4biWOMF2h/CqXSPsHavwwlSzN8Om8QIPIRiYh4xWQpQ2HJis8qpdI3x1xzxH59o0k5ywcj4zzRhDs5vjSckDe0Y4PtfmidOLGGPNBLqZdX30pEAb05tvse1SAnjDgVGmmgnnGgmj5WCwCPIEVCOPTqaQUlCLApJCU2hJ5AtayXlvR6fXHI610dj2P8+TjJR9upmilSo0dvOlb/lfLwfcs7VGN9e8dPsQ2hieO9cYiJOHX7qF04sdnjgxz1uqsG2oxHQ7J08Lewxpr2utDfXIZ7wWs3+iSr3kc2y2PajYJYVi33iVnSNl6wqr9CCcWhnDsdk29VKwphjaaGD2ZlnnbzTLzeFwOByOa4kTbHcIvi/5wdfvHbhEGmPopDlCSrLCtkpO1iLGazHveMkWfF/yHfdv5bmpJk+cXOTcUkI58lFG00kKhBAcmKyw2Mk510hJC01eGAJP43mCvDDk/Zaovl0/mq1DMa/aO8ZjRxdY7OQ0EkUphMAT5MoKx1IgMcBSUjBaDminBYW2bZbCmEG1wOG4U5H03BoFqDVSLdqZYqgsiXyP0BNkWpPlBk/a9udyHCAMfPPkIvsmKsy1Uv7d3xy8QJx8x0u28c1jcwBMNRNSLaiVAqJCE0hBWtgX3ztW4Z5tdYSwpiPLZ8WWB17351b7dNPiknNlGwnM7nO1bo79mbmNZLk5HA6Hw3EtcYLtDuKt924BOJ/DlhboXFEOfe7eUuXb755YsQt9YLLGj7/tbn7js4f4H4fmmGm1McYG6O4YKWMwnG0kvGhLlWY35/mpJmlhkOK8ohLL/lsJfcarEZ1MMVIJ+fa7x/nWqSUWuzndzFbkxqoh+ycqPH2mwVglIis0udJkyhAGkkro0U4K2vn6s9ccjtuF5REX4hLOO8pArgy+B9PNAoFg91hMrgytpKCdWkfWeing3FJKKfDYPlyiFMRMNxMeOzLLN07MUwt9OrmtXhVKE/kBo6WAVqro5Ipq5NFIFFPNlHu2sabT43oCry82V7bewOzVz79SN8fVM3MbyXJzOBwOh+Na4QTbHcZb793Cm+6e4PGTC8w0UwyGveMVhuLworvQcehz3/Yake8R+ZLIlzxxaokjM23e9KIJ22YlBYEvKbQaVMDqkUeh7fzaZC3iDQfGme/kfOP4ApEnGamE/INXVDnb6NrKWuixrV7i5EKHQEoe2DuCJwWPHZ7jxHyHcmDnUbpOrDnuUKRgcH0NxkTXIJTgCcFsM0cb2DNWJvSsM6MQAt+zs6aNJCdXmtftGyVXhmfPLrLQyeikBbOtlDDwKHv2BZUxtJOcVlrYIGygk2k8KWgkOWeXElppccGs2NXMla0nMHsjc2mXY6Mzcw6Hw+FwXA+cYLsD8X3Ja+8au+zj+rvNC52Ml+8cHixglroZStk5tcePLyCEzWPaOVJmtpkw387RQDtX1OKAvWNl7t8xzEg5IC003zq5yHA54NB0k5fvHGbHsF34GGNodHNOLnQohx6eEAyVQu7bXufMYpfFbm5nZq7lP47DcROzuh14rQJbIGG0ErJvosJz51pIY82AzjUScmWIAoknPJJcsdTN0cZwbK7NXDunmxVUI59m11a8k6wg611xSlvDkrwn9MqBBwICKemkBfPtlFfvGb1gVuxq58o2ay5tPWx0Zs7hcDgcjuuBE2yOi7LWbvN8O+Vbp5aYbqVIYLaVUgo9do+UKUc+voSssGKuFPnsGinxhgPjLHYLvnBwhpPzHdqpotyz9D4+3+XVu4eJAo8XzjU5u5TgSUHoS/72yByv3TvKzuEy1cgnKbI153UcDsd5cg2z7YykMGSFQgjBdCO1YfQ9oyGwIk5gRdgL55qUIp+xSkhWaJJC43uCdmoIewaxBuvUagCtDE1dUAo8XrKtQikM+D/ftG9Np0e4+rmyq33+ermSmTmHw+FwOK417q7juCird5vn2ynfPLlIo5sTeNLa9eeglGGqmbJVCHwp8TyJ58FkNaKba04tdHnqTIOphs1HigPJZD2m0c1ZbGd88eAsnmczo7YNx7x4S40kV3z16DyPPDvFXeMVpITYE7S1GZiYOO3muJPoS5P1eO54QqC0tqYgwrYz1mOf5V1+Wlt//9CXNNOC4bJ1glXGoI0myTUGiHqhh6tH5gSgjeHobIf/6f5tFxVrfa50rmyznr8ernRmzuFwOByOa4kLznZclOW7zcYYDk+36WaKLfWYSuiTKRtuXQo9cqWZ72QEnt21FwLKkUeuFEdm28y100F4WinwqMc+O0dKjFcjMmUIJLz9vklev3+c8WqEMVCJfBpJwTdPLTLbyqA3exP4AuneuY47ECnsh7YvLv7hba8/QSnw8D2B1qCUJiuMnSk1hkKZQdh17Ekbv9E7oCcExthKuRT2z/3j2j/b1+5rM83KWTqtDSfnOzx3rsHJ+c4gQPtWoD8zN1oJOTjdopnkFFrTTHIOTrc2fWbO4XA4HI714CpsjouyfLd5Sy1ivpNRje2u80jZZ7GbDXbZA0/STgummzBWjQB6pibYmY+kQBmDFAJPKs4sJoxWAiJfUmgNwkcKyUIn48lTSxyb65BrbbOeEJQDH4TVfHGvIqB6gdwOx51COfTo5rbl+FJoY6+NwJNoY4fPPGmdHhNtUNpQjX3u21bn+FybRlqQFRod2uP2g+l9aStuAKEn0AgKbbMVtbHff/Fklfl2xunFLmmhbvn8sus5M+dwOBwOx3pwgs1xUZY7tB2aadHNCypRRFpYp8ZtQzGtpKCVFnhSozSMlEPu3zmEMYavHl2gkysWOhm5MpRCSTn0kVLQzgq6eUE59FDahu/OtFKOzbY4s5hgsGG8yhiaSUGuCsCQF4ZWppCil0NlXIi24/ajX80yy97f5VDiSUEcSDq9IOy1MEChDWmuKAWenf/MlY3W6LX5jVZC7ttWZ7QSkhcaZaCdKoxJ8T2PHSMlTsy1ydX5PEVPCKSwItAYK/qkFJxtJEw1Uz773BQvTLWYa6XUYp96HKC05snTi7dcftn1mplzOBwOh2M9OMHmuCT93eY/+tpJjs91mGtlxIHHZD1m/0QVYwxfOzZPMykIPMH9O4cIPMnZpYQH9oyw0El57EiOLzWlwCfwJIU2dqe/sK1GSkMjKTgy3aKdFQgBJd9DSkGWna8m9AUa2N19wfkKwC3UdeVwXBbDhY6QsteaOFmNOJp2Lvl8bWyr8kg5IteafeMVKpFPN1dsG4qZqEUkuebgdIs94xV+8PV7+fMnzjLXTtk2VGKiGvH5F6Y5NttG9hoelTZIIVG9Cl0YeOwcKWEMLHZy/uCrJymHHqEvOTbXoVAa35OMlANaacEff/0U/+AV26nFwS0hfq7HzJzD4XA4HOvBCTbHZTkwWeNnHr4HEDxzdokDE1XqpWAwkP+avaN89dg8gRQDQXf/jiFGqyG/96VjCCHIlCErMgJfonulAU9Yq3BfCvJCc2qhw2g1RBtbXcgKzWKSY3qtV7m60NJfGzOYq1EGJ9wctxxrmYmI1X8WtnqdKcVsK11XVTkvNO2soBR6vP7AOG+/byufeca2+R2f61zQ5rd3vDJoAzw+32b7cMmaCxkFLOJJQarsHFwUSHYOl6iEPvPtjC31iFMLXQwwVAqoxQFB7JMrw+nFLp1McWi6xfNTTUbL4XVrk9TauCqZw+FwOG55nGBzrAvfl/yj1+zkY18qmGqmSCkGAbZz7YwH9ozwnfdvY7wWUQl9unnBr/3NQRY6GZM1O9PWSgu6mZVckS967V6CsWqE7wmmGgmtVPUCeRXtTGE0SIk1OFmGwLaICSF67VkgMaSFU2yOWwsJPSfH80Jt+bvYlzBWDdkxUuLvTiySFfYauphrZP/rrUyRKsMDEyM8/NKtHJiscWDy4m1+a7UBttOC//qN46AWiUOPTlcxXA7YWo8JfBvEXQo9tg+XODLbRmnDjqGYyLcOJlprG3afKQJPsKUWUYl8njqzdM3bJA9NN2/5eTqHw+FwOMAJNscGWO8wvtaG3/z8YdppwVApoBR67Bopc2axy3wnQxtIC0PgCcqhx2v3jiCE4PMvzNDNCnwp6eYKsCvYYo1hHQO0M03oCaQQ5Eq76prjlkQB0pyfWVuNFIIt1ZjdIyWeOdtAG02hANG31l97jrMcegyVbDVr33jVHusybX7Lv39ouskjz05bh9YSbB8qkRQJtcgnU3buzbZGV+hmCt03I+kdyxjDfDvr5b9JMmVbKWtxQDXyOTjd4tNPT7FvvLrpVa9D000+9qVjzLcztg3FlMMSnay4LkLR4XA4HI7Nxgk2x4ZYzzB+P3B733iVvDBMNxNGKyFbhyK6eYHS1lZcYAh9yblGwtZ6iZ3DMacWE/ZPVHhhqkWhNPllkrJt5c0pNcetjQbERYRXrgzPT7dopgXlwMNoQ0upNTcoPAGBL9k+FPPtB8aRUrDQzvj68XnqpWDdbYHLBc+OeggG7t5S5WwzR0rBi7fWmahG1HqusTPaBt7nSg9m7bJC080LPCFIC4UnBUEv000IwbahmEPTLU4vdjd1Vkxrw18/NcV8O+Puyeqgdft6CEWHw+FwOK4FTrA5NsTFZkKWf/3cUkI3L9g+XGL/ZIWlbsbphQ6FNmSFsZbjBmJPUo08np9q8a3TSwjsgu/0QpfIl2RFcaP/ug7HNUWAtdvXF4o1T9p2yUJDWmhOzHcIPYEBPA+MuvA5BpisRbz+wATDlZDpZsIzZxv81qOHiQJvXW2BqwWPREMXttRj9oyVba5iK2XfeGUghkJPEvgSX0paqTUOaqUFrVT1ctgMoe/x3LkWvucxWgkphZ6N/Mg29zrvbxhtG4pXBF/DtRWKDofD4XBcK5xgc6yb1TMhkSeZqEXsGClxeqHLTDMlVdbV8eR8l1LgUWjDXCdjrpmSryqWdXPNifnuBZWC6WZqW6suXVxzOG55zOD/LkRp2y45+LOx1TaA0JeUQ0k3K8iWPUgbCKTAGM1cK+UrR+Zopor9k1XuGqvQzdVl2wIvEDy98xNCcGCyxnw74/hch50jZSbrEd1Mca6RsH2ohO8JQik510yYaaYorQk8QeB5lCOfRjfjmycXecWuYQJPEPkelXBzb0PtrCApFOWwtOb3r5VQdDgcDofjWuEEm+OiLK+azTRT/urJcyx07ExIkkueP9fkS4fn6GQFpcBj92iZF2+tEfkeR2fafOHgLFlhBVzkS/JspQJbbVsO4AsoXJej4w4h8qwwWy+FgcATKG0QygbRi2UB8gI4u5Twl0+eQwpopYpyKDky3WKxnbN/ssLdk9VLtgVeSvCMVkJetWeEx48vMN9O6WQFke/xsp3DfO8DNT773DRzzZRmWpCXNGng0cmUjQKpxsSBNSo5NN1kqBTwsp3D7BheW1hdKZXQJ/Y9OllBLQ4u+H43U9dEKDocDofDca1wdyzHmiyvpnXzguNzXQqlee1dI+RK8+TpJTqZQmLbGz0pWOxkPHl6iVfsGuaBPcP8yd+dplCG0XLAQje/7GtKrE6TcNFQYIfjdsGXtlLWydb3bu+bkihtQAi6mXVU7TtL9tsrA0+w1M3RBqqRx/bhMr4nmG4mNNOcV+wavmRb4OUETynwuG9bne97cPcFc3F7xsr80ddO8vTZBn6vTVJKQeRJpLTnGfqS43MdXnPXKO94yZZNnyPbMVxi/0SVp84sUe0FhfcxxnB2KeH+HUObLhQdDofD4bhWOMHmuIDVDmtV5fPCVAulNN88uYTv2cViNfJZ7OSUQo9cGaqRTztTHJ5ps20oxhMCpG197Ds9CqxN/1pVBY11y/M8gVHGFdkctzWFhma6/q2JuGeVnxSaQq+sqgXSOjwqZejmauA2aVsnPYQQhBVb3To80+YVu4ZJi7XbAi8QPMu+t1zwPLBn9AKxdWCyxj981Q5emG6ytV6iFHjkSnFkpsN8J6OdFgghqMU+77x/2zVxapRS8PBLt3BmqcvBadva2Y8gObtkDZCuhVB0OBwOh+Na4QSbYwVrOazNtlIEMF6LmGmmdDLFjuESylgDkdiTpIVGA9XYBulGvkQIu2CMem1RUtoKweVm07R2Ys1x53CxPLXVSNlrhQTiQJDkZlBdUwZ0b5NDKxDSXmfNpKDRzRkqhwghBtfnTDO9aFvgasGzox4C0EoKTjeyywqeWhQwWo4oh16vQhcwWoloJgWZ0mSFplCae7fVr+wfbB2sN4LE4XA4HHcWFzPPu9lxgs2xgrUc1kJP4nuSQkMceMy3bZaaJ3oZaNoghMATgsCTtNOCJFdkymCMtq6QnBdql1qY6lUPENhWsLXm3RyO24XLvb19AVmurP0/oBF40pzPKOxFAniiZ1Si+w6ThqlGQuhLSqFP4ElaSc7ZpS7ftn/8om2BywXPsZkGxLDUzdcleNZqSRRCUC8FGGM4ON26Li2J64kgcTgcDsedw2rzvPU4J98sOMHmWMFahgO12GekHDLTTCgFti0rKxT1UkDsSxa7OSPlgMATtJKcRpLTSnJMz/6xGnlkygwc7vpVgfXQF2wXCwd2OG521nq/e8s2Icyqx67+GtiNjL4484QNxW4lejDz2X9O4Nt+Y6XtdeNJQSdTnGkk7Bkp0c01nUwzVo0u2xbYFzwnZps88dhJ3v/3DrB7vHZZwXMztSReLijc4XA4HHcGq8d9ymGJTlZc1jn5ZsEJNscK1jIcsHbeVVppQaOb4XvSusMFHp4niAIPpQ1HZzssJbk1RTDWAAGgkShKvqRQir4BpMTOshWXa4/E2fs7bm3W2mgwxgovWFk9vtimhOhb6wNSCEq+R1AWLHZzCmWNf6wpiRlcY9rYD3iDYbGdkeea0Jfcu63O+998YF03JikFO0ZKPAHsGFl/dcq1JDocDofjZmGtcR+AWhxQjfxLOiffLDjB5ljBxRzWRishL985xFePzTPWm1mbaaZsG47ZO+bzrdOLNLoFxthFZRQIfCmteMMuSgOPQWaUlMK62gmzrnZHr1emUJd9pMNxc7BWZW35bUD0XB8vh9erlHkYSoGPEAZlDIU27Bopc3qxS5JrOx9qwJcCbeymSd90pJUWIKAS+fzA6/bwoq3XXjBdj5bEW3UWweFwOBzXj7XGffoIIS7pnHyz4ASbYwWXameaa2c8sGeE77x/G51M8fVjC0w3uvzdyUU6qUICQSDIlcGXkrgXnC2AbUMxu0ZLHJ/rcq6RUIs8kkKT5IpGolY60a1xXuYiLZEuAsBxs7Lm+7j3X09a8dROzrs0Lm//tXNqdnatXvLRBiJf0skUAkHk21nR0JfsGilxdLaDEFAKJJky2M5lex0mhcaTkn3jFapxwAtTLd5yj7nlWxJv5VkEh8PhcFw/LpUvClAKPaYaazsn3yw4wea4gPW2M73t3i38t2+e5rEjc0gJ9ThESkGjm9vAbGMzm7QxdHPNtqEy5dCnmRYkhbYVs56gk8JWHDC94OxVXEyUCWGjAJxoc9wIAgn5sjff8lw0OD+rtvwtLXuP7GSKwtg/i34VTQgypekVpin6uWvYjZBurhBCILuQa810M2EoDhkpB/jSukBON1O0NtRLAWOVkPlOzmQt4tv2j9POipt+F3E93OqzCA6Hw+G4flwuX7SbqYs6J98s3Lxn5rihrLed6YmTSxTaEPseYS8nKvAkuVJobUgLRSAFudakhaKTKe7dWuPpM0s0uqrnIHd+rm2jbpDOPdJxo5DYalg/8N0T511OhbDB2MtnNONAUu7Ne3bzgrzX3xsGAmNsf2Q/WLq/4QHQShUI2+pYCTyi0CPNNUZDN9NUIsPLdg1xdillvpWRFppK6FGNbS7icDngvu11pBQb3kXU2nB6oQvA6YUuu8f9G95yeDvMIjgcDofj+nGxcR9YmS96rd2LrwYn2BwX5XLtTKcXu5xd6lKJfBrdAmUMvhSUQolKNUoZ8sIgfYkADk61yJSmGvu9BammFgb4QtBKC3pFN4fjlsD0/s+X4HsCKSVSQK4MudL4vdy0OJBsG4qZrMcstDOSQjNCiFKaqWbCSOzTSBVpAVEvAFsEkm6mBxlrGPCFIY58JqsRjSRnuFQm9D3iQFKLArKKIc01nawgDDxAMFmP2D9RYbQSARvbRey3HB6bafCGGD7yuUPsnajf8JbD22EWweFwOBzXj5vJvfhKcYLNccW0swIp7XxaK22R5gov9PGlpBR4dExBVhiktkIuLRRD5ZAD41Xm2xmt2TbdXBF4ktCXdHLX2Oi4dfClrZpFvk83VyS57rVE2h5IKSRSanaOlHhw3xgj5XAQHh32nFb/+xNnmGnngxy1pDD43vlq2+C1BFTjkCRXHJ/vsKUe8bJdwwSeZKGd8X0P7qZeCoh8ye9/5QTPnm1wYKJKvRQMRM1GdhGXtxzuqIdgYKgU3BQth7fDLILD4XA4ri+3unuxE2yOK6YS+pQCnx3DHvPtnKlGQiPJ0dqgtHWxM8BoOeTuyRpCCMarAc9PNUkyhdGGdq7xPVdac9x65BoCbefKtNb0LVINAs+DTGk8Idg9er7CVS/Z3vn5dso3Ty5SCjwEWGMQ7MxaumyIM5QC0/Ps71ft6BmWjJRDlDFMNWzVuhL6tLOCN75ognaqmGqmgzbIjewirm45lGjoQjX2uTsOOTjd4q+fmiJ4uaSbq+vuzng7zCI4HA6H4/pzPdyLrxXujua4Ypb3BD941yhfPz7P0dk2uTLWDETAcDlg23DMC1NNDkxWeeLUEp1MUQo9tgzFTDWSFQtUh+N6sdowZKMIoNAGZRTCgOcJlDKUAkkc2ipzoQ0n5jvcu62GlHbG0xjDoakWi52cvWNlfE/wxMklMnW+qiaASiiRQpAUCt8TjFYCSqFPICXNbsHx+Q6hJ0lyxX99/DSzrWzgljhcCtg2FLPYyTe8i3hBy+Gyy1MIQSmQfPLJM3zr1CKeJ667O+PtMIvgcDgcjhvDtXQvvpY4wea4Ypb3BM+2MgQQetI642lN4Em2D5fYUo85Od/lubMNELZisNjJ0cYQepK8OB+o7XBcazwAYc1xPGlIrnDDwJdQCn2aSWHfu8qgDRTGkBaGwANPCGZaKV8+Os/9O4YohR7TjZTDs220MSx0cyTWIVJqKIcSIaCba8qRj9GGVqYotGaxnbHYscH0yhjS44o0t5b9mdLcPVkbuCWeXUoYKQd8z6t2MF6LNrSLeKmWw/l2yvNTTebbGS/aUmPnSPm6uzPeDrMIDofD4XBsBHmjT8Bxa7NvvMp3vHQrhVYcneuQK0PgCcarITtHy7RTxaHpFlLCbDujmeS0M1sxKAUeoe8he9U4AVQC6d6UjmtK30I/V5pS6HOl63oDFD0L/sEvIOkZf8y3U7q9QOulbs6J+Q7HZtucnO+Q5oqSLxkqBVSiAN+TeBKyQiOwmxrdTNFICqQQeMI6TnZz67SaF5qisKYkudIstDNypfGkoBYH3D1ZZaGT861TS7xossau0fK6BczylsMVf19jODzdppUUDJcCRsrhitebb2d8+ukptL72Wy/9WYSXbh9isZNzbLbNYifn/h1DztLf4XA4HLcdrsLmuGL6LnKPn5jn68fmSQuNL0BjQ9VCT1KPfWZbKXlhBqYMQ6UAKQXG0Jv7sclVxlhLc4UhyV29zXFtKAwEPYFVKD0Iq94oWkMnO99T2f+dwApC1RNqkS+oxz77J6p898u285+/cpzjc23GqhFRTxh5UlAv+bRSRVpo2wqZK6QUDJd8ssLOhSptkL0oDCGgFvoMlQJaacHhmTYj5bAXlXHlbokXtBz2vt5KFHPtFBCMViNq8crbRzXy+cbxeb5+fIQH9oxe8wrXrTyL4HA4HA7HRnCCzXFF9F3kTsx1OL3YIdeGQABCUChDMynIlWG4FNDJFc0kxwCp0jTSgtCzWVOZ0hgMprfa7WQ2c6ofJuxy1hzXAqMN0rNVNn2Fc2wXe5rGGof0A7RNYWiniulGQjPLmWulDJdDFjo5kzUbli2FsNWqyF4DE9WYxVaGkAACiTU0KQUegS8ZLgVobTc5Al9SFT7z7YxmUgyMTa7ULXF1y+GOegjAYjdjqZszXo3YP3E+/2y+nXJ4us1sO6XRzfmtR4/wtd0L12Wm7VadRXA4HA6HYyM4wXYHorXh9GKXZprTSgqqkU8tDi66O91/fDsrKAUeRhv+82MnODnfIVfKtkFKgZbCOkMWdiKt0IZmkhP5EoPBE3Z+KM0VndSmBgeeoNzPnDI2wwrsQrcfSgwXXxw7HFdCAQQYDOKavbf6ew1Kw/G5Nr4n+MRXTvDU2QaeEDSTgmaaM1GNiH1JKy0QQuBLyV1jFY5hK4CNpMAT9jyHSgFjlYgokEw3EyT02pAl7dRGBvS5GrfE5fbHx2YaEEOSK0YrES/aUmW0YkVc3+2ymynCXovnaOXmsP93OG4Uy++ZrvJ76+F+fo6bESfY7jD6bYx/d3KBE/MdupmiFHjsHivzyl0jvP2+LZRCb/BB1c0Un3nGZlbMtlJmWxl5oVhKcuLAo5MpPCFoZwq1zJ0/zw0CK8qS3Lad+T1Bt7xqlilDpgyBhLIv6eZ6xQLaCTXHtSJX0H/HCq6N6Y3sHbeba47MtCgFEl+AJ6EaeTSTgnONhHJo3Q4N1vp/rBpyerELBnYMl9kxHHNsrkMt9ogDj7TnBmlD63MqkYcnJaF33onyat0S+y2HJ2abPPHYSX7qHS/mk09N8/TZho0aAA5Pt+lmipFyYCuG9ZhtQ/b1Dk63+PTTU+wbr7rFjuOOoX+PPTzTGri2Xk8XVcfV4X5+jpsVJ9juIJa3MU43E5Qy1GKfNFecWuiw0Mn49DPnmKhFhL5tWZxpptRLARPVkLl2NtjF72aKcuDRTHIKZdYUViuCfz1J7EuWkrXbswptF7GuA9JxI5DXqP22Px9nsBsX082EmVZGVmikBLls1vO1e0d4+swSAsFMM0UAUSB5zd4RRivh4PmhJ2klBZP1mH3jFb55cpFzjZSdIyVKob0mL+eWuN4dZCkFO0ZKPAHsHC3zHfdv5Wwj4eB0i2rkM9tOCX3JQienFPorWiWvdIbO4bhVWR44v20oHri2uorzrYH7+TluZpxgu0Poh+HOtVIKrVHaMFa1BgXVyOdcI2G+ldmWLE/w4N5RvnJ0nnONhELZGbQ0V2ypR6SFppnktNKeWDO9hWnvtVZXK2LfLkrb6cVnaQw2PLiPFNaPxAk4x/VAmWtTZSuWHVcZODGfDEw86L2/01xzcr5D4EkqUUA19hECtgzFtJKC43MdQl+yd7zMXDvlxEKX4XLInrEyoS8Hbo0j5ZBjs22UMWwbinnrvVvYN1694JzW2kHeN17hFbuHLxsBsLxV8vET8zS6OUOlgMl6zP6J862ScOUzdA7HrcjqwPn+xkUtDqhGvqs43+S4n5/jZscJtjuEfhhuLfY5NtehGgcrAmfzQtPJFbtGrBX/dDOlnSm21WMWOhntZsbO4RJCCCJfUot8FjoZZkWoLghzYRtj6EuUNqw37srmUvVb1hyOjXMl4utKxNp6Xmf594WB0O/NehoQws7RJbnm3FLCvdvq3L2lSjn06WQFB6dbNHqRAJEv2TVaZjLXRIGk0c1Jc83r9o/xtvsmmW6k/M0z05xd6jLVSPizx0/zrZNLK1p51tpBPrPY4b9/6wx/8vgpdo2WB6YiF2sB6rdKfv34CL/16BFGKwHbhkorPk/g6mboHI5bjQsC55dxNa6tjuuD+/k5bnbcnfQOoR+GW48DCqUJlllyZ4Um7WU4SQlpT7z1HxcHHnPtDN1TZ0IIxqoRi528Z9tw3hZdYKtjLBNunVRtqN3M5lttwl/acccyWgmYa+ebflxfnM9bg0uLtZ5pKoLz7ZZG2LnNfplN9iraSW4otGbfeJlabF0ea3HAK3cN88JUi91jJf7hK3dQiwK21WPO9ipX/WrYkdkWf/XUOebbGTtGSgPBt7yVZ9949YId5Pl2xsHpNkobjDFkSjNUWmkasmckvuDvJqXggT2jfG33Ak+dWbrg+5sxQ+dw3EpcKnAeXMX5Zsf9/Bw3Oy6j+A6hH4artMb35MCNEUAZm+/kS4HR4EtJOfAGj4t8iYAVDnS+JxguBwSeFXkDC3N6/7dsg0qzserF4DgOxxXQf+tt9odb30CkL8L6r7W6OcYTUIs8RivBQOAtPzfRi60wxtr/d3ONMrYl+JunlphvZ+cfLwTbh2Nmmxm1KGDXaBm/V2m7Z2t9sNO7XIjV4mDNQOuTC50VO8jGGA5Nt+hmBWOVkOFKyGLHitz1BGH37f9HKyEHp1s0k5xcKc4sdvj/t3fnUXJd1aH/v+dONfc8S93WjGRLnvCAB7AdhGXi59iBADaTsSFAYv/AODGGPGzG4MALMzwc3npAsh4OJI/hESDGwhCDjWd5kidZsyz1pJ5qrrrD+f1xu0vdUkvqliVVq2t/1tKSuupW1ak61aq7a5+z94adIziWwdqT22T5kKgJB2s4P0EyznObzJ+Y6yRgqxETzXAzRY/GuE226FYqvRlK4Qca21SU/ICmhENnfZTGuEOmUKbs+ZiGIlPwCIIArTXZosei5jjtqQiGUtTHLSKWwjQgYhlT3lhH0pRYiCPlWIogCKYEVq+UpcIvKSAMtMKeaIq4rWiIm9gK6qImXXUR6qIWlmlQdH3KwdQvH3wdlvmfKEQy0b5CAY6pGM27PLlrdErQFnPCqpAH+2Z3pkt5tu3NjX+DHJ5wZIoeI/lyZXm0bRr4QdgbcfLteseKB31dJva0re6qZ+dwnnufH+ChrcMMZkrkSh7rnx1g80DmCF5xIU4sE5+xvWPFymfrhImM87K2pGSc5yiZPzHXyVcFNWJyM9xcKQzAhrJlInZ4Yhm1TFw/bMy7tDWJYRi0piJsHcwyWnBxLEW25LGpP0ciYtCYcOhsiFEONGNFj6KrwyWVEBY1GS9EYgKuBGziOCp7mrLnH3GWdrp9aZowc+aP/1tpaEtG8LQmFbGJWS4XvaoVyzTYPJDl5ZECg+Xp1/VOFCCZYKjwT8KxaEuFDbW3DGZpjDeilDrsN7szXcoDVL5BTkVtyn4wZXm06wdTWgPMdAnQsrYUwcmwqT9DaypCV32M1lSEgutLdTVRM/ZvON9ZHyXmmBTK/mGrtorqk/kTc51k2GrIxLfhr1nSHC6tMsPmvbZpsLw9ycLGGI1xB9tUDGSKvNiXxgs0qYhFc8IhEbUIdLiEK2abgOL1K9t532sXk4xYGErBeC8pBUQtA9uSt5g4voxXkFmzFEz3ltU6zIRZhgq/iDDADTSGMjjjpAZOXlBPzLFoSkQ466QmWpNhawzbHN/XOT6u6cYKELVNNOH+tkTEYjhXJlP0ZvTN7kyX8ixpSUz5Btkxjcqy54mseVPCITUewM10CVAQaNY/10/ZDzizp5HOhhiWaRywJPNgSyuFmC8mZ5xH8y7b9+YYzbusWVAvX1qcAGT+xFwmGbYaM1HhbfdogUzJJVv0SEYsUlGbgrtvCdNzvWkyRY8V7UmWtiWxDYOyH2AZsH0oz+KWBNddsJjuxjibBjI8t2cML9DsHC6QzpcZLZQxlCLQGssI+6wJcaxN7ClTavZLcS0F9TELX0O25OEH4X0FhAFa1DHRGuIKIrZJQ9zh9O4Gbv/Tk/nff9zOxj1jJCMW2ZLHWMHFNFTYq9D3QYVLHr1AT/ldCBvKGyQiFvmyz5bBLEnHxLZMRvJl+tKH/2Z3YinPxONPXhY5ufjHwsb4lG+QO+oi1Mcs+sZKWAbEIxZLWxOV/W0Tt+usj/LUIV43qa4mxD6TP2MP1+dQzD0yf2KukoCthhlK0Vkfm/Kf0bLWFI/tGOaf7ttCcyJCxzQnYUsNg9G8i6EUhqFIOBaur9m2N4fraxoSDoYRZu/KbkDAvhNpidvEsWSosBKjDsaXMI4HbeZ+AdzkWM4gfF96OtzXpVW4zwzAHL+hH4RZtogVLiH2Sh62oRjIlPjff9zOys5UJRCKWAYl3w8zSkrh2AZ6/MEtQ2GgcYMwk2eZBjHbpKMuihdohrIlxooulDwGMyUuWNbCpadMX16/Mv5ZLOWZ3Edty2CWiGWOZwwNlrclqYvZM2q8PZlUVxNiKsNQ8uXECUzmT8xFVV2v9vvf/54rrriCrq4ulFL87Gc/m3K91prbb7+dzs5OYrEYa9eu5aWXXppyzPDwMO94xzuoq6ujoaGB9773vWSz2SnHPP3007z2ta8lGo3S3d3NF7/4xQPG8u///u+sXLmSaDTKmjVr+NWvfjXrsZwINg9k+PZ/beEr6zfx9Xtf4ivrN/Ht/9pSKQxgGIq6mE3ENmmrOzBYgwOLIGQKLi/0Znh5pMBYwWUwU8IPdHhbpSq92kz5hkocazrcN2lZioRjEjH3VXecdMh4ZkthG1O/RCgHU/v/aR0uCW5NOcQdM8y8aehujvPaFa30NMXZuGeM374wwJ+sbGN1Vz0F18f1NL7WxByTnsZ45XcqEbFIRi0cU1Uazi9ojFWuW9gYozUZoTUZ4ZSuOt7/2iUzWoYzm6U8y9pS/NXFS/nIG1bwd5ev4jNXrebPTu8C1BEtAZLqakIIIcSxVdVP0Fwux2mnncb111/Pm970pgOu/+IXv8jXv/51/vmf/5nFixdz2223sW7dOp577jmi0bA30Dve8Q56e3tZv349ruty3XXX8f73v5+77roLgHQ6zaWXXsratWu58847eeaZZ7j++utpaGjg/e9/PwB//OMfueaaa7jjjjv4b//tv3HXXXdx1VVXsWHDBlavXj3jscx10zXN3b9X07K21JQTsImeUJNNPgH7zXP93PGfzzOYLREEmkLZwzUNbNMIGwOjJ2U3ZA+LOLZ8wEBhoCh4friscTw4m2hWPUEpjanCEiPufqlfywiX8/laE2hY3p6if6xIxDI4o7uRnuZ45cuMZMTipYEsL/Zl+MDrlrBnrMD//sM2fr95EEW4zNJQipF8iXw5oOz5KAW2aVAfczANhR8E5Es+mZJH3LE4uTPF3myZ3nRxxt/0zmYpz+RvkFd2wAVLW454CdBMl2RKdTUhhBDiyFQ1YHvjG9/IG9/4xmmv01rz1a9+lU984hNceeWVAPzLv/wL7e3t/OxnP+Pqq6/m+eef5+677+bRRx/lrLPOAuAb3/gGf/qnf8o//uM/0tXVxQ9+8APK5TLf/e53cRyHU045hSeffJIvf/nLlYDta1/7Gpdddhm33HILAJ/97GdZv3493/zmN7nzzjtnNJa5Lgj0AU1zIWzOO3HCec+z/SxpSc74BOy53jE++f+eZThXrvRxCwirzXl+2O8t7pjEHItMIWyyHWg9qybaQsxUpReg1uPVSsMvChwjzO42JWxKXri2cbTg4/mgjHC5o20oFBpvvMS+YSgStkkA1Mds/uy0Lu59foCuhih1MWfq404ugZ8u0tOc4F3nn8RQvsxj24cZyuYIdEDZC3CDsNF8MmoTt8NKrGMFl7G8izf+O2SZij1jBSKWOetlhEe6lOeVLAGabklm1DYZzJToHSvQnIywdpVUVxNCCCGO1Jxdo7Jt2zb6+vpYu3Zt5bL6+nrOPfdcHnzwQa6++moefPBBGhoaKsEawNq1azEMg4cffpg///M/58EHH+R1r3sdjrPvJGvdunV84QtfYGRkhMbGRh588EFuvvnmKY+/bt26yhLNmYxlOqVSiVKpVPk5nU4D4Louruse8vlPXH+442Zq90iB7YNpFtQ5GExtDqWABXUO2wbS7NybYUFjjLUrm+kby7G1P00yao1nAcJKci1Jh+UtUb7xm03ki2WaogYF10cTNuBGhXuG4hGDupiN5wcUjLDrlG/oufum20/E0FP+Fsffkc7BRLEbhzDDprVPoaTx/ABPg23uOzb8tyZiKgylwoqNWtNeH8U2FMP5MmXXxTE1KcdA6QPL9Sds2Ou5pPNF3JTNSY1Rrjq1ne0DafaUC7i+jwEkLUXEMUlFDUpuQKFUwlaKhphJxDRwrHAT3nCmgKEUA6M5ljZXNzM1k/+LTmqM8u5zF3Lv8wM8/fIou0YKFF2fmG2StBW/eXYPOmhjSWvyeA173jnanwli9mQOqk/moPpkDo6umb6Oc/bcua+vD4D29vYpl7e3t1eu6+vro62tbcr1lmXR1NQ05ZjFixcfcB8T1zU2NtLX13fYxzncWKZzxx138OlPf/qAy++55x7i8Zl9m71+/foZHTcTF0YJA7XCQQ6IwlMP7qpUhDvLAOr2O2Y87s1v3c57FwGLDvWIPnDwprsnis+eJaVSqu3ozMH0fdEONPGf574vWxjcyNrk1Iv2tywJmx/fw+ZJl/3l4umO9A59R5OMvPgIv3pxRoceczP5v2gBsKABaJh86Rhk+3jh0Rd44ZiMrLYczc8EcWRkDqpP5qD6ZA6Ojnw+P6Pj5mzANh98/OMfn5K5S6fTdHd3c+mll1JXt38kNJXruqxfv543vOEN2PaB+8hma/dIgW/9bjP1MZtk9MBpzxbDUuQ3XLKMBY0xtg5m+T8P72QkWxrPsBn4QUC26OFYJgOZYrjnpeRRdAPKfnDQHWonagPtiKH57FkBtz1mUApkOVc1HO85MFW4PNLXkBgv49+cjPDNa87g7uf62LBzhK76GI5pkoyalRL4WwZznNJVx/UXLMYwVOX3zTIUG/ekidoKx9qX1it7PsM5l6FsibIfELdNok7Y27Dshk2/GxMOS1oSfOyNq1jQWL0s20z/LwoCzf++fxvP9aYr7QEmTPcaidk52p8JYvZkDqpP5qD6ZA6OronVd4czZwO2jo4OAPr7++ns7Kxc3t/fz+mnn145ZmBgYMrtPM9jeHi4cvuOjg76+/unHDPx8+GOmXz94cYynUgkQiQSOeBy27Zn/CafzbGH0tNisai1jo17xlgedQ44mdqdLrNmQT09LWFVuN+8MMTenMfy9vopx7ZpzeM7RtgxUgIN2bKm4Gr0EbcqnvtKgaLkz9/ndyI4nnNgGwrHMih4YXPsRmWydaTIUM5n694iz/bmSEQsWpMRuhqiFNyApkSUN6zuIhIJU9DFoEDO09RFLQq+Jhqx8fSk8RuKcuDhaYNyoLEx8N3wy41YxKExbpMveWwbLpL39Jz4UDzc/0W7hvNs3lugrT4OhjX1CxwFbfVxXhosMJDzpGT2K3C0PhPEkZM5qD6Zg+qTOTg6ZvoaVrWs/6EsXryYjo4O7r333spl6XSahx9+mPPOOw+A8847j9HRUR5//PHKMb/97W8JgoBzzz23cszvf//7KWtE169fz6te9SoaGxsrx0x+nIljJh5nJmOZ6yYKAzQlHDb1Z9kzWqA/XWTPaIFN/dkpPZcO1Qh3JF9mrBBmBgYyJfLuwTNrQpyIAh1WNrUsg4WNcZIRk2/+djN7xoqc0dPAouYEANv2Znlk2zARy2DdyR3YpsELfWl2DefDjJllEgQayzBw/alLOl0/GO9LqIk7Jl31MRY2xuhujNFVHyXuWERsk3zZJ1s6MfqX7evHNv33gPu3AxFCCCHEzFQ1w5bNZtm8ed+Oj23btvHkk0/S1NRET08PN910E5/73OdYvnx5pZR+V1cXV111FQCrVq3isssu4y//8i+58847cV2XG2+8kauvvpquri4A3v72t/PpT3+a9773vdx6661s3LiRr33ta3zlK1+pPO6HP/xhLrroIr70pS9x+eWX88Mf/pDHHnuM73znO0BYBe5wYzkRLGtL8Scr2/j+A9t5ds8Yrh9gmwaLmhO85ayFlZ5LEydeMTtKuuBS9gMc08ANAp7aNcpoPqwK6c10S5AQJxDbUrSkIrTXRVnamuT53jSDmRJndDdQF7Opi9rEh032jBUYzpV5cucIm/oyoBQtSYfmhENLMkKgNf2ZEg0xi73ZMk7CqCyhzBY9GuI2Q7kSlmGQjJgYxr7vz7TWlNyAuGNOu4R5LppNOxAhhBBCzFxVPzkfe+wxLrnkksrPE/u9rr32Wr7//e/z0Y9+lFwux/vf/35GR0e58MILufvuu6f0PfvBD37AjTfeyOtf/3oMw+DNb34zX//61yvX19fXc88993DDDTfw6le/mpaWFm6//fZKSX+A888/n7vuuotPfOIT/N3f/R3Lly/nZz/7WaUHGzCjscx1mwcy/PaFARIRk9csaarsS8sUPX77wgAnNccrfdjKXsBDW4fIlX28IMBSinzZx/UDSl6A1pJXE/OPbYBlGCxrTbKys45M0SNT8nAsxd5cmRf7s/SlCwxly2itsUyDvaUS9fEwk1b2AvZmSzy8bThsL2AoLMNAKRjKlojYJiU3wLIMHMugIRbBsRQjeZdk1MI2w2xctuhhWQbdjTFSkZkvOQkCfcT91F4p6ccmhBBCHBtVDdguvvjiQ574K6X4zGc+w2c+85mDHtPU1FRpkn0wp556Kn/4wx8Oecxb3vIW3vKWt7yiscxlk/uwrWhPVb7pzxQ9bNPg5ZE8v97Yx5KLkxRcj8FMid2jBZrjNnHbwvV99uZKeH7YEsAwwFJQkCybmCdsE+qjNgUvoD9TYmUnlP2wfxooXurPhC0qXB/DUDiGQbro4foBTUoRtRS96SKWoVjYEGW04GKbBr4Ol0BiGmSKHnHHpLsxxhndjQxlS7w0kMULAkbyLtmSh2WE/dksw+DMnsYZBzibBzL8emM/WwazFD2fqGWytDXJutXtlez5sTRdP7aYY1Io+/SOFacsuxZCCCHEzMnalBqx/7604VyZzQNZRvJlvPEKj4OZPlYvrOe+FwcZzbu4fsDLY0VMwAs0RTegshNHKt2LecJUELEMLNPANAxsQzOSK7NjOI+lFCXXR6mw+XYyYjFa8IhaYSbM9QMCDf3pIoahCLRGmwYD2TIlL8D1XVqTDo5lcNqCBq4+t5u6mE0qYrOgIcbWvVm+98B2hrIlFjbGKv0OM0WP5mRkxgHO5oEM33tgO8O5Mp31UeJOjHzZY+OeMfaMFbjugkXHJWhb1pbiugsWVQLH/nSRiGWyZkE9l55yfAJHIYQQYr6RgK1G7CsIEAv33ewapVD2SEZt7Gi4BLI/XeRbv93M7pECtqnorI8yknPDoC7QEqOJecdUUBezaE1GGcmXSRddDAVDuTKPbBsCHVaKDAJNW8rC15pAhw3icyWPQINpAAr8QKMDTc73CYCkY4HWRGyTQjngqZdHefNZCzm5s77y+PsHOPmyR8QyOXVhw4wDnMnZ8+VtycpSxFTUJhmxeGkgyz3P9rOkJXlcslvL2lIsuThZtaWZQgghxHwjAVuNmCgIkCu5bB7IUih7NCX2lfdXCuqjFrtHi4wWXVa2JzENg0zBJWqb2AaMFMITVCHmAwX7MlolF9NQBDoMgAwDorZJU8KhUPLZMZxnKFciGbVRQK7k4wUaQ4E1fjutNSjQAejxXxTDMIhaJsmIxcsjBe59vp8LlrZMCV5eaYBzqKquSoVfvGweyLJ7tHDcyukbhpLS/UIIIcRRIgFbjZgoCPDI9iGGcyUc06Dg+pgq7DmVLXrUxWwKbhEF5N2AiAlFLyw7rrVGKZAa/uJEMNGiev8tlmGQBpYZFghxfY1jQbrgYShQaJShiFgm9VGbVR11WIZiMFvC1xCML4Es+xrHDKs+en6AUqA1jG9VI9CaouuTitk4lkHZD0hELHrHitMGTq8kwJmcPZ9OzDHpTxelnL4QQghxgpqzfdjE0TVREEDr8Bv5PWMFXh4psGM4z+bBLEopuhpi2KaBY4YBnBeEy78MBSUvwJc1keIE4bMvWLONsCG1qcK/DaWI2ya2aWCoMPsc6IDyeJuLZNSioz5KtuTx1MtjeIGmpykOGlYvrOfUhfVEbQPHMolaBoHW4RcZKvzLVGHgZhiKpnhY4TFb9GhNRTCVOuqB0+Ry+tORcvpCCCHEiU0CthpjmQpFmA2opMvG/7JNBUqRiFjEHYtMMWw2Xiz7pAvy7bw48Uy815UK/w1hwGabBhFTYVsGhbI/nhlT1MVsOuti1MfscDlk2WPr3hzL25NYpqI/XaK9LkpzMoJtKkp+gGOZxB2LqG1hKCr31ZqKYBhhgZ+YY9JVHyVqH/3AaSJ73jtWPKDq7kQ5/WVtSSmnL4QQQpyg5CvXGjFRmMAxDU7pqqN3rEQqamIZYT+o4VyZvtEihlLEHJOzTmpgy2CWkXyGbMmTgiPihGNCmPUaj2H8cIsZSkHR9bEtg5RlUPQ07XURfK1JRS2idrigUilFMmoxnCuzoCHKivYUS1oSDGZKRCyDsqtY3pZkQWOcloSD1pqHtg2za7hAzDEIxiurttVFWdISZyjnHpM+ZFJOXwghhJjfJGCrEROFCboaYrSmouTKE1UiDTTgWAY7hvOs7Kwj7pjsHClQcn3QWgqNiBOGMZ5J88dXKdqmwhv/QRP+KY83fg+0QcQyiTsGZy1qYsdQnoFMWIZ+oniHPb48uHesyPlLW3j/a5fQmy7yfG+aXz7TS8n1aUtFKgFSWyqKH2iaEg5dDTHqojamAX3p0jENnKScvhBCCDF/ScBWIyYXJjANxendDZU+bNmSh6EUqajF1ed0YyrF1+99id6xIr4GxwKpVyDmOgUkIxZaa7wgLL2vxveVKQUxSxExTQINbhDgB5qobdBeF2aklrYlyJRchnNlklEL2zTIlTzyZb/SE82yDLqb4nQ3xVnSmjggQDpvaTOv6kjxQm+GLYNZhnKl4xY4STl9IYQQYn6SgK1GTC5MkIqG+3POXtRIpuhR9gPKno/na1a2p/iPp3rprI+yqCnOE7tGUWh2jRQrGYqDMTmwKp8Qx4tlhEFbxDaJ2iatSYfGuM1zvWlMwyARsfCCAK3DLycWtyQolH3yZZ89owVWtKc4vbuBLQM5hvNlskWXfDlgWVuSGy5ZekCwdagA6ZJXtVUlcJJy+kIIIcT8IwFbjZgoTLBxzxjJiIVSCqXCIgtaa14ayLJmQT0aKksntYZ4xEIBtlXC9TUKDr5E8iBl/y0FniyrFDNkG2HhjoPtm1SEwVmgwwDF8/W+LJpj4lgG9TGHk7vq2TWSpykR4exFTSilKPsBjmmQioa/A5miy87hPBHbrOz/Or2ngcFMid6xAs3JCDdcvIwV7dNnxg4WIM33wCkItGTyhBBCiONEArYaMbkwwab+DKmota9pcNGrLPkquH5l6aShoDHuMJAu0BBzGM6VCPRB47JpAzmlDn7iLcT+6iMGyjDx/ICCe2C+VhHuU7MtA9s0aE449KeLFN2AqG2RcExaUlEWNEQZypVJRCy0hmTUxpwmoIg5JhHL4PI1nbzUn2XLYJaSFy5vPH9pi+z/msbmgUxlKWjR84laJktbk6xbLa+VEEIIcSxIwFZDlrWl+JOVbXz/ge08uyeNO953alFLgresbGNZW4pdw/kpSyeXtSXJljxcX5OI2ORLLhNtpyY7WBCnpjlWCADHCL9IKHlhhswA2uqixByLouvTny5BEG6eXNaaYG/eJxUxyRZ90qXwcq01XQ0xlrQm6UhF6UsXMQ0AxZoFYc+0n2zYXXk/72+iR9mqzjrWrmqXrNFhbB7I8L0HtjOcK9NZHyXuxMiXPTbuGWPPWIHrLlgkQZsQQghxlEnAVkM2D2T47QsDJCIW5y1pxjAUQaBJFz1++8IAJzXHWdKSnLJ0sinhVAqUmGMFXN8HX2MaClMpfK3Hy6QHlUp8Ew4WxInaZhD2AzQUaBSmoVFKYRuKkq8JymFmrSHhYCsbyHByZx3P9ecZyZUpuD4KjaEMMkWfrkaHt57VPe2+MYCndo3xzO5ROuo0bqArSyIBeseKlVL7c30ZY7WXIU60BhnOlVnelqxU0kxFbZIRi5cGstzzbD9LWpIS6AohhBBHkQRsNWLyydaK9n0nWwAd43vY7nm2nw9elJx26eSChrBR8EnNcTJFj4WNMQyl2NSfYThXxsDDMRV5N6DsB9hGGMwBeLImUhAWpdGE+88iloHW4OmAhGNRH7NoTUVoSkTCJbm2xakL63lVW5zclscARcw22FV0KXoBpqFw/QBlGozlXX76xG5Oao5Pm91Z2Zninuf6ePrlMRwr7DuYGm8O39McPyF6lM2FZYi9Y0W2DIb7/Cb//wFhz7rO+iibB7LsHi3M6cBXCCGEONFIwFYjJvqwzeRk61BLJy9Z2cZDW4epjzn4WrOiI8X2vTly5RyBhohtoNGkIna4H26afUiithiE74tkxCJdcMdL7gcYKgza8mUPNwiwTIMlLUnecEo3qzrrWNAQw/c9frUF/vripXztd1t5eThPfcwiHrGJWAZKQbbo8dSuUe56eCefuPzkKcHXRFa5LmZjGYpsyaPk+fQWPVpTEf5kfCnwXDZXliFObg0ynZhj0p8ukpMeIEIIIcRRJQFbjZh8sqW1rpTzn1geNvlk61BLJ+/bNMiOoTyb+jMoBZZh0BCz6KqPMpgtYShwTJu6mM3I3jK+rImseQFh8ZnWVIRU1KJ3rEjRCzDwsS1FY9KhPuZQdAMe2jZMwQtY0prAMBT+pHh/U3+GqG3SVhel5AWVLwOSEYvRgsvDW4d4eSRPT3MifNxA85/P9LJ5IENzwqEtFSEZMfECsA1FX7rEi30ZLnlV25zNsM2lZYj7twbZ38R+wIRT2x8r1V66KoQQYv6p7U/WGjJxsrVnNE/fWInhfBkvCLAMg6a4Q0d9hIhlErdN/uOp3mmXTjrZEv/14gAFNyAZsWhNOXiBZvNgltGciz9pD9torlypGil72UTRDRjIlNBaEwSaQINpQHdjnIa4g1IKrTVDuTKb+jP8emMfSy5OVm6/fSjHWN4lGTXZMZyvZOoALEMRd0wKrs/WvblKwPbvj+/iXx7cQcH10RpMQ9EQszm9p4HF4wHOXF/CN5vM+LF+Dp310QNag0zQWk/ZD1ir5sLSVSGEEPOPUe0BiONjQUOMhrjNo9tH6E8XiNoGjXGHqG3Qny7w6PYRGuJ2pQ/b/ieIWmu2DOYwjTAjF7UNRvMug+kSIzkXbzxYM1X4x50UvEmwJgINo/kyfqAJxvc2amAo54YFawgDkFTUwg80T788xu7RwpT7cIOAvrESI7kyQaCxTYVjGgQa0gWXdNFjz1h4m3uf7+dbv9tMuugSsQzqohaOZTCUK3P/S3vZtjdLzDEpef6cXsK3LzM+/Xdrx/M5TLQGaUo4vDSQJVN08YKATNHlpYEsTQnnhNgPeKxMLF3duGeMhrjNkpYkDXGbjXvG+N4D29k8kKn2EIUQQpygJGCrJROR037f1E/8rDj4CWKm6DGSL9MQt7FNxfL2FM0Jm4FMEV/va2aciJg4Vm2esIlD8wLIFDzG4zMUUPZ8hnNl9HgQZ4c1+cm73pQgpLspPr7fzQc0tmVgqrDSpGWE1SZ9X/PY1iG2DGb43gPbyJd9Eo6JZRoYhqoEbiUv4Mldo+SK7pxfwjd5GeJ0jvcyxGVtKa67YBGru+oZzbts35tjNO+yZkF9TZf033/pamq8718qarO8Lclwrsw9z/YTTNesUgghhDiMuXumIo6q3aMFRgsuZy9qpHesxEi+TLbkYRkG7XVROuoijORdskVv2n0qZT/A8wMcS2EaBq3JCJ4XEGhwTLBMA88PKPsaLVUhxUFMLkHjBmD4AZmSR9kLiNgmrh++eeK2NSUIMZUibluMUMZAVQI8DXh+mLUzFNy/ZYiXR4q80J+hNelQ8jS5sodpmygVZolijslIrszzfRkuWtE2p5fwLWiIzblliMvaUiy5OCn7tCaZS0tXhRBCzD8SsNWIiczZkpYkCxvjBxQd8bVm+94cyYg17QmiYxpYhiKdd+lqjJOKWrzkht/620ZY7S/QoAKNYTD1zFyIcQowFJViNK6n0YRL+hzLIFP0MA3FqQvrK1UiAfKuT0vKYTBbJNAaLwjvK/y3xgCitoljmWgFJc9nrODSlIxQ9gMKro8znpVThF9AOJYx55fwTSxD3DNW4KWBMCCIOSaFsk/vWLFqyxDnes+6400qaAohhDiWJGCrEftXeKuLTa3yVih5RCyTVNSe9gQRNAHhifaSlni438ixUAp8rSsFRkxTESY/ZOmPONDEu8JQhEE+EAQBI3mXkhuggdO6G1i3umNKlciEY9GSitCccXC9gKIXZtVKno9tKpIRazzba9CScIiYBiUvIF/2aa+LMJJzKbg+ZR0QBJqIZfLnZyw8IZbwTSxDnChm0Z8uErFM1iyo59JTpJjFXCAVNIUQQhxL8ulRI2aztMow1LQniK9d1kJ/psRQzsWxTE5qjhO1TXIln/GtR+jxjIcQ5qRM2oSJTbOWEe4/K41Xq8mVPBpiDhetaOGac3sOCEI666OsWVDPtsEcthnQXm9TdH0G0iVsU+EGGgW010VY2ppg4540e7Nl8iWXloRDV0OUshfg+gH9mRKrOlL82aldx+V1OBpkGeLcNheXrgohhJg/JGCrEbNdWnWwE8TNgxn+72O72TIYVolL2Cb5so83vm9NgrXaZALsF6DtH6yZgGMbGITvEw0kIyandNXha/iri5dy8Yrpe6IZhuKy1R280JfhqV2jjObLOJZBoAOKvgIN7XVRlrWlME2TM3oa+cNLg+TKHumiS2PCoewHDOXKNMYd3nPBYizrxKq5JMsQ5665unRVCCHE/CABWw2Z7dKq/U8QNw9kWP/sAIOZIpmiy8ujBWIRi+Vxi61785Xqf+LEpSDcg6jDJYuacPlioPf9rQDHUkTtcKms1gamoVGEma6yH+D7QWWfmWUoLFOhxm/va2C871p3U5xVnXWMFTyWt6UOeUK7rC3FTWuXc9fDO3lo6xBDuTJlXxOzDXpa4qxZ0EBTwgFgcUuCfNnlqV1pCq5PfqSAbRq8qj3Ftecv4vWr2o/5aylqiyxdFUIIcaxIwFZjlrWlWPS6BBt2jTCUK9OccDizu/Gw2YaJHkPDuTIddVF6x4o448vaRos+HXUxQLM3V6boBthGeGK+f5ZFzF0G0N0YJWpbDGZLuL5G67DFQ0M8QipqkYqaXH5qFy3JCEopFjXH8bVmw45Riq7PsrYErYkIv3q2j7uf7aOzLkLvaIG+dBlPa+KmItCMV4NULG5J0JcuzXi52LK2FJ+4/GReHsmzZTDLL57qZTBb5LSFDRjGvvew1hrbNLn2vB7OXtzEcN6d8XtdiCMlS1eFEEIcCxKw1ZjNAxnu3tjHM7vHyJc94o7FIwuGuWx1x0G/AZ7oMTSULdNRF2E4X2YwU6Ih7hDogL50kbht0Zx0iLs+JTegLNm2E0bEUjTEHYquD0oRi5h0WTH600WypQDLNOlpjnNmTyNrV7UTc8zKyWih7HPPs+H7Ked63P+SxeoFdSxsjNNZF6MpYdNZH2Pj7jTbh/Lk3QDbMIg7JrZpkC15LGyMz2q5mGEoepoT9DQn6G6Kh02JB3PTLkO7bE2nZDbEcSVLV4UQQhxtErDVkM0DGb76m5fY1JfB15pwwZti22COF/oy3LR2+bQnt7tHCzyxa4SRXJntQznyZY/hXJlMycQLNK6nGXHLpItueAMV3vX4X2KOMgh7pgfjZfEXtySIWiajBRfPD7AMxZoF9bz3wiWc3FVHwfVY/2y43Kvo+ZS9gF3DeYpeeCxA2Qt4bMcIEcvANg1cP+Ck5jirF9SzuCXB1r05MkWXXNmnLmpzzqJm1q0+8uVisgxNCCGEEPOdBGw1Igg0dz28k6d2jeKYilTMrpxQZwouT+0a5a6Hd/KJy08+INPxfG+aTX0Z7PHbOabDaN5lNO+C1iil0AH4QVjefyJIC8NBCdrmIgXUxyw0kC56DOXKnNyV4lUddQxmSvSOFWlORrjhkqWsaK9j80CGf/7jDoZz5TCTZUf53YsD7BzOY5uKroYYlqEYzYdLYktewIKGKFFbsXVvjuFcmTNPauTMnga27s2RiFi8/Zwezl/acsjMWjBexGZTf4a6eHTa5WWyDE0IIYQQ85kEbDXi5ZE8D20dwlTQPL7/CCBimThJg/50kYe3DvHySJ6e5kTldkGgeWz7CF6gaUo4OKZBMfDHg7OwlHoQhD3apovMJFibm4ywsCKmYdAUd8iXPXYMhdmpqG1x/tKWSoZqYknscK7M8rYkSinG8mUGMiUcy0AB2WLYEDjQUBe1yLs+Q7kyFy5tpj9dYsdwng07Rji5s45zFzfPKPu1eSDDPc/sYQFw531bsC2bpa3JaTNysgxNCCGEEPOVBGw1YuveHGN5l+aUM6VHEIBSivq4zVC2zNa9uSkB2+7RAoOZIp31UQazJXxfkyv7lDyfIAhP+iUoO3EowmWQEcukvS5KzDaxTMXebIm2Ooe3nt3D0tZkpQDIruGwuMfTL4/S1RCtvHdGCi5F1w8bASvIlXxQ4FgGhqGIWuE+N60UZy9uYmFTnOFciWvO7eGsk5oOm/2aKHIzliuyIAWLmxNkXc3GPWPsGStw3QWLZLmjEEIIIWqCBGw1RCtQHOxEefrLc2WPkh/QUR9j2948Jc/HNhWmoTCUpuwfu/GKo8MAJmrAWEYYoFumwrEMIrZJyfNxLJOIZdBRH6W7Kc7mgUxlX9hgtsiWwRxjBZfl7amwdP54lK7RWMoI90RqMMcDOr3vAJRStNVFyJc96mL2YYO1yRm9Fa0JKIYZtFTUIhmxeGkgyz3P9rOkJSnLHoUQQggx70l96xqxuCVBQyzce6b11JyY1pqxvEt9zGFxS2LKdQnHImIa9I0VSEZMGuM2oAgCjSfB2nEXtw3qoiYzqUxvALYBlgkx28A2wh5rSikMpTDHe6Flix6pqEVDzCHhWJXs1sY9YzTEbRY3J4nZJr1jRZ7cNcpwrkxj3CZqm5TcAD8IMFUYxPtaozWU3ICoPfF+gULZJ2KZYUbuMHaPFtgyGDYfni4b3FkfZfNAlt2jhSN5CYUQQgghTigSsNWI7sY4r1ncRKA1Q7lyuKRRa0peuNco0JrzljTR3Th1H9CChhitqWilTHpXQ4z2lIM53ggZDpabE0ebqaAuZrO4JcmS1gT1UWva114R/mKbCgylUErRURfFNo0wyNaauGOggeFcmahtErctlren6KyLTtmvloraNMRt2lNRLAPyZY8tg1lSUYuFjTE0kCl6RO2wVH+x7JMve2hgYWOMupiN1presSLL2pIz6rWWK3sUvbD/23RiTpgVzJW9I34tTxRBoNk1nOeFvjS7hvOVIixCCCGEqB2yJLJGGIbi7a/pYSBbYlN/hkxx38muaShO627gmnN7DlhiZhiKsxY1cvfGXjJFl1TUJlv2w2VwRkAgnbGPC9tgPODSpIsuphFmmurjPgPpIqloGBi5QVgIpuwFuH64w9A2DGxLkYxaeHkXpcJMVcH1qY/bxG2LnuawF1pvunhAdkspxdK2BJmSS7rg0p8uMlpwWdKSoG+sRN71sMzxpZBa42toTUZY1VlHtuRVgv2Z9lpLOBZRywyXUEYO/E5pNtm6E9nkZalFzydqmQctuiKEEEKI+Wt+n/GIKZa1pbhp7XLufma8cbbrEbctTl1Yz7pDNM5e1VnHio4UI7kyo4XwpN22DOKOwVjBoyRB2zFlAFHbpD5m41gGDXGHlR0pIpaJ5wfc+8IAqxfU0ZKMUPICXD8IA6XRIn3pIkXXZyzv0pKMcsHSFixDMZx3CXRAQ8xheXuqUrXxhb70eHZraiasKRHh9O4GXurPsmskz/ahHK3JKJev6SDQmj1jRfLlMGtrABHbJF1wKbnBrHuiLWiIsbQ1ycY9Y6Rap45jIlu3ZkH9jLJ1J6qJZakTbRTiTox82ZOiK0IIIUQNkoCtxixrS/HXl8yuZ9WChhhndDfyzO4xFjTGKPsBMdskX/KwDF8Ctlmyxkvq+3rfctKDvYK2EZbedyyDpoSDYSjyZR9nfBNbuuSScExGci6ZgsdIwcULAizDoCFqkYwmOKk5weWndrKkJVlZ8nqw+Z+c3UpF7SljaUpEWNUZVhS95pyp1SQn319nXZTedPGIe6IZhmLd6nb2jBXYMphjSQr8ICDnBrPO1p2IpmujAJCK2lJ0RQghhKhBErDVoImeVUGg2T1aYNNAZtoT64nrc2WP07rr2T2aDws9aM3eTBE/ANNUOFpR9iRoOxhDwXgRRQwFlqnoqIswnPeIWAbNcZuSHzCUczEUpAseauK4VASNAhVm2Sb2nT2xczTMnBVcbNNgy2AWpRTtdRHqYzaFss+24Tx1UZsPXtTJJa9qnzKmg/Usm5zdSkasKUU/tNb0pUuctrCB1y1vnfJe2f/+XmlPtGVtKa67YBH3PLMHsnvYMZTHsuxZZ+tORLMpuiK954QQQoj5TwK2GnW4/THTXR9WDEzw3J40ubJP0rGIOTZJHdA7VpJ+bPtRQMRSJBwLN9C4foCBwjI1vlYsaU3g+ZqC6xNoOLkzLJn/6I4RYrbJmoX1tCWjuH7AUy+PMZwro9GM5cv4foBpGKSiNn4QEGiNY0DB9Sn7YYZtSUsCyzB4sS/DJa9qm1E2ZnJ266WBMGiIOSaFsn/cs1vL2lJ0X7iYu+9+gQ9ctJS6eHTW2boT0b6iK9Mv+Yw5Jv3jGUwhhBBCzH8SsNWgw+2P+ZOVbfz2hYEDru8dK2KbioWNMUZyYbanPmbRnyljAFLlfx/bVMQsE42m5AckoxZJJ8LebImiq7FNg1WddRTLPk/sGsULNIEGxzJZ2V4HwNKWfcvhwv1jaZ7dk0YDtmUSBJqi6zOSL2MbBm4QZuHO6G4gYpmkohbZkjfrbMxEdmsiYO9PF4lYJqu76jm1ux5vvHLh8QieJu5/RXsK27YPc/T8cKhlqVA7RVeEEEIIEZJP/BpzuP0xm/ozfP+P20k4FivaD7x+w84R8mWf85a2sH0oH37TX/IwTfAlYgtL6itwTINLVrbia9g9UiBf9vCDMFCrjzssbomze6TA3myJmG3SloqQitq0paJcfmon//Xi4JQMlz3e6Lo+5rCwMcpI3sULNLapyBTD64qeT+9okZXtPq2pKHDk2ZhlbSmWXLxvr+PeTIknd47y0w27pWLhMXa4Zam1UHRFCCGEEPtIwFZjDrc/JhW1eHZPmvOWNB9k/0yMHUN5vCDg7EWN7BjK88TOAMuAl0eLlGu4AIkibFBtGgoFjOTLLGtL0dMUYzBTonesyCkL6vmri5ewN1Pmrkd2ohQsaUmQiNjkyx67RvLkyh5/srKNF3ozUzJcS1qTaA2ur/EDTXPCoeyFSyNRELdN0iWPrXtzdDfFw9L902RjJu9NPFRRkIm9jpsHMvznxj6pWHiczKVlqUIIIYSoPgnYaszh9seYhgr3Wh3kZLA1FSHmmPSOFemsj9GUcIhHLCKmwjJKuL4+YC/bxD2ZCibXJrGAE2UXjmL6So5q0t9hoRCDmG3g+prWVJTRvEvJC4Om85e2cOkp7SxpSXLvc1vQGk5b2DBtFcAX+zJ84HVLplRbDLTm8798ns2DWVJRG6XCzFrMNsmVPRxTYRsG2aJHpuiRiloHZGNm29tLKhZWx8GWpdZC0RUhhBBCTCUBW4053P6YiWV7QTB9pqzo+vQ0xUmMn6x31EVwLINte3MU3QClwr5hEzfX43+M8b9NY/zfGhwLPPfYPM+jyQDqYyZeACU3wJ302uxfAdI2w6yWF2jO6GngohVtZIou2ZJHMmoRsUx2jeRnVAWwN12csu8sCDSd9TGefHmUxrhdOb4p4VDyfLIln1TUBBVm9/rSU7MxR9LbSyoWVs/+y1KPpEWCEEIIIU58ErDVmMPtj8kUPRa1JEgXPTq0nnb/zJk9jaw9uY31zw7wxK4RBjNFyn6AaShijonr+RQmpdIm9nVpHf4UcQy0hlTUItBlSt6BWbmDUeN/goP8fKQUELY2U2g0/qQ71ICpDEwzrMI4mdZhZk0pUCiKro+pwkzlzqECBdfjdy8MTslo1cUs9mZLdB1kD9LB9p0ZhmLtyW3ct2mAvZkSDQkH2zQwDIjZJoZS2GY4hkLZ57Tuhko25kgzZVKxsLomlqUKIYQQonZJwFZjDrc/pjkZ4S3jVSIPtX9mWVuKJc1JvvjrFyi6PjHb4ImdY/haow2FQRiE2SbYponrh6XnTQVFNyBqKxpiYZZob6bETNq4KcA0wVQK39eYpkIpFZa4B2zTwAt0ZR/dwZYxTrk/A4IAkhETZShMFVZqjFgGI9kCjN9H0fMxDQOlxzOI4/cRjB9gaPCVJlfWOKaiuynKlsEM3/rdFspeMCWjtWUwy67hPC1Jh+6mxAHjOlQVwPOXtnDJyjbuf2kvhbJPTnuYhsHCpjiLW+K8PFJgcUuC6y5YTHdjvBJ8HWmmTCoWCiGEEEJUl5xl1aCZ7I85qTl+2P0zvekie7NlVrSnSEYsskWfPWMFHNNh10gBLwjCTJUKxgtymBiGYqzgkStphnIlUlGbzvoow/kyBTfAGt8M5gca01BYhgqDwECDgqZEhDUL6smVPTrromGgF2gs0yBiG+RLPvdvHmQ4HzahDjQoHQZWE8GbAqKWIuqYKBSB1rQkHWKOhTm+L0wpRdIxgDEMwmIiyjAolME2wDQMil5QWfoZED6OMZ5dU1qxeTBHd2OMM3sap2S0Tl1QT+9okY170uNL3IzK3ByuCqBhKN5+bg9FN2D3aJ7GuENd1MY0oC9dYmFjnHe+5iROap4aCB5ppqzaFQsnluZu6s/UTB82IYQQQojJJGCrUYfbHzOT/TOTgwClFMvak2TLHqN5F8tUuH4YMBnjAZVpKPLlcMkg7Kt26OuwUmJjIkKm6LGkNU7EMnmhL8NIrowfBBQ9zcLGGDetXc75S1r4p99vZeOesSnL+wCGVImEY1H2NVprXF+TjFgkoybDWRdPB8RsM1xGqcPgigB60yUWN5tEJmWK6qMmAB31EU5qSbF5MIdlGtTHbOpjFtuH8njj2bxgPFhzLIOexhi5ckCm6HL2SQ0HZLQMw2D1gjqe2DnK07vHWNqanFUVwGVtKa6/cF/APZQrHbYgxZFmyqpZsXDzQIZ7ntnDAuDO+7ZgW7a0EhBCCCFEzZGArYYdbn/M4a7fPwhoSkQ4vbuBZ3enGcmVgYllhwaWaVDywuqTqaiFH0Bd1OK07gZsw6AvXaC9PsKChhijBZf6mMNrljSPl8Mv0JyMcMPFy1jREZ6oTxdE9I4WeHT7CADnLm4iXXDZNJAlU3JxfZ8lrUmaUxF2DOUouz5KGXTWR0lGTB7cNsyWwRxd9VEaEg6Fsk+mUIJO+Ls3rqI+GePO/9rMQKxMwfWJWAaGUphKY1lhkRY/0NRFLerjDulSnkBrYvb0v2KdDTH2Zsssbk4ymnenZDHXntw2HrCmD1poYrYFKV5JpqwaFQsnCqSM5YosSMHi5gRZV0srASGEEELUHAnYxBGbLghoSkS4YFlzuFdrb47GuEVnfZyi6zOQLmGbCjfQJCImGs2OoTwlL6DgeuwcLvCaJc101k+Uwy9OKYc/+QR9/yCib6zA9qECMdvknMWNNCejaK3paojxzO4xRgsuhgHZoovrBdiWSdyxWN6eoinhEHNM/rhlmL3ZMtmSh2OZLG9LAnkuXtnOlqECUcfi1IVxntk9xki+HGbndLifTqtwL1jcsRjOlUlGLPxAkyl5NCUjB7x2hbJPSzLC9RcuQilVCboKZZ/1zx5Ydv8Np7QRs60DgrOZFqR4pZmy41mxcHKBlBWtCShSCfSllYAQQgghao0EbOKIHSoISEbD7JtlmOP9ycK9YuUAHNPAMQ1G8mUMpWhMOCScCP3pIpsHMnQ3xvmLV3fTVh85ZGAwOYjYMpjlXx/ZSVd9jLrYvpL3Pc0JklGb58YzM0EAyahFe12Upa1JmhIOAEtaUzQnImzdm+PSU9pZ0Z5iTUeSe+65G9iXTYzaBqd3N7Bx9xhjBRdMA+1r0BpDKZSCtroo7akIL/ZnGMmX6RlvYj1hckZr4aTCIJsHMvzzgweW3X9o6xD3PNdHaypsoXC43mkH80ozZcerYqG0EhBCCCGE2EcCNvGKHCwIuORVbfQ0xdm4J02x7FP0AjRh8Y6WhMOesSKGUrSlIpS8gL5MkXzZxzCgP11iJO9y2xWrDntCPhFE5MoepqFIRA58SzclHM5d0sSj20fwgoA1XQ00xO0DgoFE1CIVtThrURMrO+pw3X1N4iZnE5e3JblwWTMl1+flsQIRBWUfopZBQ8xmUVOc3WMFVrSnCLRmU3+GrobYITNaByu77/qakXyZwWwJy1S8ZnEzBdc/4qWBJ0Jvr6kFUg5s2CCtBIQQQghRSyRgE0ckCPSUk/4PvG4JveMn0RNBwNa9Wb57/zZ2jxZoiNnsGMoznCuRKXoEQVjMo+QF9I4VyJcDUjGLtlSUfNlny2CWb/1uC//fnyybUUByuKIaRTcIs2k6zPbtH6zBoUvU759NjNkGZd8f37sWVsBsSTn0pYts3psjFbFY2prEsQxKbsDO4TwRyzhoRmu6rJLWms0DWYquT0ddhFzJJ1/2qYsdunfa4cz13l6T57IuYhxwvbQSEEIIIUQtkTMeMWubBzKVjNrkfVbrVrezsqOuclxYzXBx5di6mM1YwSXQmrhjkHAsdo+GwVoiYtKWjGIaBomIouwFDGVLMw5IZlJU49QFDWitebY3fUQl6ieyiXdv7ONXz/SSLfm0JiNhCwJTUXQDcmUfP9DUx23WLKin4PrsGS0SsQwuP62TVR1102a0piu7nyl6jOTLJKM2tqnIl8uUxzt6z+elgZPnMtU6dS6ORysBIYQQQoi5RAI2MWNBoPnjlr3c9chOciWPJS0JuiLhPquDLdHbfwne3kyJ+14c4O5n++lPh8sgUzGLtmS4/w3A9QMs05hVQDKTohrrVrcDYf+4Iy1Rv6wtxRWnGTzz8hgr2lM0xh2SEZNM0eOJXaMooD5mU/Z1JRu2oj3Mhm3uz7J25fT3P12GsOT5FMoehoJsMcDzA0qej9YapdS8XRo4eS63DOZYkgI/CMi5wTFvJSCEEEIIMddIwCZmZPNAppJZGsqVaYzZlD3NsrawcMehluhNWYLXAa9Z3IxSBo9uH8IwoC0VZtYgzKBkix5tdVFaUxF2DOVnHJDMtKjGKy1RX3B9TFOxsDEeVookzHiVvIDGhINtGuTd2WXD9s8QjuRdXujLsDdbpi9dxAs0jmnw+PYR9tQXWdqWwDaNebs0cGIu73lmD2T3sGMoj2XZx7SVgBBCCCHEXDT/zvTEUTfRE+vlkbAEf3tdBEMZDGaKZEsep3c30JRwZpwRsyyDt569kP50kf50iXzZJxFRuH5AtugRc8L9X0U3mHVAMpOiGq+08MZ02bCyH+AFAbZphRlCI6yEOeFw2bDJWaUndo4ykCmSL/n4QYDraWxTYZsG6aKHH+RJF8s0JiKct6R53i4NXNaWovvCxdx99wt84KKl1MWjc65AihBCCCHEsXbgjn4hJplcvXBBQwylIGKZRCyDpoRDoeyxZTCL1pqYY1Ly/BllxJa1pbjhkmUsbQ0bR4/kyhTdgLa6KKd3N9AYt+kdK7KsLTnrgGQio7eyo47upvi0J/gzOeZgJrJhvWNFtNZA2KrAMgzKnk+26NGUcEhF9wWaMymUsawtxbXnnwSE+9eyZRdjfOljxA5bCvhaU/YDBjIlMgWXtavm99LAiee2oj0163kSQgghhJgPJGAThzS5emHEMrEMA3fSUr9kNGwUnSl6s67et6IjxW1XrOLsxU101EdZs6CO07vrsU3FSwPZObtXaSIb1pRweGkgS6boEnNMEo5JX7pE1A6LsEyu9jjT4DNmW7QkHU7vaaAh5rCoJcGS1gR1URs/AB2Ee+Pa6iK0pCKVfX9CCCGEEGJ+kiWR4pAmVy80FDTFHQYyRZyEgVLhMr1syaPk+Yzk3VlX71vRXsf/9yfLKnvKdgzlZ72nrBr23y9X8oo0Jhy8QFM3XtXRCwLyJY+te3MkIxZrFtYf9n5zZY+SH1AXtTHNsK+coRQx26TsBbhBQK7kc0pnPdmSN+8KjgghhBBCiKkkYBOHtP9+raVtCTIll+FcmWTUItCgdZiJW9gYP6KM2InQzHk604274Hqsf3aALYNZNg9k2ZstAQqt4acbdvP0rjHWrT54IDrxegeBrmQzI5aJUoqIbYIHURsCredtwREhhBBCCLGPnO3VsP2bX08XJO1fvbApEeH07ga2DOQYypUYK7g0JSKcs6iJdas7jjgjdrSbOc/kuR2t+9x/3MtaU5X2B0rBkpYEiYh9yPYHEyZe72d2j9EYsxnMlirZzIkKmq2pCJmix6kLG+ZtwZHZOBZzLYQQQggxV0jAVqMO1fx6ciAxXX+zupjNqzqSbN2rWNaW5OpzerhgacucOUme6XM7lvf51K4xtIbTFjZU9rKlovYh2x/A1Nc7V/YwDcVQtkTENim5AZYVFjdpTkbm5P6+4+1YzLUQQgghxFwiAVsNmijTP5wr01kfJe4cvvn1dL3Lzl3cPOf2mc32uc3E1sEs//LwyzO+z8mFWiaCtQkz6ck2+fV+YtcIO4fzZIoeccekuzHGmT2Nc+51r4ZjMddCCCGEEHONBGw1ZnKZ/uVtyRlnf06EfWZH+twO597nB2Z1n5MLtUzncD3ZYOrrnSm6ZEseyahFKmLPude9Go7VXAshhBBCzDUSsNWYV5L9Odr7zI62V5rZOphte3Ozus/pGmtPNtP2B3P99a6mYzXXQgghhBBzjfRhqzH7sj/TBwuzaX491xyr5zbb+5yusfaE2fRkEwc3n9/HQgghhBCTScBWYyZnf6Yz2+bXc8mxem6zvc/pGmt7QUCm6M7phuAnkvn8PhZCCCGEmEwCthozn7M/x+q5LW5JzPo+JwqHrO6qZzTvsn1vjtHxxuJSDOOVm8/vYyGEEEKIyeTr5xozXZn+mGNSKPv0jhVP6OzPsXpur1/Vxu50edb3eSIUajlRzef3sRBCCCHEZBKw1aCDlelfs6D+hC8Xfyye25LW5BHfpxQOOXbm8/tYCCGEEGKCBGw1aj5nf47Fc5vPr9eJTOZFCCGEEPOdBGw1bD5nf47Fc5vPr9eJTOZFCCGEEPOZFB0RQgghhBBCiDlKAjYhhBBCCCGEmKMkYJulb33rWyxatIhoNMq5557LI488Uu0hCSGEEEIIIeYpCdhm4Uc/+hE333wzn/zkJ9mwYQOnnXYa69atY2BgoNpDE0IIIYQQQsxDErDNwpe//GX+8i//kuuuu46TTz6ZO++8k3g8zne/+91qD00IIYQQQggxD0mVyBkql8s8/vjjfPzjH69cZhgGa9eu5cEHH5z2NqVSiVKpVPk5nU4D4Louruse8vEmrj/cceLYkTmoPpmD6pM5mBtkHqpP5qD6ZA6qT+bg6Jrp66i01voYj2Ve2LNnDwsWLOCPf/wj5513XuXyj370o9x33308/PDDB9zmU5/6FJ/+9KcPuPyuu+4iHpcy5EIIIYQQQtSqfD7P29/+dsbGxqirqzvocZJhO4Y+/vGPc/PNN1d+TqfTdHd3c+mllx5yUiCMuNevX88b3vAGbNs+1kMV05A5qD6Zg+qTOZgbZB6qT+ag+mQOqk/m4OiaWH13OBKwzVBLSwumadLf3z/l8v7+fjo6Oqa9TSQSIRKJHHC5bdszfpPP5lhxbMgcVJ/MQfXJHMwNMg/VJ3NQfTIH1SdzcHTM9DWUoiMz5DgOr371q7n33nsrlwVBwL333jtliaQQQgghhBBCHC2SYZuFm2++mWuvvZazzjqLc845h69+9avkcjmuu+66ag9NCCGEEEIIMQ9JwDYLb3vb2xgcHOT222+nr6+P008/nbvvvpv29vZqD00IIYQQQggxD0nANks33ngjN954Y7WHIYQQQgghhKgBErAdRxMdFGZSEcZ1XfL5POl0WjZ1VonMQfXJHFSfzMHcIPNQfTIH1SdzUH0yB0fXRExwuC5rErAdR5lMBoDu7u4qj0QIIYQQQggxF2QyGerr6w96vTTOPo6CIGDPnj2kUimUUoc8dqJn265duw7bs00cGzIH1SdzUH0yB3ODzEP1yRxUn8xB9ckcHF1aazKZDF1dXRjGwYv3S4btODIMg4ULF87qNnV1dfILUWUyB9Unc1B9Mgdzg8xD9ckcVJ/MQfXJHBw9h8qsTZA+bEIIIYQQQggxR0nAJoQQQgghhBBzlARsc1QkEuGTn/wkkUik2kOpWTIH1SdzUH0yB3ODzEP1yRxUn8xB9ckcVIcUHRFCCCGEEEKIOUoybEIIIYQQQggxR0nAJoQQQgghhBBzlARsQgghhBBCCDFHScAmhBBCCCGEEHOUBGxz0Le+9S0WLVpENBrl3HPP5ZFHHqn2kGrKHXfcwdlnn00qlaKtrY2rrrqKF198sdrDqmn/8A//gFKKm266qdpDqSm7d+/mne98J83NzcRiMdasWcNjjz1W7WHVDN/3ue2221i8eDGxWIylS5fy2c9+FqkVduz8/ve/54orrqCrqwulFD/72c+mXK+15vbbb6ezs5NYLMbatWt56aWXqjPYeexQ8+C6Lrfeeitr1qwhkUjQ1dXFu9/9bvbs2VO9Ac9Dh/tdmOyDH/wgSim++tWvHrfx1RoJ2OaYH/3oR9x888188pOfZMOGDZx22mmsW7eOgYGBag+tZtx3333ccMMNPPTQQ6xfvx7Xdbn00kvJ5XLVHlpNevTRR/mnf/onTj311GoPpaaMjIxwwQUXYNs2//mf/8lzzz3Hl770JRobG6s9tJrxhS98gW9/+9t885vf5Pnnn+cLX/gCX/ziF/nGN75R7aHNW7lcjtNOO41vfetb017/xS9+ka9//evceeedPPzwwyQSCdatW0exWDzOI53fDjUP+XyeDRs2cNttt7FhwwZ+8pOf8OKLL/Jnf/ZnVRjp/HW434UJP/3pT3nooYfo6uo6TiOrUVrMKeecc46+4YYbKj/7vq+7urr0HXfcUcVR1baBgQEN6Pvuu6/aQ6k5mUxGL1++XK9fv15fdNFF+sMf/nC1h1Qzbr31Vn3hhRdWexg17fLLL9fXX3/9lMve9KY36Xe84x1VGlFtAfRPf/rTys9BEOiOjg79P/7H/6hcNjo6qiORiP7Xf/3XKoywNuw/D9N55JFHNKB37NhxfAZVYw42By+//LJesGCB3rhxoz7ppJP0V77yleM+tlohGbY5pFwu8/jjj7N27drKZYZhsHbtWh588MEqjqy2jY2NAdDU1FTlkdSeG264gcsvv3zK74Q4Pn7+859z1lln8Za3vIW2tjbOOOMM/tf/+l/VHlZNOf/887n33nvZtGkTAE899RT3338/b3zjG6s8stq0bds2+vr6pvx/VF9fz7nnniuf0VU2NjaGUoqGhoZqD6VmBEHAu971Lm655RZOOeWUag9n3rOqPQCxz969e/F9n/b29imXt7e388ILL1RpVLUtCAJuuukmLrjgAlavXl3t4dSUH/7wh2zYsIFHH3202kOpSVu3buXb3/42N998M3/3d3/Ho48+yoc+9CEcx+Haa6+t9vBqwsc+9jHS6TQrV67ENE183+fv//7vecc73lHtodWkvr4+gGk/oyeuE8dfsVjk1ltv5ZprrqGurq7aw6kZX/jCF7Asiw996EPVHkpNkIBNiEO44YYb2LhxI/fff3+1h1JTdu3axYc//GHWr19PNBqt9nBqUhAEnHXWWXz+858H4IwzzmDjxo3ceeedErAdJ//2b//GD37wA+666y5OOeUUnnzySW666Sa6urpkDoQgLEDy1re+Fa013/72t6s9nJrx+OOP87WvfY0NGzaglKr2cGqCLImcQ1paWjBNk/7+/imX9/f309HRUaVR1a4bb7yRX/ziF/zud79j4cKF1R5OTXn88ccZGBjgzDPPxLIsLMvivvvu4+tf/zqWZeH7frWHOO91dnZy8sknT7ls1apV7Ny5s0ojqj233HILH/vYx7j66qtZs2YN73rXu/jIRz7CHXfcUe2h1aSJz2H5jJ4bJoK1HTt2sH79esmuHUd/+MMfGBgYoKenp/IZvWPHDv7mb/6GRYsWVXt485IEbHOI4zi8+tWv5t57761cFgQB9957L+edd14VR1ZbtNbceOON/PSnP+W3v/0tixcvrvaQas7rX/96nnnmGZ588snKn7POOot3vOMdPPnkk5imWe0hznsXXHDBAe0sNm3axEknnVSlEdWefD6PYUz9mDZNkyAIqjSi2rZ48WI6OjqmfEan02kefvhh+Yw+ziaCtZdeeonf/OY3NDc3V3tINeVd73oXTz/99JTP6K6uLm655RZ+/etfV3t485IsiZxjbr75Zq699lrOOusszjnnHL761a+Sy+W47rrrqj20mnHDDTdw11138f/+3/8jlUpV9ibU19cTi8WqPLrakEqlDtgzmEgkaG5ulr2Ex8lHPvIRzj//fD7/+c/z1re+lUceeYTvfOc7fOc736n20GrGFVdcwd///d/T09PDKaecwhNPPMGXv/xlrr/++moPbd7KZrNs3ry58vO2bdt48sknaWpqoqenh5tuuonPfe5zLF++nMWLF3PbbbfR1dXFVVddVb1Bz0OHmofOzk7+4i/+gg0bNvCLX/wC3/crn9NNTU04jlOtYc8rh/td2D9Itm2bjo4OXvWqVx3vodaGapepFAf6xje+oXt6erTjOPqcc87RDz30ULWHVFOAaf9873vfq/bQapqU9T/+/uM//kOvXr1aRyIRvXLlSv2d73yn2kOqKel0Wn/4wx/WPT09OhqN6iVLluj//t//uy6VStUe2rz1u9/9btr//6+99lqtdVja/7bbbtPt7e06Eono17/+9frFF1+s7qDnoUPNw7Zt2w76Of273/2u2kOfNw73u7A/Ket/bCmttT5OsaEQQgghhBBCiFmQPWxCCCGEEEIIMUdJwCaEEEIIIYQQc5QEbEIIIYQQQggxR0nAJoQQQgghhBBzlARsQgghhBBCCDFHScAmhBBCCCGEEHOUBGxCCCGEEEIIMUdJwCaEEEIIIYQQc5QEbEIIIQTwX//1XyilGB0dBeD73/8+DQ0NVR2TEEIIIQGbEEKIOe8973kPSik++MEPHnDdDTfcgFKK97znPUf1Md/2trexadOmo3qf03nPe97DVVdddcwfRwghxIlJAjYhhBAnhO7ubn74wx9SKBQqlxWLRe666y56enqO+uPFYjHa2tqO+v0KIYQQsyEBmxBCiBPCmWeeSXd3Nz/5yU8ql/3kJz+hp6eHM844Y8qxQRBwxx13sHjxYmKxGKeddhr/9//+3ynH/OpXv2LFihXEYjEuueQStm/fPuX6/ZdEbtmyhSuvvJL29naSySRnn302v/nNb6bcZtGiRXz+85/n+uuvJ5VK0dPTw3e+851ZPc+LL76YD33oQ3z0ox+lqamJjo4OPvWpT005ZnR0lA984AO0t7cTjUZZvXo1v/jFLyrX//jHP+aUU04hEomwaNEivvSlLx0wzs997nO8+93vJplMctJJJ/Hzn/+cwcFBrrzySpLJJKeeeiqPPfbYlNvdf//9vPa1ryUWi9Hd3c2HPvQhcrncrJ6fEEKI2ZGATQghxAnj+uuv53vf+17l5+9+97tcd911Bxx3xx138C//8i/ceeedPPvss3zkIx/hne98J/fddx8Au3bt4k1vehNXXHEFTz75JO973/v42Mc+dsjHzmaz/Omf/in33nsvTzzxBJdddhlXXHEFO3funHLcl770Jc466yyeeOIJ/vqv/5q/+qu/4sUXX5zV8/znf/5nEokEDz/8MF/84hf5zGc+w/r164EwGH3jG9/IAw88wP/5P/+H5557jn/4h3/ANE0AHn/8cd761rdy9dVX88wzz/CpT32K2267je9///tTHuMrX/kKF1xwAU888QSXX34573rXu3j3u9/NO9/5TjZs2MDSpUt597vfjdYaCAPWyy67jDe/+c08/fTT/OhHP+L+++/nxhtvnNVzE0IIMUtaCCGEmOOuvfZafeWVV+qBgQEdiUT09u3b9fbt23U0GtWDg4P6yiuv1Ndee63WWutisajj8bj+4x//OOU+3vve9+prrrlGa631xz/+cX3yySdPuf7WW2/VgB4ZGdFaa/29731P19fXH3Jcp5xyiv7GN75R+fmkk07S73znOys/B0Gg29ra9Le//e3DPrcJF110kb7wwgunHHP22WfrW2+9VWut9a9//WttGIZ+8cUXp72/t7/97foNb3jDlMtuueWWKc93/3H29vZqQN92222Vyx588EEN6N7eXq11+Pq9//3vn3K/f/jDH7RhGLpQKBz0+QkhhHhlrCrHi0IIIcSMtba2cvnll/P9738frTWXX345LS0tU47ZvHkz+XyeN7zhDVMuL5fLlaWTzz//POeee+6U688777xDPnY2m+VTn/oUv/zlL+nt7cXzPAqFwgEZtlNPPbXyb6UUHR0dDAwMzOp5Tr4PgM7Ozsp9PPnkkyxcuJAVK1ZMe9vnn3+eK6+8csplF1xwAV/96lfxfb+SiZv8GO3t7QCsWbPmgMsGBgbo6Ojgqaee4umnn+YHP/hB5RitNUEQsG3bNlatWjWr5yiEEGJmJGATQghxQrn++usry/C+9a1vHXB9NpsF4Je//CULFiyYcl0kEjnix/3bv/1b1q9fzz/+4z+ybNkyYrEYf/EXf0G5XJ5ynG3bU35WShEEwawe61D3EYvFjmD0h34MpdRBL5t43Gw2ywc+8AE+9KEPHXBfx6LoixBCiJAEbEIIIU4ol112GeVyGaUU69atO+D6k08+mUgkws6dO7noooumvY9Vq1bx85//fMplDz300CEf94EHHuA973kPf/7nfw6EAcz+hUqOh1NPPZWXX36ZTZs2TZtlW7VqFQ888MCUyx544AFWrFhRya4diTPPPJPnnnuOZcuWHfF9CCGEmD0J2IQQQpxQTNPk+eefr/x7f6lUir/927/lIx/5CEEQcOGFFzI2NsYDDzxAXV0d1157LR/84Af50pe+xC233ML73vc+Hn/88QOKcuxv+fLl/OQnP+GKK65AKcVtt90268zZ0XDRRRfxute9jje/+c18+ctfZtmyZbzwwgsopbjsssv4m7/5G84++2w++9nP8ra3vY0HH3yQb37zm/zP//k/X9Hj3nrrrbzmNa/hxhtv5H3vex+JRILnnnuO9evX881vfvMoPTshhBD7kyqRQgghTjh1dXXU1dUd9PrPfvaz3Hbbbdxxxx2sWrWKyy67jF/+8pcsXrwYCJfw/fjHP+ZnP/sZp512GnfeeSef//znD/mYX/7yl2lsbOT888/niiuuYN26dZx55plH9XnN1I9//GPOPvtsrrnmGk4++WQ++tGP4vs+EGbC/u3f/o0f/vCHrF69mttvv53PfOYzr7ix+Kmnnsp9993Hpk2beO1rX8sZZ5zB7bffTldX11F4RkIIIQ5GaT1er1cIIYQQQgghxJwiGTYhhBBCCCGEmKMkYBNCCCGEEEKIOUoCNiGEEEIIIYSYoyRgE0IIIYQQQog5SgI2IYQQQgghhJijJGATQgghhBBCiDlKAjYhhBBCCCGEmKMkYBNCCCGEEEKIOUoCNiGEEEIIIYSYoyRgE0IIIYQQQog5SgI2IYQQQgghhJij/n9SbpM7RtnzLQAAAABJRU5ErkJggg==\n" + }, + "metadata": {} + } + ] + }, + { "cell_type": "markdown", + "metadata": { + "id": "51e78673" + }, "source": [ - "For longer text generations, you can stream the response. This displays the output token by token as it's generated, rather than waiting for the entire response to complete. This provides a more interactive and responsive experience. To enable this, simply set stream=True." + "## Split the data (if necessary)\n", + "\n", + "### Subtask:\n", + "Split the updated dataset (`X_engineered`, `y`) into training and testing sets." ] }, { + "cell_type": "markdown", "metadata": { - "id": "CpMmpaVClSBV", - "cellView": "form" + "id": "4ac8f448" }, + "source": [ + "**Reasoning**:\n", + "Split the features and target into training and testing sets using train_test_split as instructed and print their shapes." + ] + }, + { "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "bc5d10a6", + "outputId": "dd263b3d-2f14-4292-aaab-70bec3edac8c" + }, "source": [ - "#@title Text formatting setup\n", - "#code is not necessary for colab.ai, but is useful in fomatting text chunks\n", - "import sys\n", + "from sklearn.model_selection import train_test_split\n", "\n", - "class LineWrapper:\n", - " def __init__(self, max_length=80):\n", - " self.max_length = max_length\n", - " self.current_line_length = 0\n", + "# Split the dataset into training and testing sets\n", + "X_train_engineered, X_test_engineered, y_train_engineered, y_test_engineered = train_test_split(X_engineered, y, test_size=0.2, random_state=42)\n", "\n", - " def print(self, text_chunk):\n", - " i = 0\n", - " n = len(text_chunk)\n", - " while i < n:\n", - " start_index = i\n", - " while i < n and text_chunk[i] not in ' \\n': # Find end of word\n", - " i += 1\n", - " current_word = text_chunk[start_index:i]\n", + "# Print the shapes of the resulting sets\n", + "print(f\"Shape of X_train_engineered: {X_train_engineered.shape}\")\n", + "print(f\"Shape of X_test_engineered: {X_test_engineered.shape}\")\n", + "print(f\"Shape of y_train_engineered: {y_train_engineered.shape}\")\n", + "print(f\"Shape of y_test_engineered: {y_test_engineered.shape}\")" + ], + "execution_count": 73, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Shape of X_train_engineered: (13600, 11)\n", + "Shape of X_test_engineered: (3400, 11)\n", + "Shape of y_train_engineered: (13600,)\n", + "Shape of y_test_engineered: (3400,)\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "d7a020a4" + }, + "source": [ + "**Reasoning**:\n", + "Select the updated set of features for training the model, including the engineered features." + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 502 + }, + "id": "456aa011", + "outputId": "4853b65f-42eb-401b-92db-f6c9f8c7ea71" + }, + "source": [ + "# Define the list of features, including the original and engineered ones\n", + "features_engineered = ['longitude', 'latitude', 'housing_median_age', 'total_rooms',\n", + " 'total_bedrooms', 'population', 'households', 'median_income',\n", + " 'rooms_per_household', 'bedrooms_per_room', 'population_per_household']\n", "\n", - " delimiter = \"\"\n", - " if i < n: # If not end of chunk, we found a delimiter\n", - " delimiter = text_chunk[i]\n", - " i += 1 # Consume delimiter\n", + "# Create a new DataFrame X_engineered by selecting these columns from df\n", + "X_engineered = df[features_engineered]\n", "\n", - " if current_word:\n", - " needs_leading_space = (self.current_line_length > 0)\n", + "# Keep the target variable y as it is (the 'median_house_value' column from df)\n", + "# y was already defined in a previous step as df['median_house_value']\n", "\n", - " # Case 1: Word itself is too long for a line (must be broken)\n", - " if len(current_word) > self.max_length:\n", - " if needs_leading_space: # Newline if current line has content\n", - " sys.stdout.write('\\n')\n", - " self.current_line_length = 0\n", - " for char_val in current_word: # Break the long word\n", - " if self.current_line_length >= self.max_length:\n", - " sys.stdout.write('\\n')\n", - " self.current_line_length = 0\n", - " sys.stdout.write(char_val)\n", - " self.current_line_length += 1\n", - " # Case 2: Word doesn't fit on current line (print on new line)\n", - " elif self.current_line_length + (1 if needs_leading_space else 0) + len(current_word) > self.max_length:\n", - " sys.stdout.write('\\n')\n", - " sys.stdout.write(current_word)\n", - " self.current_line_length = len(current_word)\n", - " # Case 3: Word fits on current line\n", - " else:\n", - " if needs_leading_space:\n", - " # Define punctuation that should not have a leading space\n", - " # when they form an entire \"word\" (token) following another word.\n", - " no_leading_space_punctuation = {\n", - " \",\", \".\", \";\", \":\", \"!\", \"?\", # Standard sentence punctuation\n", - " \")\", \"]\", \"}\", # Closing brackets\n", - " \"'s\", \"'S\", \"'re\", \"'RE\", \"'ve\", \"'VE\", # Common contractions\n", - " \"'m\", \"'M\", \"'ll\", \"'LL\", \"'d\", \"'D\",\n", - " \"n't\", \"N'T\",\n", - " \"...\", \"â€Ļ\" # Ellipses\n", - " }\n", - " if current_word not in no_leading_space_punctuation:\n", - " sys.stdout.write(' ')\n", - " self.current_line_length += 1\n", - " sys.stdout.write(current_word)\n", - " self.current_line_length += len(current_word)\n", + "# Print the head of X_engineered and y to verify\n", + "print(\"Head of X_engineered:\")\n", + "display(X_engineered.head())\n", "\n", - " if delimiter == '\\n':\n", - " sys.stdout.write('\\n')\n", - " self.current_line_length = 0\n", - " elif delimiter == ' ':\n", - " # If line is full and a space delimiter arrives, it implies a wrap.\n", - " if self.current_line_length >= self.max_length:\n", - " sys.stdout.write('\\n')\n", - " self.current_line_length = 0\n", + "print(\"\\nHead of y:\")\n", + "display(y.head())" + ], + "execution_count": 72, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Head of X_engineered:\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", + "0 -114.31 34.19 15.0 5612.0 1283.0 \n", + "1 -114.47 34.40 19.0 7650.0 1901.0 \n", + "2 -114.56 33.69 17.0 720.0 174.0 \n", + "3 -114.57 33.64 14.0 1501.0 337.0 \n", + "4 -114.57 33.57 20.0 1454.0 326.0 \n", + "\n", + " population households median_income rooms_per_household \\\n", + "0 1015.0 472.0 1.4936 11.889831 \n", + "1 1129.0 463.0 1.8200 16.522678 \n", + "2 333.0 117.0 1.6509 6.153846 \n", + "3 515.0 226.0 3.1917 6.641593 \n", + "4 624.0 262.0 1.9250 5.549618 \n", + "\n", + " bedrooms_per_room population_per_household \n", + "0 0.228617 2.150424 \n", + "1 0.248497 2.438445 \n", + "2 0.241667 2.846154 \n", + "3 0.224517 2.278761 \n", + "4 0.224209 2.381679 " + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_incomerooms_per_householdbedrooms_per_roompopulation_per_household
0-114.3134.1915.05612.01283.01015.0472.01.493611.8898310.2286172.150424
1-114.4734.4019.07650.01901.01129.0463.01.820016.5226780.2484972.438445
2-114.5633.6917.0720.0174.0333.0117.01.65096.1538460.2416672.846154
3-114.5733.6414.01501.0337.0515.0226.03.19176.6415930.2245172.278761
4-114.5733.5720.01454.0326.0624.0262.01.92505.5496180.2242092.381679
\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"display(y\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.11216059914247682,\n \"min\": -114.57,\n \"max\": -114.31,\n \"num_unique_values\": 4,\n \"samples\": [\n -114.47,\n -114.57,\n -114.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3723842101915701,\n \"min\": 33.57,\n \"max\": 34.4,\n \"num_unique_values\": 5,\n \"samples\": [\n 34.4,\n 33.57,\n 33.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.5495097567963922,\n \"min\": 14.0,\n \"max\": 20.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 19.0,\n 20.0,\n 17.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3063.09350167441,\n \"min\": 720.0,\n \"max\": 7650.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 7650.0,\n 1454.0,\n 720.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 754.3743765531807,\n \"min\": 174.0,\n \"max\": 1901.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1901.0,\n 326.0,\n 174.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 337.36656621544466,\n \"min\": 333.0,\n \"max\": 1129.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1129.0,\n 624.0,\n 333.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 155.11447385721294,\n \"min\": 117.0,\n \"max\": 472.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 463.0,\n 262.0,\n 117.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6773416737511431,\n \"min\": 1.4936,\n \"max\": 3.1917,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.82,\n 1.925,\n 1.6509\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rooms_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 4.740564553544767,\n \"min\": 5.549618320610687,\n \"max\": 16.52267818574514,\n \"num_unique_values\": 5,\n \"samples\": [\n 16.52267818574514,\n 5.549618320610687,\n 6.153846153846154\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"bedrooms_per_room\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.010982410746386893,\n \"min\": 0.22420907840440166,\n \"max\": 0.24849673202614378,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.24849673202614378,\n 0.22420907840440166,\n 0.24166666666666667\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.26269348663282854,\n \"min\": 2.1504237288135593,\n \"max\": 2.8461538461538463,\n \"num_unique_values\": 5,\n \"samples\": [\n 2.4384449244060473,\n 2.381679389312977,\n 2.8461538461538463\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\n", + "Head of y:\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "0 66900.0\n", + "1 80100.0\n", + "2 85700.0\n", + "3 73400.0\n", + "4 65500.0\n", + "Name: median_house_value, dtype: float64" + ], + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
median_house_value
066900.0
180100.0
285700.0
373400.0
465500.0
\n", + "

" + ] + }, + "metadata": {} + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "b43fab9e" + }, + "source": [ + "## Identify potential new features\n", "\n", - " sys.stdout.flush()\n" + "### Subtask:\n", + "Determine which existing features can be combined or transformed to create meaningful new features (e.g., ratios, polynomial features, interaction terms)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "adbc82dc" + }, + "source": [ + "**Reasoning**:\n", + "Describe the rationale for choosing features to create based on the analysis of existing features and potential relationships." + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "b9a2f488" + }, + "source": [ + "# Rationale for choosing new features:\n", + "# Based on domain knowledge and common practices in housing price prediction,\n", + "# ratios of existing features can provide more meaningful insights into the\n", + "# characteristics of a housing block group than the raw counts alone.\n", + "\n", + "# 1. Rooms per household ('rooms_per_household'):\n", + "# This ratio (total_rooms / households) can indicate the average number of rooms\n", + "# available per household in a block group. It might be a strong predictor\n", + "# of housing value, as larger houses (more rooms per household) are often\n", + "# associated with higher values.\n", + "\n", + "# 2. Bedrooms per room ('bedrooms_per_room'):\n", + "# This ratio (total_bedrooms / total_rooms) can provide an idea of the\n", + "# proportion of rooms that are bedrooms. A higher ratio might indicate\n", + "# a different type of housing stock which could influence the median house value.\n", + "\n", + "# 3. Population per household ('population_per_household'):\n", + "# This ratio (population / households) represents the average household size.\n", + "# Larger household sizes in a block group might correlate with different housing\n", + "# demands and potentially impact housing values.\n", + "\n", + "# These ratios normalize the counts by the number of households or rooms,\n", + "# making them potentially more robust indicators than the raw counts themselves." ], - "outputs": [], - "execution_count": 29 + "execution_count": 70, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "7c4d97dd" + }, + "source": [ + "## Create new features\n", + "\n", + "### Subtask:\n", + "Write code to generate the new features and add them to the DataFrame." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "a9a73659" + }, + "source": [ + "**Reasoning**:\n", + "Generate the new features by calculating the ratios as described in the instructions and add them as new columns to the DataFrame. Then, display the head of the updated DataFrame to confirm the changes." + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 226 + }, + "id": "cc30b3e9", + "outputId": "39dd1ff6-7638-4e06-8d39-5952d6fd886d" + }, + "source": [ + "# Calculate 'rooms_per_household' and add it as a new column\n", + "df['rooms_per_household'] = df['total_rooms'] / df['households']\n", + "\n", + "# Calculate 'bedrooms_per_room' and add it as a new column\n", + "df['bedrooms_per_room'] = df['total_bedrooms'] / df['total_rooms']\n", + "\n", + "# Calculate 'population_per_household' and add it as a new column\n", + "df['population_per_household'] = df['population'] / df['households']\n", + "\n", + "# Display the head of the DataFrame to verify the new columns\n", + "display(df.head())" + ], + "execution_count": 71, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", + "0 -114.31 34.19 15.0 5612.0 1283.0 \n", + "1 -114.47 34.40 19.0 7650.0 1901.0 \n", + "2 -114.56 33.69 17.0 720.0 174.0 \n", + "3 -114.57 33.64 14.0 1501.0 337.0 \n", + "4 -114.57 33.57 20.0 1454.0 326.0 \n", + "\n", + " population households median_income median_house_value \\\n", + "0 1015.0 472.0 1.4936 66900.0 \n", + "1 1129.0 463.0 1.8200 80100.0 \n", + "2 333.0 117.0 1.6509 85700.0 \n", + "3 515.0 226.0 3.1917 73400.0 \n", + "4 624.0 262.0 1.9250 65500.0 \n", + "\n", + " rooms_per_household bedrooms_per_room population_per_household \n", + "0 11.889831 0.228617 2.150424 \n", + "1 16.522678 0.248497 2.438445 \n", + "2 6.153846 0.241667 2.846154 \n", + "3 6.641593 0.224517 2.278761 \n", + "4 5.549618 0.224209 2.381679 " + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_incomemedian_house_valuerooms_per_householdbedrooms_per_roompopulation_per_household
0-114.3134.1915.05612.01283.01015.0472.01.493666900.011.8898310.2286172.150424
1-114.4734.4019.07650.01901.01129.0463.01.820080100.016.5226780.2484972.438445
2-114.5633.6917.0720.0174.0333.0117.01.650985700.06.1538460.2416672.846154
3-114.5733.6414.01501.0337.0515.0226.03.191773400.06.6415930.2245172.278761
4-114.5733.5720.01454.0326.0624.0262.01.925065500.05.5496180.2242092.381679
\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"display(df\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.11216059914247682,\n \"min\": -114.57,\n \"max\": -114.31,\n \"num_unique_values\": 4,\n \"samples\": [\n -114.47,\n -114.57,\n -114.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3723842101915701,\n \"min\": 33.57,\n \"max\": 34.4,\n \"num_unique_values\": 5,\n \"samples\": [\n 34.4,\n 33.57,\n 33.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.5495097567963922,\n \"min\": 14.0,\n \"max\": 20.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 19.0,\n 20.0,\n 17.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3063.09350167441,\n \"min\": 720.0,\n \"max\": 7650.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 7650.0,\n 1454.0,\n 720.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 754.3743765531807,\n \"min\": 174.0,\n \"max\": 1901.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1901.0,\n 326.0,\n 174.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 337.36656621544466,\n \"min\": 333.0,\n \"max\": 1129.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1129.0,\n 624.0,\n 333.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 155.11447385721294,\n \"min\": 117.0,\n \"max\": 472.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 463.0,\n 262.0,\n 117.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6773416737511431,\n \"min\": 1.4936,\n \"max\": 3.1917,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.82,\n 1.925,\n 1.6509\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_house_value\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 8611.15555544086,\n \"min\": 65500.0,\n \"max\": 85700.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 80100.0,\n 65500.0,\n 85700.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rooms_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 4.740564553544767,\n \"min\": 5.549618320610687,\n \"max\": 16.52267818574514,\n \"num_unique_values\": 5,\n \"samples\": [\n 16.52267818574514,\n 5.549618320610687,\n 6.153846153846154\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"bedrooms_per_room\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.010982410746386893,\n \"min\": 0.22420907840440166,\n \"max\": 0.24849673202614378,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.24849673202614378,\n 0.22420907840440166,\n 0.24166666666666667\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.26269348663282854,\n \"min\": 2.1504237288135593,\n \"max\": 2.8461538461538463,\n \"num_unique_values\": 5,\n \"samples\": [\n 2.4384449244060473,\n 2.381679389312977,\n 2.8461538461538463\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {} + } + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 300 + }, + "id": "088fbfe6", + "outputId": "19fbc262-b2f7-4230-80f3-7729bc94b395" + }, + "source": [ + "# Display summary statistics of the DataFrame\n", + "display(df.describe())" + ], + "execution_count": 61, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + " longitude latitude housing_median_age total_rooms \\\n", + "count 17000.000000 17000.000000 17000.000000 17000.000000 \n", + "mean -119.562108 35.625225 28.589353 2643.664412 \n", + "std 2.005166 2.137340 12.586937 2179.947071 \n", + "min -124.350000 32.540000 1.000000 2.000000 \n", + "25% -121.790000 33.930000 18.000000 1462.000000 \n", + "50% -118.490000 34.250000 29.000000 2127.000000 \n", + "75% -118.000000 37.720000 37.000000 3151.250000 \n", + "max -114.310000 41.950000 52.000000 37937.000000 \n", + "\n", + " total_bedrooms population households median_income \\\n", + "count 17000.000000 17000.000000 17000.000000 17000.000000 \n", + "mean 539.410824 1429.573941 501.221941 3.883578 \n", + "std 421.499452 1147.852959 384.520841 1.908157 \n", + "min 1.000000 3.000000 1.000000 0.499900 \n", + "25% 297.000000 790.000000 282.000000 2.566375 \n", + "50% 434.000000 1167.000000 409.000000 3.544600 \n", + "75% 648.250000 1721.000000 605.250000 4.767000 \n", + "max 6445.000000 35682.000000 6082.000000 15.000100 \n", + "\n", + " median_house_value \n", + "count 17000.000000 \n", + "mean 207300.912353 \n", + "std 115983.764387 \n", + "min 14999.000000 \n", + "25% 119400.000000 \n", + "50% 180400.000000 \n", + "75% 265000.000000 \n", + "max 500001.000000 " + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_incomemedian_house_value
count17000.00000017000.00000017000.00000017000.00000017000.00000017000.00000017000.00000017000.00000017000.000000
mean-119.56210835.62522528.5893532643.664412539.4108241429.573941501.2219413.883578207300.912353
std2.0051662.13734012.5869372179.947071421.4994521147.852959384.5208411.908157115983.764387
min-124.35000032.5400001.0000002.0000001.0000003.0000001.0000000.49990014999.000000
25%-121.79000033.93000018.0000001462.000000297.000000790.000000282.0000002.566375119400.000000
50%-118.49000034.25000029.0000002127.000000434.0000001167.000000409.0000003.544600180400.000000
75%-118.00000037.72000037.0000003151.250000648.2500001721.000000605.2500004.767000265000.000000
max-114.31000041.95000052.00000037937.0000006445.00000035682.0000006082.00000015.000100500001.000000
\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"display(df\",\n \"rows\": 8,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6046.6451651071675,\n \"min\": -124.35,\n \"max\": 17000.0,\n \"num_unique_values\": 8,\n \"samples\": [\n -119.5621082352941,\n -118.49,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 5999.40166383228,\n \"min\": 2.1373397946570734,\n \"max\": 17000.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 35.62522470588235,\n 34.25,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6001.428368089024,\n \"min\": 1.0,\n \"max\": 17000.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 28.58935294117647,\n 29.0,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 13113.353227786365,\n \"min\": 2.0,\n \"max\": 37937.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 2643.664411764706,\n 2127.0,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 5959.238771737063,\n \"min\": 1.0,\n \"max\": 17000.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 539.4108235294118,\n 434.0,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 12740.640658201448,\n \"min\": 3.0,\n \"max\": 35682.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 1429.5739411764705,\n 1167.0,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 5942.738122392389,\n \"min\": 1.0,\n \"max\": 17000.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 501.2219411764706,\n 409.0,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6008.784464952051,\n \"min\": 0.4999,\n \"max\": 17000.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 3.8835781000000007,\n 3.5446,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_house_value\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 156700.95757149634,\n \"min\": 14999.0,\n \"max\": 500001.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 207300.91235294117,\n 180400.0,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {} + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "990723df" + }, + "source": [ + "## Visualize the results (optional)\n", + "\n", + "### Subtask:\n", + "Visualize the predictions of the new model versus the actual values." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "f76956a7" + }, + "source": [ + "**Reasoning**:\n", + "Create a scatter plot of the actual vs. predicted values from the Ridge model, add labels, title, a diagonal line for perfect predictions, and a grid." + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 564 + }, + "id": "217c1753", + "outputId": "e128dbc4-ef05-4b67-9c85-2008a218bf79" + }, + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "# Create a scatter plot of actual vs. predicted values for the Ridge model\n", + "plt.figure(figsize=(8, 6))\n", + "plt.scatter(y_test, y_pred_ridge, alpha=0.5)\n", + "\n", + "# Add labels and title\n", + "plt.xlabel('Actual Values')\n", + "plt.ylabel('Predicted Values')\n", + "plt.title('Actual vs. Predicted Values (Ridge Regression)')\n", + "\n", + "# Add a diagonal line for perfect predictions\n", + "# Determine the range for the diagonal line based on both actual and predicted values\n", + "plot_range = [min(y_test.min(), y_pred_ridge.min()), max(y_test.max(), y_pred_ridge.max())]\n", + "plt.plot(plot_range, plot_range, color='red', linestyle='--')\n", + "\n", + "# Add a grid\n", + "plt.grid(True)\n", + "\n", + "# Show the plot\n", + "plt.show()" + ], + "execution_count": 60, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": {} + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "08f6f818" + }, + "source": [ + "## Choose a new model\n", + "\n", + "### Subtask:\n", + "Select a different regression algorithm to try (e.g., Ridge, Lasso, Decision Tree Regressor)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "5c407870" + }, + "source": [ + "**Reasoning**:\n", + "Choose a different regression algorithm and mention it in a markdown cell." + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "be170e13" + }, + "source": [ + "# Choosing Ridge Regression as an alternative regression model.\n", + "# Ridge is a linear model with L2 regularization.\n", + "# It can help to prevent overfitting, especially when dealing with multicollinearity\n", + "# among predictor variables, which might be present in this dataset.\n", + "# This choice is a common next step after trying simple Linear Regression." + ], + "execution_count": 58, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "805f79fa" + }, + "source": [ + "## Train the new model\n", + "\n", + "### Subtask:\n", + "Instantiate and train the chosen model using the training data (`X_train`, `y_train`)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "26859879" + }, + "source": [ + "**Reasoning**:\n", + "Instantiate and train the Ridge model using the training data." + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "d79f43a6", + "outputId": "a89b316f-4463-4130-842a-60bc4a3dcb66" + }, + "source": [ + "from sklearn.linear_model import Ridge\n", + "\n", + "# Instantiate a Ridge model object with default parameters\n", + "ridge_model = Ridge()\n", + "\n", + "# Fit the Ridge model to the training data\n", + "ridge_model.fit(X_train, y_train)\n", + "\n", + "print(\"Ridge Regression model trained successfully.\")" + ], + "execution_count": 59, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Ridge Regression model trained successfully.\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "f8addd87" + }, + "source": [ + "## Visualize the results (optional)\n", + "\n", + "### Subtask:\n", + "Visualize the predictions versus the actual values." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "246fbfca" + }, + "source": [ + "**Reasoning**:\n", + "Create a scatter plot of actual vs. predicted values and add a diagonal line for perfect predictions." + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 564 + }, + "id": "c5f468af", + "outputId": "0fe9f1bd-73d2-468e-f639-a5b3c8d2397e" + }, + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "# Create a scatter plot\n", + "plt.figure(figsize=(8, 6))\n", + "plt.scatter(y_test, y_pred, alpha=0.5)\n", + "\n", + "# Add labels and title\n", + "plt.xlabel('Actual Values')\n", + "plt.ylabel('Predicted Values')\n", + "plt.title('Actual vs. Predicted Values')\n", + "\n", + "# Add a diagonal line for perfect predictions\n", + "# Determine the range for the diagonal line\n", + "plot_range = [min(y_test.min(), y_pred.min()), max(y_test.max(), y_pred.max())]\n", + "plt.plot(plot_range, plot_range, color='red', linestyle='--')\n", + "\n", + "# Add a grid\n", + "plt.grid(True)\n", + "\n", + "# Show the plot\n", + "plt.show()" + ], + "execution_count": 52, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": {} + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "e57b3e2a" + }, + "source": [ + "## Summary:\n", + "\n", + "### Data Analysis Key Findings\n", + "\n", + "* The `california_housing_train.csv` dataset was successfully loaded, containing 17000 entries and 9 columns of `float64` data type.\n", + "* No missing values were found in the dataset after filling the initial missing values in `total_rooms` and `total_bedrooms` with their respective medians.\n", + "* The dataset was split into training (13600 samples) and testing (3400 samples) sets, with features including 'longitude', 'latitude', 'housing\\_median\\_age', 'total\\_rooms', 'total\\_bedrooms', 'population', 'households', and 'median\\_income', and the target being 'median\\_house\\_value'.\n", + "* A Linear Regression model was successfully trained on the training data.\n", + "* The model achieved a Mean Squared Error (MSE) of approximately $4,634,658,406.22$ and an R-squared (R2) score of approximately 0.6636 on the testing data.\n", + "\n", + "### Insights or Next Steps\n", + "\n", + "* The R-squared score of 0.66 suggests the model explains a reasonable portion of the variance in median house values, but there is room for improvement.\n", + "* Further steps could involve exploring feature engineering, trying different regression algorithms (e.g., Ridge, Lasso, or more complex models), or performing hyperparameter tuning to potentially improve the model's performance." + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 472 + }, + "id": "1180b0f9", + "outputId": "72250dc2-ed91-403e-ae11-4c06e5d76e5f" + }, + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "# Plot the original data points\n", + "plt.scatter(X, y, color='blue', label='Original Data')\n", + "\n", + "# Plot the regression line\n", + "# We need to predict y values for the range of X values to plot the line\n", + "plt.plot(X, model.predict(X), color='red', label='Regression Line')\n", + "\n", + "plt.xlabel('Features (X)')\n", + "plt.ylabel('Target (y)')\n", + "plt.title('Linear Regression Example')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "plt.show()" + ], + "execution_count": 44, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": {} + } + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "dddf50ae", + "outputId": "72351ca1-e604-4cc9-bbcd-3c233eb08732" + }, + "source": [ + "import numpy as np\n", + "from sklearn.linear_model import LinearRegression\n", + "\n", + "# Generate some sample data\n", + "# X represents the features (input), y represents the target (output)\n", + "X = np.array([1, 2, 3, 4, 5, 6]).reshape(-1, 1) # Reshape for scikit-learn\n", + "y = np.array([2, 4, 5, 4, 5, 6])\n", + "\n", + "# Create a Linear Regression model\n", + "model = LinearRegression()\n", + "\n", + "# Train the model using the data\n", + "model.fit(X, y)\n", + "\n", + "# Make a prediction\n", + "new_X = np.array([7]).reshape(-1, 1)\n", + "prediction = model.predict(new_X)\n", + "\n", + "print(f\"Features (X):\\n{X}\")\n", + "print(f\"Target (y):\\n{y}\")\n", + "print(f\"Prediction for X={new_X[0][0]}: {prediction[0]}\")" + ], + "execution_count": 43, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Features (X):\n", + "[[1]\n", + " [2]\n", + " [3]\n", + " [4]\n", + " [5]\n", + " [6]]\n", + "Target (y):\n", + "[2 4 5 4 5 6]\n", + "Prediction for X=7: 6.533333333333333\n" + ] + } + ] + }, + { + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 339 + }, + "id": "NHO9VzO9AHZP", + "outputId": "dc325df0-1368-45f6-e1da-50d8d58dd59a" + }, + "cell_type": "code", + "source": [ + "# @title Choose a different model\n", + "from google.colab import ai\n", + "\n", + "response = ai.generate_text(\"What is the capital of England\", model_name='google/gemini-2.0-flash-lite')\n", + "print(response)" + ], + "outputs": [ + { + "output_type": "error", + "ename": "InternalServerError", + "evalue": "Error code: 503 - {'message': 'The requested model is currently unavailable.', 'type': 'invalid_request_error'}", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mInternalServerError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m/tmp/ipython-input-1810143207.py\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mgoogle\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolab\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mai\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mresponse\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mai\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgenerate_text\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"What is the capital of England\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodel_name\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'google/gemini-2.0-flash-lite'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 5\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/colab/ai.py\u001b[0m in \u001b[0;36mgenerate_text\u001b[0;34m(prompt, model_name, stream)\u001b[0m\n\u001b[1;32m 83\u001b[0m )\n\u001b[1;32m 84\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 85\u001b[0;31m response = client.chat.completions.create(\n\u001b[0m\u001b[1;32m 86\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmodel_name\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 87\u001b[0m \u001b[0mmessages\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m{\u001b[0m\u001b[0;34m'role'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'user'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'content'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mprompt\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/_utils/_utils.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 284\u001b[0m \u001b[0mmsg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34mf\"Missing required argument: {quote(missing[0])}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 285\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmsg\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 286\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 287\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 288\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mwrapper\u001b[0m \u001b[0;31m# type: ignore\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/resources/chat/completions/completions.py\u001b[0m in \u001b[0;36mcreate\u001b[0;34m(self, messages, model, audio, frequency_penalty, function_call, functions, logit_bias, logprobs, max_completion_tokens, max_tokens, metadata, modalities, n, parallel_tool_calls, prediction, presence_penalty, prompt_cache_key, reasoning_effort, response_format, safety_identifier, seed, service_tier, stop, store, stream, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, verbosity, web_search_options, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m 1145\u001b[0m ) -> ChatCompletion | Stream[ChatCompletionChunk]:\n\u001b[1;32m 1146\u001b[0m \u001b[0mvalidate_response_format\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponse_format\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1147\u001b[0;31m return self._post(\n\u001b[0m\u001b[1;32m 1148\u001b[0m \u001b[0;34m\"/chat/completions\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1149\u001b[0m body=maybe_transform(\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/_base_client.py\u001b[0m in \u001b[0;36mpost\u001b[0;34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1257\u001b[0m \u001b[0mmethod\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"post\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0murl\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mjson_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mbody\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfiles\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mto_httpx_files\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfiles\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0moptions\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1258\u001b[0m )\n\u001b[0;32m-> 1259\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mcast\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mResponseT\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcast_to\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mopts\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstream\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstream\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstream_cls\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstream_cls\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1260\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1261\u001b[0m def patch(\n", + "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/_base_client.py\u001b[0m in \u001b[0;36mrequest\u001b[0;34m(self, cast_to, options, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1045\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1046\u001b[0m \u001b[0mlog\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdebug\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Re-raising status error\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1047\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_make_status_error_from_response\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0merr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresponse\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1048\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1049\u001b[0m \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mInternalServerError\u001b[0m: Error code: 503 - {'message': 'The requested model is currently unavailable.', 'type': 'invalid_request_error'}" + ] + } + ], + "execution_count": 41 + }, + { + "metadata": { + "id": "ysDdFbH_Dgtz" + }, + "cell_type": "markdown", + "source": [ + "For longer text generations, you can stream the response. This displays the output token by token as it's generated, rather than waiting for the entire response to complete. This provides a more interactive and responsive experience. To enable this, simply set stream=True." + ] + }, + { + "metadata": { + "id": "4BNgxiB6--_5" + }, + "cell_type": "code", + "source": [ + "# @title Simple streaming example\n", + "from google.colab import ai\n", + "\n", + "stream = ai.generate_text(\"Tell me a short story.\", stream=True)\n", + "for text in stream:\n", + " print(text, end='')" + ], + "outputs": [], + "execution_count": null + }, + { + "metadata": { + "id": "CpMmpaVClSBV", + "cellView": "form" + }, + "cell_type": "code", + "source": [ + "#@title Text formatting setup\n", + "#code is not necessary for colab.ai, but is useful in fomatting text chunks\n", + "import sys\n", + "\n", + "class LineWrapper:\n", + " def __init__(self, max_length=80):\n", + " self.max_length = max_length\n", + " self.current_line_length = 0\n", + "\n", + " def print(self, text_chunk):\n", + " i = 0\n", + " n = len(text_chunk)\n", + " while i < n:\n", + " start_index = i\n", + " while i < n and text_chunk[i] not in ' \\n': # Find end of word\n", + " i += 1\n", + " current_word = text_chunk[start_index:i]\n", + "\n", + " delimiter = \"\"\n", + " if i < n: # If not end of chunk, we found a delimiter\n", + " delimiter = text_chunk[i]\n", + " i += 1 # Consume delimiter\n", + "\n", + " if current_word:\n", + " needs_leading_space = (self.current_line_length > 0)\n", + "\n", + " # Case 1: Word itself is too long for a line (must be broken)\n", + " if len(current_word) > self.max_length:\n", + " if needs_leading_space: # Newline if current line has content\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", + " for char_val in current_word: # Break the long word\n", + " if self.current_line_length >= self.max_length:\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", + " sys.stdout.write(char_val)\n", + " self.current_line_length += 1\n", + " # Case 2: Word doesn't fit on current line (print on new line)\n", + " elif self.current_line_length + (1 if needs_leading_space else 0) + len(current_word) > self.max_length:\n", + " sys.stdout.write('\\n')\n", + " sys.stdout.write(current_word)\n", + " self.current_line_length = len(current_word)\n", + " # Case 3: Word fits on current line\n", + " else:\n", + " if needs_leading_space:\n", + " # Define punctuation that should not have a leading space\n", + " # when they form an entire \"word\" (token) following another word.\n", + " no_leading_space_punctuation = {\n", + " \",\", \".\", \";\", \":\", \"!\", \"?\", # Standard sentence punctuation\n", + " \")\", \"]\", \"}\", # Closing brackets\n", + " \"'s\", \"'S\", \"'re\", \"'RE\", \"'ve\", \"'VE\", # Common contractions\n", + " \"'m\", \"'M\", \"'ll\", \"'LL\", \"'d\", \"'D\",\n", + " \"n't\", \"N'T\",\n", + " \"...\", \"â€Ļ\" # Ellipses\n", + " }\n", + " if current_word not in no_leading_space_punctuation:\n", + " sys.stdout.write(' ')\n", + " self.current_line_length += 1\n", + " sys.stdout.write(current_word)\n", + " self.current_line_length += len(current_word)\n", + "\n", + " if delimiter == '\\n':\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", + " elif delimiter == ' ':\n", + " # If line is full and a space delimiter arrives, it implies a wrap.\n", + " if self.current_line_length >= self.max_length:\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", + "\n", + " sys.stdout.flush()\n" + ], + "outputs": [], + "execution_count": null + }, + { + "metadata": { + "id": "DWiLPzTnRoy-" + }, + "cell_type": "code", + "source": [ + "# @title Formatted streaming example\n", + "from google.colab import ai\n", + "\n", + "wrapper = LineWrapper()\n", + "for chunk in ai.generate_text('Give me a long winded description about the evolution of the Roman Empire.', model_name='google/gemini-2.0-flash', stream=True):\n", + " wrapper.print(chunk)" + ], + "outputs": [], + "execution_count": null + }, + { + "cell_type": "markdown", + "metadata": { + "id": "c5851539" + }, + "source": [ + "# Task\n", + "Train a linear regression model on a more complex dataset from \"/content/sample_data/\"." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "3a7e5b4d" + }, + "source": [ + "## Load the dataset\n", + "\n", + "### Subtask:\n", + "Load a more complex dataset, such as one from the `/content/sample_data/` directory, into a pandas DataFrame.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "7f24f0a9" + }, + "source": [ + "**Reasoning**:\n", + "The subtask is to load a dataset from `/content/sample_data/` into a pandas DataFrame. I need to import pandas and then use `pd.read_csv` to load a file. Displaying the head of the dataframe will confirm the data has been loaded.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "f8c9aec7", + "outputId": "3c80b854-df9a-474b-aa6c-7b74a09832cd" + }, + "source": [ + "import pandas as pd\n", + "\n", + "# Load a sample dataset from /content/sample_data/ - choosing california_housing_train.csv\n", + "try:\n", + " df = pd.read_csv('/content/sample_data/california_housing_train.csv')\n", + " # Display the first few rows\n", + " display(df.head())\n", + "except FileNotFoundError:\n", + " print(\"File not found. Please check the file path.\")\n", + "except Exception as e:\n", + " print(f\"An error occurred: {e}\")" + ], + "execution_count": 45, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", + "0 -114.31 34.19 15.0 5612.0 1283.0 \n", + "1 -114.47 34.40 19.0 7650.0 1901.0 \n", + "2 -114.56 33.69 17.0 720.0 174.0 \n", + "3 -114.57 33.64 14.0 1501.0 337.0 \n", + "4 -114.57 33.57 20.0 1454.0 326.0 \n", + "\n", + " population households median_income median_house_value \n", + "0 1015.0 472.0 1.4936 66900.0 \n", + "1 1129.0 463.0 1.8200 80100.0 \n", + "2 333.0 117.0 1.6509 85700.0 \n", + "3 515.0 226.0 3.1917 73400.0 \n", + "4 624.0 262.0 1.9250 65500.0 " + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_incomemedian_house_value
0-114.3134.1915.05612.01283.01015.0472.01.493666900.0
1-114.4734.4019.07650.01901.01129.0463.01.820080100.0
2-114.5633.6917.0720.0174.0333.0117.01.650985700.0
3-114.5733.6414.01501.0337.0515.0226.03.191773400.0
4-114.5733.5720.01454.0326.0624.0262.01.925065500.0
\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \" print(f\\\"An error occurred: {e}\\\")\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.11216059914247682,\n \"min\": -114.57,\n \"max\": -114.31,\n \"num_unique_values\": 4,\n \"samples\": [\n -114.47,\n -114.57,\n -114.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3723842101915701,\n \"min\": 33.57,\n \"max\": 34.4,\n \"num_unique_values\": 5,\n \"samples\": [\n 34.4,\n 33.57,\n 33.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.5495097567963922,\n \"min\": 14.0,\n \"max\": 20.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 19.0,\n 20.0,\n 17.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3063.09350167441,\n \"min\": 720.0,\n \"max\": 7650.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 7650.0,\n 1454.0,\n 720.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 754.3743765531807,\n \"min\": 174.0,\n \"max\": 1901.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1901.0,\n 326.0,\n 174.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 337.36656621544466,\n \"min\": 333.0,\n \"max\": 1129.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1129.0,\n 624.0,\n 333.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 155.11447385721294,\n \"min\": 117.0,\n \"max\": 472.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 463.0,\n 262.0,\n 117.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6773416737511431,\n \"min\": 1.4936,\n \"max\": 3.1917,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.82,\n 1.925,\n 1.6509\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_house_value\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 8611.15555544086,\n \"min\": 65500.0,\n \"max\": 85700.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 80100.0,\n 65500.0,\n 85700.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {} + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ff7bf690" + }, + "source": [ + "## Explore and preprocess the data\n", + "\n", + "### Subtask:\n", + "Inspect the dataset, handle any missing values, and select the features and target variable for the linear regression model.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "6383359c" + }, + "source": [ + "**Reasoning**:\n", + "Display DataFrame info, check for missing values, and handle them if necessary before selecting features and target variables.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000 + }, + "id": "9347ab12", + "outputId": "e238cd9f-b998-4979-8f7f-4516c2d5b9ce" + }, + "source": [ + "# Display info about the DataFrame\n", + "df.info()\n", + "\n", + "# Check for missing values\n", + "print(\"\\nMissing values per column:\")\n", + "print(df.isnull().sum())\n", + "\n", + "# Handle missing values if any.\n", + "# The isnull().sum() output will show if there are any missing values.\n", + "# Based on the output of isnull().sum(), if 'total_bedrooms' has missing values,\n", + "# we will fill them with the median as it's a common practice for numerical features\n", + "# and less sensitive to outliers than the mean.\n", + "if df['total_bedrooms'].isnull().sum() > 0:\n", + " median_bedrooms = df['total_bedrooms'].median()\n", + " df['total_bedrooms'].fillna(median_bedrooms, inplace=True)\n", + " print(\"\\nMissing values in 'total_bedrooms' filled with median.\")\n", + "\n", + "# Also fill missing values in 'total_rooms' with the median\n", + "if df['total_rooms'].isnull().sum() > 0:\n", + " median_rooms = df['total_rooms'].median()\n", + " df['total_rooms'].fillna(median_rooms, inplace=True)\n", + " print(\"Missing values in 'total_rooms' filled with median.\")\n", + "\n", + "print(df.isnull().sum()) # Verify after filling\n", + "\n", + "# Select features (X) and target variable (y)\n", + "# We will use several numerical features as predictors for 'median_house_value'\n", + "features = ['longitude', 'latitude', 'housing_median_age', 'total_rooms',\n", + " 'total_bedrooms', 'population', 'households', 'median_income']\n", + "X = df[features]\n", + "y = df['median_house_value']\n", + "\n", + "print(\"\\nFeatures (X) and Target (y) selected.\")\n", + "display(X.head())\n", + "display(y.head())" + ], + "execution_count": 51, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\n", + "RangeIndex: 17000 entries, 0 to 16999\n", + "Data columns (total 9 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 longitude 17000 non-null float64\n", + " 1 latitude 17000 non-null float64\n", + " 2 housing_median_age 17000 non-null float64\n", + " 3 total_rooms 17000 non-null float64\n", + " 4 total_bedrooms 17000 non-null float64\n", + " 5 population 17000 non-null float64\n", + " 6 households 17000 non-null float64\n", + " 7 median_income 17000 non-null float64\n", + " 8 median_house_value 17000 non-null float64\n", + "dtypes: float64(9)\n", + "memory usage: 1.2 MB\n", + "\n", + "Missing values per column:\n", + "longitude 0\n", + "latitude 0\n", + "housing_median_age 0\n", + "total_rooms 0\n", + "total_bedrooms 0\n", + "population 0\n", + "households 0\n", + "median_income 0\n", + "median_house_value 0\n", + "dtype: int64\n", + "longitude 0\n", + "latitude 0\n", + "housing_median_age 0\n", + "total_rooms 0\n", + "total_bedrooms 0\n", + "population 0\n", + "households 0\n", + "median_income 0\n", + "median_house_value 0\n", + "dtype: int64\n", + "\n", + "Features (X) and Target (y) selected.\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", + "0 -114.31 34.19 15.0 5612.0 1283.0 \n", + "1 -114.47 34.40 19.0 7650.0 1901.0 \n", + "2 -114.56 33.69 17.0 720.0 174.0 \n", + "3 -114.57 33.64 14.0 1501.0 337.0 \n", + "4 -114.57 33.57 20.0 1454.0 326.0 \n", + "\n", + " population households median_income \n", + "0 1015.0 472.0 1.4936 \n", + "1 1129.0 463.0 1.8200 \n", + "2 333.0 117.0 1.6509 \n", + "3 515.0 226.0 3.1917 \n", + "4 624.0 262.0 1.9250 " + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_income
0-114.3134.1915.05612.01283.01015.0472.01.4936
1-114.4734.4019.07650.01901.01129.0463.01.8200
2-114.5633.6917.0720.0174.0333.0117.01.6509
3-114.5733.6414.01501.0337.0515.0226.03.1917
4-114.5733.5720.01454.0326.0624.0262.01.9250
\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"display(y\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.11216059914247682,\n \"min\": -114.57,\n \"max\": -114.31,\n \"num_unique_values\": 4,\n \"samples\": [\n -114.47,\n -114.57,\n -114.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3723842101915701,\n \"min\": 33.57,\n \"max\": 34.4,\n \"num_unique_values\": 5,\n \"samples\": [\n 34.4,\n 33.57,\n 33.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.5495097567963922,\n \"min\": 14.0,\n \"max\": 20.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 19.0,\n 20.0,\n 17.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3063.09350167441,\n \"min\": 720.0,\n \"max\": 7650.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 7650.0,\n 1454.0,\n 720.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 754.3743765531807,\n \"min\": 174.0,\n \"max\": 1901.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1901.0,\n 326.0,\n 174.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 337.36656621544466,\n \"min\": 333.0,\n \"max\": 1129.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1129.0,\n 624.0,\n 333.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 155.11447385721294,\n \"min\": 117.0,\n \"max\": 472.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 463.0,\n 262.0,\n 117.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6773416737511431,\n \"min\": 1.4936,\n \"max\": 3.1917,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.82,\n 1.925,\n 1.6509\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "0 66900.0\n", + "1 80100.0\n", + "2 85700.0\n", + "3 73400.0\n", + "4 65500.0\n", + "Name: median_house_value, dtype: float64" + ], + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
median_house_value
066900.0
180100.0
285700.0
373400.0
465500.0
\n", + "

" + ] + }, + "metadata": {} + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "85d33c8f" + }, + "source": [ + "## Split the data\n", + "\n", + "### Subtask:\n", + "Split the dataset into training and testing sets.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "d1eda7b0" + }, + "source": [ + "**Reasoning**:\n", + "Split the features and target into training and testing sets using train_test_split as instructed and print their shapes.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "94b0ab2d", + "outputId": "00c1f1db-e5dd-41a2-fa47-856be16a4315" + }, + "source": [ + "from sklearn.model_selection import train_test_split\n", + "\n", + "# Split the dataset into training and testing sets\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", + "\n", + "# Print the shapes of the resulting sets\n", + "print(f\"Shape of X_train: {X_train.shape}\")\n", + "print(f\"Shape of X_test: {X_test.shape}\")\n", + "print(f\"Shape of y_train: {y_train.shape}\")\n", + "print(f\"Shape of y_test: {y_test.shape}\")" + ], + "execution_count": 47, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Shape of X_train: (13600, 8)\n", + "Shape of X_test: (3400, 8)\n", + "Shape of y_train: (13600,)\n", + "Shape of y_test: (3400,)\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "6c3c850b" + }, + "source": [ + "## Train the model\n", + "\n", + "### Subtask:\n", + "Train the linear regression model on the training data.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "6ecedb3e" + }, + "source": [ + "**Reasoning**:\n", + "Train the linear regression model using the training data (X_train and y_train).\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "f3b32a6a", + "outputId": "8d3ca35c-58bf-4fb4-c819-e1b16edf6ab0" + }, + "source": [ + "from sklearn.linear_model import LinearRegression\n", + "\n", + "# Instantiate a Linear Regression model object\n", + "model = LinearRegression()\n", + "\n", + "# Fit the model to the training data\n", + "model.fit(X_train, y_train)\n", + "\n", + "print(\"Linear Regression model trained successfully.\")" + ], + "execution_count": 48, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Linear Regression model trained successfully.\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "7ed84711" + }, + "source": [ + "## Evaluate the model\n", + "\n", + "### Subtask:\n", + "Evaluate the trained model's performance on the testing data using appropriate metrics.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "76f31bb2" + }, + "source": [ + "**Reasoning**:\n", + "Evaluate the trained model's performance on the testing data using appropriate metrics.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "fa02f998", + "outputId": "7934427f-d65c-4cd9-acaf-25328e8c7e9a" + }, + "source": [ + "from sklearn.metrics import mean_squared_error, r2_score\n", + "\n", + "# Use the trained model to make predictions on the testing features\n", + "y_pred = model.predict(X_test)\n", + "\n", + "# Calculate the Mean Squared Error (MSE)\n", + "mse = mean_squared_error(y_test, y_pred)\n", + "\n", + "# Calculate the R-squared score\n", + "r2 = r2_score(y_test, y_pred)\n", + "\n", + "# Print the calculated metrics\n", + "print(f\"Mean Squared Error (MSE): {mse}\")\n", + "print(f\"R-squared (R2) Score: {r2}\")" + ], + "execution_count": 49, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Mean Squared Error (MSE): 4634658406.223264\n", + "R-squared (R2) Score: 0.6636396350243869\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ab47ee9a" + }, + "source": [ + "## Visualize the results (optional)\n", + "\n", + "### Subtask:\n", + "Visualize the predictions versus the actual values.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "f73af8ad" + }, + "source": [ + "**Reasoning**:\n", + "Create a scatter plot of actual vs. predicted values and add a diagonal line for perfect predictions.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 564 + }, + "id": "6fd07845", + "outputId": "231bd57e-6082-4a7a-ba97-a6766703e0d3" + }, + "source": [ + "# Create a scatter plot\n", + "plt.figure(figsize=(8, 6))\n", + "plt.scatter(y_test, y_pred, alpha=0.5)\n", + "\n", + "# Add labels and title\n", + "plt.xlabel('Actual Values')\n", + "plt.ylabel('Predicted Values')\n", + "plt.title('Actual vs. Predicted Values')\n", + "\n", + "# Add a diagonal line for perfect predictions\n", + "# Determine the range for the diagonal line\n", + "plot_range = [min(y_test.min(), y_pred.min()), max(y_test.max(), y_pred.max())]\n", + "plt.plot(plot_range, plot_range, color='red', linestyle='--')\n", + "\n", + "# Add a grid\n", + "plt.grid(True)\n", + "\n", + "# Show the plot\n", + "plt.show()" + ], + "execution_count": 50, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": {} + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "745ce34d" + }, + "source": [ + "## Summary:\n", + "\n", + "### Data Analysis Key Findings\n", + "\n", + "* The `california_housing_train.csv` dataset was successfully loaded, containing 17000 entries and 9 columns of `float64` data type.\n", + "* No missing values were found in the dataset, eliminating the need for imputation.\n", + "* The dataset was split into training (13600 samples) and testing (3400 samples) sets, with features including 'longitude', 'latitude', 'housing\\_median\\_age', 'total\\_rooms', 'total\\_bedrooms', 'population', 'households', and 'median\\_income', and the target being 'median\\_house\\_value'.\n", + "* A Linear Regression model was successfully trained on the training data.\n", + "* The model achieved a Mean Squared Error (MSE) of approximately $4,634,658,406.22$ and an R-squared (R2) score of approximately 0.6636 on the testing data.\n", + "\n", + "### Insights or Next Steps\n", + "\n", + "* The R-squared score of 0.66 suggests the model explains a reasonable portion of the variance in median house values, but there is room for improvement.\n", + "* Further steps could involve exploring feature engineering, trying different regression algorithms (e.g., Ridge, Lasso, or more complex models), or performing hyperparameter tuning to potentially improve the model's performance.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "624e20aa" + }, + "source": [ + "# Task\n", + "Generate a plan to train and evaluate a new regression model on the existing dataset, compare its performance to the previously trained linear regression model, and summarize the findings." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "b0b03c2e" + }, + "source": [ + "## Choose a new model\n", + "\n", + "### Subtask:\n", + "Select a different regression algorithm to try (e.g., Ridge, Lasso, Decision Tree Regressor).\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "a377d954" + }, + "source": [ + "**Reasoning**:\n", + "Choose a different regression algorithm and mention it in a markdown cell.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "866a3b17" + }, + "source": [ + "# Choosing Ridge Regression as an alternative regression model.\n", + "# Ridge is a linear model with L2 regularization.\n", + "# It can help to prevent overfitting, especially when dealing with multicollinearity\n", + "# among predictor variables, which might be present in this dataset.\n", + "# This choice is a common next step after trying simple Linear Regression." + ], + "execution_count": 53, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "49297f4f" + }, + "source": [ + "## Train the new model\n", + "\n", + "### Subtask:\n", + "Instantiate and train the chosen model using the training data (`X_train`, `y_train`).\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "8ac64541" + }, + "source": [ + "**Reasoning**:\n", + "Instantiate and train the Ridge model using the training data.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "1722a73a", + "outputId": "cefe469e-f3e3-43df-a176-be746c544892" + }, + "source": [ + "from sklearn.linear_model import Ridge\n", + "\n", + "# Instantiate a Ridge model object with default parameters\n", + "ridge_model = Ridge()\n", + "\n", + "# Fit the Ridge model to the training data\n", + "ridge_model.fit(X_train, y_train)\n", + "\n", + "print(\"Ridge Regression model trained successfully.\")" + ], + "execution_count": 54, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Ridge Regression model trained successfully.\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "c2c9c397" + }, + "source": [ + "## Evaluate the new model\n", + "\n", + "### Subtask:\n", + "Evaluate the new model's performance on the testing data (`X_test`, `y_test`) using appropriate metrics (e.g., MSE, R2).\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "3e06761a" + }, + "source": [ + "**Reasoning**:\n", + "Calculate MSE and R2 for the Ridge model using the test data and predictions, and print the results.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "24b91385", + "outputId": "d101835f-1af6-44b5-8581-814246a081c6" + }, + "source": [ + "from sklearn.metrics import mean_squared_error, r2_score\n", + "\n", + "# Use the trained ridge_model to make predictions on the testing features\n", + "y_pred_ridge = ridge_model.predict(X_test)\n", + "\n", + "# Calculate the Mean Squared Error (MSE) for the Ridge model\n", + "mse_ridge = mean_squared_error(y_test, y_pred_ridge)\n", + "\n", + "# Calculate the R-squared score for the Ridge model\n", + "r2_ridge = r2_score(y_test, y_pred_ridge)\n", + "\n", + "# Print the calculated metrics for the Ridge model\n", + "print(f\"Ridge Model Mean Squared Error (MSE): {mse_ridge}\")\n", + "print(f\"Ridge Model R-squared (R2) Score: {r2_ridge}\")" + ], + "execution_count": 55, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Ridge Model Mean Squared Error (MSE): 4634651616.323527\n", + "Ridge Model R-squared (R2) Score: 0.6636401278014059\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "4eeeec40" + }, + "source": [ + "## Compare model performance\n", + "\n", + "### Subtask:\n", + "Compare the performance of the new model to the linear regression model we already trained.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "fc340fa9" + }, + "source": [ + "**Reasoning**:\n", + "Compare the performance metrics of the two models and print a summary.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "bd0b8441", + "outputId": "37ba001a-d11a-492a-b20f-39599f54248e" + }, + "source": [ + "# Print the performance metrics for the Linear Regression model\n", + "print(f\"Linear Regression Model Mean Squared Error (MSE): {mse}\")\n", + "print(f\"Linear Regression Model R-squared (R2) Score: {r2}\")\n", + "\n", + "# Print the performance metrics for the Ridge Regression model\n", + "print(f\"Ridge Model Mean Squared Error (MSE): {mse_ridge}\")\n", + "print(f\"Ridge Model R-squared (R2) Score: {r2_ridge}\")\n", + "\n", + "# Compare and summarize the performance\n", + "if mse_ridge < mse:\n", + " print(\"\\nSummary: The Ridge Regression model performed slightly better than the Linear Regression model based on MSE.\")\n", + "elif mse_ridge > mse:\n", + " print(\"\\nSummary: The Linear Regression model performed slightly better than the Ridge Regression model based on MSE.\")\n", + "else:\n", + " print(\"\\nSummary: Both models performed similarly based on MSE.\")\n", + "\n", + "if r2_ridge > r2:\n", + " print(\"Summary: The Ridge Regression model performed slightly better than the Linear Regression model based on R2.\")\n", + "elif r2_ridge < r2:\n", + " print(\"Summary: The Linear Regression model performed slightly better than the Ridge Regression model based on R2.\")\n", + "else:\n", + " print(\"Summary: Both models performed similarly based on R2.\")" + ], + "execution_count": 56, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Linear Regression Model Mean Squared Error (MSE): 4634658406.223264\n", + "Linear Regression Model R-squared (R2) Score: 0.6636396350243869\n", + "Ridge Model Mean Squared Error (MSE): 4634651616.323527\n", + "Ridge Model R-squared (R2) Score: 0.6636401278014059\n", + "\n", + "Summary: The Ridge Regression model performed slightly better than the Linear Regression model based on MSE.\n", + "Summary: The Ridge Regression model performed slightly better than the Linear Regression model based on R2.\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "16995797" + }, + "source": [ + "## Visualize the results (optional)\n", + "\n", + "### Subtask:\n", + "Visualize the predictions of the new model versus the actual values.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "c5ab0a97" + }, + "source": [ + "**Reasoning**:\n", + "Create a scatter plot of the actual vs. predicted values from the Ridge model, add labels, title, a diagonal line for perfect predictions, and a grid.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 564 + }, + "id": "43d35683", + "outputId": "719837c8-17d0-4167-a20d-9fde2a146985" + }, + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "# Create a scatter plot of actual vs. predicted values for the Ridge model\n", + "plt.figure(figsize=(8, 6))\n", + "plt.scatter(y_test, y_pred_ridge, alpha=0.5)\n", + "\n", + "# Add labels and title\n", + "plt.xlabel('Actual Values')\n", + "plt.ylabel('Predicted Values')\n", + "plt.title('Actual vs. Predicted Values (Ridge Regression)')\n", + "\n", + "# Add a diagonal line for perfect predictions\n", + "# Determine the range for the diagonal line based on both actual and predicted values\n", + "plot_range = [min(y_test.min(), y_pred_ridge.min()), max(y_test.max(), y_pred_ridge.max())]\n", + "plt.plot(plot_range, plot_range, color='red', linestyle='--')\n", + "\n", + "# Add a grid\n", + "plt.grid(True)\n", + "\n", + "# Show the plot\n", + "plt.show()" + ], + "execution_count": 57, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": {} + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "3db547b6" + }, + "source": [ + "## Summary:\n", + "\n", + "### Data Analysis Key Findings\n", + "\n", + "* Ridge Regression was chosen as an alternative model to Linear Regression.\n", + "* The Ridge Regression model was successfully trained on the training data.\n", + "* The Ridge Regression model achieved a Mean Squared Error (MSE) of approximately 4,634,651,616.32 on the test set.\n", + "* The Ridge Regression model achieved an R-squared (R2) score of approximately 0.6636 on the test set.\n", + "* Comparing to the Linear Regression model (MSE: 4,634,658,406.22, R2: 0.6636), the Ridge Regression model performed slightly better based on MSE and similarly based on R2.\n", + "* A scatter plot visualizing the actual versus predicted values for the Ridge model was generated, showing the distribution of predictions relative to a perfect prediction line.\n", + "\n", + "### Insights or Next Steps\n", + "\n", + "* Although Ridge Regression showed a minor improvement, the performance difference compared to Linear Regression is minimal, suggesting that the L2 regularization had a limited impact on this specific dataset.\n", + "* Further model exploration with different algorithms (e.g., tree-based models like Random Forest or Gradient Boosting) or hyperparameter tuning of the Ridge model could potentially yield better performance.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "0f4d030b" + }, + "source": [ + "# Task\n", + "Perform feature engineering on the `df` DataFrame to create new features, train a model with the updated features, and evaluate its performance." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "a8eb897f" + }, + "source": [ + "## Identify potential new features\n", + "\n", + "### Subtask:\n", + "Determine which existing features can be combined or transformed to create meaningful new features (e.g., ratios, polynomial features, interaction terms).\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "c3d68222" + }, + "source": [ + "**Reasoning**:\n", + "Describe the rationale for choosing features to create based on the analysis of existing features and potential relationships.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "c95acba5" + }, + "source": [ + "# Rationale for choosing new features:\n", + "# Based on domain knowledge and common practices in housing price prediction,\n", + "# ratios of existing features can provide more meaningful insights into the\n", + "# characteristics of a housing block group than the raw counts alone.\n", + "\n", + "# 1. Rooms per household ('rooms_per_household'):\n", + "# This ratio (total_rooms / households) can indicate the average number of rooms\n", + "# available per household in a block group. It might be a strong predictor\n", + "# of housing value, as larger houses (more rooms per household) are often\n", + "# associated with higher values.\n", + "\n", + "# 2. Bedrooms per room ('bedrooms_per_room'):\n", + "# This ratio (total_bedrooms / total_rooms) can provide an idea of the\n", + "# proportion of rooms that are bedrooms. A higher ratio might indicate\n", + "# a different type of housing stock which could influence the median house value.\n", + "\n", + "# 3. Population per household ('population_per_household'):\n", + "# This ratio (population / households) represents the average household size.\n", + "# Larger household sizes in a block group might correlate with different housing\n", + "# demands and potentially impact housing values.\n", + "\n", + "# These ratios normalize the counts by the number of households or rooms,\n", + "# making them potentially more robust indicators than the raw counts themselves." + ], + "execution_count": 62, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "671d2b48" + }, + "source": [ + "## Create new features\n", + "\n", + "### Subtask:\n", + "Write code to generate the new features and add them to the DataFrame.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "9a28da2f" + }, + "source": [ + "**Reasoning**:\n", + "Generate the new features by calculating the ratios as described in the instructions and add them as new columns to the DataFrame. Then, display the head of the updated DataFrame to confirm the changes.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 226 + }, + "id": "5ca46b87", + "outputId": "215b5320-0102-4584-d0b4-e56999c58224" + }, + "source": [ + "# Calculate 'rooms_per_household' and add it as a new column\n", + "df['rooms_per_household'] = df['total_rooms'] / df['households']\n", + "\n", + "# Calculate 'bedrooms_per_room' and add it as a new column\n", + "df['bedrooms_per_room'] = df['total_bedrooms'] / df['total_rooms']\n", + "\n", + "# Calculate 'population_per_household' and add it as a new column\n", + "df['population_per_household'] = df['population'] / df['households']\n", + "\n", + "# Display the head of the DataFrame to verify the new columns\n", + "display(df.head())" + ], + "execution_count": 63, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", + "0 -114.31 34.19 15.0 5612.0 1283.0 \n", + "1 -114.47 34.40 19.0 7650.0 1901.0 \n", + "2 -114.56 33.69 17.0 720.0 174.0 \n", + "3 -114.57 33.64 14.0 1501.0 337.0 \n", + "4 -114.57 33.57 20.0 1454.0 326.0 \n", + "\n", + " population households median_income median_house_value \\\n", + "0 1015.0 472.0 1.4936 66900.0 \n", + "1 1129.0 463.0 1.8200 80100.0 \n", + "2 333.0 117.0 1.6509 85700.0 \n", + "3 515.0 226.0 3.1917 73400.0 \n", + "4 624.0 262.0 1.9250 65500.0 \n", + "\n", + " rooms_per_household bedrooms_per_room population_per_household \n", + "0 11.889831 0.228617 2.150424 \n", + "1 16.522678 0.248497 2.438445 \n", + "2 6.153846 0.241667 2.846154 \n", + "3 6.641593 0.224517 2.278761 \n", + "4 5.549618 0.224209 2.381679 " + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_incomemedian_house_valuerooms_per_householdbedrooms_per_roompopulation_per_household
0-114.3134.1915.05612.01283.01015.0472.01.493666900.011.8898310.2286172.150424
1-114.4734.4019.07650.01901.01129.0463.01.820080100.016.5226780.2484972.438445
2-114.5633.6917.0720.0174.0333.0117.01.650985700.06.1538460.2416672.846154
3-114.5733.6414.01501.0337.0515.0226.03.191773400.06.6415930.2245172.278761
4-114.5733.5720.01454.0326.0624.0262.01.925065500.05.5496180.2242092.381679
\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"display(df\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.11216059914247682,\n \"min\": -114.57,\n \"max\": -114.31,\n \"num_unique_values\": 4,\n \"samples\": [\n -114.47,\n -114.57,\n -114.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3723842101915701,\n \"min\": 33.57,\n \"max\": 34.4,\n \"num_unique_values\": 5,\n \"samples\": [\n 34.4,\n 33.57,\n 33.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.5495097567963922,\n \"min\": 14.0,\n \"max\": 20.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 19.0,\n 20.0,\n 17.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3063.09350167441,\n \"min\": 720.0,\n \"max\": 7650.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 7650.0,\n 1454.0,\n 720.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 754.3743765531807,\n \"min\": 174.0,\n \"max\": 1901.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1901.0,\n 326.0,\n 174.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 337.36656621544466,\n \"min\": 333.0,\n \"max\": 1129.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1129.0,\n 624.0,\n 333.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 155.11447385721294,\n \"min\": 117.0,\n \"max\": 472.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 463.0,\n 262.0,\n 117.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6773416737511431,\n \"min\": 1.4936,\n \"max\": 3.1917,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.82,\n 1.925,\n 1.6509\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_house_value\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 8611.15555544086,\n \"min\": 65500.0,\n \"max\": 85700.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 80100.0,\n 65500.0,\n 85700.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rooms_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 4.740564553544767,\n \"min\": 5.549618320610687,\n \"max\": 16.52267818574514,\n \"num_unique_values\": 5,\n \"samples\": [\n 16.52267818574514,\n 5.549618320610687,\n 6.153846153846154\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"bedrooms_per_room\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.010982410746386893,\n \"min\": 0.22420907840440166,\n \"max\": 0.24849673202614378,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.24849673202614378,\n 0.22420907840440166,\n 0.24166666666666667\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.26269348663282854,\n \"min\": 2.1504237288135593,\n \"max\": 2.8461538461538463,\n \"num_unique_values\": 5,\n \"samples\": [\n 2.4384449244060473,\n 2.381679389312977,\n 2.8461538461538463\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {} + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "7562b7a2" + }, + "source": [ + "## Update features for modeling\n", + "\n", + "### Subtask:\n", + "Select the updated set of features (including the new ones) for training the model.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "98b24e8f" + }, + "source": [ + "**Reasoning**:\n", + "Select the updated set of features for training the model, including the engineered features.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 502 + }, + "id": "6b6e7b39", + "outputId": "f06136cc-5271-432a-c6f0-fceaed2f3653" + }, + "source": [ + "# Define the list of features, including the original and engineered ones\n", + "features_engineered = ['longitude', 'latitude', 'housing_median_age', 'total_rooms',\n", + " 'total_bedrooms', 'population', 'households', 'median_income',\n", + " 'rooms_per_household', 'bedrooms_per_room', 'population_per_household']\n", + "\n", + "# Create a new DataFrame X_engineered by selecting these columns from df\n", + "X_engineered = df[features_engineered]\n", + "\n", + "# Keep the target variable y as it is (the 'median_house_value' column from df)\n", + "# y was already defined in a previous step as df['median_house_value']\n", + "\n", + "# Print the head of X_engineered and y to verify\n", + "print(\"Head of X_engineered:\")\n", + "display(X_engineered.head())\n", + "\n", + "print(\"\\nHead of y:\")\n", + "display(y.head())" + ], + "execution_count": 64, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Head of X_engineered:\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", + "0 -114.31 34.19 15.0 5612.0 1283.0 \n", + "1 -114.47 34.40 19.0 7650.0 1901.0 \n", + "2 -114.56 33.69 17.0 720.0 174.0 \n", + "3 -114.57 33.64 14.0 1501.0 337.0 \n", + "4 -114.57 33.57 20.0 1454.0 326.0 \n", + "\n", + " population households median_income rooms_per_household \\\n", + "0 1015.0 472.0 1.4936 11.889831 \n", + "1 1129.0 463.0 1.8200 16.522678 \n", + "2 333.0 117.0 1.6509 6.153846 \n", + "3 515.0 226.0 3.1917 6.641593 \n", + "4 624.0 262.0 1.9250 5.549618 \n", + "\n", + " bedrooms_per_room population_per_household \n", + "0 0.228617 2.150424 \n", + "1 0.248497 2.438445 \n", + "2 0.241667 2.846154 \n", + "3 0.224517 2.278761 \n", + "4 0.224209 2.381679 " + ], + "text/html": [ + "\n", + "
\n", + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_incomerooms_per_householdbedrooms_per_roompopulation_per_household
0-114.3134.1915.05612.01283.01015.0472.01.493611.8898310.2286172.150424
1-114.4734.4019.07650.01901.01129.0463.01.820016.5226780.2484972.438445
2-114.5633.6917.0720.0174.0333.0117.01.65096.1538460.2416672.846154
3-114.5733.6414.01501.0337.0515.0226.03.19176.6415930.2245172.278761
4-114.5733.5720.01454.0326.0624.0262.01.92505.5496180.2242092.381679
\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"display(y\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.11216059914247682,\n \"min\": -114.57,\n \"max\": -114.31,\n \"num_unique_values\": 4,\n \"samples\": [\n -114.47,\n -114.57,\n -114.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3723842101915701,\n \"min\": 33.57,\n \"max\": 34.4,\n \"num_unique_values\": 5,\n \"samples\": [\n 34.4,\n 33.57,\n 33.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.5495097567963922,\n \"min\": 14.0,\n \"max\": 20.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 19.0,\n 20.0,\n 17.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3063.09350167441,\n \"min\": 720.0,\n \"max\": 7650.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 7650.0,\n 1454.0,\n 720.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 754.3743765531807,\n \"min\": 174.0,\n \"max\": 1901.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1901.0,\n 326.0,\n 174.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 337.36656621544466,\n \"min\": 333.0,\n \"max\": 1129.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1129.0,\n 624.0,\n 333.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 155.11447385721294,\n \"min\": 117.0,\n \"max\": 472.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 463.0,\n 262.0,\n 117.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6773416737511431,\n \"min\": 1.4936,\n \"max\": 3.1917,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.82,\n 1.925,\n 1.6509\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rooms_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 4.740564553544767,\n \"min\": 5.549618320610687,\n \"max\": 16.52267818574514,\n \"num_unique_values\": 5,\n \"samples\": [\n 16.52267818574514,\n 5.549618320610687,\n 6.153846153846154\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"bedrooms_per_room\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.010982410746386893,\n \"min\": 0.22420907840440166,\n \"max\": 0.24849673202614378,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.24849673202614378,\n 0.22420907840440166,\n 0.24166666666666667\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.26269348663282854,\n \"min\": 2.1504237288135593,\n \"max\": 2.8461538461538463,\n \"num_unique_values\": 5,\n \"samples\": [\n 2.4384449244060473,\n 2.381679389312977,\n 2.8461538461538463\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\n", + "Head of y:\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "0 66900.0\n", + "1 80100.0\n", + "2 85700.0\n", + "3 73400.0\n", + "4 65500.0\n", + "Name: median_house_value, dtype: float64" + ], + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
median_house_value
066900.0
180100.0
285700.0
373400.0
465500.0
\n", + "

" + ] + }, + "metadata": {} + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "48e5c30c" + }, + "source": [ + "## Split the data (if necessary)\n", + "\n", + "### Subtask:\n", + "Split the updated dataset (`X_engineered`, `y`) into training and testing sets.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "069a70ad" + }, + "source": [ + "**Reasoning**:\n", + "Split the features and target into training and testing sets using train_test_split as instructed and print their shapes.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "6f346b39", + "outputId": "a16ab0c9-1db9-4334-b3d9-4f55acf89bb5" + }, + "source": [ + "from sklearn.model_selection import train_test_split\n", + "\n", + "# Split the dataset into training and testing sets\n", + "X_train_engineered, X_test_engineered, y_train_engineered, y_test_engineered = train_test_split(X_engineered, y, test_size=0.2, random_state=42)\n", + "\n", + "# Print the shapes of the resulting sets\n", + "print(f\"Shape of X_train_engineered: {X_train_engineered.shape}\")\n", + "print(f\"Shape of X_test_engineered: {X_test_engineered.shape}\")\n", + "print(f\"Shape of y_train_engineered: {y_train_engineered.shape}\")\n", + "print(f\"Shape of y_test_engineered: {y_test_engineered.shape}\")" + ], + "execution_count": 65, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Shape of X_train_engineered: (13600, 11)\n", + "Shape of X_test_engineered: (3400, 11)\n", + "Shape of y_train_engineered: (13600,)\n", + "Shape of y_test_engineered: (3400,)\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "62522074" + }, + "source": [ + "## Train a model with new features\n", + "\n", + "### Subtask:\n", + "Train a regression model (either the Linear Regression or Ridge model again, or a new one) using the updated features (`X_train_engineered`, `y_train_engineered`).\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "2f00df49" + }, + "source": [ + "**Reasoning**:\n", + "Instantiate and train a Linear Regression model using the engineered training data.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "f490841e", + "outputId": "38125196-8ed4-46b9-8262-c7a523495540" + }, + "source": [ + "from sklearn.linear_model import LinearRegression\n", + "\n", + "# Instantiate a Linear Regression model object\n", + "model_engineered = LinearRegression()\n", + "\n", + "# Fit the model to the engineered training data\n", + "model_engineered.fit(X_train_engineered, y_train_engineered)\n", + "\n", + "print(\"Linear Regression model trained successfully using engineered features.\")" + ], + "execution_count": 66, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Linear Regression model trained successfully using engineered features.\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "2f1cd2b0" + }, + "source": [ + "## Evaluate the model with new features\n", + "\n", + "### Subtask:\n", + "Evaluate the performance of the model trained with the new features using appropriate metrics (e.g., MSE, R2) on the testing data (`X_test_engineered`, `y_test_engineered`).\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "4b82a5e8" + }, + "source": [ + "**Reasoning**:\n", + "Calculate MSE and R2 for the model trained with engineered features using the test data and predictions, and print the results.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "f7df2324", + "outputId": "8f70c37a-28f3-4296-a098-80d6b201be3a" + }, + "source": [ + "from sklearn.metrics import mean_squared_error, r2_score\n", + "\n", + "# Use the trained model_engineered to make predictions on the engineered testing features\n", + "y_pred_engineered = model_engineered.predict(X_test_engineered)\n", + "\n", + "# Calculate the Mean Squared Error (MSE) for the model with engineered features\n", + "mse_engineered = mean_squared_error(y_test_engineered, y_pred_engineered)\n", + "\n", + "# Calculate the R-squared score for the model with engineered features\n", + "r2_engineered = r2_score(y_test_engineered, y_pred_engineered)\n", + "\n", + "# Print the calculated metrics for the model with engineered features\n", + "print(f\"Model with Engineered Features Mean Squared Error (MSE): {mse_engineered}\")\n", + "print(f\"Model with Engineered Features R-squared (R2) Score: {r2_engineered}\")" + ], + "execution_count": 67, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Model with Engineered Features Mean Squared Error (MSE): 4552463037.856813\n", + "Model with Engineered Features R-squared (R2) Score: 0.6696049644359181\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "3ca80ee6" + }, + "source": [ + "## Compare performance\n", + "\n", + "### Subtask:\n", + "Compare the performance of the model with and without the new features.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "d308c1d0" + }, + "source": [ + "**Reasoning**:\n", + "Print the performance metrics for both models and compare them based on MSE and R2 to determine which model performed better.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "0879e9ba", + "outputId": "d5679ef9-6dec-4d78-b7eb-25f46f387c92" + }, + "source": [ + "# Print the performance metrics for the Linear Regression model trained on original features\n", + "print(f\"Linear Regression Model (Original Features) MSE: {mse}\")\n", + "print(f\"Linear Regression Model (Original Features) R2 Score: {r2}\")\n", + "\n", + "# Print the performance metrics for the Linear Regression model trained on engineered features\n", + "print(f\"Linear Regression Model (Engineered Features) MSE: {mse_engineered}\")\n", + "print(f\"Linear Regression Model (Engineered Features) R2 Score: {r2_engineered}\")\n", + "\n", + "# Compare and summarize the performance based on MSE\n", + "if mse_engineered < mse:\n", + " print(\"\\nSummary: The Linear Regression model with engineered features performed better than the model with original features based on MSE (lower is better).\")\n", + "elif mse_engineered > mse:\n", + " print(\"\\nSummary: The Linear Regression model with original features performed better than the model with engineered features based on MSE (lower is better).\")\n", + "else:\n", + " print(\"\\nSummary: Both Linear Regression models performed similarly based on MSE.\")\n", + "\n", + "# Compare and summarize the performance based on R2\n", + "if r2_engineered > r2:\n", + " print(\"Summary: The Linear Regression model with engineered features performed better than the model with original features based on R2 (higher is better).\")\n", + "elif r2_engineered < r2:\n", + " print(\"Summary: The Linear Regression model with original features performed better than the model with engineered features based on R2 (higher is better).\")\n", + "else:\n", + " print(\"Summary: Both Linear Regression models performed similarly based on R2.\")" + ], + "execution_count": 68, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Linear Regression Model (Original Features) MSE: 4634658406.223264\n", + "Linear Regression Model (Original Features) R2 Score: 0.6636396350243869\n", + "Linear Regression Model (Engineered Features) MSE: 4552463037.856813\n", + "Linear Regression Model (Engineered Features) R2 Score: 0.6696049644359181\n", + "\n", + "Summary: The Linear Regression model with engineered features performed better than the model with original features based on MSE (lower is better).\n", + "Summary: The Linear Regression model with engineered features performed better than the model with original features based on R2 (higher is better).\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "f3c7a4ee" + }, + "source": [ + "## Visualize results (optional)\n", + "\n", + "### Subtask:\n", + "Visualize the predictions of the model trained with new features versus the actual values.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "63160aae" + }, + "source": [ + "**Reasoning**:\n", + "Create a scatter plot of the actual vs. predicted values from the model trained with engineered features, add labels, title, a diagonal line for perfect predictions, and a grid.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 564 + }, + "id": "29c83a42", + "outputId": "3cc8eb9a-ad15-47cd-c8ca-de2eadd1d473" + }, + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "# Create a scatter plot of actual vs. predicted values for the engineered features model\n", + "plt.figure(figsize=(8, 6))\n", + "plt.scatter(y_test_engineered, y_pred_engineered, alpha=0.5)\n", + "\n", + "# Add labels and title\n", + "plt.xlabel('Actual Values')\n", + "plt.ylabel('Predicted Values')\n", + "plt.title('Actual vs. Predicted Values (Linear Regression with Engineered Features)')\n", + "\n", + "# Add a diagonal line for perfect predictions\n", + "# Determine the range for the diagonal line based on both actual and predicted values\n", + "plot_range_engineered = [min(y_test_engineered.min(), y_pred_engineered.min()), max(y_test_engineered.max(), y_pred_engineered.max())]\n", + "plt.plot(plot_range_engineered, plot_range_engineered, color='red', linestyle='--')\n", + "\n", + "# Add a grid\n", + "plt.grid(True)\n", + "\n", + "# Show the plot\n", + "plt.show()" + ], + "execution_count": 69, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": {} + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "0f79ff4e" + }, + "source": [ + "## Summary:\n", + "\n", + "### Data Analysis Key Findings\n", + "\n", + "* Three new features were created: 'rooms\\_per\\_household', 'bedrooms\\_per\\_room', and 'population\\_per\\_household'.\n", + "* The dataset was successfully split into training (80%) and testing (20%) sets, resulting in training sets with 13600 samples and testing sets with 3400 samples.\n", + "* A Linear Regression model was trained using the dataset with the engineered features.\n", + "* The model trained with engineered features achieved a Mean Squared Error (MSE) of approximately 4,552,463,037.86 and an R-squared (R2) score of approximately 0.670 on the test set.\n", + "* Comparing the performance to the model with original features (MSE of ~4.63 billion and R2 of 0.664), the model with engineered features showed slightly better performance based on both metrics (lower MSE and higher R2).\n", + "\n", + "### Insights or Next Steps\n", + "\n", + "* The engineered features slightly improved the Linear Regression model's performance, suggesting that these ratios capture some valuable information about housing values. Further investigation into other feature engineering techniques or non-linear models could potentially yield more significant improvements.\n", + "* Visualizing the actual vs. predicted values confirms that the model's predictions generally follow the trend of the actual values, although there is still a notable spread, particularly for higher house values, indicating room for further model improvement.\n" + ] } ], "metadata": { "colab": { - "provenance": [] + "provenance": [], + "include_colab_link": true }, "kernelspec": { "name": "python3", From afae763ad33ed7ddf57079f75c4f12e5c05d6328 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 4 Oct 2025 06:01:12 +0600 Subject: [PATCH 21/28] Created using Colab --- ...Getting_started_with_google_colab_ai.ipynb | 4355 +++-------------- 1 file changed, 783 insertions(+), 3572 deletions(-) diff --git a/notebooks/Getting_started_with_google_colab_ai.ipynb b/notebooks/Getting_started_with_google_colab_ai.ipynb index 239f507..f7df2d0 100644 --- a/notebooks/Getting_started_with_google_colab_ai.ipynb +++ b/notebooks/Getting_started_with_google_colab_ai.ipynb @@ -31,7 +31,7 @@ { "metadata": { "id": "Ucchuu5vV3Jp", - "outputId": "64e293b1-b525-4f83-e7ec-1881a7acc2ec", + "outputId": "ef9b86d4-4187-4f2b-c779-bd15733480ce", "colab": { "base_uri": "https://localhost:8080/" } @@ -52,10 +52,10 @@ ] }, "metadata": {}, - "execution_count": 39 + "execution_count": 114 } ], - "execution_count": 39 + "execution_count": 114 }, { "metadata": { @@ -78,9 +78,9 @@ "id": "R7taibpc7x2l", "colab": { "base_uri": "https://localhost:8080/", - "height": 339 + "height": 373 }, - "outputId": "7e953657-296f-4311-ba72-2ea8aea67d38" + "outputId": "bd5aea0c-5846-417f-a849-bd554f5a565f" }, "cell_type": "code", "source": [ @@ -109,7 +109,218 @@ ] } ], - "execution_count": 42 + "execution_count": 115 + }, + { + "cell_type": "markdown", + "metadata": { + "id": "b1fd99c3" + }, + "source": [ + "## Visualize results (optional)\n", + "\n", + "### Subtask:\n", + "Visualize the predictions of the tuned model." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "3d084318" + }, + "source": [ + "**Reasoning**:\n", + "Create a scatter plot of the actual vs. predicted values from the tuned Ridge model, add labels, title, a diagonal line for perfect predictions, and a grid." + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "775a47d5" + }, + "source": [ + "# Create a scatter plot of actual vs. predicted values for the tuned Ridge model\n", + "plt.figure(figsize=(8, 6))\n", + "plt.scatter(y_test_engineered, y_pred_tuned_ridge, alpha=0.5)\n", + "\n", + "# Add labels and title\n", + "plt.xlabel('Actual Values')\n", + "plt.ylabel('Predicted Values')\n", + "plt.title('Actual vs. Predicted Values (Tuned Ridge Regression)')\n", + "\n", + "# Add a diagonal line for perfect predictions\n", + "# Determine the range for the diagonal line based on both actual and predicted values\n", + "plot_range_tuned = [min(y_test_engineered.min(), y_pred_tuned_ridge.min()), max(y_test_engineered.max(), y_pred_tuned_ridge.max())]\n", + "plt.plot(plot_range_tuned, plot_range_tuned, color='red', linestyle='--')\n", + "\n", + "# Add a grid\n", + "plt.grid(True)\n", + "\n", + "# Show the plot\n", + "plt.show()" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "458db442" + }, + "source": [ + "## Compare with previous models\n", + "\n", + "### Subtask:\n", + "Compare the performance of the tuned model to the previously trained models." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "28ab2164" + }, + "source": [ + "**Reasoning**:\n", + "Print the performance metrics for all models and compare them to summarize the impact of feature engineering and hyperparameter tuning." + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "fead6e74", + "outputId": "f0fc29d4-02f9-4279-cca3-d9412685208d" + }, + "source": [ + "from sklearn.metrics import mean_squared_error, r2_score\n", + "import pandas as pd\n", + "\n", + "# Store performance metrics in a dictionary\n", + "performance_metrics = {\n", + " \"Initial Linear Regression (Original Features)\": {\"MSE\": mse, \"R2\": r2},\n", + " \"Ridge Regression (Original Features, Default)\": {\"MSE\": mse_ridge, \"R2\": r2_ridge},\n", + " \"Linear Regression (Engineered Features)\": {\"MSE\": mse_engineered, \"R2\": r2_engineered},\n", + " \"Tuned Ridge Regression (Engineered Features, Tuned)\": {\"MSE\": mse_tuned_ridge, \"R2\": r2_tuned_ridge}\n", + "}\n", + "\n", + "# Print the performance metrics in a formatted way\n", + "print(\"--- Model Performance Comparison ---\")\n", + "for model_name, metrics in performance_metrics.items():\n", + " print(f\"\\n{model_name}:\")\n", + " print(f\" Mean Squared Error (MSE): {metrics['MSE']:.2f}\")\n", + " print(f\" R-squared (R2) Score: {metrics['R2']:.4f}\")\n", + "\n", + "# Summarize the findings\n", + "print(\"\\n--- Performance Comparison Summary ---\")\n", + "\n", + "# Determine the best model based on MSE and R2\n", + "best_mse_model = min(performance_metrics, key=lambda k: performance_metrics[k]['MSE'])\n", + "best_r2_model = max(performance_metrics, key=lambda k: performance_metrics[k]['R2'])\n", + "\n", + "if best_mse_model == best_r2_model:\n", + " print(f\"The {best_mse_model} performed the best based on both MSE (lower is better) and R2 (higher is better).\")\n", + "else:\n", + " print(f\"The {best_mse_model} performed the best based on MSE (lower is better).\")\n", + " print(f\"The {best_r2_model} performed the best based on R2 (higher is better).\")\n", + "\n", + "print(\"\\nImpact of Feature Engineering and Hyperparameter Tuning:\")\n", + "\n", + "# Compare Engineered Linear Regression to Initial Linear Regression\n", + "if performance_metrics[\"Linear Regression (Engineered Features)\"][\"MSE\"] < performance_metrics[\"Initial Linear Regression (Original Features)\"][\"MSE\"] \\\n", + " and performance_metrics[\"Linear Regression (Engineered Features)\"][\"R2\"] > performance_metrics[\"Initial Linear Regression (Original Features)\"][\"R2\"]:\n", + " print(\"- Feature engineering improved the performance of the Linear Regression model.\")\n", + "else:\n", + " print(\"- Feature engineering did not significantly improve the performance of the Linear Regression model.\")\n", + "\n", + "# Compare Tuned Ridge (Engineered) to Linear Regression (Engineered)\n", + "if performance_metrics[\"Tuned Ridge Regression (Engineered Features, Tuned)\"][\"MSE\"] < performance_metrics[\"Linear Regression (Engineered Features)\"][\"MSE\"] \\\n", + " and performance_metrics[\"Tuned Ridge Regression (Engineered Features, Tuned)\"][\"R2\"] > performance_metrics[\"Linear Regression (Engineered Features)\"][\"R2\"]:\n", + " print(\"- Hyperparameter tuning of the Ridge model with engineered features further improved performance compared to the Linear Regression model with engineered features.\")\n", + "else:\n", + " print(\"- Hyperparameter tuning of the Ridge model with engineered features did not significantly improve performance compared to the Linear Regression model with engineered features.\")\n", + "\n", + "# Compare Tuned Ridge (Engineered) to Default Ridge (Original)\n", + "if performance_metrics[\"Tuned Ridge Regression (Engineered Features, Tuned)\"][\"MSE\"] < performance_metrics[\"Ridge Regression (Original Features, Default)\"][\"MSE\"] \\\n", + " and performance_metrics[\"Tuned Ridge Regression (Engineered Features, Tuned)\"][\"R2\"] > performance_metrics[\"Ridge Regression (Original Features, Default)\"][\"R2\"]:\n", + " print(\"- Hyperparameter tuning of the Ridge model with engineered features improved performance compared to the Ridge model with default hyperparameters.\")\n", + "else:\n", + " print(\"- Hyperparameter tuning of the Ridge model with engineered features did not significantly improve performance compared to the Ridge model with default hyperparameters.\")" + ], + "execution_count": 116, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "--- Model Performance Comparison ---\n", + "\n", + "Initial Linear Regression (Original Features):\n", + " Mean Squared Error (MSE): 4634658406.22\n", + " R-squared (R2) Score: 0.6636\n", + "\n", + "Ridge Regression (Original Features, Default):\n", + " Mean Squared Error (MSE): 4634651616.32\n", + " R-squared (R2) Score: 0.6636\n", + "\n", + "Linear Regression (Engineered Features):\n", + " Mean Squared Error (MSE): 4552463037.86\n", + " R-squared (R2) Score: 0.6696\n", + "\n", + "Tuned Ridge Regression (Engineered Features, Tuned):\n", + " Mean Squared Error (MSE): 4552359506.89\n", + " R-squared (R2) Score: 0.6696\n", + "\n", + "--- Performance Comparison Summary ---\n", + "The Tuned Ridge Regression (Engineered Features, Tuned) performed the best based on both MSE (lower is better) and R2 (higher is better).\n", + "\n", + "Impact of Feature Engineering and Hyperparameter Tuning:\n", + "- Feature engineering improved the performance of the Linear Regression model.\n", + "- Hyperparameter tuning of the Ridge model with engineered features further improved performance compared to the Linear Regression model with engineered features.\n", + "- Hyperparameter tuning of the Ridge model with engineered features improved performance compared to the Ridge model with default hyperparameters.\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "f640e6d4" + }, + "source": [ + "## Train the final model\n", + "\n", + "### Subtask:\n", + "Train the chosen model with the best hyperparameters on the entire training set." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "3864b74e" + }, + "source": [ + "**Reasoning**:\n", + "Get the best estimator from the GridSearchCV object and train it on the entire engineered training data." + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "eb1dce30" + }, + "source": [ + "# Get the best estimator from the GridSearchCV object\n", + "best_ridge_model = grid_search.best_estimator_\n", + "\n", + "# Train the best estimator on the entire engineered training data\n", + "best_ridge_model.fit(X_train_engineered, y_train_engineered)\n", + "\n", + "print(\"Best Ridge Regression model trained on the entire engineered training set.\")" + ], + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -123,6 +334,54 @@ "Select the updated set of features (including the new ones) for training the model." ] }, + { + "cell_type": "code", + "metadata": { + "id": "56aa010d" + }, + "source": [ + "import matplotlib.pyplot as plt\n", + "import pandas as pd\n", + "\n", + "# Select the log-transformed features to visualize\n", + "features_to_visualize_log = ['total_rooms_log', 'median_income_log']\n", + "\n", + "# Create histograms for each selected log-transformed feature\n", + "df[features_to_visualize_log].hist(bins=50, figsize=(10, 5))\n", + "plt.tight_layout() # Adjust layout to prevent overlap\n", + "plt.show()" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "2c9d624d" + }, + "source": [ + "# Update the features list to include log-transformed features and exclude original skewed ones\n", + "features_engineered_transformed = ['longitude', 'latitude', 'housing_median_age',\n", + " 'total_bedrooms', 'population', 'households',\n", + " 'rooms_per_household', 'bedrooms_per_room', 'population_per_household',\n", + " 'total_rooms_log', 'median_income_log']\n", + "\n", + "# Create a new DataFrame X_engineered_transformed by selecting these columns from df\n", + "X_engineered_transformed = df[features_engineered_transformed]\n", + "\n", + "# Keep the target variable y as it is (the 'median_house_value' column from df)\n", + "# y was already defined in a previous step as df['median_house_value']\n", + "\n", + "# Print the head of X_engineered_transformed and y to verify\n", + "print(\"Head of X_engineered_transformed:\")\n", + "display(X_engineered_transformed.head())\n", + "\n", + "print(\"\\nHead of y:\")\n", + "display(y.head())" + ], + "execution_count": null, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -135,6 +394,15 @@ "Apply log transformation to skewed numerical features identified during exploration." ] }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "FoTxyfYmhYPH" + }, + "execution_count": 116, + "outputs": [] + }, { "cell_type": "markdown", "metadata": { @@ -148,12 +416,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 226 - }, - "id": "37e75b8c", - "outputId": "ca5da018-ff44-449b-d4a4-e9f45908ebfb" + "id": "37e75b8c" }, "source": [ "import numpy as np\n", @@ -168,394 +431,13 @@ "# Display the head of the DataFrame to verify the new transformed columns\n", "display(df.head())" ], - "execution_count": 76, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", - "0 -114.31 34.19 15.0 5612.0 1283.0 \n", - "1 -114.47 34.40 19.0 7650.0 1901.0 \n", - "2 -114.56 33.69 17.0 720.0 174.0 \n", - "3 -114.57 33.64 14.0 1501.0 337.0 \n", - "4 -114.57 33.57 20.0 1454.0 326.0 \n", - "\n", - " population households median_income median_house_value \\\n", - "0 1015.0 472.0 1.4936 66900.0 \n", - "1 1129.0 463.0 1.8200 80100.0 \n", - "2 333.0 117.0 1.6509 85700.0 \n", - "3 515.0 226.0 3.1917 73400.0 \n", - "4 624.0 262.0 1.9250 65500.0 \n", - "\n", - " rooms_per_household bedrooms_per_room population_per_household \\\n", - "0 11.889831 0.228617 2.150424 \n", - "1 16.522678 0.248497 2.438445 \n", - "2 6.153846 0.241667 2.846154 \n", - "3 6.641593 0.224517 2.278761 \n", - "4 5.549618 0.224209 2.381679 \n", - "\n", - " total_rooms_log median_income_log \n", - "0 8.632841 0.913727 \n", - "1 8.942592 1.036737 \n", - "2 6.580639 0.974899 \n", - "3 7.314553 1.433106 \n", - "4 7.282761 1.073294 " - ], - "text/html": [ - "\n", - "
\n", - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_incomemedian_house_valuerooms_per_householdbedrooms_per_roompopulation_per_householdtotal_rooms_logmedian_income_log
0-114.3134.1915.05612.01283.01015.0472.01.493666900.011.8898310.2286172.1504248.6328410.913727
1-114.4734.4019.07650.01901.01129.0463.01.820080100.016.5226780.2484972.4384458.9425921.036737
2-114.5633.6917.0720.0174.0333.0117.01.650985700.06.1538460.2416672.8461546.5806390.974899
3-114.5733.6414.01501.0337.0515.0226.03.191773400.06.6415930.2245172.2787617.3145531.433106
4-114.5733.5720.01454.0326.0624.0262.01.925065500.05.5496180.2242092.3816797.2827611.073294
\n", - "
\n", - "
\n", - "\n", - "
\n", - " \n", - "\n", - " \n", - "\n", - " \n", - "
\n", - "\n", - "\n", - "
\n", - " \n", - "\n", - "\n", - "\n", - " \n", - "
\n", - "\n", - "
\n", - "
\n" - ], - "application/vnd.google.colaboratory.intrinsic+json": { - "type": "dataframe", - "summary": "{\n \"name\": \"display(df\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.11216059914247682,\n \"min\": -114.57,\n \"max\": -114.31,\n \"num_unique_values\": 4,\n \"samples\": [\n -114.47,\n -114.57,\n -114.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3723842101915701,\n \"min\": 33.57,\n \"max\": 34.4,\n \"num_unique_values\": 5,\n \"samples\": [\n 34.4,\n 33.57,\n 33.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.5495097567963922,\n \"min\": 14.0,\n \"max\": 20.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 19.0,\n 20.0,\n 17.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3063.09350167441,\n \"min\": 720.0,\n \"max\": 7650.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 7650.0,\n 1454.0,\n 720.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 754.3743765531807,\n \"min\": 174.0,\n \"max\": 1901.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1901.0,\n 326.0,\n 174.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 337.36656621544466,\n \"min\": 333.0,\n \"max\": 1129.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1129.0,\n 624.0,\n 333.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 155.11447385721294,\n \"min\": 117.0,\n \"max\": 472.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 463.0,\n 262.0,\n 117.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6773416737511431,\n \"min\": 1.4936,\n \"max\": 3.1917,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.82,\n 1.925,\n 1.6509\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_house_value\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 8611.15555544086,\n \"min\": 65500.0,\n \"max\": 85700.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 80100.0,\n 65500.0,\n 85700.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rooms_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 4.740564553544767,\n \"min\": 5.549618320610687,\n \"max\": 16.52267818574514,\n \"num_unique_values\": 5,\n \"samples\": [\n 16.52267818574514,\n 5.549618320610687,\n 6.153846153846154\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"bedrooms_per_room\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.010982410746386893,\n \"min\": 0.22420907840440166,\n \"max\": 0.24849673202614378,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.24849673202614378,\n 0.22420907840440166,\n 0.24166666666666667\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.26269348663282854,\n \"min\": 2.1504237288135593,\n \"max\": 2.8461538461538463,\n \"num_unique_values\": 5,\n \"samples\": [\n 2.4384449244060473,\n 2.381679389312977,\n 2.8461538461538463\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms_log\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.9971222656686318,\n \"min\": 6.580639137284949,\n \"max\": 8.942591637231851,\n \"num_unique_values\": 5,\n \"samples\": [\n 8.942591637231851,\n 7.282761179605593,\n 6.580639137284949\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income_log\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.20315740151650868,\n \"min\": 0.9137274494709903,\n \"max\": 1.4331063795723562,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.0367368849500223,\n 1.0732944806838198,\n 0.9748992049809254\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" - } - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 934 - }, - "id": "c4b589c8", - "outputId": "9359a55d-7785-481d-a161-6de7aad9e729" + "id": "c4b589c8" }, "source": [ "import matplotlib.pyplot as plt\n", @@ -569,29 +451,13 @@ "plt.tight_layout() # Adjust layout to prevent overlap\n", "plt.show()" ], - "execution_count": 75, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 564 - }, - "id": "2e38b388", - "outputId": "f8b512f9-7578-4ccf-aec4-68da6c19621b" + "id": "2e38b388" }, "source": [ "import matplotlib.pyplot as plt\n", @@ -611,19 +477,8 @@ "# Show the plot\n", "plt.show()" ], - "execution_count": 74, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -650,11 +505,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "bc5d10a6", - "outputId": "dd263b3d-2f14-4292-aaab-70bec3edac8c" + "id": "bc5d10a6" }, "source": [ "from sklearn.model_selection import train_test_split\n", @@ -668,19 +519,8 @@ "print(f\"Shape of y_train_engineered: {y_train_engineered.shape}\")\n", "print(f\"Shape of y_test_engineered: {y_test_engineered.shape}\")" ], - "execution_count": 73, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Shape of X_train_engineered: (13600, 11)\n", - "Shape of X_test_engineered: (3400, 11)\n", - "Shape of y_train_engineered: (13600,)\n", - "Shape of y_test_engineered: (3400,)\n" - ] - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -695,12 +535,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 502 - }, - "id": "456aa011", - "outputId": "4853b65f-42eb-401b-92db-f6c9f8c7ea71" + "id": "456aa011" }, "source": [ "# Define the list of features, including the original and engineered ones\n", @@ -721,435 +556,8 @@ "print(\"\\nHead of y:\")\n", "display(y.head())" ], - "execution_count": 72, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Head of X_engineered:\n" - ] - }, - { - "output_type": "display_data", - "data": { - "text/plain": [ - " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", - "0 -114.31 34.19 15.0 5612.0 1283.0 \n", - "1 -114.47 34.40 19.0 7650.0 1901.0 \n", - "2 -114.56 33.69 17.0 720.0 174.0 \n", - "3 -114.57 33.64 14.0 1501.0 337.0 \n", - "4 -114.57 33.57 20.0 1454.0 326.0 \n", - "\n", - " population households median_income rooms_per_household \\\n", - "0 1015.0 472.0 1.4936 11.889831 \n", - "1 1129.0 463.0 1.8200 16.522678 \n", - "2 333.0 117.0 1.6509 6.153846 \n", - "3 515.0 226.0 3.1917 6.641593 \n", - "4 624.0 262.0 1.9250 5.549618 \n", - "\n", - " bedrooms_per_room population_per_household \n", - "0 0.228617 2.150424 \n", - "1 0.248497 2.438445 \n", - "2 0.241667 2.846154 \n", - "3 0.224517 2.278761 \n", - "4 0.224209 2.381679 " - ], - "text/html": [ - "\n", - "
\n", - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_incomerooms_per_householdbedrooms_per_roompopulation_per_household
0-114.3134.1915.05612.01283.01015.0472.01.493611.8898310.2286172.150424
1-114.4734.4019.07650.01901.01129.0463.01.820016.5226780.2484972.438445
2-114.5633.6917.0720.0174.0333.0117.01.65096.1538460.2416672.846154
3-114.5733.6414.01501.0337.0515.0226.03.19176.6415930.2245172.278761
4-114.5733.5720.01454.0326.0624.0262.01.92505.5496180.2242092.381679
\n", - "
\n", - "
\n", - "\n", - "
\n", - " \n", - "\n", - " \n", - "\n", - " \n", - "
\n", - "\n", - "\n", - "
\n", - " \n", - "\n", - "\n", - "\n", - " \n", - "
\n", - "\n", - "
\n", - "
\n" - ], - "application/vnd.google.colaboratory.intrinsic+json": { - "type": "dataframe", - "summary": "{\n \"name\": \"display(y\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.11216059914247682,\n \"min\": -114.57,\n \"max\": -114.31,\n \"num_unique_values\": 4,\n \"samples\": [\n -114.47,\n -114.57,\n -114.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3723842101915701,\n \"min\": 33.57,\n \"max\": 34.4,\n \"num_unique_values\": 5,\n \"samples\": [\n 34.4,\n 33.57,\n 33.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.5495097567963922,\n \"min\": 14.0,\n \"max\": 20.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 19.0,\n 20.0,\n 17.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3063.09350167441,\n \"min\": 720.0,\n \"max\": 7650.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 7650.0,\n 1454.0,\n 720.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 754.3743765531807,\n \"min\": 174.0,\n \"max\": 1901.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1901.0,\n 326.0,\n 174.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 337.36656621544466,\n \"min\": 333.0,\n \"max\": 1129.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1129.0,\n 624.0,\n 333.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 155.11447385721294,\n \"min\": 117.0,\n \"max\": 472.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 463.0,\n 262.0,\n 117.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6773416737511431,\n \"min\": 1.4936,\n \"max\": 3.1917,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.82,\n 1.925,\n 1.6509\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rooms_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 4.740564553544767,\n \"min\": 5.549618320610687,\n \"max\": 16.52267818574514,\n \"num_unique_values\": 5,\n \"samples\": [\n 16.52267818574514,\n 5.549618320610687,\n 6.153846153846154\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"bedrooms_per_room\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.010982410746386893,\n \"min\": 0.22420907840440166,\n \"max\": 0.24849673202614378,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.24849673202614378,\n 0.22420907840440166,\n 0.24166666666666667\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.26269348663282854,\n \"min\": 2.1504237288135593,\n \"max\": 2.8461538461538463,\n \"num_unique_values\": 5,\n \"samples\": [\n 2.4384449244060473,\n 2.381679389312977,\n 2.8461538461538463\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" - } - }, - "metadata": {} - }, - { - "output_type": "stream", - "name": "stdout", - "text": [ - "\n", - "Head of y:\n" - ] - }, - { - "output_type": "display_data", - "data": { - "text/plain": [ - "0 66900.0\n", - "1 80100.0\n", - "2 85700.0\n", - "3 73400.0\n", - "4 65500.0\n", - "Name: median_house_value, dtype: float64" - ], - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
median_house_value
066900.0
180100.0
285700.0
373400.0
465500.0
\n", - "

" - ] - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -1203,7 +611,7 @@ "# These ratios normalize the counts by the number of households or rooms,\n", "# making them potentially more robust indicators than the raw counts themselves." ], - "execution_count": 70, + "execution_count": null, "outputs": [] }, { @@ -1231,12 +639,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 226 - }, - "id": "cc30b3e9", - "outputId": "39dd1ff6-7638-4e06-8d39-5952d6fd886d" + "id": "cc30b3e9" }, "source": [ "# Calculate 'rooms_per_household' and add it as a new column\n", @@ -1251,766 +654,20 @@ "# Display the head of the DataFrame to verify the new columns\n", "display(df.head())" ], - "execution_count": 71, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", - "0 -114.31 34.19 15.0 5612.0 1283.0 \n", - "1 -114.47 34.40 19.0 7650.0 1901.0 \n", - "2 -114.56 33.69 17.0 720.0 174.0 \n", - "3 -114.57 33.64 14.0 1501.0 337.0 \n", - "4 -114.57 33.57 20.0 1454.0 326.0 \n", - "\n", - " population households median_income median_house_value \\\n", - "0 1015.0 472.0 1.4936 66900.0 \n", - "1 1129.0 463.0 1.8200 80100.0 \n", - "2 333.0 117.0 1.6509 85700.0 \n", - "3 515.0 226.0 3.1917 73400.0 \n", - "4 624.0 262.0 1.9250 65500.0 \n", - "\n", - " rooms_per_household bedrooms_per_room population_per_household \n", - "0 11.889831 0.228617 2.150424 \n", - "1 16.522678 0.248497 2.438445 \n", - "2 6.153846 0.241667 2.846154 \n", - "3 6.641593 0.224517 2.278761 \n", - "4 5.549618 0.224209 2.381679 " - ], - "text/html": [ - "\n", - "
\n", - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_incomemedian_house_valuerooms_per_householdbedrooms_per_roompopulation_per_household
0-114.3134.1915.05612.01283.01015.0472.01.493666900.011.8898310.2286172.150424
1-114.4734.4019.07650.01901.01129.0463.01.820080100.016.5226780.2484972.438445
2-114.5633.6917.0720.0174.0333.0117.01.650985700.06.1538460.2416672.846154
3-114.5733.6414.01501.0337.0515.0226.03.191773400.06.6415930.2245172.278761
4-114.5733.5720.01454.0326.0624.0262.01.925065500.05.5496180.2242092.381679
\n", - "
\n", - "
\n", - "\n", - "
\n", - " \n", - "\n", - " \n", - "\n", - " \n", - "
\n", - "\n", - "\n", - "
\n", - " \n", - "\n", - "\n", - "\n", - " \n", - "
\n", - "\n", - "
\n", - "
\n" - ], - "application/vnd.google.colaboratory.intrinsic+json": { - "type": "dataframe", - "summary": "{\n \"name\": \"display(df\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.11216059914247682,\n \"min\": -114.57,\n \"max\": -114.31,\n \"num_unique_values\": 4,\n \"samples\": [\n -114.47,\n -114.57,\n -114.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3723842101915701,\n \"min\": 33.57,\n \"max\": 34.4,\n \"num_unique_values\": 5,\n \"samples\": [\n 34.4,\n 33.57,\n 33.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.5495097567963922,\n \"min\": 14.0,\n \"max\": 20.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 19.0,\n 20.0,\n 17.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3063.09350167441,\n \"min\": 720.0,\n \"max\": 7650.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 7650.0,\n 1454.0,\n 720.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 754.3743765531807,\n \"min\": 174.0,\n \"max\": 1901.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1901.0,\n 326.0,\n 174.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 337.36656621544466,\n \"min\": 333.0,\n \"max\": 1129.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1129.0,\n 624.0,\n 333.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 155.11447385721294,\n \"min\": 117.0,\n \"max\": 472.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 463.0,\n 262.0,\n 117.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6773416737511431,\n \"min\": 1.4936,\n \"max\": 3.1917,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.82,\n 1.925,\n 1.6509\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_house_value\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 8611.15555544086,\n \"min\": 65500.0,\n \"max\": 85700.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 80100.0,\n 65500.0,\n 85700.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rooms_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 4.740564553544767,\n \"min\": 5.549618320610687,\n \"max\": 16.52267818574514,\n \"num_unique_values\": 5,\n \"samples\": [\n 16.52267818574514,\n 5.549618320610687,\n 6.153846153846154\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"bedrooms_per_room\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.010982410746386893,\n \"min\": 0.22420907840440166,\n \"max\": 0.24849673202614378,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.24849673202614378,\n 0.22420907840440166,\n 0.24166666666666667\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.26269348663282854,\n \"min\": 2.1504237288135593,\n \"max\": 2.8461538461538463,\n \"num_unique_values\": 5,\n \"samples\": [\n 2.4384449244060473,\n 2.381679389312977,\n 2.8461538461538463\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" - } - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 300 - }, - "id": "088fbfe6", - "outputId": "19fbc262-b2f7-4230-80f3-7729bc94b395" + "id": "088fbfe6" }, "source": [ "# Display summary statistics of the DataFrame\n", "display(df.describe())" ], - "execution_count": 61, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - " longitude latitude housing_median_age total_rooms \\\n", - "count 17000.000000 17000.000000 17000.000000 17000.000000 \n", - "mean -119.562108 35.625225 28.589353 2643.664412 \n", - "std 2.005166 2.137340 12.586937 2179.947071 \n", - "min -124.350000 32.540000 1.000000 2.000000 \n", - "25% -121.790000 33.930000 18.000000 1462.000000 \n", - "50% -118.490000 34.250000 29.000000 2127.000000 \n", - "75% -118.000000 37.720000 37.000000 3151.250000 \n", - "max -114.310000 41.950000 52.000000 37937.000000 \n", - "\n", - " total_bedrooms population households median_income \\\n", - "count 17000.000000 17000.000000 17000.000000 17000.000000 \n", - "mean 539.410824 1429.573941 501.221941 3.883578 \n", - "std 421.499452 1147.852959 384.520841 1.908157 \n", - "min 1.000000 3.000000 1.000000 0.499900 \n", - "25% 297.000000 790.000000 282.000000 2.566375 \n", - "50% 434.000000 1167.000000 409.000000 3.544600 \n", - "75% 648.250000 1721.000000 605.250000 4.767000 \n", - "max 6445.000000 35682.000000 6082.000000 15.000100 \n", - "\n", - " median_house_value \n", - "count 17000.000000 \n", - "mean 207300.912353 \n", - "std 115983.764387 \n", - "min 14999.000000 \n", - "25% 119400.000000 \n", - "50% 180400.000000 \n", - "75% 265000.000000 \n", - "max 500001.000000 " - ], - "text/html": [ - "\n", - "
\n", - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_incomemedian_house_value
count17000.00000017000.00000017000.00000017000.00000017000.00000017000.00000017000.00000017000.00000017000.000000
mean-119.56210835.62522528.5893532643.664412539.4108241429.573941501.2219413.883578207300.912353
std2.0051662.13734012.5869372179.947071421.4994521147.852959384.5208411.908157115983.764387
min-124.35000032.5400001.0000002.0000001.0000003.0000001.0000000.49990014999.000000
25%-121.79000033.93000018.0000001462.000000297.000000790.000000282.0000002.566375119400.000000
50%-118.49000034.25000029.0000002127.000000434.0000001167.000000409.0000003.544600180400.000000
75%-118.00000037.72000037.0000003151.250000648.2500001721.000000605.2500004.767000265000.000000
max-114.31000041.95000052.00000037937.0000006445.00000035682.0000006082.00000015.000100500001.000000
\n", - "
\n", - "
\n", - "\n", - "
\n", - " \n", - "\n", - " \n", - "\n", - " \n", - "
\n", - "\n", - "\n", - "
\n", - " \n", - "\n", - "\n", - "\n", - " \n", - "
\n", - "\n", - "
\n", - "
\n" - ], - "application/vnd.google.colaboratory.intrinsic+json": { - "type": "dataframe", - "summary": "{\n \"name\": \"display(df\",\n \"rows\": 8,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6046.6451651071675,\n \"min\": -124.35,\n \"max\": 17000.0,\n \"num_unique_values\": 8,\n \"samples\": [\n -119.5621082352941,\n -118.49,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 5999.40166383228,\n \"min\": 2.1373397946570734,\n \"max\": 17000.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 35.62522470588235,\n 34.25,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6001.428368089024,\n \"min\": 1.0,\n \"max\": 17000.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 28.58935294117647,\n 29.0,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 13113.353227786365,\n \"min\": 2.0,\n \"max\": 37937.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 2643.664411764706,\n 2127.0,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 5959.238771737063,\n \"min\": 1.0,\n \"max\": 17000.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 539.4108235294118,\n 434.0,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 12740.640658201448,\n \"min\": 3.0,\n \"max\": 35682.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 1429.5739411764705,\n 1167.0,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 5942.738122392389,\n \"min\": 1.0,\n \"max\": 17000.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 501.2219411764706,\n 409.0,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6008.784464952051,\n \"min\": 0.4999,\n \"max\": 17000.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 3.8835781000000007,\n 3.5446,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_house_value\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 156700.95757149634,\n \"min\": 14999.0,\n \"max\": 500001.0,\n \"num_unique_values\": 8,\n \"samples\": [\n 207300.91235294117,\n 180400.0,\n 17000.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" - } - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -2037,12 +694,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 564 - }, - "id": "217c1753", - "outputId": "e128dbc4-ef05-4b67-9c85-2008a218bf79" + "id": "217c1753" }, "source": [ "import matplotlib.pyplot as plt\n", @@ -2067,19 +719,8 @@ "# Show the plot\n", "plt.show()" ], - "execution_count": 60, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -2115,7 +756,7 @@ "# among predictor variables, which might be present in this dataset.\n", "# This choice is a common next step after trying simple Linear Regression." ], - "execution_count": 58, + "execution_count": null, "outputs": [] }, { @@ -2143,11 +784,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "d79f43a6", - "outputId": "a89b316f-4463-4130-842a-60bc4a3dcb66" + "id": "d79f43a6" }, "source": [ "from sklearn.linear_model import Ridge\n", @@ -2160,16 +797,8 @@ "\n", "print(\"Ridge Regression model trained successfully.\")" ], - "execution_count": 59, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Ridge Regression model trained successfully.\n" - ] - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -2196,12 +825,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 564 - }, - "id": "c5f468af", - "outputId": "0fe9f1bd-73d2-468e-f639-a5b3c8d2397e" + "id": "c5f468af" }, "source": [ "import matplotlib.pyplot as plt\n", @@ -2226,19 +850,8 @@ "# Show the plot\n", "plt.show()" ], - "execution_count": 52, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -2265,12 +878,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 472 - }, - "id": "1180b0f9", - "outputId": "72250dc2-ed91-403e-ae11-4c06e5d76e5f" + "id": "1180b0f9" }, "source": [ "import matplotlib.pyplot as plt\n", @@ -2289,28 +897,13 @@ "plt.grid(True)\n", "plt.show()" ], - "execution_count": 44, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "dddf50ae", - "outputId": "72351ca1-e604-4cc9-bbcd-3c233eb08732" + "id": "dddf50ae" }, "source": [ "import numpy as np\n", @@ -2335,34 +928,12 @@ "print(f\"Target (y):\\n{y}\")\n", "print(f\"Prediction for X={new_X[0][0]}: {prediction[0]}\")" ], - "execution_count": 43, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Features (X):\n", - "[[1]\n", - " [2]\n", - " [3]\n", - " [4]\n", - " [5]\n", - " [6]]\n", - "Target (y):\n", - "[2 4 5 4 5 6]\n", - "Prediction for X=7: 6.533333333333333\n" - ] - } - ] + "execution_count": null, + "outputs": [] }, { "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 339 - }, - "id": "NHO9VzO9AHZP", - "outputId": "dc325df0-1368-45f6-e1da-50d8d58dd59a" + "id": "NHO9VzO9AHZP" }, "cell_type": "code", "source": [ @@ -2372,25 +943,8 @@ "response = ai.generate_text(\"What is the capital of England\", model_name='google/gemini-2.0-flash-lite')\n", "print(response)" ], - "outputs": [ - { - "output_type": "error", - "ename": "InternalServerError", - "evalue": "Error code: 503 - {'message': 'The requested model is currently unavailable.', 'type': 'invalid_request_error'}", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mInternalServerError\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m/tmp/ipython-input-1810143207.py\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mgoogle\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolab\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mai\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mresponse\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mai\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgenerate_text\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"What is the capital of England\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodel_name\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'google/gemini-2.0-flash-lite'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 5\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/colab/ai.py\u001b[0m in \u001b[0;36mgenerate_text\u001b[0;34m(prompt, model_name, stream)\u001b[0m\n\u001b[1;32m 83\u001b[0m )\n\u001b[1;32m 84\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 85\u001b[0;31m response = client.chat.completions.create(\n\u001b[0m\u001b[1;32m 86\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmodel_name\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 87\u001b[0m \u001b[0mmessages\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m{\u001b[0m\u001b[0;34m'role'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'user'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'content'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mprompt\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/_utils/_utils.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 284\u001b[0m \u001b[0mmsg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34mf\"Missing required argument: {quote(missing[0])}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 285\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmsg\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 286\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 287\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 288\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mwrapper\u001b[0m \u001b[0;31m# type: ignore\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/resources/chat/completions/completions.py\u001b[0m in \u001b[0;36mcreate\u001b[0;34m(self, messages, model, audio, frequency_penalty, function_call, functions, logit_bias, logprobs, max_completion_tokens, max_tokens, metadata, modalities, n, parallel_tool_calls, prediction, presence_penalty, prompt_cache_key, reasoning_effort, response_format, safety_identifier, seed, service_tier, stop, store, stream, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, verbosity, web_search_options, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m 1145\u001b[0m ) -> ChatCompletion | Stream[ChatCompletionChunk]:\n\u001b[1;32m 1146\u001b[0m \u001b[0mvalidate_response_format\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponse_format\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1147\u001b[0;31m return self._post(\n\u001b[0m\u001b[1;32m 1148\u001b[0m \u001b[0;34m\"/chat/completions\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1149\u001b[0m body=maybe_transform(\n", - "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/_base_client.py\u001b[0m in \u001b[0;36mpost\u001b[0;34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1257\u001b[0m \u001b[0mmethod\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"post\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0murl\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mjson_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mbody\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfiles\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mto_httpx_files\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfiles\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0moptions\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1258\u001b[0m )\n\u001b[0;32m-> 1259\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mcast\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mResponseT\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcast_to\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mopts\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstream\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstream\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstream_cls\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstream_cls\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1260\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1261\u001b[0m def patch(\n", - "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/_base_client.py\u001b[0m in \u001b[0;36mrequest\u001b[0;34m(self, cast_to, options, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1045\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1046\u001b[0m \u001b[0mlog\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdebug\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Re-raising status error\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1047\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_make_status_error_from_response\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0merr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresponse\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1048\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1049\u001b[0m \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mInternalServerError\u001b[0m: Error code: 503 - {'message': 'The requested model is currently unavailable.', 'type': 'invalid_request_error'}" - ] - } - ], - "execution_count": 41 + "outputs": [], + "execution_count": null }, { "metadata": { @@ -2551,12 +1105,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 206 - }, - "id": "f8c9aec7", - "outputId": "3c80b854-df9a-474b-aa6c-7b74a09832cd" + "id": "f8c9aec7" }, "source": [ "import pandas as pd\n", @@ -2571,340 +1120,8 @@ "except Exception as e:\n", " print(f\"An error occurred: {e}\")" ], - "execution_count": 45, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", - "0 -114.31 34.19 15.0 5612.0 1283.0 \n", - "1 -114.47 34.40 19.0 7650.0 1901.0 \n", - "2 -114.56 33.69 17.0 720.0 174.0 \n", - "3 -114.57 33.64 14.0 1501.0 337.0 \n", - "4 -114.57 33.57 20.0 1454.0 326.0 \n", - "\n", - " population households median_income median_house_value \n", - "0 1015.0 472.0 1.4936 66900.0 \n", - "1 1129.0 463.0 1.8200 80100.0 \n", - "2 333.0 117.0 1.6509 85700.0 \n", - "3 515.0 226.0 3.1917 73400.0 \n", - "4 624.0 262.0 1.9250 65500.0 " - ], - "text/html": [ - "\n", - "
\n", - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_incomemedian_house_value
0-114.3134.1915.05612.01283.01015.0472.01.493666900.0
1-114.4734.4019.07650.01901.01129.0463.01.820080100.0
2-114.5633.6917.0720.0174.0333.0117.01.650985700.0
3-114.5733.6414.01501.0337.0515.0226.03.191773400.0
4-114.5733.5720.01454.0326.0624.0262.01.925065500.0
\n", - "
\n", - "
\n", - "\n", - "
\n", - " \n", - "\n", - " \n", - "\n", - " \n", - "
\n", - "\n", - "\n", - "
\n", - " \n", - "\n", - "\n", - "\n", - " \n", - "
\n", - "\n", - "
\n", - "
\n" - ], - "application/vnd.google.colaboratory.intrinsic+json": { - "type": "dataframe", - "summary": "{\n \"name\": \" print(f\\\"An error occurred: {e}\\\")\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.11216059914247682,\n \"min\": -114.57,\n \"max\": -114.31,\n \"num_unique_values\": 4,\n \"samples\": [\n -114.47,\n -114.57,\n -114.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3723842101915701,\n \"min\": 33.57,\n \"max\": 34.4,\n \"num_unique_values\": 5,\n \"samples\": [\n 34.4,\n 33.57,\n 33.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.5495097567963922,\n \"min\": 14.0,\n \"max\": 20.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 19.0,\n 20.0,\n 17.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3063.09350167441,\n \"min\": 720.0,\n \"max\": 7650.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 7650.0,\n 1454.0,\n 720.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 754.3743765531807,\n \"min\": 174.0,\n \"max\": 1901.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1901.0,\n 326.0,\n 174.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 337.36656621544466,\n \"min\": 333.0,\n \"max\": 1129.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1129.0,\n 624.0,\n 333.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 155.11447385721294,\n \"min\": 117.0,\n \"max\": 472.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 463.0,\n 262.0,\n 117.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6773416737511431,\n \"min\": 1.4936,\n \"max\": 3.1917,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.82,\n 1.925,\n 1.6509\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_house_value\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 8611.15555544086,\n \"min\": 65500.0,\n \"max\": 85700.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 80100.0,\n 65500.0,\n 85700.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" - } - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -2932,12 +1149,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 1000 - }, - "id": "9347ab12", - "outputId": "e238cd9f-b998-4979-8f7f-4516c2d5b9ce" + "id": "9347ab12" }, "source": [ "# Display info about the DataFrame\n", @@ -2976,441 +1188,8 @@ "display(X.head())\n", "display(y.head())" ], - "execution_count": 51, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "\n", - "RangeIndex: 17000 entries, 0 to 16999\n", - "Data columns (total 9 columns):\n", - " # Column Non-Null Count Dtype \n", - "--- ------ -------------- ----- \n", - " 0 longitude 17000 non-null float64\n", - " 1 latitude 17000 non-null float64\n", - " 2 housing_median_age 17000 non-null float64\n", - " 3 total_rooms 17000 non-null float64\n", - " 4 total_bedrooms 17000 non-null float64\n", - " 5 population 17000 non-null float64\n", - " 6 households 17000 non-null float64\n", - " 7 median_income 17000 non-null float64\n", - " 8 median_house_value 17000 non-null float64\n", - "dtypes: float64(9)\n", - "memory usage: 1.2 MB\n", - "\n", - "Missing values per column:\n", - "longitude 0\n", - "latitude 0\n", - "housing_median_age 0\n", - "total_rooms 0\n", - "total_bedrooms 0\n", - "population 0\n", - "households 0\n", - "median_income 0\n", - "median_house_value 0\n", - "dtype: int64\n", - "longitude 0\n", - "latitude 0\n", - "housing_median_age 0\n", - "total_rooms 0\n", - "total_bedrooms 0\n", - "population 0\n", - "households 0\n", - "median_income 0\n", - "median_house_value 0\n", - "dtype: int64\n", - "\n", - "Features (X) and Target (y) selected.\n" - ] - }, - { - "output_type": "display_data", - "data": { - "text/plain": [ - " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", - "0 -114.31 34.19 15.0 5612.0 1283.0 \n", - "1 -114.47 34.40 19.0 7650.0 1901.0 \n", - "2 -114.56 33.69 17.0 720.0 174.0 \n", - "3 -114.57 33.64 14.0 1501.0 337.0 \n", - "4 -114.57 33.57 20.0 1454.0 326.0 \n", - "\n", - " population households median_income \n", - "0 1015.0 472.0 1.4936 \n", - "1 1129.0 463.0 1.8200 \n", - "2 333.0 117.0 1.6509 \n", - "3 515.0 226.0 3.1917 \n", - "4 624.0 262.0 1.9250 " - ], - "text/html": [ - "\n", - "
\n", - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_income
0-114.3134.1915.05612.01283.01015.0472.01.4936
1-114.4734.4019.07650.01901.01129.0463.01.8200
2-114.5633.6917.0720.0174.0333.0117.01.6509
3-114.5733.6414.01501.0337.0515.0226.03.1917
4-114.5733.5720.01454.0326.0624.0262.01.9250
\n", - "
\n", - "
\n", - "\n", - "
\n", - " \n", - "\n", - " \n", - "\n", - " \n", - "
\n", - "\n", - "\n", - "
\n", - " \n", - "\n", - "\n", - "\n", - " \n", - "
\n", - "\n", - "
\n", - "
\n" - ], - "application/vnd.google.colaboratory.intrinsic+json": { - "type": "dataframe", - "summary": "{\n \"name\": \"display(y\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.11216059914247682,\n \"min\": -114.57,\n \"max\": -114.31,\n \"num_unique_values\": 4,\n \"samples\": [\n -114.47,\n -114.57,\n -114.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3723842101915701,\n \"min\": 33.57,\n \"max\": 34.4,\n \"num_unique_values\": 5,\n \"samples\": [\n 34.4,\n 33.57,\n 33.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.5495097567963922,\n \"min\": 14.0,\n \"max\": 20.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 19.0,\n 20.0,\n 17.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3063.09350167441,\n \"min\": 720.0,\n \"max\": 7650.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 7650.0,\n 1454.0,\n 720.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 754.3743765531807,\n \"min\": 174.0,\n \"max\": 1901.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1901.0,\n 326.0,\n 174.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 337.36656621544466,\n \"min\": 333.0,\n \"max\": 1129.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1129.0,\n 624.0,\n 333.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 155.11447385721294,\n \"min\": 117.0,\n \"max\": 472.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 463.0,\n 262.0,\n 117.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6773416737511431,\n \"min\": 1.4936,\n \"max\": 3.1917,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.82,\n 1.925,\n 1.6509\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" - } - }, - "metadata": {} - }, - { - "output_type": "display_data", - "data": { - "text/plain": [ - "0 66900.0\n", - "1 80100.0\n", - "2 85700.0\n", - "3 73400.0\n", - "4 65500.0\n", - "Name: median_house_value, dtype: float64" - ], - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
median_house_value
066900.0
180100.0
285700.0
373400.0
465500.0
\n", - "

" - ] - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -3438,11 +1217,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "94b0ab2d", - "outputId": "00c1f1db-e5dd-41a2-fa47-856be16a4315" + "id": "94b0ab2d" }, "source": [ "from sklearn.model_selection import train_test_split\n", @@ -3456,19 +1231,8 @@ "print(f\"Shape of y_train: {y_train.shape}\")\n", "print(f\"Shape of y_test: {y_test.shape}\")" ], - "execution_count": 47, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Shape of X_train: (13600, 8)\n", - "Shape of X_test: (3400, 8)\n", - "Shape of y_train: (13600,)\n", - "Shape of y_test: (3400,)\n" - ] - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -3496,11 +1260,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "f3b32a6a", - "outputId": "8d3ca35c-58bf-4fb4-c819-e1b16edf6ab0" + "id": "f3b32a6a" }, "source": [ "from sklearn.linear_model import LinearRegression\n", @@ -3513,16 +1273,8 @@ "\n", "print(\"Linear Regression model trained successfully.\")" ], - "execution_count": 48, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Linear Regression model trained successfully.\n" - ] - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -3550,11 +1302,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "fa02f998", - "outputId": "7934427f-d65c-4cd9-acaf-25328e8c7e9a" + "id": "fa02f998" }, "source": [ "from sklearn.metrics import mean_squared_error, r2_score\n", @@ -3572,17 +1320,8 @@ "print(f\"Mean Squared Error (MSE): {mse}\")\n", "print(f\"R-squared (R2) Score: {r2}\")" ], - "execution_count": 49, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Mean Squared Error (MSE): 4634658406.223264\n", - "R-squared (R2) Score: 0.6636396350243869\n" - ] - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -3610,12 +1349,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 564 - }, - "id": "6fd07845", - "outputId": "231bd57e-6082-4a7a-ba97-a6766703e0d3" + "id": "6fd07845" }, "source": [ "# Create a scatter plot\n", @@ -3638,19 +1372,8 @@ "# Show the plot\n", "plt.show()" ], - "execution_count": 50, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -3719,7 +1442,7 @@ "# among predictor variables, which might be present in this dataset.\n", "# This choice is a common next step after trying simple Linear Regression." ], - "execution_count": 53, + "execution_count": null, "outputs": [] }, { @@ -3748,11 +1471,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "1722a73a", - "outputId": "cefe469e-f3e3-43df-a176-be746c544892" + "id": "1722a73a" }, "source": [ "from sklearn.linear_model import Ridge\n", @@ -3765,16 +1484,8 @@ "\n", "print(\"Ridge Regression model trained successfully.\")" ], - "execution_count": 54, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Ridge Regression model trained successfully.\n" - ] - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -3802,11 +1513,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "24b91385", - "outputId": "d101835f-1af6-44b5-8581-814246a081c6" + "id": "24b91385" }, "source": [ "from sklearn.metrics import mean_squared_error, r2_score\n", @@ -3824,17 +1531,8 @@ "print(f\"Ridge Model Mean Squared Error (MSE): {mse_ridge}\")\n", "print(f\"Ridge Model R-squared (R2) Score: {r2_ridge}\")" ], - "execution_count": 55, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Ridge Model Mean Squared Error (MSE): 4634651616.323527\n", - "Ridge Model R-squared (R2) Score: 0.6636401278014059\n" - ] - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -3862,11 +1560,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "bd0b8441", - "outputId": "37ba001a-d11a-492a-b20f-39599f54248e" + "id": "bd0b8441" }, "source": [ "# Print the performance metrics for the Linear Regression model\n", @@ -3892,22 +1586,8 @@ "else:\n", " print(\"Summary: Both models performed similarly based on R2.\")" ], - "execution_count": 56, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Linear Regression Model Mean Squared Error (MSE): 4634658406.223264\n", - "Linear Regression Model R-squared (R2) Score: 0.6636396350243869\n", - "Ridge Model Mean Squared Error (MSE): 4634651616.323527\n", - "Ridge Model R-squared (R2) Score: 0.6636401278014059\n", - "\n", - "Summary: The Ridge Regression model performed slightly better than the Linear Regression model based on MSE.\n", - "Summary: The Ridge Regression model performed slightly better than the Linear Regression model based on R2.\n" - ] - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -3935,12 +1615,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 564 - }, - "id": "43d35683", - "outputId": "719837c8-17d0-4167-a20d-9fde2a146985" + "id": "43d35683" }, "source": [ "import matplotlib.pyplot as plt\n", @@ -3965,19 +1640,8 @@ "# Show the plot\n", "plt.show()" ], - "execution_count": 57, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -4065,7 +1729,7 @@ "# These ratios normalize the counts by the number of households or rooms,\n", "# making them potentially more robust indicators than the raw counts themselves." ], - "execution_count": 62, + "execution_count": null, "outputs": [] }, { @@ -4094,12 +1758,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 226 - }, - "id": "5ca46b87", - "outputId": "215b5320-0102-4584-d0b4-e56999c58224" + "id": "5ca46b87" }, "source": [ "# Calculate 'rooms_per_household' and add it as a new column\n", @@ -4114,365 +1773,8 @@ "# Display the head of the DataFrame to verify the new columns\n", "display(df.head())" ], - "execution_count": 63, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", - "0 -114.31 34.19 15.0 5612.0 1283.0 \n", - "1 -114.47 34.40 19.0 7650.0 1901.0 \n", - "2 -114.56 33.69 17.0 720.0 174.0 \n", - "3 -114.57 33.64 14.0 1501.0 337.0 \n", - "4 -114.57 33.57 20.0 1454.0 326.0 \n", - "\n", - " population households median_income median_house_value \\\n", - "0 1015.0 472.0 1.4936 66900.0 \n", - "1 1129.0 463.0 1.8200 80100.0 \n", - "2 333.0 117.0 1.6509 85700.0 \n", - "3 515.0 226.0 3.1917 73400.0 \n", - "4 624.0 262.0 1.9250 65500.0 \n", - "\n", - " rooms_per_household bedrooms_per_room population_per_household \n", - "0 11.889831 0.228617 2.150424 \n", - "1 16.522678 0.248497 2.438445 \n", - "2 6.153846 0.241667 2.846154 \n", - "3 6.641593 0.224517 2.278761 \n", - "4 5.549618 0.224209 2.381679 " - ], - "text/html": [ - "\n", - "
\n", - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_incomemedian_house_valuerooms_per_householdbedrooms_per_roompopulation_per_household
0-114.3134.1915.05612.01283.01015.0472.01.493666900.011.8898310.2286172.150424
1-114.4734.4019.07650.01901.01129.0463.01.820080100.016.5226780.2484972.438445
2-114.5633.6917.0720.0174.0333.0117.01.650985700.06.1538460.2416672.846154
3-114.5733.6414.01501.0337.0515.0226.03.191773400.06.6415930.2245172.278761
4-114.5733.5720.01454.0326.0624.0262.01.925065500.05.5496180.2242092.381679
\n", - "
\n", - "
\n", - "\n", - "
\n", - " \n", - "\n", - " \n", - "\n", - " \n", - "
\n", - "\n", - "\n", - "
\n", - " \n", - "\n", - "\n", - "\n", - " \n", - "
\n", - "\n", - "
\n", - "
\n" - ], - "application/vnd.google.colaboratory.intrinsic+json": { - "type": "dataframe", - "summary": "{\n \"name\": \"display(df\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.11216059914247682,\n \"min\": -114.57,\n \"max\": -114.31,\n \"num_unique_values\": 4,\n \"samples\": [\n -114.47,\n -114.57,\n -114.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3723842101915701,\n \"min\": 33.57,\n \"max\": 34.4,\n \"num_unique_values\": 5,\n \"samples\": [\n 34.4,\n 33.57,\n 33.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.5495097567963922,\n \"min\": 14.0,\n \"max\": 20.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 19.0,\n 20.0,\n 17.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3063.09350167441,\n \"min\": 720.0,\n \"max\": 7650.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 7650.0,\n 1454.0,\n 720.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 754.3743765531807,\n \"min\": 174.0,\n \"max\": 1901.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1901.0,\n 326.0,\n 174.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 337.36656621544466,\n \"min\": 333.0,\n \"max\": 1129.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1129.0,\n 624.0,\n 333.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 155.11447385721294,\n \"min\": 117.0,\n \"max\": 472.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 463.0,\n 262.0,\n 117.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6773416737511431,\n \"min\": 1.4936,\n \"max\": 3.1917,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.82,\n 1.925,\n 1.6509\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_house_value\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 8611.15555544086,\n \"min\": 65500.0,\n \"max\": 85700.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 80100.0,\n 65500.0,\n 85700.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rooms_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 4.740564553544767,\n \"min\": 5.549618320610687,\n \"max\": 16.52267818574514,\n \"num_unique_values\": 5,\n \"samples\": [\n 16.52267818574514,\n 5.549618320610687,\n 6.153846153846154\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"bedrooms_per_room\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.010982410746386893,\n \"min\": 0.22420907840440166,\n \"max\": 0.24849673202614378,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.24849673202614378,\n 0.22420907840440166,\n 0.24166666666666667\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.26269348663282854,\n \"min\": 2.1504237288135593,\n \"max\": 2.8461538461538463,\n \"num_unique_values\": 5,\n \"samples\": [\n 2.4384449244060473,\n 2.381679389312977,\n 2.8461538461538463\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" - } - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -4500,12 +1802,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 502 - }, - "id": "6b6e7b39", - "outputId": "f06136cc-5271-432a-c6f0-fceaed2f3653" + "id": "6b6e7b39" }, "source": [ "# Define the list of features, including the original and engineered ones\n", @@ -4526,435 +1823,8 @@ "print(\"\\nHead of y:\")\n", "display(y.head())" ], - "execution_count": 64, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Head of X_engineered:\n" - ] - }, - { - "output_type": "display_data", - "data": { - "text/plain": [ - " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", - "0 -114.31 34.19 15.0 5612.0 1283.0 \n", - "1 -114.47 34.40 19.0 7650.0 1901.0 \n", - "2 -114.56 33.69 17.0 720.0 174.0 \n", - "3 -114.57 33.64 14.0 1501.0 337.0 \n", - "4 -114.57 33.57 20.0 1454.0 326.0 \n", - "\n", - " population households median_income rooms_per_household \\\n", - "0 1015.0 472.0 1.4936 11.889831 \n", - "1 1129.0 463.0 1.8200 16.522678 \n", - "2 333.0 117.0 1.6509 6.153846 \n", - "3 515.0 226.0 3.1917 6.641593 \n", - "4 624.0 262.0 1.9250 5.549618 \n", - "\n", - " bedrooms_per_room population_per_household \n", - "0 0.228617 2.150424 \n", - "1 0.248497 2.438445 \n", - "2 0.241667 2.846154 \n", - "3 0.224517 2.278761 \n", - "4 0.224209 2.381679 " - ], - "text/html": [ - "\n", - "
\n", - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_incomerooms_per_householdbedrooms_per_roompopulation_per_household
0-114.3134.1915.05612.01283.01015.0472.01.493611.8898310.2286172.150424
1-114.4734.4019.07650.01901.01129.0463.01.820016.5226780.2484972.438445
2-114.5633.6917.0720.0174.0333.0117.01.65096.1538460.2416672.846154
3-114.5733.6414.01501.0337.0515.0226.03.19176.6415930.2245172.278761
4-114.5733.5720.01454.0326.0624.0262.01.92505.5496180.2242092.381679
\n", - "
\n", - "
\n", - "\n", - "
\n", - " \n", - "\n", - " \n", - "\n", - " \n", - "
\n", - "\n", - "\n", - "
\n", - " \n", - "\n", - "\n", - "\n", - " \n", - "
\n", - "\n", - "
\n", - "
\n" - ], - "application/vnd.google.colaboratory.intrinsic+json": { - "type": "dataframe", - "summary": "{\n \"name\": \"display(y\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.11216059914247682,\n \"min\": -114.57,\n \"max\": -114.31,\n \"num_unique_values\": 4,\n \"samples\": [\n -114.47,\n -114.57,\n -114.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3723842101915701,\n \"min\": 33.57,\n \"max\": 34.4,\n \"num_unique_values\": 5,\n \"samples\": [\n 34.4,\n 33.57,\n 33.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.5495097567963922,\n \"min\": 14.0,\n \"max\": 20.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 19.0,\n 20.0,\n 17.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3063.09350167441,\n \"min\": 720.0,\n \"max\": 7650.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 7650.0,\n 1454.0,\n 720.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 754.3743765531807,\n \"min\": 174.0,\n \"max\": 1901.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1901.0,\n 326.0,\n 174.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 337.36656621544466,\n \"min\": 333.0,\n \"max\": 1129.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 1129.0,\n 624.0,\n 333.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 155.11447385721294,\n \"min\": 117.0,\n \"max\": 472.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 463.0,\n 262.0,\n 117.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6773416737511431,\n \"min\": 1.4936,\n \"max\": 3.1917,\n \"num_unique_values\": 5,\n \"samples\": [\n 1.82,\n 1.925,\n 1.6509\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rooms_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 4.740564553544767,\n \"min\": 5.549618320610687,\n \"max\": 16.52267818574514,\n \"num_unique_values\": 5,\n \"samples\": [\n 16.52267818574514,\n 5.549618320610687,\n 6.153846153846154\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"bedrooms_per_room\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.010982410746386893,\n \"min\": 0.22420907840440166,\n \"max\": 0.24849673202614378,\n \"num_unique_values\": 5,\n \"samples\": [\n 0.24849673202614378,\n 0.22420907840440166,\n 0.24166666666666667\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population_per_household\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.26269348663282854,\n \"min\": 2.1504237288135593,\n \"max\": 2.8461538461538463,\n \"num_unique_values\": 5,\n \"samples\": [\n 2.4384449244060473,\n 2.381679389312977,\n 2.8461538461538463\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" - } - }, - "metadata": {} - }, - { - "output_type": "stream", - "name": "stdout", - "text": [ - "\n", - "Head of y:\n" - ] - }, - { - "output_type": "display_data", - "data": { - "text/plain": [ - "0 66900.0\n", - "1 80100.0\n", - "2 85700.0\n", - "3 73400.0\n", - "4 65500.0\n", - "Name: median_house_value, dtype: float64" - ], - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
median_house_value
066900.0
180100.0
285700.0
373400.0
465500.0
\n", - "

" - ] - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -4982,11 +1852,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "6f346b39", - "outputId": "a16ab0c9-1db9-4334-b3d9-4f55acf89bb5" + "id": "6f346b39" }, "source": [ "from sklearn.model_selection import train_test_split\n", @@ -5000,19 +1866,8 @@ "print(f\"Shape of y_train_engineered: {y_train_engineered.shape}\")\n", "print(f\"Shape of y_test_engineered: {y_test_engineered.shape}\")" ], - "execution_count": 65, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Shape of X_train_engineered: (13600, 11)\n", - "Shape of X_test_engineered: (3400, 11)\n", - "Shape of y_train_engineered: (13600,)\n", - "Shape of y_test_engineered: (3400,)\n" - ] - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -5040,11 +1895,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "f490841e", - "outputId": "38125196-8ed4-46b9-8262-c7a523495540" + "id": "f490841e" }, "source": [ "from sklearn.linear_model import LinearRegression\n", @@ -5057,16 +1908,8 @@ "\n", "print(\"Linear Regression model trained successfully using engineered features.\")" ], - "execution_count": 66, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Linear Regression model trained successfully using engineered features.\n" - ] - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -5094,11 +1937,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "f7df2324", - "outputId": "8f70c37a-28f3-4296-a098-80d6b201be3a" + "id": "f7df2324" }, "source": [ "from sklearn.metrics import mean_squared_error, r2_score\n", @@ -5116,17 +1955,8 @@ "print(f\"Model with Engineered Features Mean Squared Error (MSE): {mse_engineered}\")\n", "print(f\"Model with Engineered Features R-squared (R2) Score: {r2_engineered}\")" ], - "execution_count": 67, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Model with Engineered Features Mean Squared Error (MSE): 4552463037.856813\n", - "Model with Engineered Features R-squared (R2) Score: 0.6696049644359181\n" - ] - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -5154,11 +1984,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "0879e9ba", - "outputId": "d5679ef9-6dec-4d78-b7eb-25f46f387c92" + "id": "0879e9ba" }, "source": [ "# Print the performance metrics for the Linear Regression model trained on original features\n", @@ -5185,22 +2011,8 @@ "else:\n", " print(\"Summary: Both Linear Regression models performed similarly based on R2.\")" ], - "execution_count": 68, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Linear Regression Model (Original Features) MSE: 4634658406.223264\n", - "Linear Regression Model (Original Features) R2 Score: 0.6636396350243869\n", - "Linear Regression Model (Engineered Features) MSE: 4552463037.856813\n", - "Linear Regression Model (Engineered Features) R2 Score: 0.6696049644359181\n", - "\n", - "Summary: The Linear Regression model with engineered features performed better than the model with original features based on MSE (lower is better).\n", - "Summary: The Linear Regression model with engineered features performed better than the model with original features based on R2 (higher is better).\n" - ] - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -5228,12 +2040,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 564 - }, - "id": "29c83a42", - "outputId": "3cc8eb9a-ad15-47cd-c8ca-de2eadd1d473" + "id": "29c83a42" }, "source": [ "import matplotlib.pyplot as plt\n", @@ -5258,19 +2065,8 @@ "# Show the plot\n", "plt.show()" ], - "execution_count": 69, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": {} - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -5293,6 +2089,421 @@ "* The engineered features slightly improved the Linear Regression model's performance, suggesting that these ratios capture some valuable information about housing values. Further investigation into other feature engineering techniques or non-linear models could potentially yield more significant improvements.\n", "* Visualizing the actual vs. predicted values confirms that the model's predictions generally follow the trend of the actual values, although there is still a notable spread, particularly for higher house values, indicating room for further model improvement.\n" ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "077a42d1" + }, + "source": [ + "# Task\n", + "Explore Ridge or Lasso Regression for hyperparameter tuning." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "3b52b9ea" + }, + "source": [ + "## Choose a model for tuning\n", + "\n", + "### Subtask:\n", + "Select either Ridge or Lasso Regression for hyperparameter tuning.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "630393a2" + }, + "source": [ + "## Define the parameter grid\n", + "\n", + "### Subtask:\n", + "Specify the range of hyperparameter values to search over.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "5a0d3854" + }, + "source": [ + "**Reasoning**:\n", + "Define a range of alpha values for hyperparameter tuning of the Ridge model and store them in a dictionary named `param_grid`.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "16943d5b" + }, + "source": [ + "import numpy as np\n", + "\n", + "# Choose a range of alpha values for Ridge Regression\n", + "# Using a logarithmic scale from 0.1 to 100.\n", + "alpha_range = np.logspace(-1, 2, 100)\n", + "\n", + "# Create a dictionary named param_grid\n", + "param_grid = {'alpha': alpha_range}\n", + "\n", + "print(\"Hyperparameter grid for Ridge Regression:\")\n", + "print(param_grid)" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "a699be97" + }, + "source": [ + "## Set up cross-validation\n", + "\n", + "### Subtask:\n", + "Choose a cross-validation strategy (e.g., K-Fold) to evaluate different parameter combinations robustly.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ea3e61d1" + }, + "source": [ + "**Reasoning**:\n", + "Instantiate a KFold object with the specified parameters for cross-validation.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "b614f69b" + }, + "source": [ + "from sklearn.model_selection import KFold\n", + "\n", + "# Instantiate a KFold object\n", + "# n_splits=5 is a common choice for K-Fold cross-validation\n", + "# shuffle=True shuffles the data before splitting, which is important if the data\n", + "# has any inherent order.\n", + "# random_state ensures that the shuffling is the same each time the code is run,\n", + "# making the results reproducible.\n", + "kf = KFold(n_splits=5, shuffle=True, random_state=42)\n", + "\n", + "print(\"KFold cross-validation strategy instantiated.\")" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "67bc814f" + }, + "source": [ + "## Perform hyperparameter search\n", + "\n", + "### Subtask:\n", + "Use a tuning method (e.g., GridSearchCV or RandomizedSearchCV) to find the best hyperparameters.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "58664285" + }, + "source": [ + "**Reasoning**:\n", + "Instantiate and fit GridSearchCV to find the best hyperparameters for the Ridge model using the defined parameter grid and cross-validation strategy. Then, print the best parameters and best score.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "4be9680c" + }, + "source": [ + "from sklearn.model_selection import GridSearchCV\n", + "\n", + "# Instantiate a GridSearchCV object\n", + "# estimator: The model to tune (ridge_model)\n", + "# param_grid: The grid of hyperparameters to search over\n", + "# scoring: The metric to optimize (Negative Mean Squared Error, as GridSearchCV maximizes scores)\n", + "# cv: The cross-validation strategy (kf)\n", + "grid_search = GridSearchCV(estimator=ridge_model, param_grid=param_grid,\n", + " scoring='neg_mean_squared_error', cv=kf)\n", + "\n", + "# Fit the GridSearchCV object to the training data\n", + "grid_search.fit(X_train_engineered, y_train_engineered)\n", + "\n", + "# Print the best hyperparameters found by the search\n", + "print(\"Best hyperparameters found by GridSearchCV:\")\n", + "print(grid_search.best_params_)\n", + "\n", + "# Print the best cross-validation score achieved during the search\n", + "# Note: The score is negative MSE, so we take the negative to get the actual MSE\n", + "print(\"\\nBest cross-validation MSE score:\")\n", + "print(-grid_search.best_score_)" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "c34eafb5" + }, + "source": [ + "## Train the final model\n", + "\n", + "### Subtask:\n", + "Train the chosen model with the best hyperparameters on the entire training set.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "2bb1ff8e" + }, + "source": [ + "**Reasoning**:\n", + "Get the best estimator from the GridSearchCV object and train it on the entire engineered training data.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "f0c2ff41" + }, + "source": [ + "# Get the best estimator from the GridSearchCV object\n", + "best_ridge_model = grid_search.best_estimator_\n", + "\n", + "# Train the best estimator on the entire engineered training data\n", + "best_ridge_model.fit(X_train_engineered, y_train_engineered)\n", + "\n", + "print(\"Best Ridge Regression model trained on the entire engineered training set.\")" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "cfdf5774" + }, + "source": [ + "## Evaluate the tuned model\n", + "\n", + "### Subtask:\n", + "Evaluate the performance of the tuned model on the testing data.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "1de3530d" + }, + "source": [ + "**Reasoning**:\n", + "Calculate MSE and R2 for the tuned Ridge model using the test data and predictions, and print the results.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "4c2707bc" + }, + "source": [ + "from sklearn.metrics import mean_squared_error, r2_score\n", + "\n", + "# Use the trained best_ridge_model to make predictions on the engineered testing features\n", + "y_pred_tuned_ridge = best_ridge_model.predict(X_test_engineered)\n", + "\n", + "# Calculate the Mean Squared Error (MSE) for the tuned Ridge model\n", + "mse_tuned_ridge = mean_squared_error(y_test_engineered, y_pred_tuned_ridge)\n", + "\n", + "# Calculate the R-squared score for the tuned Ridge model\n", + "r2_tuned_ridge = r2_score(y_test_engineered, y_pred_tuned_ridge)\n", + "\n", + "# Print the calculated metrics for the tuned Ridge model\n", + "print(f\"Tuned Ridge Model Mean Squared Error (MSE): {mse_tuned_ridge}\")\n", + "print(f\"Tuned Ridge Model R-squared (R2) Score: {r2_tuned_ridge}\")" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "1c16553d" + }, + "source": [ + "## Compare with previous models\n", + "\n", + "### Subtask:\n", + "Compare the performance of the tuned model to the previously trained models.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "a0724b9c" + }, + "source": [ + "**Reasoning**:\n", + "Print the performance metrics for all models and compare them to summarize the impact of feature engineering and hyperparameter tuning.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "342f0d26" + }, + "source": [ + "# Print the performance metrics for all models for comparison\n", + "\n", + "# Initial Linear Regression model (original features)\n", + "print(f\"Initial Linear Regression Model (Original Features) MSE: {mse}\")\n", + "print(f\"Initial Linear Regression Model (Original Features) R2 Score: {r2}\")\n", + "\n", + "# Ridge Regression model (original features, default hyperparameters)\n", + "print(f\"Ridge Regression Model (Original Features, Default Hyperparameters) MSE: {mse_ridge}\")\n", + "print(f\"Ridge Regression Model (Original Features, Default Hyperparameters) R2 Score: {r2_ridge}\")\n", + "\n", + "# Linear Regression model (engineered features)\n", + "print(f\"Linear Regression Model (Engineered Features) MSE: {mse_engineered}\")\n", + "print(f\"Linear Regression Model (Engineered Features) R2 Score: {r2_engineered}\")\n", + "\n", + "# Tuned Ridge Regression model (engineered features, tuned hyperparameters)\n", + "print(f\"Tuned Ridge Regression Model (Engineered Features, Tuned Hyperparameters) MSE: {mse_tuned_ridge}\")\n", + "print(f\"Tuned Ridge Regression Model (Engineered Features, Tuned Hyperparameters) R2 Score: {r2_tuned_ridge}\")\n", + "\n", + "# Summarize the findings\n", + "print(\"\\n--- Performance Comparison Summary ---\")\n", + "\n", + "# Compare MSE\n", + "if mse_tuned_ridge < mse_engineered and mse_tuned_ridge < mse_ridge and mse_tuned_ridge < mse:\n", + " print(\"The Tuned Ridge Regression model with engineered features performed the best based on MSE (lower is better).\")\n", + "elif mse_engineered < mse_tuned_ridge and mse_engineered < mse_ridge and mse_engineered < mse:\n", + " print(\"The Linear Regression model with engineered features performed the best based on MSE (lower is better).\")\n", + "elif mse_ridge < mse_tuned_ridge and mse_ridge < mse_engineered and mse_ridge < mse:\n", + " print(\"The Ridge Regression model with default hyperparameters performed the best based on MSE (lower is better).\")\n", + "else:\n", + " print(\"The Initial Linear Regression model with original features performed the best based on MSE (lower is better).\")\n", + "\n", + "# Compare R2\n", + "if r2_tuned_ridge > r2_engineered and r2_tuned_ridge > r2_ridge and r2_tuned_ridge > r2:\n", + " print(\"The Tuned Ridge Regression model with engineered features performed the best based on R2 (higher is better).\")\n", + "elif r2_engineered > r2_tuned_ridge and r2_engineered > r2_ridge and r2_engineered > r2:\n", + " print(\"The Linear Regression model with engineered features performed the best based on R2 (higher is better).\")\n", + "elif r2_ridge > r2_tuned_ridge and r2_ridge > r2_engineered and r2_ridge > r2:\n", + " print(\"The Ridge Regression model with default hyperparameters performed the best based on R2 (higher is better).\")\n", + "else:\n", + " print(\"The Initial Linear Regression model with original features performed the best based on R2 (higher is better).\")\n", + "\n", + "print(\"\\nImpact of Feature Engineering and Hyperparameter Tuning:\")\n", + "if mse_engineered < mse and r2_engineered > r2:\n", + " print(\"- Feature engineering improved the performance of the Linear Regression model.\")\n", + "else:\n", + " print(\"- Feature engineering did not significantly improve the performance of the Linear Regression model.\")\n", + "\n", + "if mse_tuned_ridge < mse_engineered and r2_tuned_ridge > r2_engineered:\n", + " print(\"- Hyperparameter tuning of the Ridge model with engineered features further improved performance compared to the Linear Regression model with engineered features.\")\n", + "else:\n", + " print(\"- Hyperparameter tuning of the Ridge model with engineered features did not significantly improve performance compared to the Linear Regression model with engineered features.\")\n", + "\n", + "if mse_tuned_ridge < mse_ridge and r2_tuned_ridge > r2_ridge:\n", + " print(\"- Hyperparameter tuning of the Ridge model with engineered features improved performance compared to the Ridge model with default hyperparameters.\")\n", + "else:\n", + " print(\"- Hyperparameter tuning of the Ridge model with engineered features did not significantly improve performance compared to the Ridge model with default hyperparameters.\")" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ae3a5dad" + }, + "source": [ + "## Visualize results (optional)\n", + "\n", + "### Subtask:\n", + "Visualize the predictions of the tuned model.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "8f7dba0d" + }, + "source": [ + "**Reasoning**:\n", + "Create a scatter plot of the actual vs. predicted values from the tuned Ridge model, add labels, title, a diagonal line for perfect predictions, and a grid.\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "0845a2f0" + }, + "source": [ + "# Create a scatter plot of actual vs. predicted values for the tuned Ridge model\n", + "plt.figure(figsize=(8, 6))\n", + "plt.scatter(y_test_engineered, y_pred_tuned_ridge, alpha=0.5)\n", + "\n", + "# Add labels and title\n", + "plt.xlabel('Actual Values')\n", + "plt.ylabel('Predicted Values')\n", + "plt.title('Actual vs. Predicted Values (Tuned Ridge Regression)')\n", + "\n", + "# Add a diagonal line for perfect predictions\n", + "# Determine the range for the diagonal line based on both actual and predicted values\n", + "plot_range_tuned = [min(y_test_engineered.min(), y_pred_tuned_ridge.min()), max(y_test_engineered.max(), y_pred_tuned_ridge.max())]\n", + "plt.plot(plot_range_tuned, plot_range_tuned, color='red', linestyle='--')\n", + "\n", + "# Add a grid\n", + "plt.grid(True)\n", + "\n", + "# Show the plot\n", + "plt.show()" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "dc0dada1" + }, + "source": [ + "## Summary:\n", + "\n", + "### Data Analysis Key Findings\n", + "\n", + "* The hyperparameter tuning process for the Ridge Regression model with engineered features identified an optimal `alpha` of 0.1.\n", + "* The best cross-validation Mean Squared Error (MSE) achieved during the grid search was approximately 5,070,263,224.18.\n", + "* The tuned Ridge Regression model with engineered features achieved a Mean Squared Error (MSE) of approximately 4,552,359,506.89 and an R-squared (R2) score of approximately 0.67 on the testing data.\n", + "* Feature engineering improved the performance of the Linear Regression model compared to using original features.\n", + "* Hyperparameter tuning of the Ridge model with engineered features further improved performance compared to both the Linear Regression model with engineered features and the Ridge model with default hyperparameters.\n", + "* The Tuned Ridge Regression model with engineered features was the best-performing model among those evaluated, based on the lowest MSE and highest R2 score.\n", + "\n", + "### Insights or Next Steps\n", + "\n", + "* The visualization of actual vs. predicted values for the tuned Ridge model shows a reasonable spread around the perfect prediction line, suggesting the model captures a significant portion of the variance but still has notable errors for some predictions.\n", + "* Further exploration could involve trying other regression algorithms (e.g., Lasso, ElasticNet, Gradient Boosting) or more advanced feature engineering techniques to potentially improve the model's performance further.\n" + ] } ], "metadata": { From a366ca85de4506b23d7ba4aaf5d3c186c10d1230 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 4 Oct 2025 06:43:31 +0600 Subject: [PATCH 22/28] Created using Colab --- ...Getting_started_with_google_colab_ai.ipynb | 105 +++++++++--------- 1 file changed, 54 insertions(+), 51 deletions(-) diff --git a/notebooks/Getting_started_with_google_colab_ai.ipynb b/notebooks/Getting_started_with_google_colab_ai.ipynb index f7df2d0..256a5df 100644 --- a/notebooks/Getting_started_with_google_colab_ai.ipynb +++ b/notebooks/Getting_started_with_google_colab_ai.ipynb @@ -31,7 +31,7 @@ { "metadata": { "id": "Ucchuu5vV3Jp", - "outputId": "ef9b86d4-4187-4f2b-c779-bd15733480ce", + "outputId": "112c3376-3eb7-4ea4-f2fd-938de9ea87e9", "colab": { "base_uri": "https://localhost:8080/" } @@ -52,10 +52,10 @@ ] }, "metadata": {}, - "execution_count": 114 + "execution_count": 125 } ], - "execution_count": 114 + "execution_count": 125 }, { "metadata": { @@ -78,9 +78,9 @@ "id": "R7taibpc7x2l", "colab": { "base_uri": "https://localhost:8080/", - "height": 373 + "height": 339 }, - "outputId": "bd5aea0c-5846-417f-a849-bd554f5a565f" + "outputId": "ac9ac044-b1fc-4a45-e5a1-1854b28cdd68" }, "cell_type": "code", "source": [ @@ -109,7 +109,30 @@ ] } ], - "execution_count": 115 + "execution_count": 126 + }, + { + "cell_type": "markdown", + "metadata": { + "id": "45ff94ed" + }, + "source": [ + "## Summary:\n", + "\n", + "### Data Analysis Key Findings\n", + "\n", + "* The hyperparameter tuning process for the Ridge Regression model with engineered features identified an optimal `alpha` of 0.1.\n", + "* The best cross-validation Mean Squared Error (MSE) achieved during the grid search was approximately 5,070,263,224.18.\n", + "* The tuned Ridge Regression model with engineered features achieved a Mean Squared Error (MSE) of approximately 4,552,359,506.89 and an R-squared (R2) score of approximately 0.67 on the testing data.\n", + "* Feature engineering improved the performance of the Linear Regression model compared to using original features.\n", + "* Hyperparameter tuning of the Ridge model with engineered features further improved performance compared to both the Linear Regression model with engineered features and the Ridge model with default hyperparameters.\n", + "* The Tuned Ridge Regression model with engineered features was the best-performing model among those evaluated, based on the lowest MSE and highest R2 score.\n", + "\n", + "### Insights or Next Steps\n", + "\n", + "* The visualization of actual vs. predicted values for the tuned Ridge model shows a reasonable spread around the perfect prediction line, suggesting the model captures a significant portion of the variance but still has notable errors for some predictions.\n", + "* Further exploration could involve trying other regression algorithms (e.g., Lasso, ElasticNet, Gradient Boosting) or more advanced feature engineering techniques to potentially improve the model's performance further." + ] }, { "cell_type": "markdown", @@ -136,12 +159,17 @@ { "cell_type": "code", "metadata": { - "id": "775a47d5" + "colab": { + "base_uri": "https://localhost:8080/", + "height": 564 + }, + "id": "775a47d5", + "outputId": "53e4846c-731c-4dc4-bb8b-2c8ce5f939e3" }, "source": [ "# Create a scatter plot of actual vs. predicted values for the tuned Ridge model\n", "plt.figure(figsize=(8, 6))\n", - "plt.scatter(y_test_engineered, y_pred_tuned_ridge, alpha=0.5)\n", + "plt.scatter(y_test_engineered, y_pred_tuned_ridge, alpha=0.5) # Scatter plot with transparency\n", "\n", "# Add labels and title\n", "plt.xlabel('Actual Values')\n", @@ -151,7 +179,7 @@ "# Add a diagonal line for perfect predictions\n", "# Determine the range for the diagonal line based on both actual and predicted values\n", "plot_range_tuned = [min(y_test_engineered.min(), y_pred_tuned_ridge.min()), max(y_test_engineered.max(), y_pred_tuned_ridge.max())]\n", - "plt.plot(plot_range_tuned, plot_range_tuned, color='red', linestyle='--')\n", + "plt.plot(plot_range_tuned, plot_range_tuned, color='red', linestyle='--') # Plotting the diagonal line\n", "\n", "# Add a grid\n", "plt.grid(True)\n", @@ -159,8 +187,19 @@ "# Show the plot\n", "plt.show()" ], - "execution_count": null, - "outputs": [] + "execution_count": 127, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": {} + } + ] }, { "cell_type": "markdown", @@ -187,11 +226,7 @@ { "cell_type": "code", "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "fead6e74", - "outputId": "f0fc29d4-02f9-4279-cca3-d9412685208d" + "id": "fead6e74" }, "source": [ "from sklearn.metrics import mean_squared_error, r2_score\n", @@ -248,40 +283,8 @@ "else:\n", " print(\"- Hyperparameter tuning of the Ridge model with engineered features did not significantly improve performance compared to the Ridge model with default hyperparameters.\")" ], - "execution_count": 116, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "--- Model Performance Comparison ---\n", - "\n", - "Initial Linear Regression (Original Features):\n", - " Mean Squared Error (MSE): 4634658406.22\n", - " R-squared (R2) Score: 0.6636\n", - "\n", - "Ridge Regression (Original Features, Default):\n", - " Mean Squared Error (MSE): 4634651616.32\n", - " R-squared (R2) Score: 0.6636\n", - "\n", - "Linear Regression (Engineered Features):\n", - " Mean Squared Error (MSE): 4552463037.86\n", - " R-squared (R2) Score: 0.6696\n", - "\n", - "Tuned Ridge Regression (Engineered Features, Tuned):\n", - " Mean Squared Error (MSE): 4552359506.89\n", - " R-squared (R2) Score: 0.6696\n", - "\n", - "--- Performance Comparison Summary ---\n", - "The Tuned Ridge Regression (Engineered Features, Tuned) performed the best based on both MSE (lower is better) and R2 (higher is better).\n", - "\n", - "Impact of Feature Engineering and Hyperparameter Tuning:\n", - "- Feature engineering improved the performance of the Linear Regression model.\n", - "- Hyperparameter tuning of the Ridge model with engineered features further improved performance compared to the Linear Regression model with engineered features.\n", - "- Hyperparameter tuning of the Ridge model with engineered features improved performance compared to the Ridge model with default hyperparameters.\n" - ] - } - ] + "execution_count": null, + "outputs": [] }, { "cell_type": "markdown", @@ -400,7 +403,7 @@ "metadata": { "id": "FoTxyfYmhYPH" }, - "execution_count": 116, + "execution_count": null, "outputs": [] }, { From cef94803828fe8dfd9d4481af5b5a245fe7048ee Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 4 Oct 2025 07:46:18 +0600 Subject: [PATCH 23/28] Created using Colab --- ...Getting_started_with_google_colab_ai.ipynb | 2455 +---------------- 1 file changed, 98 insertions(+), 2357 deletions(-) diff --git a/notebooks/Getting_started_with_google_colab_ai.ipynb b/notebooks/Getting_started_with_google_colab_ai.ipynb index 256a5df..12c72a8 100644 --- a/notebooks/Getting_started_with_google_colab_ai.ipynb +++ b/notebooks/Getting_started_with_google_colab_ai.ipynb @@ -31,7 +31,7 @@ { "metadata": { "id": "Ucchuu5vV3Jp", - "outputId": "112c3376-3eb7-4ea4-f2fd-938de9ea87e9", + "outputId": "553795f3-2666-42d6-dc8e-074932326207", "colab": { "base_uri": "https://localhost:8080/" } @@ -52,10 +52,10 @@ ] }, "metadata": {}, - "execution_count": 125 + "execution_count": 12 } ], - "execution_count": 125 + "execution_count": 12 }, { "metadata": { @@ -80,7 +80,7 @@ "base_uri": "https://localhost:8080/", "height": 339 }, - "outputId": "ac9ac044-b1fc-4a45-e5a1-1854b28cdd68" + "outputId": "ff5e983a-b672-4b14-d791-a8c7900995a9" }, "cell_type": "code", "source": [ @@ -109,2404 +109,145 @@ ] } ], - "execution_count": 126 + "execution_count": 13 }, { - "cell_type": "markdown", - "metadata": { - "id": "45ff94ed" - }, - "source": [ - "## Summary:\n", - "\n", - "### Data Analysis Key Findings\n", - "\n", - "* The hyperparameter tuning process for the Ridge Regression model with engineered features identified an optimal `alpha` of 0.1.\n", - "* The best cross-validation Mean Squared Error (MSE) achieved during the grid search was approximately 5,070,263,224.18.\n", - "* The tuned Ridge Regression model with engineered features achieved a Mean Squared Error (MSE) of approximately 4,552,359,506.89 and an R-squared (R2) score of approximately 0.67 on the testing data.\n", - "* Feature engineering improved the performance of the Linear Regression model compared to using original features.\n", - "* Hyperparameter tuning of the Ridge model with engineered features further improved performance compared to both the Linear Regression model with engineered features and the Ridge model with default hyperparameters.\n", - "* The Tuned Ridge Regression model with engineered features was the best-performing model among those evaluated, based on the lowest MSE and highest R2 score.\n", - "\n", - "### Insights or Next Steps\n", - "\n", - "* The visualization of actual vs. predicted values for the tuned Ridge model shows a reasonable spread around the perfect prediction line, suggesting the model captures a significant portion of the variance but still has notable errors for some predictions.\n", - "* Further exploration could involve trying other regression algorithms (e.g., Lasso, ElasticNet, Gradient Boosting) or more advanced feature engineering techniques to potentially improve the model's performance further." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "b1fd99c3" - }, - "source": [ - "## Visualize results (optional)\n", - "\n", - "### Subtask:\n", - "Visualize the predictions of the tuned model." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "3d084318" - }, - "source": [ - "**Reasoning**:\n", - "Create a scatter plot of the actual vs. predicted values from the tuned Ridge model, add labels, title, a diagonal line for perfect predictions, and a grid." - ] - }, - { - "cell_type": "code", - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/", - "height": 564 - }, - "id": "775a47d5", - "outputId": "53e4846c-731c-4dc4-bb8b-2c8ce5f939e3" - }, - "source": [ - "# Create a scatter plot of actual vs. predicted values for the tuned Ridge model\n", - "plt.figure(figsize=(8, 6))\n", - "plt.scatter(y_test_engineered, y_pred_tuned_ridge, alpha=0.5) # Scatter plot with transparency\n", - "\n", - "# Add labels and title\n", - "plt.xlabel('Actual Values')\n", - "plt.ylabel('Predicted Values')\n", - "plt.title('Actual vs. Predicted Values (Tuned Ridge Regression)')\n", - "\n", - "# Add a diagonal line for perfect predictions\n", - "# Determine the range for the diagonal line based on both actual and predicted values\n", - "plot_range_tuned = [min(y_test_engineered.min(), y_pred_tuned_ridge.min()), max(y_test_engineered.max(), y_pred_tuned_ridge.max())]\n", - "plt.plot(plot_range_tuned, plot_range_tuned, color='red', linestyle='--') # Plotting the diagonal line\n", - "\n", - "# Add a grid\n", - "plt.grid(True)\n", - "\n", - "# Show the plot\n", - "plt.show()" - ], - "execution_count": 127, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "
" - ], - "image/png": "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\n" - }, - "metadata": {} - } - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "458db442" - }, - "source": [ - "## Compare with previous models\n", - "\n", - "### Subtask:\n", - "Compare the performance of the tuned model to the previously trained models." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "28ab2164" - }, - "source": [ - "**Reasoning**:\n", - "Print the performance metrics for all models and compare them to summarize the impact of feature engineering and hyperparameter tuning." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "fead6e74" - }, - "source": [ - "from sklearn.metrics import mean_squared_error, r2_score\n", - "import pandas as pd\n", - "\n", - "# Store performance metrics in a dictionary\n", - "performance_metrics = {\n", - " \"Initial Linear Regression (Original Features)\": {\"MSE\": mse, \"R2\": r2},\n", - " \"Ridge Regression (Original Features, Default)\": {\"MSE\": mse_ridge, \"R2\": r2_ridge},\n", - " \"Linear Regression (Engineered Features)\": {\"MSE\": mse_engineered, \"R2\": r2_engineered},\n", - " \"Tuned Ridge Regression (Engineered Features, Tuned)\": {\"MSE\": mse_tuned_ridge, \"R2\": r2_tuned_ridge}\n", - "}\n", - "\n", - "# Print the performance metrics in a formatted way\n", - "print(\"--- Model Performance Comparison ---\")\n", - "for model_name, metrics in performance_metrics.items():\n", - " print(f\"\\n{model_name}:\")\n", - " print(f\" Mean Squared Error (MSE): {metrics['MSE']:.2f}\")\n", - " print(f\" R-squared (R2) Score: {metrics['R2']:.4f}\")\n", - "\n", - "# Summarize the findings\n", - "print(\"\\n--- Performance Comparison Summary ---\")\n", - "\n", - "# Determine the best model based on MSE and R2\n", - "best_mse_model = min(performance_metrics, key=lambda k: performance_metrics[k]['MSE'])\n", - "best_r2_model = max(performance_metrics, key=lambda k: performance_metrics[k]['R2'])\n", - "\n", - "if best_mse_model == best_r2_model:\n", - " print(f\"The {best_mse_model} performed the best based on both MSE (lower is better) and R2 (higher is better).\")\n", - "else:\n", - " print(f\"The {best_mse_model} performed the best based on MSE (lower is better).\")\n", - " print(f\"The {best_r2_model} performed the best based on R2 (higher is better).\")\n", - "\n", - "print(\"\\nImpact of Feature Engineering and Hyperparameter Tuning:\")\n", - "\n", - "# Compare Engineered Linear Regression to Initial Linear Regression\n", - "if performance_metrics[\"Linear Regression (Engineered Features)\"][\"MSE\"] < performance_metrics[\"Initial Linear Regression (Original Features)\"][\"MSE\"] \\\n", - " and performance_metrics[\"Linear Regression (Engineered Features)\"][\"R2\"] > performance_metrics[\"Initial Linear Regression (Original Features)\"][\"R2\"]:\n", - " print(\"- Feature engineering improved the performance of the Linear Regression model.\")\n", - "else:\n", - " print(\"- Feature engineering did not significantly improve the performance of the Linear Regression model.\")\n", - "\n", - "# Compare Tuned Ridge (Engineered) to Linear Regression (Engineered)\n", - "if performance_metrics[\"Tuned Ridge Regression (Engineered Features, Tuned)\"][\"MSE\"] < performance_metrics[\"Linear Regression (Engineered Features)\"][\"MSE\"] \\\n", - " and performance_metrics[\"Tuned Ridge Regression (Engineered Features, Tuned)\"][\"R2\"] > performance_metrics[\"Linear Regression (Engineered Features)\"][\"R2\"]:\n", - " print(\"- Hyperparameter tuning of the Ridge model with engineered features further improved performance compared to the Linear Regression model with engineered features.\")\n", - "else:\n", - " print(\"- Hyperparameter tuning of the Ridge model with engineered features did not significantly improve performance compared to the Linear Regression model with engineered features.\")\n", - "\n", - "# Compare Tuned Ridge (Engineered) to Default Ridge (Original)\n", - "if performance_metrics[\"Tuned Ridge Regression (Engineered Features, Tuned)\"][\"MSE\"] < performance_metrics[\"Ridge Regression (Original Features, Default)\"][\"MSE\"] \\\n", - " and performance_metrics[\"Tuned Ridge Regression (Engineered Features, Tuned)\"][\"R2\"] > performance_metrics[\"Ridge Regression (Original Features, Default)\"][\"R2\"]:\n", - " print(\"- Hyperparameter tuning of the Ridge model with engineered features improved performance compared to the Ridge model with default hyperparameters.\")\n", - "else:\n", - " print(\"- Hyperparameter tuning of the Ridge model with engineered features did not significantly improve performance compared to the Ridge model with default hyperparameters.\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "f640e6d4" - }, - "source": [ - "## Train the final model\n", - "\n", - "### Subtask:\n", - "Train the chosen model with the best hyperparameters on the entire training set." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "3864b74e" - }, - "source": [ - "**Reasoning**:\n", - "Get the best estimator from the GridSearchCV object and train it on the entire engineered training data." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "eb1dce30" - }, - "source": [ - "# Get the best estimator from the GridSearchCV object\n", - "best_ridge_model = grid_search.best_estimator_\n", - "\n", - "# Train the best estimator on the entire engineered training data\n", - "best_ridge_model.fit(X_train_engineered, y_train_engineered)\n", - "\n", - "print(\"Best Ridge Regression model trained on the entire engineered training set.\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "c3867202" - }, - "source": [ - "## Update features for modeling\n", - "\n", - "### Subtask:\n", - "Select the updated set of features (including the new ones) for training the model." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "56aa010d" - }, - "source": [ - "import matplotlib.pyplot as plt\n", - "import pandas as pd\n", - "\n", - "# Select the log-transformed features to visualize\n", - "features_to_visualize_log = ['total_rooms_log', 'median_income_log']\n", - "\n", - "# Create histograms for each selected log-transformed feature\n", - "df[features_to_visualize_log].hist(bins=50, figsize=(10, 5))\n", - "plt.tight_layout() # Adjust layout to prevent overlap\n", - "plt.show()" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "code", - "metadata": { - "id": "2c9d624d" - }, - "source": [ - "# Update the features list to include log-transformed features and exclude original skewed ones\n", - "features_engineered_transformed = ['longitude', 'latitude', 'housing_median_age',\n", - " 'total_bedrooms', 'population', 'households',\n", - " 'rooms_per_household', 'bedrooms_per_room', 'population_per_household',\n", - " 'total_rooms_log', 'median_income_log']\n", - "\n", - "# Create a new DataFrame X_engineered_transformed by selecting these columns from df\n", - "X_engineered_transformed = df[features_engineered_transformed]\n", - "\n", - "# Keep the target variable y as it is (the 'median_house_value' column from df)\n", - "# y was already defined in a previous step as df['median_house_value']\n", - "\n", - "# Print the head of X_engineered_transformed and y to verify\n", - "print(\"Head of X_engineered_transformed:\")\n", - "display(X_engineered_transformed.head())\n", - "\n", - "print(\"\\nHead of y:\")\n", - "display(y.head())" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "33d4932e" - }, - "source": [ - "## Apply Transformations to Skewed Features\n", - "\n", - "### Subtask:\n", - "Apply log transformation to skewed numerical features identified during exploration." - ] - }, - { - "cell_type": "code", - "source": [], - "metadata": { - "id": "FoTxyfYmhYPH" - }, - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "50c1cff1" - }, - "source": [ - "**Reasoning**:\n", - "Apply log transformation to 'total_rooms' and 'median_income' to reduce skewness and display the head of the DataFrame to show the transformed columns." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "37e75b8c" - }, - "source": [ - "import numpy as np\n", - "\n", - "# Apply log transformation to 'total_rooms' and 'median_income'\n", - "# Add a small constant (e.g., 1) before taking the log to handle potential zero values,\n", - "# although based on describe() output, these columns don't have zeros.\n", - "# Using np.log1p which calculates log(1+x) is a robust way to handle this.\n", - "df['total_rooms_log'] = np.log1p(df['total_rooms'])\n", - "df['median_income_log'] = np.log1p(df['median_income'])\n", - "\n", - "# Display the head of the DataFrame to verify the new transformed columns\n", - "display(df.head())" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "code", - "metadata": { - "id": "c4b589c8" - }, - "source": [ - "import matplotlib.pyplot as plt\n", - "import pandas as pd\n", - "\n", - "# Select a few numerical features to visualize\n", - "features_to_visualize = ['housing_median_age', 'total_rooms', 'median_income', 'median_house_value']\n", - "\n", - "# Create histograms for each selected feature\n", - "df[features_to_visualize].hist(bins=50, figsize=(15, 10))\n", - "plt.tight_layout() # Adjust layout to prevent overlap\n", - "plt.show()" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "code", - "metadata": { - "id": "2e38b388" - }, - "source": [ - "import matplotlib.pyplot as plt\n", - "\n", - "# Create a scatter plot of median_income vs. median_house_value\n", - "plt.figure(figsize=(10, 6))\n", - "plt.scatter(df['median_income'], df['median_house_value'], alpha=0.5)\n", - "\n", - "# Add labels and title\n", - "plt.xlabel('Median Income')\n", - "plt.ylabel('Median House Value')\n", - "plt.title('Relationship between Median Income and Median House Value')\n", - "\n", - "# Add a grid for better readability\n", - "plt.grid(True)\n", - "\n", - "# Show the plot\n", - "plt.show()" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "51e78673" - }, - "source": [ - "## Split the data (if necessary)\n", - "\n", - "### Subtask:\n", - "Split the updated dataset (`X_engineered`, `y`) into training and testing sets." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "4ac8f448" - }, - "source": [ - "**Reasoning**:\n", - "Split the features and target into training and testing sets using train_test_split as instructed and print their shapes." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "bc5d10a6" - }, - "source": [ - "from sklearn.model_selection import train_test_split\n", - "\n", - "# Split the dataset into training and testing sets\n", - "X_train_engineered, X_test_engineered, y_train_engineered, y_test_engineered = train_test_split(X_engineered, y, test_size=0.2, random_state=42)\n", - "\n", - "# Print the shapes of the resulting sets\n", - "print(f\"Shape of X_train_engineered: {X_train_engineered.shape}\")\n", - "print(f\"Shape of X_test_engineered: {X_test_engineered.shape}\")\n", - "print(f\"Shape of y_train_engineered: {y_train_engineered.shape}\")\n", - "print(f\"Shape of y_test_engineered: {y_test_engineered.shape}\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "d7a020a4" - }, - "source": [ - "**Reasoning**:\n", - "Select the updated set of features for training the model, including the engineered features." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "456aa011" - }, - "source": [ - "# Define the list of features, including the original and engineered ones\n", - "features_engineered = ['longitude', 'latitude', 'housing_median_age', 'total_rooms',\n", - " 'total_bedrooms', 'population', 'households', 'median_income',\n", - " 'rooms_per_household', 'bedrooms_per_room', 'population_per_household']\n", - "\n", - "# Create a new DataFrame X_engineered by selecting these columns from df\n", - "X_engineered = df[features_engineered]\n", - "\n", - "# Keep the target variable y as it is (the 'median_house_value' column from df)\n", - "# y was already defined in a previous step as df['median_house_value']\n", - "\n", - "# Print the head of X_engineered and y to verify\n", - "print(\"Head of X_engineered:\")\n", - "display(X_engineered.head())\n", - "\n", - "print(\"\\nHead of y:\")\n", - "display(y.head())" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "b43fab9e" - }, - "source": [ - "## Identify potential new features\n", - "\n", - "### Subtask:\n", - "Determine which existing features can be combined or transformed to create meaningful new features (e.g., ratios, polynomial features, interaction terms)." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "adbc82dc" - }, - "source": [ - "**Reasoning**:\n", - "Describe the rationale for choosing features to create based on the analysis of existing features and potential relationships." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "b9a2f488" - }, - "source": [ - "# Rationale for choosing new features:\n", - "# Based on domain knowledge and common practices in housing price prediction,\n", - "# ratios of existing features can provide more meaningful insights into the\n", - "# characteristics of a housing block group than the raw counts alone.\n", - "\n", - "# 1. Rooms per household ('rooms_per_household'):\n", - "# This ratio (total_rooms / households) can indicate the average number of rooms\n", - "# available per household in a block group. It might be a strong predictor\n", - "# of housing value, as larger houses (more rooms per household) are often\n", - "# associated with higher values.\n", - "\n", - "# 2. Bedrooms per room ('bedrooms_per_room'):\n", - "# This ratio (total_bedrooms / total_rooms) can provide an idea of the\n", - "# proportion of rooms that are bedrooms. A higher ratio might indicate\n", - "# a different type of housing stock which could influence the median house value.\n", - "\n", - "# 3. Population per household ('population_per_household'):\n", - "# This ratio (population / households) represents the average household size.\n", - "# Larger household sizes in a block group might correlate with different housing\n", - "# demands and potentially impact housing values.\n", - "\n", - "# These ratios normalize the counts by the number of households or rooms,\n", - "# making them potentially more robust indicators than the raw counts themselves." - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "7c4d97dd" - }, - "source": [ - "## Create new features\n", - "\n", - "### Subtask:\n", - "Write code to generate the new features and add them to the DataFrame." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "a9a73659" - }, - "source": [ - "**Reasoning**:\n", - "Generate the new features by calculating the ratios as described in the instructions and add them as new columns to the DataFrame. Then, display the head of the updated DataFrame to confirm the changes." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "cc30b3e9" - }, - "source": [ - "# Calculate 'rooms_per_household' and add it as a new column\n", - "df['rooms_per_household'] = df['total_rooms'] / df['households']\n", - "\n", - "# Calculate 'bedrooms_per_room' and add it as a new column\n", - "df['bedrooms_per_room'] = df['total_bedrooms'] / df['total_rooms']\n", - "\n", - "# Calculate 'population_per_household' and add it as a new column\n", - "df['population_per_household'] = df['population'] / df['households']\n", - "\n", - "# Display the head of the DataFrame to verify the new columns\n", - "display(df.head())" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "code", - "metadata": { - "id": "088fbfe6" - }, - "source": [ - "# Display summary statistics of the DataFrame\n", - "display(df.describe())" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "990723df" - }, - "source": [ - "## Visualize the results (optional)\n", - "\n", - "### Subtask:\n", - "Visualize the predictions of the new model versus the actual values." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "f76956a7" - }, - "source": [ - "**Reasoning**:\n", - "Create a scatter plot of the actual vs. predicted values from the Ridge model, add labels, title, a diagonal line for perfect predictions, and a grid." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "217c1753" - }, - "source": [ - "import matplotlib.pyplot as plt\n", - "\n", - "# Create a scatter plot of actual vs. predicted values for the Ridge model\n", - "plt.figure(figsize=(8, 6))\n", - "plt.scatter(y_test, y_pred_ridge, alpha=0.5)\n", - "\n", - "# Add labels and title\n", - "plt.xlabel('Actual Values')\n", - "plt.ylabel('Predicted Values')\n", - "plt.title('Actual vs. Predicted Values (Ridge Regression)')\n", - "\n", - "# Add a diagonal line for perfect predictions\n", - "# Determine the range for the diagonal line based on both actual and predicted values\n", - "plot_range = [min(y_test.min(), y_pred_ridge.min()), max(y_test.max(), y_pred_ridge.max())]\n", - "plt.plot(plot_range, plot_range, color='red', linestyle='--')\n", - "\n", - "# Add a grid\n", - "plt.grid(True)\n", - "\n", - "# Show the plot\n", - "plt.show()" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "08f6f818" - }, - "source": [ - "## Choose a new model\n", - "\n", - "### Subtask:\n", - "Select a different regression algorithm to try (e.g., Ridge, Lasso, Decision Tree Regressor)." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "5c407870" - }, - "source": [ - "**Reasoning**:\n", - "Choose a different regression algorithm and mention it in a markdown cell." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "be170e13" - }, - "source": [ - "# Choosing Ridge Regression as an alternative regression model.\n", - "# Ridge is a linear model with L2 regularization.\n", - "# It can help to prevent overfitting, especially when dealing with multicollinearity\n", - "# among predictor variables, which might be present in this dataset.\n", - "# This choice is a common next step after trying simple Linear Regression." - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "805f79fa" - }, - "source": [ - "## Train the new model\n", - "\n", - "### Subtask:\n", - "Instantiate and train the chosen model using the training data (`X_train`, `y_train`)." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "26859879" - }, - "source": [ - "**Reasoning**:\n", - "Instantiate and train the Ridge model using the training data." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "d79f43a6" - }, - "source": [ - "from sklearn.linear_model import Ridge\n", - "\n", - "# Instantiate a Ridge model object with default parameters\n", - "ridge_model = Ridge()\n", - "\n", - "# Fit the Ridge model to the training data\n", - "ridge_model.fit(X_train, y_train)\n", - "\n", - "print(\"Ridge Regression model trained successfully.\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "f8addd87" - }, - "source": [ - "## Visualize the results (optional)\n", - "\n", - "### Subtask:\n", - "Visualize the predictions versus the actual values." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "246fbfca" - }, - "source": [ - "**Reasoning**:\n", - "Create a scatter plot of actual vs. predicted values and add a diagonal line for perfect predictions." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "c5f468af" - }, - "source": [ - "import matplotlib.pyplot as plt\n", - "\n", - "# Create a scatter plot\n", - "plt.figure(figsize=(8, 6))\n", - "plt.scatter(y_test, y_pred, alpha=0.5)\n", - "\n", - "# Add labels and title\n", - "plt.xlabel('Actual Values')\n", - "plt.ylabel('Predicted Values')\n", - "plt.title('Actual vs. Predicted Values')\n", - "\n", - "# Add a diagonal line for perfect predictions\n", - "# Determine the range for the diagonal line\n", - "plot_range = [min(y_test.min(), y_pred.min()), max(y_test.max(), y_pred.max())]\n", - "plt.plot(plot_range, plot_range, color='red', linestyle='--')\n", - "\n", - "# Add a grid\n", - "plt.grid(True)\n", - "\n", - "# Show the plot\n", - "plt.show()" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "e57b3e2a" - }, - "source": [ - "## Summary:\n", - "\n", - "### Data Analysis Key Findings\n", - "\n", - "* The `california_housing_train.csv` dataset was successfully loaded, containing 17000 entries and 9 columns of `float64` data type.\n", - "* No missing values were found in the dataset after filling the initial missing values in `total_rooms` and `total_bedrooms` with their respective medians.\n", - "* The dataset was split into training (13600 samples) and testing (3400 samples) sets, with features including 'longitude', 'latitude', 'housing\\_median\\_age', 'total\\_rooms', 'total\\_bedrooms', 'population', 'households', and 'median\\_income', and the target being 'median\\_house\\_value'.\n", - "* A Linear Regression model was successfully trained on the training data.\n", - "* The model achieved a Mean Squared Error (MSE) of approximately $4,634,658,406.22$ and an R-squared (R2) score of approximately 0.6636 on the testing data.\n", - "\n", - "### Insights or Next Steps\n", - "\n", - "* The R-squared score of 0.66 suggests the model explains a reasonable portion of the variance in median house values, but there is room for improvement.\n", - "* Further steps could involve exploring feature engineering, trying different regression algorithms (e.g., Ridge, Lasso, or more complex models), or performing hyperparameter tuning to potentially improve the model's performance." - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "1180b0f9" - }, - "source": [ - "import matplotlib.pyplot as plt\n", - "\n", - "# Plot the original data points\n", - "plt.scatter(X, y, color='blue', label='Original Data')\n", - "\n", - "# Plot the regression line\n", - "# We need to predict y values for the range of X values to plot the line\n", - "plt.plot(X, model.predict(X), color='red', label='Regression Line')\n", - "\n", - "plt.xlabel('Features (X)')\n", - "plt.ylabel('Target (y)')\n", - "plt.title('Linear Regression Example')\n", - "plt.legend()\n", - "plt.grid(True)\n", - "plt.show()" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "code", - "metadata": { - "id": "dddf50ae" - }, - "source": [ - "import numpy as np\n", - "from sklearn.linear_model import LinearRegression\n", - "\n", - "# Generate some sample data\n", - "# X represents the features (input), y represents the target (output)\n", - "X = np.array([1, 2, 3, 4, 5, 6]).reshape(-1, 1) # Reshape for scikit-learn\n", - "y = np.array([2, 4, 5, 4, 5, 6])\n", - "\n", - "# Create a Linear Regression model\n", - "model = LinearRegression()\n", - "\n", - "# Train the model using the data\n", - "model.fit(X, y)\n", - "\n", - "# Make a prediction\n", - "new_X = np.array([7]).reshape(-1, 1)\n", - "prediction = model.predict(new_X)\n", - "\n", - "print(f\"Features (X):\\n{X}\")\n", - "print(f\"Target (y):\\n{y}\")\n", - "print(f\"Prediction for X={new_X[0][0]}: {prediction[0]}\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "metadata": { - "id": "NHO9VzO9AHZP" - }, - "cell_type": "code", - "source": [ - "# @title Choose a different model\n", - "from google.colab import ai\n", - "\n", - "response = ai.generate_text(\"What is the capital of England\", model_name='google/gemini-2.0-flash-lite')\n", - "print(response)" - ], - "outputs": [], - "execution_count": null - }, - { - "metadata": { - "id": "ysDdFbH_Dgtz" - }, - "cell_type": "markdown", - "source": [ - "For longer text generations, you can stream the response. This displays the output token by token as it's generated, rather than waiting for the entire response to complete. This provides a more interactive and responsive experience. To enable this, simply set stream=True." - ] - }, - { - "metadata": { - "id": "4BNgxiB6--_5" - }, - "cell_type": "code", - "source": [ - "# @title Simple streaming example\n", - "from google.colab import ai\n", - "\n", - "stream = ai.generate_text(\"Tell me a short story.\", stream=True)\n", - "for text in stream:\n", - " print(text, end='')" - ], - "outputs": [], - "execution_count": null - }, - { - "metadata": { - "id": "CpMmpaVClSBV", - "cellView": "form" - }, - "cell_type": "code", - "source": [ - "#@title Text formatting setup\n", - "#code is not necessary for colab.ai, but is useful in fomatting text chunks\n", - "import sys\n", - "\n", - "class LineWrapper:\n", - " def __init__(self, max_length=80):\n", - " self.max_length = max_length\n", - " self.current_line_length = 0\n", - "\n", - " def print(self, text_chunk):\n", - " i = 0\n", - " n = len(text_chunk)\n", - " while i < n:\n", - " start_index = i\n", - " while i < n and text_chunk[i] not in ' \\n': # Find end of word\n", - " i += 1\n", - " current_word = text_chunk[start_index:i]\n", - "\n", - " delimiter = \"\"\n", - " if i < n: # If not end of chunk, we found a delimiter\n", - " delimiter = text_chunk[i]\n", - " i += 1 # Consume delimiter\n", - "\n", - " if current_word:\n", - " needs_leading_space = (self.current_line_length > 0)\n", - "\n", - " # Case 1: Word itself is too long for a line (must be broken)\n", - " if len(current_word) > self.max_length:\n", - " if needs_leading_space: # Newline if current line has content\n", - " sys.stdout.write('\\n')\n", - " self.current_line_length = 0\n", - " for char_val in current_word: # Break the long word\n", - " if self.current_line_length >= self.max_length:\n", - " sys.stdout.write('\\n')\n", - " self.current_line_length = 0\n", - " sys.stdout.write(char_val)\n", - " self.current_line_length += 1\n", - " # Case 2: Word doesn't fit on current line (print on new line)\n", - " elif self.current_line_length + (1 if needs_leading_space else 0) + len(current_word) > self.max_length:\n", - " sys.stdout.write('\\n')\n", - " sys.stdout.write(current_word)\n", - " self.current_line_length = len(current_word)\n", - " # Case 3: Word fits on current line\n", - " else:\n", - " if needs_leading_space:\n", - " # Define punctuation that should not have a leading space\n", - " # when they form an entire \"word\" (token) following another word.\n", - " no_leading_space_punctuation = {\n", - " \",\", \".\", \";\", \":\", \"!\", \"?\", # Standard sentence punctuation\n", - " \")\", \"]\", \"}\", # Closing brackets\n", - " \"'s\", \"'S\", \"'re\", \"'RE\", \"'ve\", \"'VE\", # Common contractions\n", - " \"'m\", \"'M\", \"'ll\", \"'LL\", \"'d\", \"'D\",\n", - " \"n't\", \"N'T\",\n", - " \"...\", \"â€Ļ\" # Ellipses\n", - " }\n", - " if current_word not in no_leading_space_punctuation:\n", - " sys.stdout.write(' ')\n", - " self.current_line_length += 1\n", - " sys.stdout.write(current_word)\n", - " self.current_line_length += len(current_word)\n", - "\n", - " if delimiter == '\\n':\n", - " sys.stdout.write('\\n')\n", - " self.current_line_length = 0\n", - " elif delimiter == ' ':\n", - " # If line is full and a space delimiter arrives, it implies a wrap.\n", - " if self.current_line_length >= self.max_length:\n", - " sys.stdout.write('\\n')\n", - " self.current_line_length = 0\n", - "\n", - " sys.stdout.flush()\n" - ], - "outputs": [], - "execution_count": null - }, - { - "metadata": { - "id": "DWiLPzTnRoy-" - }, - "cell_type": "code", - "source": [ - "# @title Formatted streaming example\n", - "from google.colab import ai\n", - "\n", - "wrapper = LineWrapper()\n", - "for chunk in ai.generate_text('Give me a long winded description about the evolution of the Roman Empire.', model_name='google/gemini-2.0-flash', stream=True):\n", - " wrapper.print(chunk)" - ], - "outputs": [], - "execution_count": null - }, - { - "cell_type": "markdown", - "metadata": { - "id": "c5851539" - }, - "source": [ - "# Task\n", - "Train a linear regression model on a more complex dataset from \"/content/sample_data/\"." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "3a7e5b4d" - }, - "source": [ - "## Load the dataset\n", - "\n", - "### Subtask:\n", - "Load a more complex dataset, such as one from the `/content/sample_data/` directory, into a pandas DataFrame.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "7f24f0a9" - }, - "source": [ - "**Reasoning**:\n", - "The subtask is to load a dataset from `/content/sample_data/` into a pandas DataFrame. I need to import pandas and then use `pd.read_csv` to load a file. Displaying the head of the dataframe will confirm the data has been loaded.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "f8c9aec7" - }, - "source": [ - "import pandas as pd\n", - "\n", - "# Load a sample dataset from /content/sample_data/ - choosing california_housing_train.csv\n", - "try:\n", - " df = pd.read_csv('/content/sample_data/california_housing_train.csv')\n", - " # Display the first few rows\n", - " display(df.head())\n", - "except FileNotFoundError:\n", - " print(\"File not found. Please check the file path.\")\n", - "except Exception as e:\n", - " print(f\"An error occurred: {e}\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "ff7bf690" - }, - "source": [ - "## Explore and preprocess the data\n", - "\n", - "### Subtask:\n", - "Inspect the dataset, handle any missing values, and select the features and target variable for the linear regression model.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "6383359c" - }, - "source": [ - "**Reasoning**:\n", - "Display DataFrame info, check for missing values, and handle them if necessary before selecting features and target variables.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "9347ab12" - }, - "source": [ - "# Display info about the DataFrame\n", - "df.info()\n", - "\n", - "# Check for missing values\n", - "print(\"\\nMissing values per column:\")\n", - "print(df.isnull().sum())\n", - "\n", - "# Handle missing values if any.\n", - "# The isnull().sum() output will show if there are any missing values.\n", - "# Based on the output of isnull().sum(), if 'total_bedrooms' has missing values,\n", - "# we will fill them with the median as it's a common practice for numerical features\n", - "# and less sensitive to outliers than the mean.\n", - "if df['total_bedrooms'].isnull().sum() > 0:\n", - " median_bedrooms = df['total_bedrooms'].median()\n", - " df['total_bedrooms'].fillna(median_bedrooms, inplace=True)\n", - " print(\"\\nMissing values in 'total_bedrooms' filled with median.\")\n", - "\n", - "# Also fill missing values in 'total_rooms' with the median\n", - "if df['total_rooms'].isnull().sum() > 0:\n", - " median_rooms = df['total_rooms'].median()\n", - " df['total_rooms'].fillna(median_rooms, inplace=True)\n", - " print(\"Missing values in 'total_rooms' filled with median.\")\n", - "\n", - "print(df.isnull().sum()) # Verify after filling\n", - "\n", - "# Select features (X) and target variable (y)\n", - "# We will use several numerical features as predictors for 'median_house_value'\n", - "features = ['longitude', 'latitude', 'housing_median_age', 'total_rooms',\n", - " 'total_bedrooms', 'population', 'households', 'median_income']\n", - "X = df[features]\n", - "y = df['median_house_value']\n", - "\n", - "print(\"\\nFeatures (X) and Target (y) selected.\")\n", - "display(X.head())\n", - "display(y.head())" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "85d33c8f" - }, - "source": [ - "## Split the data\n", - "\n", - "### Subtask:\n", - "Split the dataset into training and testing sets.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "d1eda7b0" - }, - "source": [ - "**Reasoning**:\n", - "Split the features and target into training and testing sets using train_test_split as instructed and print their shapes.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "94b0ab2d" - }, - "source": [ - "from sklearn.model_selection import train_test_split\n", - "\n", - "# Split the dataset into training and testing sets\n", - "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", - "\n", - "# Print the shapes of the resulting sets\n", - "print(f\"Shape of X_train: {X_train.shape}\")\n", - "print(f\"Shape of X_test: {X_test.shape}\")\n", - "print(f\"Shape of y_train: {y_train.shape}\")\n", - "print(f\"Shape of y_test: {y_test.shape}\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "6c3c850b" - }, - "source": [ - "## Train the model\n", - "\n", - "### Subtask:\n", - "Train the linear regression model on the training data.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "6ecedb3e" - }, - "source": [ - "**Reasoning**:\n", - "Train the linear regression model using the training data (X_train and y_train).\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "f3b32a6a" - }, - "source": [ - "from sklearn.linear_model import LinearRegression\n", - "\n", - "# Instantiate a Linear Regression model object\n", - "model = LinearRegression()\n", - "\n", - "# Fit the model to the training data\n", - "model.fit(X_train, y_train)\n", - "\n", - "print(\"Linear Regression model trained successfully.\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "7ed84711" - }, - "source": [ - "## Evaluate the model\n", - "\n", - "### Subtask:\n", - "Evaluate the trained model's performance on the testing data using appropriate metrics.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "76f31bb2" - }, - "source": [ - "**Reasoning**:\n", - "Evaluate the trained model's performance on the testing data using appropriate metrics.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "fa02f998" - }, - "source": [ - "from sklearn.metrics import mean_squared_error, r2_score\n", - "\n", - "# Use the trained model to make predictions on the testing features\n", - "y_pred = model.predict(X_test)\n", - "\n", - "# Calculate the Mean Squared Error (MSE)\n", - "mse = mean_squared_error(y_test, y_pred)\n", - "\n", - "# Calculate the R-squared score\n", - "r2 = r2_score(y_test, y_pred)\n", - "\n", - "# Print the calculated metrics\n", - "print(f\"Mean Squared Error (MSE): {mse}\")\n", - "print(f\"R-squared (R2) Score: {r2}\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "ab47ee9a" - }, - "source": [ - "## Visualize the results (optional)\n", - "\n", - "### Subtask:\n", - "Visualize the predictions versus the actual values.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "f73af8ad" - }, - "source": [ - "**Reasoning**:\n", - "Create a scatter plot of actual vs. predicted values and add a diagonal line for perfect predictions.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "6fd07845" - }, - "source": [ - "# Create a scatter plot\n", - "plt.figure(figsize=(8, 6))\n", - "plt.scatter(y_test, y_pred, alpha=0.5)\n", - "\n", - "# Add labels and title\n", - "plt.xlabel('Actual Values')\n", - "plt.ylabel('Predicted Values')\n", - "plt.title('Actual vs. Predicted Values')\n", - "\n", - "# Add a diagonal line for perfect predictions\n", - "# Determine the range for the diagonal line\n", - "plot_range = [min(y_test.min(), y_pred.min()), max(y_test.max(), y_pred.max())]\n", - "plt.plot(plot_range, plot_range, color='red', linestyle='--')\n", - "\n", - "# Add a grid\n", - "plt.grid(True)\n", - "\n", - "# Show the plot\n", - "plt.show()" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "745ce34d" - }, - "source": [ - "## Summary:\n", - "\n", - "### Data Analysis Key Findings\n", - "\n", - "* The `california_housing_train.csv` dataset was successfully loaded, containing 17000 entries and 9 columns of `float64` data type.\n", - "* No missing values were found in the dataset, eliminating the need for imputation.\n", - "* The dataset was split into training (13600 samples) and testing (3400 samples) sets, with features including 'longitude', 'latitude', 'housing\\_median\\_age', 'total\\_rooms', 'total\\_bedrooms', 'population', 'households', and 'median\\_income', and the target being 'median\\_house\\_value'.\n", - "* A Linear Regression model was successfully trained on the training data.\n", - "* The model achieved a Mean Squared Error (MSE) of approximately $4,634,658,406.22$ and an R-squared (R2) score of approximately 0.6636 on the testing data.\n", - "\n", - "### Insights or Next Steps\n", - "\n", - "* The R-squared score of 0.66 suggests the model explains a reasonable portion of the variance in median house values, but there is room for improvement.\n", - "* Further steps could involve exploring feature engineering, trying different regression algorithms (e.g., Ridge, Lasso, or more complex models), or performing hyperparameter tuning to potentially improve the model's performance.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "624e20aa" - }, - "source": [ - "# Task\n", - "Generate a plan to train and evaluate a new regression model on the existing dataset, compare its performance to the previously trained linear regression model, and summarize the findings." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "b0b03c2e" - }, - "source": [ - "## Choose a new model\n", - "\n", - "### Subtask:\n", - "Select a different regression algorithm to try (e.g., Ridge, Lasso, Decision Tree Regressor).\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "a377d954" - }, - "source": [ - "**Reasoning**:\n", - "Choose a different regression algorithm and mention it in a markdown cell.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "866a3b17" - }, - "source": [ - "# Choosing Ridge Regression as an alternative regression model.\n", - "# Ridge is a linear model with L2 regularization.\n", - "# It can help to prevent overfitting, especially when dealing with multicollinearity\n", - "# among predictor variables, which might be present in this dataset.\n", - "# This choice is a common next step after trying simple Linear Regression." - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "49297f4f" - }, - "source": [ - "## Train the new model\n", - "\n", - "### Subtask:\n", - "Instantiate and train the chosen model using the training data (`X_train`, `y_train`).\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "8ac64541" - }, - "source": [ - "**Reasoning**:\n", - "Instantiate and train the Ridge model using the training data.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "1722a73a" - }, - "source": [ - "from sklearn.linear_model import Ridge\n", - "\n", - "# Instantiate a Ridge model object with default parameters\n", - "ridge_model = Ridge()\n", - "\n", - "# Fit the Ridge model to the training data\n", - "ridge_model.fit(X_train, y_train)\n", - "\n", - "print(\"Ridge Regression model trained successfully.\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "c2c9c397" - }, - "source": [ - "## Evaluate the new model\n", - "\n", - "### Subtask:\n", - "Evaluate the new model's performance on the testing data (`X_test`, `y_test`) using appropriate metrics (e.g., MSE, R2).\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "3e06761a" - }, - "source": [ - "**Reasoning**:\n", - "Calculate MSE and R2 for the Ridge model using the test data and predictions, and print the results.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "24b91385" - }, - "source": [ - "from sklearn.metrics import mean_squared_error, r2_score\n", - "\n", - "# Use the trained ridge_model to make predictions on the testing features\n", - "y_pred_ridge = ridge_model.predict(X_test)\n", - "\n", - "# Calculate the Mean Squared Error (MSE) for the Ridge model\n", - "mse_ridge = mean_squared_error(y_test, y_pred_ridge)\n", - "\n", - "# Calculate the R-squared score for the Ridge model\n", - "r2_ridge = r2_score(y_test, y_pred_ridge)\n", - "\n", - "# Print the calculated metrics for the Ridge model\n", - "print(f\"Ridge Model Mean Squared Error (MSE): {mse_ridge}\")\n", - "print(f\"Ridge Model R-squared (R2) Score: {r2_ridge}\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "4eeeec40" - }, - "source": [ - "## Compare model performance\n", - "\n", - "### Subtask:\n", - "Compare the performance of the new model to the linear regression model we already trained.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "fc340fa9" - }, - "source": [ - "**Reasoning**:\n", - "Compare the performance metrics of the two models and print a summary.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "bd0b8441" - }, - "source": [ - "# Print the performance metrics for the Linear Regression model\n", - "print(f\"Linear Regression Model Mean Squared Error (MSE): {mse}\")\n", - "print(f\"Linear Regression Model R-squared (R2) Score: {r2}\")\n", - "\n", - "# Print the performance metrics for the Ridge Regression model\n", - "print(f\"Ridge Model Mean Squared Error (MSE): {mse_ridge}\")\n", - "print(f\"Ridge Model R-squared (R2) Score: {r2_ridge}\")\n", - "\n", - "# Compare and summarize the performance\n", - "if mse_ridge < mse:\n", - " print(\"\\nSummary: The Ridge Regression model performed slightly better than the Linear Regression model based on MSE.\")\n", - "elif mse_ridge > mse:\n", - " print(\"\\nSummary: The Linear Regression model performed slightly better than the Ridge Regression model based on MSE.\")\n", - "else:\n", - " print(\"\\nSummary: Both models performed similarly based on MSE.\")\n", - "\n", - "if r2_ridge > r2:\n", - " print(\"Summary: The Ridge Regression model performed slightly better than the Linear Regression model based on R2.\")\n", - "elif r2_ridge < r2:\n", - " print(\"Summary: The Linear Regression model performed slightly better than the Ridge Regression model based on R2.\")\n", - "else:\n", - " print(\"Summary: Both models performed similarly based on R2.\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "16995797" - }, - "source": [ - "## Visualize the results (optional)\n", - "\n", - "### Subtask:\n", - "Visualize the predictions of the new model versus the actual values.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "c5ab0a97" - }, - "source": [ - "**Reasoning**:\n", - "Create a scatter plot of the actual vs. predicted values from the Ridge model, add labels, title, a diagonal line for perfect predictions, and a grid.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "43d35683" - }, - "source": [ - "import matplotlib.pyplot as plt\n", - "\n", - "# Create a scatter plot of actual vs. predicted values for the Ridge model\n", - "plt.figure(figsize=(8, 6))\n", - "plt.scatter(y_test, y_pred_ridge, alpha=0.5)\n", - "\n", - "# Add labels and title\n", - "plt.xlabel('Actual Values')\n", - "plt.ylabel('Predicted Values')\n", - "plt.title('Actual vs. Predicted Values (Ridge Regression)')\n", - "\n", - "# Add a diagonal line for perfect predictions\n", - "# Determine the range for the diagonal line based on both actual and predicted values\n", - "plot_range = [min(y_test.min(), y_pred_ridge.min()), max(y_test.max(), y_pred_ridge.max())]\n", - "plt.plot(plot_range, plot_range, color='red', linestyle='--')\n", - "\n", - "# Add a grid\n", - "plt.grid(True)\n", - "\n", - "# Show the plot\n", - "plt.show()" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "3db547b6" - }, - "source": [ - "## Summary:\n", - "\n", - "### Data Analysis Key Findings\n", - "\n", - "* Ridge Regression was chosen as an alternative model to Linear Regression.\n", - "* The Ridge Regression model was successfully trained on the training data.\n", - "* The Ridge Regression model achieved a Mean Squared Error (MSE) of approximately 4,634,651,616.32 on the test set.\n", - "* The Ridge Regression model achieved an R-squared (R2) score of approximately 0.6636 on the test set.\n", - "* Comparing to the Linear Regression model (MSE: 4,634,658,406.22, R2: 0.6636), the Ridge Regression model performed slightly better based on MSE and similarly based on R2.\n", - "* A scatter plot visualizing the actual versus predicted values for the Ridge model was generated, showing the distribution of predictions relative to a perfect prediction line.\n", - "\n", - "### Insights or Next Steps\n", - "\n", - "* Although Ridge Regression showed a minor improvement, the performance difference compared to Linear Regression is minimal, suggesting that the L2 regularization had a limited impact on this specific dataset.\n", - "* Further model exploration with different algorithms (e.g., tree-based models like Random Forest or Gradient Boosting) or hyperparameter tuning of the Ridge model could potentially yield better performance.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "0f4d030b" - }, - "source": [ - "# Task\n", - "Perform feature engineering on the `df` DataFrame to create new features, train a model with the updated features, and evaluate its performance." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "a8eb897f" - }, - "source": [ - "## Identify potential new features\n", - "\n", - "### Subtask:\n", - "Determine which existing features can be combined or transformed to create meaningful new features (e.g., ratios, polynomial features, interaction terms).\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "c3d68222" - }, - "source": [ - "**Reasoning**:\n", - "Describe the rationale for choosing features to create based on the analysis of existing features and potential relationships.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "c95acba5" - }, - "source": [ - "# Rationale for choosing new features:\n", - "# Based on domain knowledge and common practices in housing price prediction,\n", - "# ratios of existing features can provide more meaningful insights into the\n", - "# characteristics of a housing block group than the raw counts alone.\n", - "\n", - "# 1. Rooms per household ('rooms_per_household'):\n", - "# This ratio (total_rooms / households) can indicate the average number of rooms\n", - "# available per household in a block group. It might be a strong predictor\n", - "# of housing value, as larger houses (more rooms per household) are often\n", - "# associated with higher values.\n", - "\n", - "# 2. Bedrooms per room ('bedrooms_per_room'):\n", - "# This ratio (total_bedrooms / total_rooms) can provide an idea of the\n", - "# proportion of rooms that are bedrooms. A higher ratio might indicate\n", - "# a different type of housing stock which could influence the median house value.\n", - "\n", - "# 3. Population per household ('population_per_household'):\n", - "# This ratio (population / households) represents the average household size.\n", - "# Larger household sizes in a block group might correlate with different housing\n", - "# demands and potentially impact housing values.\n", - "\n", - "# These ratios normalize the counts by the number of households or rooms,\n", - "# making them potentially more robust indicators than the raw counts themselves." - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "671d2b48" - }, - "source": [ - "## Create new features\n", - "\n", - "### Subtask:\n", - "Write code to generate the new features and add them to the DataFrame.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "9a28da2f" - }, - "source": [ - "**Reasoning**:\n", - "Generate the new features by calculating the ratios as described in the instructions and add them as new columns to the DataFrame. Then, display the head of the updated DataFrame to confirm the changes.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "5ca46b87" - }, - "source": [ - "# Calculate 'rooms_per_household' and add it as a new column\n", - "df['rooms_per_household'] = df['total_rooms'] / df['households']\n", - "\n", - "# Calculate 'bedrooms_per_room' and add it as a new column\n", - "df['bedrooms_per_room'] = df['total_bedrooms'] / df['total_rooms']\n", - "\n", - "# Calculate 'population_per_household' and add it as a new column\n", - "df['population_per_household'] = df['population'] / df['households']\n", - "\n", - "# Display the head of the DataFrame to verify the new columns\n", - "display(df.head())" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "7562b7a2" - }, - "source": [ - "## Update features for modeling\n", - "\n", - "### Subtask:\n", - "Select the updated set of features (including the new ones) for training the model.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "98b24e8f" - }, - "source": [ - "**Reasoning**:\n", - "Select the updated set of features for training the model, including the engineered features.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "6b6e7b39" - }, - "source": [ - "# Define the list of features, including the original and engineered ones\n", - "features_engineered = ['longitude', 'latitude', 'housing_median_age', 'total_rooms',\n", - " 'total_bedrooms', 'population', 'households', 'median_income',\n", - " 'rooms_per_household', 'bedrooms_per_room', 'population_per_household']\n", - "\n", - "# Create a new DataFrame X_engineered by selecting these columns from df\n", - "X_engineered = df[features_engineered]\n", - "\n", - "# Keep the target variable y as it is (the 'median_house_value' column from df)\n", - "# y was already defined in a previous step as df['median_house_value']\n", - "\n", - "# Print the head of X_engineered and y to verify\n", - "print(\"Head of X_engineered:\")\n", - "display(X_engineered.head())\n", - "\n", - "print(\"\\nHead of y:\")\n", - "display(y.head())" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "48e5c30c" - }, - "source": [ - "## Split the data (if necessary)\n", - "\n", - "### Subtask:\n", - "Split the updated dataset (`X_engineered`, `y`) into training and testing sets.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "069a70ad" - }, - "source": [ - "**Reasoning**:\n", - "Split the features and target into training and testing sets using train_test_split as instructed and print their shapes.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "6f346b39" - }, - "source": [ - "from sklearn.model_selection import train_test_split\n", - "\n", - "# Split the dataset into training and testing sets\n", - "X_train_engineered, X_test_engineered, y_train_engineered, y_test_engineered = train_test_split(X_engineered, y, test_size=0.2, random_state=42)\n", - "\n", - "# Print the shapes of the resulting sets\n", - "print(f\"Shape of X_train_engineered: {X_train_engineered.shape}\")\n", - "print(f\"Shape of X_test_engineered: {X_test_engineered.shape}\")\n", - "print(f\"Shape of y_train_engineered: {y_train_engineered.shape}\")\n", - "print(f\"Shape of y_test_engineered: {y_test_engineered.shape}\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "62522074" - }, - "source": [ - "## Train a model with new features\n", - "\n", - "### Subtask:\n", - "Train a regression model (either the Linear Regression or Ridge model again, or a new one) using the updated features (`X_train_engineered`, `y_train_engineered`).\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "2f00df49" - }, - "source": [ - "**Reasoning**:\n", - "Instantiate and train a Linear Regression model using the engineered training data.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "f490841e" - }, - "source": [ - "from sklearn.linear_model import LinearRegression\n", - "\n", - "# Instantiate a Linear Regression model object\n", - "model_engineered = LinearRegression()\n", - "\n", - "# Fit the model to the engineered training data\n", - "model_engineered.fit(X_train_engineered, y_train_engineered)\n", - "\n", - "print(\"Linear Regression model trained successfully using engineered features.\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "2f1cd2b0" - }, - "source": [ - "## Evaluate the model with new features\n", - "\n", - "### Subtask:\n", - "Evaluate the performance of the model trained with the new features using appropriate metrics (e.g., MSE, R2) on the testing data (`X_test_engineered`, `y_test_engineered`).\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "4b82a5e8" - }, - "source": [ - "**Reasoning**:\n", - "Calculate MSE and R2 for the model trained with engineered features using the test data and predictions, and print the results.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "f7df2324" - }, - "source": [ - "from sklearn.metrics import mean_squared_error, r2_score\n", - "\n", - "# Use the trained model_engineered to make predictions on the engineered testing features\n", - "y_pred_engineered = model_engineered.predict(X_test_engineered)\n", - "\n", - "# Calculate the Mean Squared Error (MSE) for the model with engineered features\n", - "mse_engineered = mean_squared_error(y_test_engineered, y_pred_engineered)\n", - "\n", - "# Calculate the R-squared score for the model with engineered features\n", - "r2_engineered = r2_score(y_test_engineered, y_pred_engineered)\n", - "\n", - "# Print the calculated metrics for the model with engineered features\n", - "print(f\"Model with Engineered Features Mean Squared Error (MSE): {mse_engineered}\")\n", - "print(f\"Model with Engineered Features R-squared (R2) Score: {r2_engineered}\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "3ca80ee6" - }, - "source": [ - "## Compare performance\n", - "\n", - "### Subtask:\n", - "Compare the performance of the model with and without the new features.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "d308c1d0" - }, - "source": [ - "**Reasoning**:\n", - "Print the performance metrics for both models and compare them based on MSE and R2 to determine which model performed better.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "0879e9ba" - }, - "source": [ - "# Print the performance metrics for the Linear Regression model trained on original features\n", - "print(f\"Linear Regression Model (Original Features) MSE: {mse}\")\n", - "print(f\"Linear Regression Model (Original Features) R2 Score: {r2}\")\n", - "\n", - "# Print the performance metrics for the Linear Regression model trained on engineered features\n", - "print(f\"Linear Regression Model (Engineered Features) MSE: {mse_engineered}\")\n", - "print(f\"Linear Regression Model (Engineered Features) R2 Score: {r2_engineered}\")\n", - "\n", - "# Compare and summarize the performance based on MSE\n", - "if mse_engineered < mse:\n", - " print(\"\\nSummary: The Linear Regression model with engineered features performed better than the model with original features based on MSE (lower is better).\")\n", - "elif mse_engineered > mse:\n", - " print(\"\\nSummary: The Linear Regression model with original features performed better than the model with engineered features based on MSE (lower is better).\")\n", - "else:\n", - " print(\"\\nSummary: Both Linear Regression models performed similarly based on MSE.\")\n", - "\n", - "# Compare and summarize the performance based on R2\n", - "if r2_engineered > r2:\n", - " print(\"Summary: The Linear Regression model with engineered features performed better than the model with original features based on R2 (higher is better).\")\n", - "elif r2_engineered < r2:\n", - " print(\"Summary: The Linear Regression model with original features performed better than the model with engineered features based on R2 (higher is better).\")\n", - "else:\n", - " print(\"Summary: Both Linear Regression models performed similarly based on R2.\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "f3c7a4ee" - }, - "source": [ - "## Visualize results (optional)\n", - "\n", - "### Subtask:\n", - "Visualize the predictions of the model trained with new features versus the actual values.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "63160aae" - }, - "source": [ - "**Reasoning**:\n", - "Create a scatter plot of the actual vs. predicted values from the model trained with engineered features, add labels, title, a diagonal line for perfect predictions, and a grid.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "29c83a42" - }, - "source": [ - "import matplotlib.pyplot as plt\n", - "\n", - "# Create a scatter plot of actual vs. predicted values for the engineered features model\n", - "plt.figure(figsize=(8, 6))\n", - "plt.scatter(y_test_engineered, y_pred_engineered, alpha=0.5)\n", - "\n", - "# Add labels and title\n", - "plt.xlabel('Actual Values')\n", - "plt.ylabel('Predicted Values')\n", - "plt.title('Actual vs. Predicted Values (Linear Regression with Engineered Features)')\n", - "\n", - "# Add a diagonal line for perfect predictions\n", - "# Determine the range for the diagonal line based on both actual and predicted values\n", - "plot_range_engineered = [min(y_test_engineered.min(), y_pred_engineered.min()), max(y_test_engineered.max(), y_pred_engineered.max())]\n", - "plt.plot(plot_range_engineered, plot_range_engineered, color='red', linestyle='--')\n", - "\n", - "# Add a grid\n", - "plt.grid(True)\n", - "\n", - "# Show the plot\n", - "plt.show()" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "0f79ff4e" - }, - "source": [ - "## Summary:\n", - "\n", - "### Data Analysis Key Findings\n", - "\n", - "* Three new features were created: 'rooms\\_per\\_household', 'bedrooms\\_per\\_room', and 'population\\_per\\_household'.\n", - "* The dataset was successfully split into training (80%) and testing (20%) sets, resulting in training sets with 13600 samples and testing sets with 3400 samples.\n", - "* A Linear Regression model was trained using the dataset with the engineered features.\n", - "* The model trained with engineered features achieved a Mean Squared Error (MSE) of approximately 4,552,463,037.86 and an R-squared (R2) score of approximately 0.670 on the test set.\n", - "* Comparing the performance to the model with original features (MSE of ~4.63 billion and R2 of 0.664), the model with engineered features showed slightly better performance based on both metrics (lower MSE and higher R2).\n", - "\n", - "### Insights or Next Steps\n", - "\n", - "* The engineered features slightly improved the Linear Regression model's performance, suggesting that these ratios capture some valuable information about housing values. Further investigation into other feature engineering techniques or non-linear models could potentially yield more significant improvements.\n", - "* Visualizing the actual vs. predicted values confirms that the model's predictions generally follow the trend of the actual values, although there is still a notable spread, particularly for higher house values, indicating room for further model improvement.\n" - ] - }, - { - "cell_type": "markdown", "metadata": { - "id": "077a42d1" - }, - "source": [ - "# Task\n", - "Explore Ridge or Lasso Regression for hyperparameter tuning." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "3b52b9ea" - }, - "source": [ - "## Choose a model for tuning\n", - "\n", - "### Subtask:\n", - "Select either Ridge or Lasso Regression for hyperparameter tuning.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "630393a2" - }, - "source": [ - "## Define the parameter grid\n", - "\n", - "### Subtask:\n", - "Specify the range of hyperparameter values to search over.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "5a0d3854" - }, - "source": [ - "**Reasoning**:\n", - "Define a range of alpha values for hyperparameter tuning of the Ridge model and store them in a dictionary named `param_grid`.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "16943d5b" - }, - "source": [ - "import numpy as np\n", - "\n", - "# Choose a range of alpha values for Ridge Regression\n", - "# Using a logarithmic scale from 0.1 to 100.\n", - "alpha_range = np.logspace(-1, 2, 100)\n", - "\n", - "# Create a dictionary named param_grid\n", - "param_grid = {'alpha': alpha_range}\n", - "\n", - "print(\"Hyperparameter grid for Ridge Regression:\")\n", - "print(param_grid)" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "a699be97" - }, - "source": [ - "## Set up cross-validation\n", - "\n", - "### Subtask:\n", - "Choose a cross-validation strategy (e.g., K-Fold) to evaluate different parameter combinations robustly.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "ea3e61d1" - }, - "source": [ - "**Reasoning**:\n", - "Instantiate a KFold object with the specified parameters for cross-validation.\n", - "\n" - ] - }, - { - "cell_type": "code", - "metadata": { - "id": "b614f69b" - }, - "source": [ - "from sklearn.model_selection import KFold\n", - "\n", - "# Instantiate a KFold object\n", - "# n_splits=5 is a common choice for K-Fold cross-validation\n", - "# shuffle=True shuffles the data before splitting, which is important if the data\n", - "# has any inherent order.\n", - "# random_state ensures that the shuffling is the same each time the code is run,\n", - "# making the results reproducible.\n", - "kf = KFold(n_splits=5, shuffle=True, random_state=42)\n", - "\n", - "print(\"KFold cross-validation strategy instantiated.\")" - ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "67bc814f" - }, - "source": [ - "## Perform hyperparameter search\n", - "\n", - "### Subtask:\n", - "Use a tuning method (e.g., GridSearchCV or RandomizedSearchCV) to find the best hyperparameters.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "58664285" + "id": "NHO9VzO9AHZP" }, - "source": [ - "**Reasoning**:\n", - "Instantiate and fit GridSearchCV to find the best hyperparameters for the Ridge model using the defined parameter grid and cross-validation strategy. Then, print the best parameters and best score.\n", - "\n" - ] - }, - { "cell_type": "code", - "metadata": { - "id": "4be9680c" - }, "source": [ - "from sklearn.model_selection import GridSearchCV\n", - "\n", - "# Instantiate a GridSearchCV object\n", - "# estimator: The model to tune (ridge_model)\n", - "# param_grid: The grid of hyperparameters to search over\n", - "# scoring: The metric to optimize (Negative Mean Squared Error, as GridSearchCV maximizes scores)\n", - "# cv: The cross-validation strategy (kf)\n", - "grid_search = GridSearchCV(estimator=ridge_model, param_grid=param_grid,\n", - " scoring='neg_mean_squared_error', cv=kf)\n", - "\n", - "# Fit the GridSearchCV object to the training data\n", - "grid_search.fit(X_train_engineered, y_train_engineered)\n", - "\n", - "# Print the best hyperparameters found by the search\n", - "print(\"Best hyperparameters found by GridSearchCV:\")\n", - "print(grid_search.best_params_)\n", + "# @title Choose a different model\n", + "from google.colab import ai\n", "\n", - "# Print the best cross-validation score achieved during the search\n", - "# Note: The score is negative MSE, so we take the negative to get the actual MSE\n", - "print(\"\\nBest cross-validation MSE score:\")\n", - "print(-grid_search.best_score_)" + "response = ai.generate_text(\"What is the capital of England\", model_name='google/gemini-2.0-flash-lite')\n", + "print(response)" ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "c34eafb5" - }, - "source": [ - "## Train the final model\n", - "\n", - "### Subtask:\n", - "Train the chosen model with the best hyperparameters on the entire training set.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "2bb1ff8e" - }, - "source": [ - "**Reasoning**:\n", - "Get the best estimator from the GridSearchCV object and train it on the entire engineered training data.\n", - "\n" - ] + "outputs": [], + "execution_count": null }, { - "cell_type": "code", "metadata": { - "id": "f0c2ff41" + "id": "ysDdFbH_Dgtz" }, - "source": [ - "# Get the best estimator from the GridSearchCV object\n", - "best_ridge_model = grid_search.best_estimator_\n", - "\n", - "# Train the best estimator on the entire engineered training data\n", - "best_ridge_model.fit(X_train_engineered, y_train_engineered)\n", - "\n", - "print(\"Best Ridge Regression model trained on the entire engineered training set.\")" - ], - "execution_count": null, - "outputs": [] - }, - { "cell_type": "markdown", - "metadata": { - "id": "cfdf5774" - }, "source": [ - "## Evaluate the tuned model\n", - "\n", - "### Subtask:\n", - "Evaluate the performance of the tuned model on the testing data.\n" + "For longer text generations, you can stream the response. This displays the output token by token as it's generated, rather than waiting for the entire response to complete. This provides a more interactive and responsive experience. To enable this, simply set stream=True." ] }, { - "cell_type": "markdown", "metadata": { - "id": "1de3530d" + "id": "4BNgxiB6--_5" }, - "source": [ - "**Reasoning**:\n", - "Calculate MSE and R2 for the tuned Ridge model using the test data and predictions, and print the results.\n", - "\n" - ] - }, - { "cell_type": "code", - "metadata": { - "id": "4c2707bc" - }, "source": [ - "from sklearn.metrics import mean_squared_error, r2_score\n", - "\n", - "# Use the trained best_ridge_model to make predictions on the engineered testing features\n", - "y_pred_tuned_ridge = best_ridge_model.predict(X_test_engineered)\n", - "\n", - "# Calculate the Mean Squared Error (MSE) for the tuned Ridge model\n", - "mse_tuned_ridge = mean_squared_error(y_test_engineered, y_pred_tuned_ridge)\n", - "\n", - "# Calculate the R-squared score for the tuned Ridge model\n", - "r2_tuned_ridge = r2_score(y_test_engineered, y_pred_tuned_ridge)\n", + "# @title Simple streaming example\n", + "from google.colab import ai\n", "\n", - "# Print the calculated metrics for the tuned Ridge model\n", - "print(f\"Tuned Ridge Model Mean Squared Error (MSE): {mse_tuned_ridge}\")\n", - "print(f\"Tuned Ridge Model R-squared (R2) Score: {r2_tuned_ridge}\")" + "stream = ai.generate_text(\"Tell me a short story.\", stream=True)\n", + "for text in stream:\n", + " print(text, end='')" ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "1c16553d" - }, - "source": [ - "## Compare with previous models\n", - "\n", - "### Subtask:\n", - "Compare the performance of the tuned model to the previously trained models.\n" - ] + "outputs": [], + "execution_count": null }, { - "cell_type": "markdown", "metadata": { - "id": "a0724b9c" + "id": "CpMmpaVClSBV", + "cellView": "form" }, - "source": [ - "**Reasoning**:\n", - "Print the performance metrics for all models and compare them to summarize the impact of feature engineering and hyperparameter tuning.\n", - "\n" - ] - }, - { "cell_type": "code", - "metadata": { - "id": "342f0d26" - }, "source": [ - "# Print the performance metrics for all models for comparison\n", - "\n", - "# Initial Linear Regression model (original features)\n", - "print(f\"Initial Linear Regression Model (Original Features) MSE: {mse}\")\n", - "print(f\"Initial Linear Regression Model (Original Features) R2 Score: {r2}\")\n", - "\n", - "# Ridge Regression model (original features, default hyperparameters)\n", - "print(f\"Ridge Regression Model (Original Features, Default Hyperparameters) MSE: {mse_ridge}\")\n", - "print(f\"Ridge Regression Model (Original Features, Default Hyperparameters) R2 Score: {r2_ridge}\")\n", - "\n", - "# Linear Regression model (engineered features)\n", - "print(f\"Linear Regression Model (Engineered Features) MSE: {mse_engineered}\")\n", - "print(f\"Linear Regression Model (Engineered Features) R2 Score: {r2_engineered}\")\n", + "#@title Text formatting setup\n", + "#code is not necessary for colab.ai, but is useful in fomatting text chunks\n", + "import sys\n", "\n", - "# Tuned Ridge Regression model (engineered features, tuned hyperparameters)\n", - "print(f\"Tuned Ridge Regression Model (Engineered Features, Tuned Hyperparameters) MSE: {mse_tuned_ridge}\")\n", - "print(f\"Tuned Ridge Regression Model (Engineered Features, Tuned Hyperparameters) R2 Score: {r2_tuned_ridge}\")\n", + "class LineWrapper:\n", + " def __init__(self, max_length=80):\n", + " self.max_length = max_length\n", + " self.current_line_length = 0\n", "\n", - "# Summarize the findings\n", - "print(\"\\n--- Performance Comparison Summary ---\")\n", + " def print(self, text_chunk):\n", + " i = 0\n", + " n = len(text_chunk)\n", + " while i < n:\n", + " start_index = i\n", + " while i < n and text_chunk[i] not in ' \\n': # Find end of word\n", + " i += 1\n", + " current_word = text_chunk[start_index:i]\n", "\n", - "# Compare MSE\n", - "if mse_tuned_ridge < mse_engineered and mse_tuned_ridge < mse_ridge and mse_tuned_ridge < mse:\n", - " print(\"The Tuned Ridge Regression model with engineered features performed the best based on MSE (lower is better).\")\n", - "elif mse_engineered < mse_tuned_ridge and mse_engineered < mse_ridge and mse_engineered < mse:\n", - " print(\"The Linear Regression model with engineered features performed the best based on MSE (lower is better).\")\n", - "elif mse_ridge < mse_tuned_ridge and mse_ridge < mse_engineered and mse_ridge < mse:\n", - " print(\"The Ridge Regression model with default hyperparameters performed the best based on MSE (lower is better).\")\n", - "else:\n", - " print(\"The Initial Linear Regression model with original features performed the best based on MSE (lower is better).\")\n", + " delimiter = \"\"\n", + " if i < n: # If not end of chunk, we found a delimiter\n", + " delimiter = text_chunk[i]\n", + " i += 1 # Consume delimiter\n", "\n", - "# Compare R2\n", - "if r2_tuned_ridge > r2_engineered and r2_tuned_ridge > r2_ridge and r2_tuned_ridge > r2:\n", - " print(\"The Tuned Ridge Regression model with engineered features performed the best based on R2 (higher is better).\")\n", - "elif r2_engineered > r2_tuned_ridge and r2_engineered > r2_ridge and r2_engineered > r2:\n", - " print(\"The Linear Regression model with engineered features performed the best based on R2 (higher is better).\")\n", - "elif r2_ridge > r2_tuned_ridge and r2_ridge > r2_engineered and r2_ridge > r2:\n", - " print(\"The Ridge Regression model with default hyperparameters performed the best based on R2 (higher is better).\")\n", - "else:\n", - " print(\"The Initial Linear Regression model with original features performed the best based on R2 (higher is better).\")\n", + " if current_word:\n", + " needs_leading_space = (self.current_line_length > 0)\n", "\n", - "print(\"\\nImpact of Feature Engineering and Hyperparameter Tuning:\")\n", - "if mse_engineered < mse and r2_engineered > r2:\n", - " print(\"- Feature engineering improved the performance of the Linear Regression model.\")\n", - "else:\n", - " print(\"- Feature engineering did not significantly improve the performance of the Linear Regression model.\")\n", + " # Case 1: Word itself is too long for a line (must be broken)\n", + " if len(current_word) > self.max_length:\n", + " if needs_leading_space: # Newline if current line has content\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", + " for char_val in current_word: # Break the long word\n", + " if self.current_line_length >= self.max_length:\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", + " sys.stdout.write(char_val)\n", + " self.current_line_length += 1\n", + " # Case 2: Word doesn't fit on current line (print on new line)\n", + " elif self.current_line_length + (1 if needs_leading_space else 0) + len(current_word) > self.max_length:\n", + " sys.stdout.write('\\n')\n", + " sys.stdout.write(current_word)\n", + " self.current_line_length = len(current_word)\n", + " # Case 3: Word fits on current line\n", + " else:\n", + " if needs_leading_space:\n", + " # Define punctuation that should not have a leading space\n", + " # when they form an entire \"word\" (token) following another word.\n", + " no_leading_space_punctuation = {\n", + " \",\", \".\", \";\", \":\", \"!\", \"?\", # Standard sentence punctuation\n", + " \")\", \"]\", \"}\", # Closing brackets\n", + " \"'s\", \"'S\", \"'re\", \"'RE\", \"'ve\", \"'VE\", # Common contractions\n", + " \"'m\", \"'M\", \"'ll\", \"'LL\", \"'d\", \"'D\",\n", + " \"n't\", \"N'T\",\n", + " \"...\", \"â€Ļ\" # Ellipses\n", + " }\n", + " if current_word not in no_leading_space_punctuation:\n", + " sys.stdout.write(' ')\n", + " self.current_line_length += 1\n", + " sys.stdout.write(current_word)\n", + " self.current_line_length += len(current_word)\n", "\n", - "if mse_tuned_ridge < mse_engineered and r2_tuned_ridge > r2_engineered:\n", - " print(\"- Hyperparameter tuning of the Ridge model with engineered features further improved performance compared to the Linear Regression model with engineered features.\")\n", - "else:\n", - " print(\"- Hyperparameter tuning of the Ridge model with engineered features did not significantly improve performance compared to the Linear Regression model with engineered features.\")\n", + " if delimiter == '\\n':\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", + " elif delimiter == ' ':\n", + " # If line is full and a space delimiter arrives, it implies a wrap.\n", + " if self.current_line_length >= self.max_length:\n", + " sys.stdout.write('\\n')\n", + " self.current_line_length = 0\n", "\n", - "if mse_tuned_ridge < mse_ridge and r2_tuned_ridge > r2_ridge:\n", - " print(\"- Hyperparameter tuning of the Ridge model with engineered features improved performance compared to the Ridge model with default hyperparameters.\")\n", - "else:\n", - " print(\"- Hyperparameter tuning of the Ridge model with engineered features did not significantly improve performance compared to the Ridge model with default hyperparameters.\")" + " sys.stdout.flush()\n" ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "ae3a5dad" - }, - "source": [ - "## Visualize results (optional)\n", - "\n", - "### Subtask:\n", - "Visualize the predictions of the tuned model.\n" - ] + "outputs": [], + "execution_count": null }, { - "cell_type": "markdown", "metadata": { - "id": "8f7dba0d" + "id": "DWiLPzTnRoy-" }, - "source": [ - "**Reasoning**:\n", - "Create a scatter plot of the actual vs. predicted values from the tuned Ridge model, add labels, title, a diagonal line for perfect predictions, and a grid.\n", - "\n" - ] - }, - { "cell_type": "code", - "metadata": { - "id": "0845a2f0" - }, "source": [ - "# Create a scatter plot of actual vs. predicted values for the tuned Ridge model\n", - "plt.figure(figsize=(8, 6))\n", - "plt.scatter(y_test_engineered, y_pred_tuned_ridge, alpha=0.5)\n", - "\n", - "# Add labels and title\n", - "plt.xlabel('Actual Values')\n", - "plt.ylabel('Predicted Values')\n", - "plt.title('Actual vs. Predicted Values (Tuned Ridge Regression)')\n", - "\n", - "# Add a diagonal line for perfect predictions\n", - "# Determine the range for the diagonal line based on both actual and predicted values\n", - "plot_range_tuned = [min(y_test_engineered.min(), y_pred_tuned_ridge.min()), max(y_test_engineered.max(), y_pred_tuned_ridge.max())]\n", - "plt.plot(plot_range_tuned, plot_range_tuned, color='red', linestyle='--')\n", - "\n", - "# Add a grid\n", - "plt.grid(True)\n", + "# @title Formatted streaming example\n", + "from google.colab import ai\n", "\n", - "# Show the plot\n", - "plt.show()" + "wrapper = LineWrapper()\n", + "for chunk in ai.generate_text('Give me a long winded description about the evolution of the Roman Empire.', model_name='google/gemini-2.0-flash', stream=True):\n", + " wrapper.print(chunk)" ], - "execution_count": null, - "outputs": [] - }, - { - "cell_type": "markdown", - "metadata": { - "id": "dc0dada1" - }, - "source": [ - "## Summary:\n", - "\n", - "### Data Analysis Key Findings\n", - "\n", - "* The hyperparameter tuning process for the Ridge Regression model with engineered features identified an optimal `alpha` of 0.1.\n", - "* The best cross-validation Mean Squared Error (MSE) achieved during the grid search was approximately 5,070,263,224.18.\n", - "* The tuned Ridge Regression model with engineered features achieved a Mean Squared Error (MSE) of approximately 4,552,359,506.89 and an R-squared (R2) score of approximately 0.67 on the testing data.\n", - "* Feature engineering improved the performance of the Linear Regression model compared to using original features.\n", - "* Hyperparameter tuning of the Ridge model with engineered features further improved performance compared to both the Linear Regression model with engineered features and the Ridge model with default hyperparameters.\n", - "* The Tuned Ridge Regression model with engineered features was the best-performing model among those evaluated, based on the lowest MSE and highest R2 score.\n", - "\n", - "### Insights or Next Steps\n", - "\n", - "* The visualization of actual vs. predicted values for the tuned Ridge model shows a reasonable spread around the perfect prediction line, suggesting the model captures a significant portion of the variance but still has notable errors for some predictions.\n", - "* Further exploration could involve trying other regression algorithms (e.g., Lasso, ElasticNet, Gradient Boosting) or more advanced feature engineering techniques to potentially improve the model's performance further.\n" - ] + "outputs": [], + "execution_count": null } ], "metadata": { From 4703d254a93b914effcf6933a140d90a3f6167af Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 4 Oct 2025 14:26:24 +0600 Subject: [PATCH 24/28] Add initial IntelliJ IDEA project files Added .idea directory with project configuration files including module, VCS, and device streaming settings. This sets up the project structure for development in IntelliJ IDEA. --- .idea/.github.iml | 9 + .idea/.gitignore | 3 + .idea/misc.xml | 1176 +++++++++++++++++++++++++++++++++++++++++++++ .idea/modules.xml | 8 + .idea/vcs.xml | 6 + 5 files changed, 1202 insertions(+) create mode 100644 .idea/.github.iml create mode 100644 .idea/.gitignore create mode 100644 .idea/misc.xml create mode 100644 .idea/modules.xml create mode 100644 .idea/vcs.xml diff --git a/.idea/.github.iml b/.idea/.github.iml new file mode 100644 index 0000000..d6ebd48 --- /dev/null +++ b/.idea/.github.iml @@ -0,0 +1,9 @@ + + + + + + + + + \ No newline at end of file diff --git a/.idea/.gitignore b/.idea/.gitignore new file mode 100644 index 0000000..26d3352 --- /dev/null +++ b/.idea/.gitignore @@ -0,0 +1,3 @@ +# Default ignored files +/shelf/ +/workspace.xml diff --git a/.idea/misc.xml b/.idea/misc.xml new file mode 100644 index 0000000..3fe2d8e --- /dev/null +++ b/.idea/misc.xml @@ -0,0 +1,1176 @@ + + + + + + + + + \ No newline at end of file diff --git a/.idea/modules.xml b/.idea/modules.xml new file mode 100644 index 0000000..854e742 --- /dev/null +++ b/.idea/modules.xml @@ -0,0 +1,8 @@ + + + + + + + + \ No newline at end of file diff --git a/.idea/vcs.xml b/.idea/vcs.xml new file mode 100644 index 0000000..35eb1dd --- /dev/null +++ b/.idea/vcs.xml @@ -0,0 +1,6 @@ + + + + + + \ No newline at end of file From 65178d41f6d866b3fd8e468790f779129cc10bac Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 4 Oct 2025 14:32:55 +0600 Subject: [PATCH 25/28] Add IDE workspace configuration file Added .idea/workspace.xml to store project-specific IDE settings. This file is typically generated by JetBrains IDEs and contains workspace preferences. --- .idea/workspace.xml | 49 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) create mode 100644 .idea/workspace.xml diff --git a/.idea/workspace.xml b/.idea/workspace.xml new file mode 100644 index 0000000..d3e8493 --- /dev/null +++ b/.idea/workspace.xml @@ -0,0 +1,49 @@ + + + + + + + + + + + + + + + + + + + + 1759564680061 + + + + \ No newline at end of file From edb06452806e31b4b460cfcdba1fa7cc81be2268 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sat, 4 Oct 2025 15:06:22 +0600 Subject: [PATCH 26/28] Update IDE configuration files Modified .idea/misc.xml and workspace.xml to reflect recent IDE state changes, including changelist updates, project color info formatting, new run activity, and VCS log tab properties. --- .idea/misc.xml | 1 - .idea/workspace.xml | 22 ++++++++++++++++++---- 2 files changed, 18 insertions(+), 5 deletions(-) diff --git a/.idea/misc.xml b/.idea/misc.xml index 3fe2d8e..2adfc2d 100644 --- a/.idea/misc.xml +++ b/.idea/misc.xml @@ -1,4 +1,3 @@ - - + + + \ No newline at end of file From a9dd5d62df35cc7a94e279e4460ebb8dbf989956 Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sun, 5 Oct 2025 04:26:35 +0600 Subject: [PATCH 27/28] Add project code style and Sweep config files Added .idea/SweepConfig.xml and code style configuration files to set up project-specific code formatting and Sweep tool settings. Updated workspace.xml to reflect these changes and include new project settings. --- .idea/SweepConfig.xml | 14 ++++ .idea/codeStyles/Project.xml | 120 +++++++++++++++++++++++++++ .idea/codeStyles/codeStyleConfig.xml | 5 ++ .idea/workspace.xml | 9 +- 4 files changed, 147 insertions(+), 1 deletion(-) create mode 100644 .idea/SweepConfig.xml create mode 100644 .idea/codeStyles/Project.xml create mode 100644 .idea/codeStyles/codeStyleConfig.xml diff --git a/.idea/SweepConfig.xml b/.idea/SweepConfig.xml new file mode 100644 index 0000000..1b3a926 --- /dev/null +++ b/.idea/SweepConfig.xml @@ -0,0 +1,14 @@ + + + + + + \ No newline at end of file diff --git a/.idea/codeStyles/Project.xml b/.idea/codeStyles/Project.xml new file mode 100644 index 0000000..57b2461 --- /dev/null +++ b/.idea/codeStyles/Project.xml @@ -0,0 +1,120 @@ + + + + + + + + \ No newline at end of file diff --git a/.idea/codeStyles/codeStyleConfig.xml b/.idea/codeStyles/codeStyleConfig.xml new file mode 100644 index 0000000..a55e7a1 --- /dev/null +++ b/.idea/codeStyles/codeStyleConfig.xml @@ -0,0 +1,5 @@ + + + + \ No newline at end of file diff --git a/.idea/workspace.xml b/.idea/workspace.xml index fef8cbf..6f02999 100644 --- a/.idea/workspace.xml +++ b/.idea/workspace.xml @@ -6,6 +6,7 @@ + From f92bb97030172065e1fef26430c8c0128c624adf Mon Sep 17 00:00:00 2001 From: Kazi Wahid Al Taher Date: Sun, 5 Oct 2025 18:49:22 +0600 Subject: [PATCH 28/28] Remove .idea config and update Colab notebook Deleted the .idea directory and related files, and added .idea to .gitignore to prevent future commits. Cleaned up the Google Colab notebook by removing the Colab badge, outdated code cells, and error outputs, and updated the list of available models. --- .gitignore | 3 + .idea/.github.iml | 9 -- .idea/.gitignore | 3 - .idea/modules.xml | 8 -- .idea/vcs.xml | 6 - ...Getting_started_with_google_colab_ai.ipynb | 134 ++++++------------ 6 files changed, 43 insertions(+), 120 deletions(-) create mode 100644 .gitignore delete mode 100644 .idea/.github.iml delete mode 100644 .idea/.gitignore delete mode 100644 .idea/modules.xml delete mode 100644 .idea/vcs.xml diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..cbef664 --- /dev/null +++ b/.gitignore @@ -0,0 +1,3 @@ +/.idea +/.idea +.idea/.github.iml diff --git a/.idea/.github.iml b/.idea/.github.iml deleted file mode 100644 index d6ebd48..0000000 --- a/.idea/.github.iml +++ /dev/null @@ -1,9 +0,0 @@ - - - - - - - - - \ No newline at end of file diff --git a/.idea/.gitignore b/.idea/.gitignore deleted file mode 100644 index 26d3352..0000000 --- a/.idea/.gitignore +++ /dev/null @@ -1,3 +0,0 @@ -# Default ignored files -/shelf/ -/workspace.xml diff --git a/.idea/modules.xml b/.idea/modules.xml deleted file mode 100644 index 854e742..0000000 --- a/.idea/modules.xml +++ /dev/null @@ -1,8 +0,0 @@ - - - - - - - - \ No newline at end of file diff --git a/.idea/vcs.xml b/.idea/vcs.xml deleted file mode 100644 index 35eb1dd..0000000 --- a/.idea/vcs.xml +++ /dev/null @@ -1,6 +0,0 @@ - - - - - - \ No newline at end of file diff --git a/notebooks/Getting_started_with_google_colab_ai.ipynb b/notebooks/Getting_started_with_google_colab_ai.ipynb index 12c72a8..ea523ac 100644 --- a/notebooks/Getting_started_with_google_colab_ai.ipynb +++ b/notebooks/Getting_started_with_google_colab_ai.ipynb @@ -1,15 +1,5 @@ { "cells": [ - { - "cell_type": "markdown", - "metadata": { - "id": "view-in-github", - "colab_type": "text" - }, - "source": [ - "\"Open" - ] - }, { "metadata": { "id": "wdj9RMfoGPC2" @@ -31,7 +21,7 @@ { "metadata": { "id": "Ucchuu5vV3Jp", - "outputId": "553795f3-2666-42d6-dc8e-074932326207", + "outputId": "a3004031-0e0c-4f8d-842d-a79421f51e11", "colab": { "base_uri": "https://localhost:8080/" } @@ -48,14 +38,31 @@ "output_type": "execute_result", "data": { "text/plain": [ - "['google/gemini-2.5-flash', 'google/gemini-2.5-flash-lite']" + "['google/gemini-2.0-flash',\n", + " 'google/gemini-2.0-flash-lite',\n", + " 'google/gemini-2.5-flash',\n", + " 'google/gemini-2.5-flash-lite',\n", + " 'google/gemini-2.5-pro',\n", + " 'google/gemma-3-12b',\n", + " 'google/gemma-3-1b',\n", + " 'google/gemma-3-27b',\n", + " 'google/gemma-3-4b']" ] }, "metadata": {}, - "execution_count": 12 + "execution_count": 27 } ], - "execution_count": 12 + "execution_count": 27 + }, + { + "cell_type": "code", + "source": [], + "metadata": { + "id": "9D74LOIiggIt" + }, + "execution_count": 27, + "outputs": [] }, { "metadata": { @@ -74,57 +81,29 @@ ] }, { + "cell_type": "code", + "source": [], "metadata": { - "id": "R7taibpc7x2l", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 339 - }, - "outputId": "ff5e983a-b672-4b14-d791-a8c7900995a9" + "id": "8fjql8kzgin1" }, - "cell_type": "code", - "source": [ - "# @title Simple batch generation example\n", - "# Only text-to-text input/output is supported\n", - "from google.colab import ai\n", - "\n", - "response = ai.generate_text(\"What is the capital of France?\")\n", - "print(response)" - ], - "outputs": [ - { - "output_type": "error", - "ename": "APIStatusError", - "evalue": "Error code: 402 - {'message': 'Colab Models is only available to Colab Pro and Pro+ subscribers.', 'type': 'invalid_request_error'}", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mAPIStatusError\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m/tmp/ipython-input-1782392906.py\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mgoogle\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolab\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mai\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m \u001b[0mresponse\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mai\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgenerate_text\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"What is the capital of France?\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 6\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/google/colab/ai.py\u001b[0m in \u001b[0;36mgenerate_text\u001b[0;34m(prompt, model_name, stream)\u001b[0m\n\u001b[1;32m 83\u001b[0m )\n\u001b[1;32m 84\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 85\u001b[0;31m response = client.chat.completions.create(\n\u001b[0m\u001b[1;32m 86\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmodel_name\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 87\u001b[0m \u001b[0mmessages\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m{\u001b[0m\u001b[0;34m'role'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;34m'user'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'content'\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mprompt\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/_utils/_utils.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 284\u001b[0m \u001b[0mmsg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34mf\"Missing required argument: {quote(missing[0])}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 285\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmsg\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 286\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 287\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 288\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mwrapper\u001b[0m \u001b[0;31m# type: ignore\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/resources/chat/completions/completions.py\u001b[0m in \u001b[0;36mcreate\u001b[0;34m(self, messages, model, audio, frequency_penalty, function_call, functions, logit_bias, logprobs, max_completion_tokens, max_tokens, metadata, modalities, n, parallel_tool_calls, prediction, presence_penalty, prompt_cache_key, reasoning_effort, response_format, safety_identifier, seed, service_tier, stop, store, stream, stream_options, temperature, tool_choice, tools, top_logprobs, top_p, user, verbosity, web_search_options, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m 1145\u001b[0m ) -> ChatCompletion | Stream[ChatCompletionChunk]:\n\u001b[1;32m 1146\u001b[0m \u001b[0mvalidate_response_format\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponse_format\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1147\u001b[0;31m return self._post(\n\u001b[0m\u001b[1;32m 1148\u001b[0m \u001b[0;34m\"/chat/completions\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1149\u001b[0m body=maybe_transform(\n", - "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/_base_client.py\u001b[0m in \u001b[0;36mpost\u001b[0;34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1257\u001b[0m \u001b[0mmethod\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"post\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0murl\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mjson_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mbody\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfiles\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mto_httpx_files\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfiles\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0moptions\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1258\u001b[0m )\n\u001b[0;32m-> 1259\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mcast\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mResponseT\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcast_to\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mopts\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstream\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstream\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstream_cls\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstream_cls\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1260\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1261\u001b[0m def patch(\n", - "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/openai/_base_client.py\u001b[0m in \u001b[0;36mrequest\u001b[0;34m(self, cast_to, options, stream, stream_cls)\u001b[0m\n\u001b[1;32m 1045\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1046\u001b[0m \u001b[0mlog\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdebug\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Re-raising status error\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1047\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_make_status_error_from_response\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0merr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresponse\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1048\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1049\u001b[0m \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mAPIStatusError\u001b[0m: Error code: 402 - {'message': 'Colab Models is only available to Colab Pro and Pro+ subscribers.', 'type': 'invalid_request_error'}" - ] - } - ], - "execution_count": 13 + "execution_count": 27, + "outputs": [] }, { + "cell_type": "markdown", + "source": [], "metadata": { - "id": "NHO9VzO9AHZP" - }, + "id": "cNSefuDZgjqV" + } + }, + { "cell_type": "code", - "source": [ - "# @title Choose a different model\n", - "from google.colab import ai\n", - "\n", - "response = ai.generate_text(\"What is the capital of England\", model_name='google/gemini-2.0-flash-lite')\n", - "print(response)" - ], - "outputs": [], - "execution_count": null + "source": [], + "metadata": { + "id": "0_KsQAqsgkW9" + }, + "execution_count": 27, + "outputs": [] }, { "metadata": { @@ -135,22 +114,6 @@ "For longer text generations, you can stream the response. This displays the output token by token as it's generated, rather than waiting for the entire response to complete. This provides a more interactive and responsive experience. To enable this, simply set stream=True." ] }, - { - "metadata": { - "id": "4BNgxiB6--_5" - }, - "cell_type": "code", - "source": [ - "# @title Simple streaming example\n", - "from google.colab import ai\n", - "\n", - "stream = ai.generate_text(\"Tell me a short story.\", stream=True)\n", - "for text in stream:\n", - " print(text, end='')" - ], - "outputs": [], - "execution_count": null - }, { "metadata": { "id": "CpMmpaVClSBV", @@ -231,29 +194,12 @@ " sys.stdout.flush()\n" ], "outputs": [], - "execution_count": null - }, - { - "metadata": { - "id": "DWiLPzTnRoy-" - }, - "cell_type": "code", - "source": [ - "# @title Formatted streaming example\n", - "from google.colab import ai\n", - "\n", - "wrapper = LineWrapper()\n", - "for chunk in ai.generate_text('Give me a long winded description about the evolution of the Roman Empire.', model_name='google/gemini-2.0-flash', stream=True):\n", - " wrapper.print(chunk)" - ], - "outputs": [], - "execution_count": null + "execution_count": 29 } ], "metadata": { "colab": { - "provenance": [], - "include_colab_link": true + "provenance": [] }, "kernelspec": { "name": "python3",