Plotting Hardware Evaluation

notebooks/extract_cpus_from_tpc.ipynb

@@ -0,0 +1,194 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Input:\n",
+    "- tpc_cpu.csv (manually created by DES team, based on TPC-C and TPC-Hv2 (SF 1000) result data.)\n",
+    "### Output:\n",
+    "- tpc_xeon.csv\n",
+    "- tpc_sku.csv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install pandas duckdb matplotlib seaborn\n",
+    "\n",
+    "import pandas as pd\n",
+    "import duckdb\n",
+    "import os\n",
+    "import matplotlib.pyplot as plt\n",
+    "import re\n",
+    "import seaborn as sns\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "file_path = '../tpc_cpu.csv'\n",
+    "if os.path.exists(file_path):\n",
+    "    df = pd.read_csv(file_path, sep=\",\")\n",
+    "else:\n",
+    "    raise FileNotFoundError(f\"The file {file_path} does not exist.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def extract_performance_id(name):\n",
+    "    match = re.search(r'\\d{4}', name)\n",
+    "    if match:\n",
+    "        return match.group(0)[-2:]\n",
+    "    return None\n",
+    "\n",
+    "def extract_sku_level(name):\n",
+    "    match = re.search(r'\\d{4}', name)\n",
+    "    if match:\n",
+    "        return int(match.group(0)[0])\n",
+    "    return None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Clean / add data\n",
+    "print(\"TPC result count\", len(df))\n",
+    "df = df[df['model'].str.contains('xeon', case=False, na=False)]\n",
+    "print(\"TPC result count with XEON CPUs\", len(df))\n",
+    "df['performance_id'] = df['model'].apply(extract_performance_id)\n",
+    "df['sku_level'] = df['model'].apply(extract_sku_level)\n",
+    "# display(df)\n",
+    "# df = df[df['sku_level'] != '']\n",
+    "display(df)\n",
+    "df.to_csv(\"../tpc_sku.csv\", header=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sku_counts = df['sku_level'].value_counts().sort_index()\n",
+    "\n",
+    "# Creating the bar plot\n",
+    "plt.figure(figsize=(10, 3))\n",
+    "sku_counts.plot(kind='bar')\n",
+    "\n",
+    "# Adding titles and labels\n",
+    "plt.title('Occurrences of sku_level')\n",
+    "plt.xlabel('SKU Level')\n",
+    "plt.ylabel('Number of Occurrences')\n",
+    "\n",
+    "# Setting y-axis to show only integer values\n",
+    "plt.yticks(np.arange(0, sku_counts.max() + 1, 1))\n",
+    "\n",
+    "# Displaying the plot\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sku_counts = df['performance_id'].value_counts().sort_index()\n",
+    "\n",
+    "# Creating the bar plot\n",
+    "plt.figure(figsize=(6, 2))\n",
+    "sku_counts.plot(kind='bar')\n",
+    "\n",
+    "# Adding titles and labels\n",
+    "plt.title('Occurrences of performance_id')\n",
+    "plt.xlabel('Perf ID')\n",
+    "plt.ylabel('Number of Occurrences')\n",
+    "\n",
+    "# Setting y-axis to show only integer values\n",
+    "plt.yticks(np.arange(0, sku_counts.max() + 1, 1))\n",
+    "\n",
+    "# Displaying the plot\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_csv(\"../tpc_xeon.csv\")\n",
+    "cpu_models = df['model']\n",
+    "cpu_models.to_csv(\"../tpc_xeon_names.csv\")\n",
+    "\n",
+    "# Filter with sku level\n",
+    "df = df[df['sku_level'] >= 5]\n",
+    "\n",
+    "sku_counts = df['performance_id'].value_counts().sort_index()\n",
+    "\n",
+    "# Creating the bar plot\n",
+    "plt.figure(figsize=(6, 2))\n",
+    "sku_counts.plot(kind='bar')\n",
+    "\n",
+    "# Adding titles and labels\n",
+    "plt.title('Occurrences of performance_id')\n",
+    "plt.xlabel('Perf ID')\n",
+    "plt.ylabel('Number of Occurrences')\n",
+    "\n",
+    "# Setting y-axis to show only integer values\n",
+    "plt.yticks(np.arange(0, sku_counts.max() + 1, 1))\n",
+    "\n",
+    "# Displaying the plot\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# con = duckdb.connect(\"../spec.db\") # assumes DuckDB DB \"spec.db\" in root dir\n",
+    "# con.sql(\"DROP TABLE IF EXISTS spec\")\n",
+    "# con.sql(\"CREATE TABLE spec AS SELECT * FROM df_combined\")\n",
+    "# con.close()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}