29 code review

.flake8

@@ -0,0 +1,3 @@
+[flake8]
+exclude = .venv/*
+docstring-convention=google

.gitignore

@@ -0,0 +1,228 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python,venv,visualstudiocode
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,venv,visualstudiocode
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### venv ###
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+[Ss]cripts
+pyvenv.cfg
+pip-selfcheck.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+# End of https://www.toptal.com/developers/gitignore/api/python,venv,visualstudiocode
+
+uv.lock
+.ruff_cache
+
+# Data Folders
+data
+
+# Model Storage
+model_checkpoints/*
+
+
+# testing/debugging notebooks
+test.ipynb
+buowset.ipynb
+
+# Question: do we want to commit vscode setting.json files?
+settings.json
+
+# Block all configs besides the example config
+whoot_model_training/configs
+!whoot_model_training/configs/config.yml

.python-version

@@ -0,0 +1 @@
+3.12

README.md

@@ -1,2 +1,45 @@
 # whoot
 Tools for capturing, analyzing, and parsing audio data
+
+# Installation Instructions
+
+## Default Python Instructions
+1) Install Python>=3.10
+2) Create a virtual enviroment via `python -m venv`
+3) Activate the enviroment using an activate script:
+
+- Windows: `.venv\Scripts\activate`
+- macOS/Linux: `source .venv/bin/activate`
+
+If this works, you should see in your command line `(whoot)`. If not check https://docs.python.org/3/library/venv.html#how-venvs-work
+
+4) Run in project root `pip install -e .`
+
+To install optional dependencies run `pip install -e .[extra1,extra2,...]`
+
+Current support optional dependency collections include
+
+- `cpu`: Installs torch and torchvision for CPU use only
+- `cu128`: Installs torch and torchvision with Cuda 12.8 Binaries
+- `model-training`: Required for running scripts in `whoot/model_training`, make sure to add either `cpu` or `cu128`
+- `dev`: Installs linters pylint and flake8. MUST be used by developers of whoot
+
+## Usage
+
+Once the enviroment is activated, you should be able to do `python path/to/script.py` to run any of the whoot scripts. If a script states a package is missing, you might not be using the virtual enviroment.
+
+# Developer Notes
+
+## Creating a new Project
+
+When adding a new package, like `assess_birdnet` to the whoot toolkit, add your package name to the `[tool.setuptools]` section of `pyproject.toml` 
+
+### Linting 
+
+Style guidelines are listed in `.flake8` and `pylintrc`. To use these tools do the following
+
+1) Follow the Installation Instructions, on pip install do `pip install -e .[dev,extra1,extra2,...]`.
+2) Activate the environment
+
+To run the linters run `python -m flake8` and `python -m pylint --recursive y PATH/TO/FILES.py`
+In order to contribute to whoot, both of these must be cleared. 

cfgs/params_segment_2017_data.yaml

@@ -0,0 +1,2 @@
+#length added to beginning and end of detection segment (ms)
+padding: 100

comet_ml_panels/leaderboard.py

@@ -0,0 +1,85 @@
+# """Creates the Leaderboard for Comet ML Panels
+
+# This script queries from a given Comet ML project a DataFrame of
+# model metrics at each step for each model in the project
+# Then displays the top models.
+
+# Example:
+#     This is not intended to be run locally. Please test on Comet-ML.
+
+# For Developers:
+#     For more on adding to this see docs at
+#     https://www.comet.com/docs/v2/guides/comet-ui/experiment-management/visualizations/python-panel/
+
+#     Note that updating this file does not update comet-ml. Please
+#     go into the project to update after pushing to GitHub.
+
+#     Do not include Doc string in comet-ml... for some reason this
+#     is displayed in the comet-ml panel if copied directly
+# """
+from comet_ml import API, APIExperiment, ui
+import pandas as pd
+import numpy as np
+
+# Initialize Comet API
+api = API()
+
+# Select the experiments and metrics to compare
+available_metrics = ["train/valid_cMAP", "train/valid_ROCAUC"]
+selected_metric = ui.dropdown("Select a metric:", available_metrics)
+
+experiment_keys = api.get_panel_experiment_keys()
+data = api.get_metrics_for_chart(
+    experiment_keys, metrics=[selected_metric], parameters=["task"])
+
+# Given all experiments, find all possible tasks to measure!
+available_tasks = list(
+    set(data[key]["params"]["task"]
+        for key in data if "task" in data[key]["params"])
+)
+available_tasks.append(None)
+selected_task = ui.dropdown("Select a Task:", available_tasks)
+
+processed_data = []
+
+for key in data:
+    # Note, some of the early runs have no value for the task
+    # The following code handles those cases
+    TASK = None
+    if "task" in data[key]["params"]:
+        TASK = data[key]["params"]["task"]
+
+    # Only display the leaderboard for tasks we want
+    # This CAN include runs with no task
+    if TASK is not selected_task and TASK != selected_task:
+        continue
+
+    # Failed runs may not have metrics
+    if len(data[key]["metrics"]) == 0:
+        continue
+
+    metric_values = data[key]["metrics"][0]["values"]
+    max_index = np.argmax(metric_values)
+
+    processed_data.append({
+        "experiment_name": data[key]["experimentName"],
+        "experiment_key": key,
+        selected_metric: max(metric_values),
+        "step": data[key]["metrics"][0]["steps"][max_index],
+    })
+
+leaderboard_df = pd.DataFrame(processed_data).sort_values(
+    selected_metric, ascending=False)
+
+leaderboard_df["users"] = leaderboard_df["experiment_key"].apply(
+    lambda key: APIExperiment(previous_experiment=key).get_user()
+)
+
+col_order = [
+    "experiment_name",
+    selected_metric,
+    "experiment_key",
+    "step",
+    "users"
+]
+ui.display(leaderboard_df[col_order])