Thanks for your interest in contributing! This document explains how to get started and our basic workflows.
- Fork the repo and clone your fork.
- Create a virtual environment and install dependencies:
- Runtime:
pip install -r requirements.txt - Notebooks/dev:
pip install -r requirements-dev.txt(optional)
- Runtime:
- Ensure the runtime assets exist:
data/processed/city_features_engineered.csvdata/processed/scaler.pkldata/processed/feature_columns.pklmodels/xgboost.pkl
- Create a feature branch:
git checkout -b feature/short-description - Run the app locally:
streamlit run streamlit_app.py - Add tests or notebook updates if you change data or model logic.
- Python 3.11+ recommended locally
- Follow PEP 8 style guidelines
- Keep
requirements.txtminimal for runtime; userequirements-dev.txtfor notebook tooling
- Commit with clear messages:
feat: add city filter - Push your branch and open a Pull Request (PR)
- Fill out the PR template (see .github/pull_request_template.md)
- Ensure CI (if configured) passes
- A maintainer will review and merge
- Use GitHub Issues. Please include:
- Steps to reproduce
- Expected behavior
- Actual behavior and logs/screenshots
- Environment (OS, Python version)
See SECURITY.md for reporting vulnerabilities. Please do not disclose security issues publicly before they are resolved.