StigmaSense

A Python toolkit for mpox related mental health stigma research using machine learning and natural language processing.

Prerequisites

• Python 3.11 or higher
• pip (Python package installer)

Setup Instructions

1. Install uv (modern Python package manager):

   pip install uv
   

2. Clone the repository:

   git clone <repository-url>
   cd StigmaSense
   

3. Install dependencies:

   uv sync
   

4. Activate the virtual environment:

   source .venv/bin/activate  # On Unix/macOS
   # or
   .venv\Scripts\activate     # On Windows
   

Development Setup

For development with additional tools:

# Install with development dependencies
uv sync --group dev

This includes linting, formatting, and type checking tools:

• ruff: Fast Python linter and formatter
• black: Code formatter
• isort: Import sorter
• mypy: Static type checker
• pre-commit: Git hooks for code quality

Usage

Jupyter Notebooks

Explore the analysis notebooks in the notebooks/ directory:

# Start Jupyter Lab
jupyter lab notebooks/

Available notebooks:

• wrangle.ipynb: Data preprocessing and cleaning
• explore.ipynb: Initial data exploration

Project Structure

StigmaSense/
├── data/                   # Data storage and management
│   ├── raw/               # Raw, unprocessed data
│   ├── processed/         # Cleaned and preprocessed data
│   ├── modeling/          # Data prepared for modeling
│   ├── cache/             # Cached intermediate results
│   ├── chromadb/          # Vector database storage
│   └── prompts/           # Prompt templates for LLMs
├── models/                # Pre-trained and fine-tuned models
├── notebooks/             # Jupyter notebooks for analysis
├── scripts/               # Utility and processing scripts
├── src/stigmasense/       # Main Python package
└── pyproject.toml         # Project configuration and dependencies

Development Commands

Contributing

1. Fork the repository
2. Create a feature branch
3. Install development dependencies: uv sync --group dev
4. Make your changes and ensure code quality:

   uv run ruff check      # Check for linting issues
   uv run ruff format     # Format code
   

5. Test your changes
6. Submit a pull request