Diversity IQ is an AI-powered tool that helps detect bias in your dataset before model training. It analyzes categorical features like gender or ethnicity, flags imbalance, and offers suggestions to improve fairness — helping you build ethical AI from the ground up.

Follow the steps below to run the project locally.

git clone https://github.com/your-username/diversity-iq.git
cd diversity-iq

Make sure Python 3.8+ is installed.

pip install -r requirements.txt

In the root directory, create a .env file and add your OpenAI API key:

OPEN_AI_API=your_openai_api_key_here

uvicorn main:app --reload

The backend will start at:
📍 http://127.0.0.1:8000

cd frontend

npm install

npm start

The frontend will start at:
🌐 http://localhost:3000

• 📊 Category-wise Distribution Stats
• ⚖️ Fairness Verdict
• 💡 Actionable Suggestions to improve dataset balance
• 🧠 Uses OpenAI for smart analysis
• 📈 Ready for frontend visualization

Upload a CSV file with columns like gender, ethnicity, etc. The tool returns:

{
  "gender": {
    "male": 60,
    "female": 40
  },
  "genderComment": "One category has over 50% representation. Consider balancing.",
  "verdict": "Unfair Distribution"
}

• Frontend: React.js
• Backend: FastAPI
• AI Integration: OpenAI API
• Languages: Python, JavaScript