This project is a web application that evaluates AI systems based on various criteria such as fairness, accountability, and transparency. The scores are visualized using a radial graph, and the data is stored in an SQLite database.
- Fairness Assessment: Evaluates AI systems based on demographic parity, equal opportunity, and absence of disparate impact.
- Accountability Assessment: Scores AI systems on documentation practices, auditability, and compliance with ethical guidelines.
- Transparency Assessment: Measures explainability, user interface design, and decision-making documentation.
- Data Storage: Stores the assessment scores and generated graphs in an SQLite database.
- Graph Visualization: Displays a radial graph representing the scores.
- Python: Programming language used for the backend.
- Flask: Micro web framework for Python.
- SQLite: Database for storing scores and graphs.
- Plotly: Library for creating interactive graphs.
- Bootstrap: Frontend framework for styling the web pages.
- Heroku: Platform for deploying the web application.
-
Clone the repository:
git clone https://github.com/yourusername/explainability-scoring-system.git cd explainability-scoring-system
-
Create a virtual environment:
python -m venv venv source venv/bin/activate # On Windows use `venv\Scripts\activate`
-
Install dependencies:
pip install -r requirements.txt
-
Initialize the database:
python database_setup.py
-
Run the application:
python app.py
-
Open your browser and visit:
http://127.0.0.1:5000
To deploy the application on Heroku, follow these steps:
-
Login to Heroku:
heroku login
-
Create a new Heroku app:
heroku create your-app-name
-
Push the code to Heroku:
git push heroku main
-
Run database setup on Heroku:
heroku run python database_setup.py
-
Open the deployed app:
heroku open
- Home Page: Enter the AI system title and scores for each criterion, then click "Calculate".
- View Results: Click "View Stored Scores" to see all stored scores and view individual score details and graphs.
Contributions are welcome! Please fork the repository and create a pull request with your changes.
This project is licensed under the MIT License. See the LICENSE file for details.
For any questions or feedback, please contact [email protected].