Welcome to MANILA’s documentation!

MANILA is a low-code web-application to benchmark the fairness and effectiveness of machine learning models and fairness enhancing methods.

Installation

To install MANILA, you can use the following command:

Using Docker

To run the application using Docker, execute the following command:

docker-compose up

The application will be available at http://localhost:3000.

Manually

To run the application manually, follow the steps below:

  1. Install the dependencies of the backend:

cd app
pip install -r requirements.txt
  1. Install and launch the Redis database (refer to the official documentation (https://redis.io/download) for more information).

  2. Launch the backend:

cd app
python manila/app.py
  1. Launch the Celery worker:

cd app/manila
celery -A run_celery.celery worker --loglevel=info
  1. Install the dependencies of the frontend:

cd frontend
npm install
  1. Launch the frontend:

cd frontend
npm start

The application will be available at http://localhost:3000.

Citation Request

Please cite our work if you use MANILA in your research:

d’Aloisio, G., Di Marco, A., Stilo, G. (2023). Democratizing Quality-Based Machine Learning Development through Extended Feature Models. In: Lambers, L., Uchitel, S. (eds) Fundamental Approaches to Software Engineering. FASE 2023. Lecture Notes in Computer Science, vol 13991. Springer, Cham. https://doi.org/10.1007/978-3-031-30826-0_5

@inproceedings{d2023democratizing,
   title={Democratizing Quality-Based Machine Learning Development through Extended Feature Models},
   author={d’Aloisio, Giordano and Di Marco, Antinisca and Stilo, Giovanni},
   booktitle={International Conference on Fundamental Approaches to Software Engineering},
   pages={88--110},
   year={2023},
   doi={10.1007/978-3-031-30826-0_5},
   organization={Springer Nature Switzerland Cham}
}

Contents