fairfru 1.9.2

A bias measure based on the fuzzy rough set theory

Using fuzzy-rough sets to measure bias in pattern classification problems

This python package contains a bias metric based on the paper "A fuzzy-rough uncertainty measure to discover bias encoded explicitly or implicitly in features of structured pattern classification datasets" (Link to publication).

This bias metric measures the extent to which a feature in a dataset influences the outcome variable.

fairfru (see here) is a Python package providing algorithms able to quantify fairness in automated decision making using the fuzzy-rough set theory.

Installation

Use the package manager pip to install FairFRU.

pip install fairfru

Usage

import fairfru

See the Measuring_bias.ipynb file for an example of how to use this approach.

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

License

MIT