aprofs package metadada

aprofs: Approximate Prediction Feature Selection using Shapley Values

Welcome to aprofs, an open-source Python package designed to simplify the process of feature selection using approximate prediction with Shapley values.

The idea is that using on this package you can speed up feature selection (in an approximate way).

Please look at the package website for more resources: Aprofs Documentation

Features

• Feature Selection: aprofs uses Shapley values, a concept from cooperative game theory, to identify the most important features in your dataset.

• Feature Visualization: aprofs uses Shapley values to check the marginal behavior of the feature used by the model using pdp plots.

Installation

You can install aprofs via pip:

pip install aprofs==0.0.5

Usage

Please look into the website here: Aprofs Documentation

Contributing

As an open-source project, we welcome contributions from the community. I will create a CONTRIBUTING.md for guidelines on how to contribute.

License This project is licensed under the terms of the MIT license.