Python implementation of the rulefit algorithm

A game theoretic approach to explain the output of any machine learning model.

OpenXAI : Towards a Transparent Evaluation of Model Explanations

A Python framework for the quantitative evaluation of eXplainable AI methods

Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

OmniXAI: A Library for eXplainable AI

A Toolbox for the Evaluation of machine learning Explanations

Modular Python Toolbox for Fairness, Accountability and Transparency Forensics

A toolbox to iNNvestigate neural networks' predictions!

Shapley Interactions and Shapley Values for Machine Learning

Lime: Explaining the predictions of any machine learning classifier