Welcome to the SHAP documentation 

SHAP (SHapley Additive exPlanations) is a game theoretic approach to explain the output of any machine learning model. It connects optimal credit allocation with local explanations using the classic Shapley values from game theory and their related extensions (see papers for details and citations).

Install 

SHAP can be installed from either PyPI or conda-forge :

pip install shap
conda install -c conda-forge shap
Introduction
Topical overviews

An introduction to explainable AI with Shapley values
Be careful when interpreting predictive models in search of causal insights
Explaining quantitative measures of fairness