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:

pip install shap

or conda-forge:

conda install -c conda-forge shap

Contents

• API Reference
  • Core Explainers
  • Other Explainers
  • Plots
  • Datasets
• Examples
  • General
  • Kernel Explainer
  • Tree Explainer
  • Deep Explainer
  • Gradient Explainer
  • Linear Explainer
  • Partition Explainer
  • Plots