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

Installers

Info: This package contains files in non-standard labels.

conda install

  • linux-64  v0.27.0
  • win-64  v0.27.0
  • osx-64  v0.27.0
To install this package with conda run one of the following:
conda install -c conda-forge shap
conda install -c conda-forge/label/cf201901 shap

Description

SHAP (SHapley Additive exPlanations) is a unified approach to explain the output of any machine learning model. SHAP connects game theory with local explanations, uniting several previous methods and representing the only possible consistent and locally accurate additive feature attribution method based on expectations.

PRIVACY POLICY  |  EULA (Anaconda Cloud v2.33.29) © 2019 Anaconda, Inc. All Rights Reserved.