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-ppc64le  v0.40.0
  • osx-arm64  v0.40.0
  • linux-64  v0.40.0
  • linux-aarch64  v0.40.0
  • osx-64  v0.40.0
  • win-64  v0.40.0
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
conda install -c conda-forge/label/cf202003 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.


© 2022 Anaconda, Inc. All Rights Reserved. (v2.35.6 fab5c9df) Legal | Privacy Policy