A unified approach to explain the output of any machine learning model.
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.
Release history Release notifications
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size & hash SHA256 hash help||File type||Python version||Upload date|
|shap-0.28.3-cp36-cp36m-macosx_10_7_x86_64.whl (274.5 kB) Copy SHA256 hash SHA256||Wheel||3.6|
|shap-0.28.3-cp36-cp36m-win_amd64.whl (251.9 kB) Copy SHA256 hash SHA256||Wheel||3.6|
|shap-0.28.3-cp37-cp37m-win_amd64.whl (251.9 kB) Copy SHA256 hash SHA256||Wheel||3.7|
|shap-0.28.3.tar.gz (222.7 kB) Copy SHA256 hash SHA256||Source||None|