Skip to main content

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

Project 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.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

shap-0.31.0.tar.gz (257.3 kB view details)

Uploaded Source

Built Distributions

shap-0.31.0-cp37-cp37m-win_amd64.whl (289.5 kB view details)

Uploaded CPython 3.7m Windows x86-64

shap-0.31.0-cp37-cp37m-macosx_10_7_x86_64.whl (292.7 kB view details)

Uploaded CPython 3.7m macOS 10.7+ x86-64

shap-0.31.0-cp36-cp36m-win_amd64.whl (289.5 kB view details)

Uploaded CPython 3.6m Windows x86-64

File details

Details for the file shap-0.31.0.tar.gz.

File metadata

  • Download URL: shap-0.31.0.tar.gz
  • Upload date:
  • Size: 257.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.7

File hashes

Hashes for shap-0.31.0.tar.gz
Algorithm Hash digest
SHA256 981a79ad451526cba1b6a63d6c2267e9451a17a6fecfbbd904f95c4db048d180
MD5 c07617206d288624c19d685c51944899
BLAKE2b-256 2b4b5944c379c94f8f6335dd36b9316292236e3da0dee8da806f60aecf0d5ce7

See more details on using hashes here.

File details

Details for the file shap-0.31.0-cp37-cp37m-win_amd64.whl.

File metadata

  • Download URL: shap-0.31.0-cp37-cp37m-win_amd64.whl
  • Upload date:
  • Size: 289.5 kB
  • Tags: CPython 3.7m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.7

File hashes

Hashes for shap-0.31.0-cp37-cp37m-win_amd64.whl
Algorithm Hash digest
SHA256 bb0813331b058f702db9070348c450e3a239d0af8ac9da87952f2f568b9b3c8e
MD5 6110428b633e665de1df1a55c81d5438
BLAKE2b-256 f9513bb6dd0af716f3a523c00fa3e58d9f739778cd3942f23527541e88235ea7

See more details on using hashes here.

File details

Details for the file shap-0.31.0-cp37-cp37m-macosx_10_7_x86_64.whl.

File metadata

File hashes

Hashes for shap-0.31.0-cp37-cp37m-macosx_10_7_x86_64.whl
Algorithm Hash digest
SHA256 bbf5afd2a4d91d109e71de8b10fa2f91539be2505d23b09ae519e7191d41faf9
MD5 7502e6808a2e43b9fd629e78370ea98d
BLAKE2b-256 375598323976e93d2f948c9450e59fa8043ce6c23ce87691c965f90540869920

See more details on using hashes here.

File details

Details for the file shap-0.31.0-cp36-cp36m-win_amd64.whl.

File metadata

  • Download URL: shap-0.31.0-cp36-cp36m-win_amd64.whl
  • Upload date:
  • Size: 289.5 kB
  • Tags: CPython 3.6m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.6

File hashes

Hashes for shap-0.31.0-cp36-cp36m-win_amd64.whl
Algorithm Hash digest
SHA256 9fda0ae2dfeca1b9ec7b2a842666fbe09f29e4d30b8f0bcd38b02de275704e9e
MD5 6e49476d887f1f78cd9ab023669b946a
BLAKE2b-256 c7f5c429de95fbdd1c5843a70cf510cf753cc709f7122e4bf67e73502c20beb0

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page