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-0.32.0.tar.gz (259.2 kB view details)

Uploaded Source

Built Distributions

shap-0.32.0-cp37-cp37m-win_amd64.whl (292.2 kB view details)

Uploaded CPython 3.7m Windows x86-64

shap-0.32.0-cp37-cp37m-macosx_10_7_x86_64.whl (294.5 kB view details)

Uploaded CPython 3.7m macOS 10.7+ x86-64

shap-0.32.0-cp36-cp36m-win_amd64.whl (292.2 kB view details)

Uploaded CPython 3.6m Windows x86-64

File details

Details for the file shap-0.32.0.tar.gz.

File metadata

  • Download URL: shap-0.32.0.tar.gz
  • Upload date:
  • Size: 259.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.7

File hashes

Hashes for shap-0.32.0.tar.gz
Algorithm Hash digest
SHA256 8cb80df60e75375519394031acc6a77cdde4db3395eb0a18ba50e3436445ef97
MD5 923f917ce213a083c5c44c524d6ece17
BLAKE2b-256 2cbe2bd61b37aad3bd3721cc6f53d081854e7d4a6deb1242cac3a8b09a3a2102

See more details on using hashes here.

File details

Details for the file shap-0.32.0-cp37-cp37m-win_amd64.whl.

File metadata

  • Download URL: shap-0.32.0-cp37-cp37m-win_amd64.whl
  • Upload date:
  • Size: 292.2 kB
  • Tags: CPython 3.7m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.7

File hashes

Hashes for shap-0.32.0-cp37-cp37m-win_amd64.whl
Algorithm Hash digest
SHA256 d7b40420fa972afb8f3053d8ffca5c81d61f76e5357a9a0c8e1c36e22e739863
MD5 524da8340524fdfd21656a697edfa219
BLAKE2b-256 a7c9b34ff28c0907d1191bdf27dce67889e91e01f445d8cb477d0d484d997735

See more details on using hashes here.

File details

Details for the file shap-0.32.0-cp37-cp37m-macosx_10_7_x86_64.whl.

File metadata

File hashes

Hashes for shap-0.32.0-cp37-cp37m-macosx_10_7_x86_64.whl
Algorithm Hash digest
SHA256 e3a86cf28649058a58c55b5785865b91f94292744640a31c87fcc55a38f5aadd
MD5 5256df052a0ca512276bc44da04d631d
BLAKE2b-256 58f3ae4191c8cd2e593a7e6d98502fe3b170c31a0d80d2d27d1ae4b7a1faf99f

See more details on using hashes here.

File details

Details for the file shap-0.32.0-cp36-cp36m-win_amd64.whl.

File metadata

  • Download URL: shap-0.32.0-cp36-cp36m-win_amd64.whl
  • Upload date:
  • Size: 292.2 kB
  • Tags: CPython 3.6m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.6

File hashes

Hashes for shap-0.32.0-cp36-cp36m-win_amd64.whl
Algorithm Hash digest
SHA256 2dd0f34bdbb31cd9d0567965f928ac889025c7fd696ed4e357e5cc5fb47a8f0a
MD5 ee15c377e52076cbbe2ad6177ede94d8
BLAKE2b-256 3cf34dbb90cc7801e874ebbbf5a8e8c3359f6f71ce38ab1216a261844d99c181

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