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-0.23.1.tar.gz (176.7 kB view details)

Uploaded Source

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

shap-0.23.1-cp37-cp37m-win_amd64.whl (188.6 kB view details)

Uploaded CPython 3.7mWindows x86-64

shap-0.23.1-cp36-cp36m-win_amd64.whl (188.6 kB view details)

Uploaded CPython 3.6mWindows x86-64

shap-0.23.1-cp36-cp36m-macosx_10_7_x86_64.whl (194.9 kB view details)

Uploaded CPython 3.6mmacOS 10.7+ x86-64

File details

Details for the file shap-0.23.1.tar.gz.

File metadata

  • Download URL: shap-0.23.1.tar.gz
  • Upload date:
  • Size: 176.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.6

File hashes

Hashes for shap-0.23.1.tar.gz
Algorithm Hash digest
SHA256 d70737e8f8a0b898757b8b5543f6437cb8c0bd144596929ad784bb70006b1799
MD5 b09dffd3af361cb2ee9ee766a335504f
BLAKE2b-256 daea8cf156400fccfc4881d0d67bcae09bd888625a365b068cd6f54cf839580a

See more details on using hashes here.

File details

Details for the file shap-0.23.1-cp37-cp37m-win_amd64.whl.

File metadata

  • Download URL: shap-0.23.1-cp37-cp37m-win_amd64.whl
  • Upload date:
  • Size: 188.6 kB
  • Tags: CPython 3.7m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.7

File hashes

Hashes for shap-0.23.1-cp37-cp37m-win_amd64.whl
Algorithm Hash digest
SHA256 14d216c78533ec076fb1fcb29d5e5b626af9066e9fd5b06fc6bb1e3ac8b0fcaf
MD5 857f748fbb5ff06a11698c458595308c
BLAKE2b-256 400675b942af15a660fff4d794bd29ba3ff99072854e0d252c0773b6a8a7dcc7

See more details on using hashes here.

File details

Details for the file shap-0.23.1-cp36-cp36m-win_amd64.whl.

File metadata

  • Download URL: shap-0.23.1-cp36-cp36m-win_amd64.whl
  • Upload date:
  • Size: 188.6 kB
  • Tags: CPython 3.6m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.6

File hashes

Hashes for shap-0.23.1-cp36-cp36m-win_amd64.whl
Algorithm Hash digest
SHA256 df4766e7cd0e140521564ef574f1f60b7b0fd257ae18288da4791a2a92f638a6
MD5 429f94c5f39619ff439dd16d789a1047
BLAKE2b-256 145d225ad9a73147b7d97ae570b7271a65e8743e8055fb0820747d60493af27c

See more details on using hashes here.

File details

Details for the file shap-0.23.1-cp36-cp36m-macosx_10_7_x86_64.whl.

File metadata

File hashes

Hashes for shap-0.23.1-cp36-cp36m-macosx_10_7_x86_64.whl
Algorithm Hash digest
SHA256 4d3b6f2f0b6e0663ae40d10461bb7ed8c337cce78f50ca1dea21fbc00c1c1d5a
MD5 30d61704adea657536f657bc3bc1a7d2
BLAKE2b-256 132d4d50871401262e730e616e4d89bb2a2ec9da961b8dd5555ff9d8c1367f9c

See more details on using hashes here.

Supported by

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