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-0.30.0.tar.gz (241.0 kB view details)

Uploaded Source

Built Distributions

shap-0.30.0-cp37-cp37m-win_amd64.whl (272.2 kB view details)

Uploaded CPython 3.7m Windows x86-64

shap-0.30.0-cp37-cp37m-macosx_10_7_x86_64.whl (274.4 kB view details)

Uploaded CPython 3.7m macOS 10.7+ x86-64

shap-0.30.0-cp36-cp36m-win_amd64.whl (272.2 kB view details)

Uploaded CPython 3.6m Windows x86-64

File details

Details for the file shap-0.30.0.tar.gz.

File metadata

  • Download URL: shap-0.30.0.tar.gz
  • Upload date:
  • Size: 241.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.7

File hashes

Hashes for shap-0.30.0.tar.gz
Algorithm Hash digest
SHA256 38dfeb51be77b7be2fc2ad41167d7f984a36840c7dde251beada0b85d911894b
MD5 6134331a905c12853a6b4731513274ec
BLAKE2b-256 3b9816829410426bdd08b836c30e164c56646d6a102afb9eadd81a6bd3a8bb65

See more details on using hashes here.

File details

Details for the file shap-0.30.0-cp37-cp37m-win_amd64.whl.

File metadata

  • Download URL: shap-0.30.0-cp37-cp37m-win_amd64.whl
  • Upload date:
  • Size: 272.2 kB
  • Tags: CPython 3.7m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.7

File hashes

Hashes for shap-0.30.0-cp37-cp37m-win_amd64.whl
Algorithm Hash digest
SHA256 7b8c74d0df2ca4798201e818a24cc328aad360d5871a92048f455e71fe115543
MD5 d1ecc87e1b62613c96eaacc2af0a76de
BLAKE2b-256 9c82f303719ba22d8135382474db9eb3ed119d922dd38b42ce369bbe2fe0f62f

See more details on using hashes here.

File details

Details for the file shap-0.30.0-cp37-cp37m-macosx_10_7_x86_64.whl.

File metadata

File hashes

Hashes for shap-0.30.0-cp37-cp37m-macosx_10_7_x86_64.whl
Algorithm Hash digest
SHA256 7316fb64cf72ac122c773c5c3dd019ffeda8379f04424684720c57594b4684ac
MD5 61df775ef5684ef849e29fe756948084
BLAKE2b-256 c5acc7617019d929a840565bb433fb71afdf9cc3bdcd52ee683e80cc84315504

See more details on using hashes here.

File details

Details for the file shap-0.30.0-cp36-cp36m-win_amd64.whl.

File metadata

  • Download URL: shap-0.30.0-cp36-cp36m-win_amd64.whl
  • Upload date:
  • Size: 272.2 kB
  • Tags: CPython 3.6m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.6

File hashes

Hashes for shap-0.30.0-cp36-cp36m-win_amd64.whl
Algorithm Hash digest
SHA256 41ee03e9dae23eee5e3d3133ca7ef2e606899c6317ffebe93e93bceeda005a37
MD5 a7522c244ee83ced218f667a7a40ffbf
BLAKE2b-256 5880bba7c7ced20bb396779fe001f5f1a7515cf1d1b705dd3c986e319fdfa950

See more details on using hashes here.

Supported by

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