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-0.39.0.tar.gz (356.2 kB view details)

Uploaded Source

Built Distributions

shap-0.39.0-cp38-cp38-win_amd64.whl (414.8 kB view details)

Uploaded CPython 3.8 Windows x86-64

shap-0.39.0-cp37-cp37m-win_amd64.whl (414.4 kB view details)

Uploaded CPython 3.7m Windows x86-64

shap-0.39.0-cp36-cp36m-win_amd64.whl (414.5 kB view details)

Uploaded CPython 3.6m Windows x86-64

File details

Details for the file shap-0.39.0.tar.gz.

File metadata

  • Download URL: shap-0.39.0.tar.gz
  • Upload date:
  • Size: 356.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/54.0.0 requests-toolbelt/0.9.1 tqdm/4.58.0 CPython/3.6.7

File hashes

Hashes for shap-0.39.0.tar.gz
Algorithm Hash digest
SHA256 0196a6c12cc98f8b48ce9c5968550902432b80290da6fa7be8655441a1c6251a
MD5 355b4dfa2b3311c6d27450a0b1b4d89d
BLAKE2b-256 b9f4c5b95cddae15be80f8e58b25edceca105aa83c0b8c86a1edad24a6af80d3

See more details on using hashes here.

File details

Details for the file shap-0.39.0-cp38-cp38-win_amd64.whl.

File metadata

  • Download URL: shap-0.39.0-cp38-cp38-win_amd64.whl
  • Upload date:
  • Size: 414.8 kB
  • Tags: CPython 3.8, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.8

File hashes

Hashes for shap-0.39.0-cp38-cp38-win_amd64.whl
Algorithm Hash digest
SHA256 c0d51b44c15eae1c12e51ed498f898cfc5e12d6be7e0d4f733ce6453f6ec85a4
MD5 6d2ba87a08e1a2edc901fbd39918a8a2
BLAKE2b-256 9d4dff8d322dbef668b7848537de20920b35870a94873bc6f8b13ad27ad251fc

See more details on using hashes here.

File details

Details for the file shap-0.39.0-cp37-cp37m-win_amd64.whl.

File metadata

  • Download URL: shap-0.39.0-cp37-cp37m-win_amd64.whl
  • Upload date:
  • Size: 414.4 kB
  • Tags: CPython 3.7m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.7

File hashes

Hashes for shap-0.39.0-cp37-cp37m-win_amd64.whl
Algorithm Hash digest
SHA256 b44f9fbb7349f5406b98b4ec24c672f8fe932606bb7574a8aae2238410c55289
MD5 9e0cfc7eab802c142d9e408d90bf11ef
BLAKE2b-256 e61cfbe599e2a3d51d3322ef379b8e77a795b424975fcb61f26174ac0217de4e

See more details on using hashes here.

File details

Details for the file shap-0.39.0-cp36-cp36m-win_amd64.whl.

File metadata

  • Download URL: shap-0.39.0-cp36-cp36m-win_amd64.whl
  • Upload date:
  • Size: 414.5 kB
  • Tags: CPython 3.6m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.6

File hashes

Hashes for shap-0.39.0-cp36-cp36m-win_amd64.whl
Algorithm Hash digest
SHA256 bf9af9b089ef95cb1ac0df80a43f8144aa9095d10f282cb5c19643ff88a6a79d
MD5 20c0f3dae6a9ac94aa41a78ebd26b866
BLAKE2b-256 954e983d786c27ff3a00c8d5e223621e744807d05bee7976b1fcd6bac452b926

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