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-0.25.1.tar.gz (199.1 kB view details)

Uploaded Source

Built Distributions

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

shap-0.25.1-cp37-cp37m-win_amd64.whl (220.2 kB view details)

Uploaded CPython 3.7mWindows x86-64

shap-0.25.1-cp36-cp36m-win_amd64.whl (220.2 kB view details)

Uploaded CPython 3.6mWindows x86-64

shap-0.25.1-cp36-cp36m-macosx_10_7_x86_64.whl (215.2 kB view details)

Uploaded CPython 3.6mmacOS 10.7+ x86-64

File details

Details for the file shap-0.25.1.tar.gz.

File metadata

  • Download URL: shap-0.25.1.tar.gz
  • Upload date:
  • Size: 199.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.6

File hashes

Hashes for shap-0.25.1.tar.gz
Algorithm Hash digest
SHA256 70b83f087cf98e4330e92d2d060f2e6833333c83d6226ae76e054e3b2c8cdd06
MD5 86c49efcb71d4f76e4e2cc0bb2377556
BLAKE2b-256 084ba86fe3851c8321b16ad1f8dcf67103937bc0112161c6e58551729e3fc11f

See more details on using hashes here.

File details

Details for the file shap-0.25.1-cp37-cp37m-win_amd64.whl.

File metadata

  • Download URL: shap-0.25.1-cp37-cp37m-win_amd64.whl
  • Upload date:
  • Size: 220.2 kB
  • Tags: CPython 3.7m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.7

File hashes

Hashes for shap-0.25.1-cp37-cp37m-win_amd64.whl
Algorithm Hash digest
SHA256 0fdf74f408d60269a19ae847fd056c20683a83f408adc1d82c7402c39b554221
MD5 29a9d75ec73f8f01443fc4c130407134
BLAKE2b-256 c6005ec7de85a749f07cf56c557e543473aeb3bfc2ada65bdee98ef9bf693f95

See more details on using hashes here.

File details

Details for the file shap-0.25.1-cp36-cp36m-win_amd64.whl.

File metadata

  • Download URL: shap-0.25.1-cp36-cp36m-win_amd64.whl
  • Upload date:
  • Size: 220.2 kB
  • Tags: CPython 3.6m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.6

File hashes

Hashes for shap-0.25.1-cp36-cp36m-win_amd64.whl
Algorithm Hash digest
SHA256 c23ef0d888f62e564ca79618dfde2ed60bd85989d00000428352d21c9e23f7f8
MD5 d0e39025397173862b01a015fea5ab8d
BLAKE2b-256 b594a99d6cab7be259e072b12bca0e692cf6149516306bb919b33878209cb81b

See more details on using hashes here.

File details

Details for the file shap-0.25.1-cp36-cp36m-macosx_10_7_x86_64.whl.

File metadata

File hashes

Hashes for shap-0.25.1-cp36-cp36m-macosx_10_7_x86_64.whl
Algorithm Hash digest
SHA256 f55bf32d4e1687c5e1cb592eeca82a7cd19e56dadf6be464f4177c27cd754e37
MD5 91c99fc9f231fedc402de2aba89adee5
BLAKE2b-256 bf5b0fa1353069b1dbb416aa230c2db31fbf7c7507a66628e21a3ee4bd566b4f

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