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.
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-0.23.2.tar.gz
(177.0 kB
view details)
Built Distribution
File details
Details for the file shap-0.23.2.tar.gz.
File metadata
- Download URL: shap-0.23.2.tar.gz
- Upload date:
- Size: 177.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: Python-urllib/3.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | b3f401a0aaa79bdf0ee2607272f66ef8b40daf968784c2ff1cbd6c7af9ed21cd |
|
| MD5 | 9f5c66b27ccf62d232cc928ebfb5399b |
|
| BLAKE2b-256 | 9b441120988efc96371bb13e6ebe67c813c6eadd3432059297afa2eaad74cccb |
File details
Details for the file shap-0.23.2-cp36-cp36m-macosx_10_7_x86_64.whl.
File metadata
- Download URL: shap-0.23.2-cp36-cp36m-macosx_10_7_x86_64.whl
- Upload date:
- Size: 195.2 kB
- Tags: CPython 3.6m, macOS 10.7+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: Python-urllib/3.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | a9b2763bf469fcd1a1bcc85a6d4b14fec940c7ec78a3a3a0d9db939ca50d7ab0 |
|
| MD5 | a19adb76542ecda9030084e8005e2433 |
|
| BLAKE2b-256 | 929a225ff4211526ab7b7bce39f637b4b616e536f627177312e024fa5584441f |
