A unified approach to explain the output of any machine learning model.
Project description
This is a fork of a newer version of the Shap library originally created by Scott Lundberg. Unfortunately, the PyPi version (as of June 2023) is outdated with the current version of Numpy so I am creating my own private fork to work with numpy 1.24 and 1.25.
SHAP (SHapley Additive exPlanations) is a game theoretic approach to explain the output of any machine learning model. It connects optimal credit allocation with local explanations using the classic Shapley values from game theory and their related extensions (see papers for details and citations).
Install
SHAP can be installed from either PyPI or conda-forge:
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
pou-shap-0.41.0.tar.gz
(386.8 kB
view hashes)
Built Distribution
Close
Hashes for pou_shap-0.41.0-cp310-cp310-win_amd64.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 053d6d3a85ced04d49b11186b1fc9b68a0c786e531c719abf5ae63abc45de743 |
|
| MD5 | eaa3ba61dd5bcd1fbaa4293994625d4a |
|
| BLAKE2b-256 | 7d6c588263113525489abeb91c54515abf3e29b9dfbd7d5c53cb9575fa8f905a |
