23 lines
650 B
Markdown
23 lines
650 B
Markdown
|
|
|
|
<p align="center">
|
|
<img src="https://raw.githubusercontent.com/shap/shap/master/docs/artwork/shap_header.png" width="800" />
|
|
</p>
|
|
|
|
---
|
|
|
|
|
|
**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](https://github.com/shap/shap#citations) for details and citations).
|
|
|
|
|
|
|
|
## Install
|
|
|
|
Shap can be installed from [npm](https://www.npmjs.com/package/shapjs):
|
|
|
|
<pre>
|
|
npm i shapjs
|
|
</pre>
|
|
|
|
Further details at https://github.com/shap/shap
|