SHAP

Implementation of the most popular algorithm for black box explainability, from the original paper authors. This is actively maintained and also provides specialized support for different model types, including tree ensembles, transformers, and deep learning models.

Logo

../_images/slundberg_shap-small.png

Website

N/A

Repository

https://github.com/slundberg/shap

Byline

A game theoretic approach to explain the output of any machine learning model.

License

MIT

Project age

6 years

Backers

Lee Lab of AI for Biological and Medical Sciences (Creator)

Size score (1 to 10, higher is better)

4.75

Trend score (1 to 10, higher is better)

5.75

Education Resources

URL

Resource Type

Description

https://shap.readthedocs.io/en/latest/index.html

Documentation

Official project documentation.

https://papers.nips.cc/paper/2017/hash/8a20a8621978632d76c43dfd28b67767-Abstract.html

Paper

Original paper at NeuroIPS 2017

Git Commit Statistics

Statistics computed using Git data through November 30, 2022.

Statistic

Lifetime

Last 12 Months

Commits

2,277

250

Lines committed

6,343,114

359,294

Unique committers

215

43

Core committers

12

3

../_images/slundberg_shap-monthly-commits.png

Similar Projects

Project

Size Score

Trend Score

Byline

Alibi Explain

3.75

8.25

Algorithms for monitoring and explaining machine learning models.

DiCE

2.0

7.5

Generate Diverse Counterfactual Explanations for any machine learning model.

Shapash

4.0

9.0

Shapash makes Machine Learning models transparent and understandable by everyone