mmschlk/shapiq
Shapley Interactions and Shapley Values for Machine Learning
This tool helps data scientists and machine learning practitioners understand why their models make certain predictions. You provide a trained machine learning model and your dataset, and it shows you how individual features and combinations of features contribute to a specific prediction. This goes beyond just knowing which features are important, revealing how they interact with each other.
695 stars. Used by 1 other package. Actively maintained with 11 commits in the last 30 days. Available on PyPI.
Use this if you need to deeply understand the synergistic or antagonistic effects of features in your machine learning model's predictions, rather than just their individual contributions.
Not ideal if you only need basic feature importance scores and aren't interested in the complex interplay between different input variables.
Stars
695
Forks
48
Language
Python
License
MIT
Category
Last pushed
Mar 13, 2026
Commits (30d)
11
Dependencies
13
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mmschlk/shapiq"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
shap/shap
A game theoretic approach to explain the output of any machine learning model.
iancovert/sage
For calculating global feature importance using Shapley values.
predict-idlab/powershap
A power-full Shapley feature selection method.
aerdem4/lofo-importance
Leave One Feature Out Importance
ReX-XAI/ReX
Causal Responsibility EXplanations for Image Classifiers and Tabular Data