mmschlk/shapiq
A Python package for approximating Shapley interactions and explaining feature interactions in machine learning model predictions.

Velocity · 7d
+0.8
★ / day
Trend
→steady
star history
SHAP-IQ (shapiq) provides tools for approximating any-order Shapley interactions and benchmarking game-theoretical algorithms for machine learning. It extends the popular shap library to help researchers and end-users explain feature interactions of model predictions. The package implements various approximation methods and supports different interaction indices like Banzhaf and Shapley values.