shap and shapiq

While SHAP is a mature, general-purpose library for computing Shapley values and SHAP interactions across diverse model types, ShapIQ is a specialized library focused specifically on higher-order Shapley interactions (n-way feature interactions), making them **complements** that users might combine when investigating both individual feature importance and complex multi-feature interaction effects.

shap
92
Verified
shapiq
81
Verified
Maintenance 20/25
Adoption 25/25
Maturity 25/25
Community 22/25
Maintenance 20/25
Adoption 21/25
Maturity 25/25
Community 15/25
Stars: 25,115
Forks: 3,481
Downloads: 14,461,405
Commits (30d): 17
Language: Jupyter Notebook
License: MIT
Stars: 695
Forks: 48
Downloads: 17,129
Commits (30d): 16
Language: Python
License: MIT
No risk flags
No risk flags

About shap

shap/shap

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

Based on the README, here's a technical summary: Implements fast exact algorithms for tree ensemble models (XGBoost, LightGBM, CatBoost, scikit-learn, PySpark) via optimized C++ backends, alongside approximation methods for deep learning (DeepExplainer leveraging DeepLIFT) and NLP transformers using coalitional game rules. Provides multiple visualization outputs—waterfall plots, force plots, dependence scatter plots, and beeswarm distributions—to show feature contributions at instance and global levels. Integrates directly with popular ML frameworks and Hugging Face transformers, supporting both tabular and text-based model explanations.

About shapiq

mmschlk/shapiq

Shapley Interactions and Shapley Values for Machine Learning

Scores updated daily from GitHub, PyPI, and npm data. How scores work