mmschlk/shapiq
A Python package for approximating Shapley interactions and explaining feature interactions in machine learning model predictions.
Not currently ranked — collecting fresh signals.
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.
Frequently asked
- What is mmschlk/shapiq?
- A Python package for approximating Shapley interactions and explaining feature interactions in machine learning model predictions.
- Is shapiq open source?
- Yes — mmschlk/shapiq is open source, released under the MIT license.
- What language is shapiq written in?
- mmschlk/shapiq is primarily written in Python.
- How popular is shapiq?
- mmschlk/shapiq has 760 stars on GitHub.
- Where can I find shapiq?
- mmschlk/shapiq is on GitHub at https://github.com/mmschlk/shapiq.