Effector: A Python package for regional explanations

TL;DR

Effector is an open-source Python package that provides efficient, unified implementations of global and regional feature effect methods for interpreting tabular machine learning models, addressing limitations of global effects in the presence of feature interactions.

Contribution

It introduces a modular, extensible package that seamlessly integrates with major ML libraries, offering state-of-the-art regional explanation techniques with comprehensive documentation.

Findings

Provides efficient implementations of regional effects methods

Addresses limitations of global effects in interacting features

Seamless integration with scikit-learn and PyTorch

Abstract

Effector is a Python package for interpreting machine learning (ML) models that are trained on tabular data through global and regional feature effects. Global effects, like Partial Dependence Plot (PDP) and Accumulated Local Effects (ALE), are widely used for explaining tabular ML models due to their simplicity -- each feature's average influence on the prediction is summarized by a single 1D plot. However, when features are interacting, global effects can be misleading. Regional effects address this by partitioning the input space into disjoint subregions with minimal interactions within each and computing a separate regional effect per subspace. Regional effects are then visualized by a set of 1D plots per feature. Effector provides efficient implementations of state-of-the-art global and regional feature effects methods under a unified API. The package integrates seamlessly with major ML libraries like scikit-learn and PyTorch. It is designed to be modular and extensible, and comes with comprehensive documentation and tutorials. Effector is an open-source project publicly available on Github at https://github.com/givasile/effector.