counterfactuals: An R Package for Counterfactual Explanation Methods
This work provides a practical tool for researchers and practitioners in machine learning to standardize and apply counterfactual explanations, but it is incremental as it builds on existing methods.
The authors tackled the lack of unified implementations for counterfactual explanation methods by introducing an R package with a modular interface, implementing three existing methods and proposing extensions for generalization and comparability, and they compared these methods across models and datasets for explanation quality and runtime.
Counterfactual explanation methods provide information on how feature values of individual observations must be changed to obtain a desired prediction. Despite the increasing amount of proposed methods in research, only a few implementations exist whose interfaces and requirements vary widely. In this work, we introduce the counterfactuals R package, which provides a modular and unified R6-based interface for counterfactual explanation methods. We implemented three existing counterfactual explanation methods and propose some optional methodological extensions to generalize these methods to different scenarios and to make them more comparable. We explain the structure and workflow of the package using real use cases and show how to integrate additional counterfactual explanation methods into the package. In addition, we compared the implemented methods for a variety of models and datasets with regard to the quality of their counterfactual explanations and their runtime behavior.