InterpretML: A Unified Framework for Machine Learning Interpretability
It addresses the problem of making interpretability tools accessible and comparable for machine learning practitioners and researchers, though it is incremental as it builds on existing algorithms.
InterpretML is an open-source Python package that provides a unified framework for machine learning interpretability, enabling practitioners to compare glassbox models and blackbox explainability techniques through a common API and visualization platform, and includes the first implementation of the Explainable Boosting Machine, which achieves accuracy comparable to blackbox models.
InterpretML is an open-source Python package which exposes machine learning interpretability algorithms to practitioners and researchers. InterpretML exposes two types of interpretability - glassbox models, which are machine learning models designed for interpretability (ex: linear models, rule lists, generalized additive models), and blackbox explainability techniques for explaining existing systems (ex: Partial Dependence, LIME). The package enables practitioners to easily compare interpretability algorithms by exposing multiple methods under a unified API, and by having a built-in, extensible visualization platform. InterpretML also includes the first implementation of the Explainable Boosting Machine, a powerful, interpretable, glassbox model that can be as accurate as many blackbox models. The MIT licensed source code can be downloaded from github.com/microsoft/interpret.