PiML Toolbox for Interpretable Machine Learning Model Development and Diagnostics

TL;DR

PiML is an open-source Python toolbox that facilitates interpretable machine learning development, diagnostics, and integration with MLOps platforms, supporting various models and explainability tools for robust, transparent AI applications.

Contribution

It introduces a comprehensive, user-friendly Python toolbox supporting interpretable models, explainability, diagnostics, and MLOps integration for machine learning workflows.

Findings

Supports a wide range of interpretable models like GAM and GAMI-Net.

Includes model-agnostic explainability tools such as LIME and SHAP.

Provides diagnostics for model reliability, robustness, and fairness.

Abstract

PiML (read $\pi$-ML, /`pai`em`el/) is an integrated and open-access Python toolbox for interpretable machine learning model development and model diagnostics. It is designed with machine learning workflows in both low-code and high-code modes, including data pipeline, model training and tuning, model interpretation and explanation, and model diagnostics and comparison. The toolbox supports a growing list of interpretable models (e.g. GAM, GAMI-Net, XGB1/XGB2) with inherent local and/or global interpretability. It also supports model-agnostic explainability tools (e.g. PFI, PDP, LIME, SHAP) and a powerful suite of model-agnostic diagnostics (e.g. weakness, reliability, robustness, resilience, fairness). Integration of PiML models and tests to existing MLOps platforms for quality assurance are enabled by flexible high-code APIs. Furthermore, PiML toolbox comes with a comprehensive user guide and hands-on examples, including the applications for model development and validation in banking. The project is available at https://github.com/SelfExplainML/PiML-Toolbox.