Interpretable Machine Learning Python Packages

interpret-core

Fit interpretable models. Explain blackbox machine learning.

aplr

APLR builds predictive, interpretable regression and classification models using Automatic Piecewise Linear Regression. It often rivals tree-based methods in predictive accuracy while offering smoother and interpretable predictions.

interpret

Fit interpretable models. Explain blackbox machine learning.

dalex

moDel Agnostic Language for Exploration and eXplanation

shapiq

Shapley Interactions and Shapley Values for Machine Learning

dice-ml

Generate Diverse Counterfactual Explanations for any machine learning model.

pytsetlinmachineparallel

Multi-threaded implementation of the Tsetlin Machine, Convolutional Tsetlin Machine, Regression Tsetlin Machine, and Weighted Tsetlin Machine, with support for continuous features and multigranularity.

piml

PiML (Python Interpretable Machine Learning) toolbox for model development & diagnostics

c50py

C5.0 decision trees and rulesets for Python: native categorical splits, missing values, boosting and rules exported to SQL, as scikit-learn estimators

xaisuite

XAISuite: Train machine learning models, generate explanations, and compare different explanation systems with just a simple line of code.

beamfeat

Interpretable feature construction with false-discovery-rate guarantees. Beam search + permutation tests/knockoffs, as scikit-learn estimators.

pyaerial

Scalable association rule mining from tabular datasets.

pyss3

A Python library for Interpretable Machine Learning in Text Classification using the SS3 model, with easy-to-use visualization tools for Explainable AI :octocat:

subspaceknn

Interpretable k-nearest-neighbour classification by ensembling kNN models on low-dimensional feature subspaces

fast-borf

Fast, interpretable Bag-of-Receptive-Fields (BORF) features for regular and irregular time series classification, with saliency explanations. IEEE Access 2024.

unifiedig

Provides a unified approach to Integrated Gradients: a common API for many models, include tree-based models; and common baseline semantics with prediction-neutral baseline distributions as the default.

psrn

[𝐍𝐚𝐭𝐮𝐫𝐞 𝐂𝐨𝐦𝐩𝐮𝐭𝐚𝐭𝐢𝐨𝐧𝐚𝐥 𝐒𝐜𝐢𝐞𝐧𝐜𝐞] ⚡️ PSE/PSRN: Fast and efficient symbolic expression discovery through parallelized symbolic enumeration. Evaluates millions of expressions simultaneously on GPU with automated subtree reuse.

pytorch-concepts

PyC (Pytorch Concepts) is a PyTorch-based library for designing concept-based interpretable deep learning models.

featuremap

FeatureMAP (Feature-preserving Manifold Approximation and Projection) is an interpratable dimensionality reduction tool.

omnixai

OmniXAI: A Library for eXplainable AI

explainx

Explain & debug any blackbox machine learning model with a single line of code.

lirisimpact

Repository contaning the original code of IMPACT algorithm, an interpretable model for ordinal predictions with multi-class outputs"

ruletreerank

RuleTreeRank (RTR) is an interpretable Learning-to-Rank framework that models ranking as a two-stage process: it first groups items with a shallow rule tree, then refines the score locally through instance-based comparisons.

calm-additive

CALM: interpretable by design — accurate locally additive models for tabular data (NeurIPS 2026)