Interpretable Ml Python Packages

interpret-core

Fit interpretable models. Explain blackbox machine learning.

captum

Model interpretability and understanding for PyTorch

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.

flash-ansr

Fast Amortized Neural Symbolic Regression with Transformers and SimpliPy

hugiml-core

High-performance interpretable ML classifier using High Utility Gain patterns (IEEE Access 2024). C++ accelerated, scikit-learn compatible, with EBM-style explanations, adaptive binning, pattern pruning, and deployment tooling for regulated domains.

zennit

Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.

endgame-ml

A unified framework for tabular, time-series, and multimodal machine learning

trust-free

An interpretable regression model in Python with Random-Forest-level accuracy

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:

dna-decode

Deterministic, interpretable genome→phenotype decoder: calls antibiotic/antiviral/antifungal resistance from DNA + names the exact genes/mutations driving each call. Spans bacteria, M. tuberculosis, fungi, HIV-1 & SARS-CoV-2 — independently validated on FREE measured wet-lab labels (EBI AMR Portal, Stanford HIVDB). Not a clinical tool.

adcd

Discover physical correction laws from anomalous data in JAX.

insurance-gam

Interpretable GAM models for insurance pricing — EBM tariffs, Actuarial NAM, Pairwise Interaction Networks (PIN), exact Shapley values

prism-iml

Convert a trained black-box binary classifier for tabular data into a standalone, auditable nomogram via functional ANOVA decomposition, LASSO selection, and partial response networks.

powerlift

Fit interpretable models. Explain blackbox machine learning.

shap-relativities

SHAP-based rating relativities from GBM models for insurance pricing — extract GLM-style factors from CatBoost, Polars

mlm-bias

Measuring Biases in Masked Language Models for PyTorch Transformers. Support for multiple social biases and evaluation measures.

pytorch-lattice

A PyTorch implementation of constrained optimization and modeling techniques

pysr-mcranmer

Symbolic Learning in Python and Julia

explainax

JAX-based Model Explanation and Interpretation Library

ct-master-build

Model interpretability and understanding for PyTorch