Interpretable Machine Learning Python Packages

interpret-core

Fit interpretable models. Explain blackbox machine learning.

interpret

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.

dice-ml

Generate Diverse Counterfactual Explanations for any machine learning model.

dalex

moDel Agnostic Language for Exploration and eXplanation

shapiq

Shapley Interactions and Shapley Values for Machine Learning

piml

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

xaisuite

XAISuite: Training and Explanation Generation Utilities for Machine Learning Models

snore-embedding

SNoRe: Scalable Unsupervised Learning of Symbolic Node Representations

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:

torch-explain

PyTorch Explain: Interpretable Deep Learning in Python.

pyaerial

An implementation of the Aerial neurosymbolic association rule mining algorithm from tabular datasets.

omnixai

OmniXAI: An Explainable AI Toolbox

explainx

Explainable AI framework for data scientists. Explain & debug any blackbox machine learning model with a single line of code. We are looking for co-authors to take this project forward. Reach out @ ms8909@nyu.edu

lirisimpact

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

midlearn

A scikit-learn compatible Python wrapper of the midr R package

xpotato

XAI based human-in-the-loop framework for automatic rule-learning.

visualime

Implementation of LIME focused on producing user-centric local explanations for image classifiers.

layerssustainabilityanalysis

LSA : Layer Sustainability Analysis framework for the analysis of layer vulnerability in a given neural network. LSA can be a helpful toolkit to assess deep neural networks and to extend the adversarial training approaches towards improving the sustainability of model layers via layer monitoring and analysis.

zennit-crp

Concept Relevance Propagation and Relevance Maximization

featuremap

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

pytorch-concepts

Concept-Based Deep Learning Library for PyTorch.

pffra

An Interpretable Machine Learning technique to analyse the contribution of features in the frequency domain. This method is inspired by permutation feature importance analysis but aims to quantify and analyse the time-series predictive model's mechanism from a global perspective.

slise

The SLISE algorithm for robust regression and explanations of black box models