Interpretable Ai Python Packages

interpret-core

Fit interpretable models. Explain blackbox machine learning.

captum

Model interpretability and understanding for PyTorch

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.

grad-cam

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

zennit

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

prosemble

A python package for prototype-based machine learning models

torch-explain

PyTorch Explain: Interpretable Deep Learning in Python.

te2rules

Python library to explain Tree Ensemble models (TE) like XGBoost, using a rule list.

pytorch-sidu

SIDU: SImilarity Difference and Uniqueness method for explainable AI

prototorch

ProtoTorch is a PyTorch-based Python toolbox for bleeding-edge research in prototype-based machine learning algorithms.

explainx

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

shapley-lz

IN PROGRESS - after the paper "Shapley-Lorenz decompositions in eXplainable Artificial Intelligence" by Giudici and Raffinetti - 2020

desdeo-brb

A trainable Belief Rule-Based (BRB) inference system with an sklearn-compatible API and optional JAX backend for differentiable training.

powerlift

Interactive Benchmarking for Machine Learning.

mlm-bias

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

xpotato

XAI human-in-the-loop information extraction framework

cromp

The official implementation of CROMP (Constrained Regression with Ordered and Margin-sensitive Parameters). CROMP allows user-defined order among the coefficients, user-defined minimum margins (i.e., percentage gaps) between them, and user-defined lower and upper bounds for each coefficient. In addition, CROMP also allows coefficients without any order or margin restrictions.

lorenz-zonoid

IN PROGRESS - after the paper "Shapley-Lorenz decompositions in eXplainable Artificial Intelligence" by Giudici and Raffinetti - 2020

deep-xf

Package towards building Explainable Forecasting and Nowcasting Models with State-of-the-art Deep Neural Networks and Dynamic Factor Model on Time Series data sets with single line of code. Also, provides utilify facility for time-series signal similarities matching, and removing noise from timeseries signals.

pytorch-lattice

A PyTorch implementation of constrained optimization and modeling techniques

bioexp

Deep Learning model analysis toolbox

nafes

A python project for prototype-based feature selection

explainax

JAX-based Model Explanation and Interpretation Library