Open-source alternatives to AIX360

This project is an agnostic model interpretability framework and explainability tool designed to provide local interpretable explanations for individual predictions. It functions as a local surrogate model that approximates the behavior of any machine learning classifier or regression model to identify the most influential features for a specific instance. The framework is designed to be model-agnostic, meaning it can explain predictions across tabular, text, and image data regardless of the underlying architecture. It employs local linear approximations and feature importance visualization t

⬛ Python Individual Conditional Expectation Plot Toolbox

Code for "High-Precision Model-Agnostic Explanations" paper

python partial dependence plot toolbox

A library for debugging/inspecting machine learning classifiers and explaining their predictions

TreeInterpreter

The official implementation of "The Shapley Value of Classifiers in Ensemble Games" (CIKM 2021).

moDel Agnostic Language for Exploration and eXplanation

Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).

A library that implements fairness-aware machine learning algorithms

(a.k.a. Path-Integrated Gradients, a.k.a. Axiomatic Attribution for Deep Networks)

Python implementation of the rulefit algorithm

XAI - An eXplainability toolbox for machine learning

WeightWatcher (WW) is an open-source, diagnostic tool for analyzing Deep Neural Networks (DNN), without needing access to training or even test data. It is based on theoretical research into Why Deep Learning Works, based on our Theory of Heavy-Tailed Self-Regularization (HT-SR). It uses ideas…

A toolbox to iNNvestigate neural networks' predictions!

A Tree based feature selection tool which combines both the Boruta feature selection algorithm with shapley values.

Bias Auditing & Fair ML Toolkit

🎆 A visualization of the CapsNet layers to better understand how it works

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

NeuroX provide all the necessary tooling to perform Interpretation and Analysis of (Deep) Neural Networks centered around Probing. Specifically, the toolkit provides:

TorchCAM: class activation explorer

effector an eXplainable AI package for tabular data. It:

This repo contains the code for our talk "Demystifying the neural network black box". Slides are available on Speaker Deck. This code has not been maintained for over a year. It's archived on 2024-12-18.

tensorflow implementation of Grad-CAM (CNN visualization)

Yellowbrick is a machine learning visualization library and model diagnostic tool designed to analyze feature importance, target distributions, and model error metrics. It serves as a visual toolkit for diagnosing underfitting and overfitting through the use of validation and learning curves. The project provides specialized suites for evaluating predictive models and unsupervised learning. It enables the determination of optimal cluster counts via elbow methods and silhouette coefficients, and assesses classifier and regressor quality through ROC curves, confusion matrices, and residual plot