Open-source alternatives to PDPbox

SHAP is a machine learning explainer that uses a game-theoretic framework to estimate the contribution of each feature to a model prediction. It provides a set of tools for quantifying how individual input features push a specific output away from a baseline value. The project includes specialized explainers for different architectures, including high-speed implementations for decision trees and ensemble models, linearization algorithms for deep learning networks, and covariance integration for linear models. It also features a model-agnostic interpretability tool that uses a kernel method to

⬛ Python Individual Conditional Expectation Plot Toolbox

Lucid is a TensorFlow interpretability toolkit and visualization library designed to analyze the internal representations of neural networks. It functions as a gradient-based optimization framework that generates images and atlases to reveal the features learned by specific neurons and layers. The library enables the creation of activation atlases and the mapping of high-dimensional neural activations into lower-dimensional spaces to study model behavior. It utilizes differentiable image parametrization to optimize visual inputs that maximally activate network components. The system covers a

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

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

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

XAI - An eXplainability toolbox for machine learning

A toolbox to iNNvestigate neural networks' predictions!

Captum is an open-source library for explaining model predictions by attributing them to input features, neurons, and layers using gradient-based and perturbation-based methods. It provides a modular framework for implementing, evaluating, and combining a range of explanation techniques, including gradient-based attribution, perturbation-based analysis, game-theoretic Shapley value approximation, and surrogate model explanations, with support for parallelization and noise stabilization. The library distinguishes itself through its breadth of attribution methods and its support for advanced in

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

moDel Agnostic Language for Exploration and eXplanation

DeepLIFT: Deep Learning Important FeaTures

Leave One Feature Out Importance

Contrastive Explanation (Foil Trees), developed at TNO/Utrecht University

Interpretability and explainability of data and machine learning models

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

effector an eXplainable AI package for tabular data. It:

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

A library that implements fairness-aware machine learning algorithms

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

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

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

Python implementation of the rulefit algorithm

TorchCAM: class activation explorer

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…

Bias Auditing & Fair ML Toolkit