Feature Importance Python Packages

captum

Model interpretability and understanding for PyTorch

shapiq

Shapley Interactions and Shapley Values for Machine Learning

mini-causal

A machine learning decision intelligence framework that helps practitioners understand how feature changes influence model behavior, performance and business decisions

dominance-analysis

This package can be used for dominance analysis or Shapley Value Regression for finding relative importance of predictors on given dataset. This library can be used for key driver analysis or marginal resource allocation models.

lofo-importance

Leave One Feature Out Importance

shapley-value-regression

A simple library to calculate Shapley values for regression models using pandas and scikit-learn.

aime-xai

AIME (Approximate Inverse Model Explanations) — inverse-operator XAI with publication-grade visualisations and an inverse-explanation evaluation suite.

treeig

Exact Integrated Gradients for tree ensembles, including XGBoost, LightGBM, Random Forests, and Gradient Boosting. Computes fast, exact feature attributions for tree models without numerical gradients, numerical integration, Monte Carlo sampling, or path approximations.

mlfeatureselection

Features selector based on the self selected-algorithm, loss function and validation method

xai

XAI - An eXplainability toolbox for machine learning

edef

Feature attribution for realized model fit (rather than predictions). EDEF provides exact additive decomposition of predictive performance for linear, PyTorch, JAX, and tree-based models, including standard errors, grouped inference, and exact TreeIG decompositions for tree-based models.

causasv

Causal feature attribution via Asymmetric Shapley Values (ASV)

msdlib

This is a custom library for data processing, visualization and machine learning tools.

robustmodelmaker

Coupling Bootstrap Stability Selection with Leakage-Safe Nested Cross-Validation for Scientific Machine Learning

pytolemaic

Package for ML model analysis

featureranker

Python package for feature ranking

acd

Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)

shapley-lz

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

dime-xai

Explains DIETClassifier model predictions in Rasa chatbot framework.

dnn-inference

Dnn-Inference is a Python module for hypothesis testing based on deep neural networks.

target-permutation-importances

A Python Package that computes Target Permutation Importances (Null Importances) of a machine learning model.

tanml

Automated validation toolkit for tabular ML models—MRM, credit risk, insurance, and other regulated use cases.

lorenz-zonoid

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

fippy

Model-Agnostic Feature Importance in Python