Feature Importance Python Packages

captum

Model interpretability and understanding for PyTorch

shapiq

Shapley Interactions and Shapley Values for Machine Learning

mini-causal

A Python package for measuring the impact of features

lofo-importance

Leave One Feature Out Importance

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.

mlfeatureselection

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

msdlib

msdlib is meant for making life easier of a common data scientist/data analyst/ML enginner.

robustmodelmaker

A reproducible model-building pipeline for small-to-medium scientific datasets

pytolemaic

Package for ML model analysis

xai

XAI - An industry-ready machine learning library that ensures explainable AI by design

target-permutation-importances

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

featureranker

Python package for feature ranking

shapley-lz

Computes the Shapley Lorenz Zonoid share of a set of covariates

acd

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

dime-xai

Implementation of Dual Interpretable Model-agnostic Explanations for Rasa DIET classifiers

dnn-inference

Significance tests of feature relevance for a black-box learner

tanml

Automated validation toolkit for tabular ML models in finance and regulated domains.

lorenz-zonoid

Computes the Shapley Lorenz Zonoid share of covariates

fippy

Model-agnostic feature importance with python.