Feature Importance Python Packages

captum

Model interpretability and understanding for PyTorch

shapiq

Shapley Interactions and Shapley Values for Machine Learning

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.

causasv

Causal feature attribution via Asymmetric Shapley Values (ASV)

pytolemaic

Toolbox for analysis of model's quality and model's description. For further details see

lofo-importance

Leave One Feature Out Importance

mlfeatureselection

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

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.

msdlib

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

xai

XAI - An eXplainability toolbox for machine learning

robustmodelmaker

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

unifiedig

Provides a unified approach to Integrated Gradients: a common API for many models, include tree-based models; and common baseline semantics with prediction-neutral baseline distributions as the default.

featureranker

Python package for feature ranking

shapley-lz

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

robustpixelmaker

Reproducible, leakage-safe feature selection that works directly on image pixels.

acd

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

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 in finance and regulated domains.

dime-xai

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

aime-xai

Approximate Inverse Model Explanations (AIME): model-agnostic XAI through an approximate inverse operator.

dnn-inference

Significance tests of feature relevance for a black-box learner

lorenz-zonoid

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

shapley-value-regression

A Python implementation of Shapley Value Regression to calculate the precise feature importance and marginal contributions of independent variables in regression models.

pyinterpret

A unified Python library for machine learning model interpretation (SHAP, LIME, permutation importance, partial dependence)