Shap Python Packages

shap

A game theoretic approach to explain the output of any machine learning model.

powershap

A power-full Shapley feature selection method.

explainerdashboard

Quickly build Explainable AI dashboards that show the inner workings of so-called "blackbox" machine learning models.

shapiq

Shapley Interactions and Shapley Values for Machine Learning

fasttreeshap

Fast SHAP value computation for interpreting tree-based models

probatus

SHAP-based validation for linear and tree-based models. Applied to binary, multiclass and regression problems.

shapash

🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

shap-hypetune

A python package for simultaneous Hyperparameters Tuning and Features Selection for Gradient Boosting Models.

xper

A methodology designed to measure the contribution of the features to the predictive performance of any econometric or machine learning model.

streamlit-shap

streamlit-shap provides a wrapper to display SHAP plots in Streamlit.

timeshap

TimeSHAP explains Recurrent Neural Network predictions.

atom-ml

A Python package for fast exploration of machine learning pipelines

shaperone

A game theoretic approach to explain the output of any machine learning model.

survshap

SurvSHAP(t): Time-dependent explanations of machine learning survival models

shap-monitor

A monitoring tool for SHAP values in machine learning models.

spml2-mltools

spml2-mltools is a convenient package for applying machine learning workflows with a Streamlit app, generating Excel outputs, and visualizations.

datatypical

Scientific Data Significance Rankings with Shapley Explanations

shap-relativities

SHAP-based rating relativities from GBM models for insurance pricing — extract GLM-style factors from CatBoost, Polars

pandasflow

A set of custom python modules for friendly workflow on pandas

insurance-glm-tools

GLM tooling for insurance pricing — nested GLM embeddings, R2VF factor level clustering, territory banding, SKATER

striders

Efficient surrogate-based model explanations (XAI) using landmark-based kernel approximations for scalable SHAP values.

tinyshap

Python package providing a minimal implementation of the SHAP algorithm using the Kernel method

spectralexplain

Fast XAI with interactions at large scale. SPEX can help you understand the output of your LLM, even if you have a long context!

insurance-interactions

Automated GLM interaction detection for insurance pricing — CANN, NID scoring, SHAP interaction values