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.

probatus

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

shapiq

Shapley Interactions and Shapley Values for Machine Learning

explainerdashboard

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

fasttreeshap

Fast SHAP value computation for interpreting tree-based models

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.

streamlit-shap

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

axon-quant

AI-native event-driven trading engine. Rust core with Python RL bindings. Built-in Gymnasium environments, LLM agents, SHAP explainability, and model ensembling — from backtesting to production.(AI 原生事件驱动交易引擎，Rust 内核，Python RL 绑定，支持 Gymnasium 环境、LLM 智能体、SHAP 可解释性与模型集成，贯穿回测到生产部署。)

xper

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

timeshap

TimeSHAP explains Recurrent Neural Network predictions.

atom-ml

Automated Tool for Optimized Modelling

shaperone

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

spml2-mltools

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

dissectml

The missing middle layer between EDA and AutoML — unified pipeline from deep data understanding to model comparison in 3 function calls. Deep EDA, 36-model battle arena, statistical significance testing, target leakage detection, and publication-ready HTML reports.

survshap

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

shap-monitor

Monitor and explain your ML model in production

insurance-glm-tools

GLM tools for UK insurance pricing: nested GLMs with entity embeddings, territory clustering, and automated factor-level banding via R2VF

striders

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

pandasflow

A set of custom python modules for friendly workflow on pandas

insurance-interactions

Automated GLM interaction detection for UK personal lines insurance using CANN + NID