shap and kernelshap

KernelSHAP is a specialized implementation of one specific SHAP algorithm (kernel-based feature attribution), while SHAP is the comprehensive library containing multiple Shapley value methods; they are complements where the focused tool serves practitioners who need that particular algorithm variant alongside or instead of the general framework.

shap
82
Verified
kernelshap
38
Emerging
Maintenance 20/25
Adoption 15/25
Maturity 25/25
Community 22/25
Maintenance 2/25
Adoption 8/25
Maturity 16/25
Community 12/25
Stars: 25,115
Forks: 3,481
Downloads:
Commits (30d): 21
Language: Jupyter Notebook
License: MIT
Stars: 60
Forks: 7
Downloads:
Commits (30d): 0
Language: R
License: GPL-2.0
No risk flags
Stale 6m No Package No Dependents

About shap

shap/shap

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

This tool helps data scientists and machine learning engineers understand why their machine learning models make specific predictions. By taking a trained model and input data, it shows how much each individual feature contributes to the final output, clarifying complex model behavior. It's designed for anyone building or using ML models who needs to explain their results, like a business analyst evaluating a credit risk model or a medical researcher interpreting a diagnostic tool.

model-interpretability machine-learning-explanation AI-explainability predictive-modeling-auditing feature-importance

About kernelshap

ModelOriented/kernelshap

Different SHAP algorithms

When working with complex models in R, understanding why a model makes a specific prediction can be challenging. This tool helps practitioners interpret model predictions by calculating SHAP values, which show how much each input feature contributes to the final output. It takes a trained model and a dataset as input and outputs numerical SHAP values that can then be visualized to explain individual predictions or overall model behavior. This is useful for data scientists, statisticians, or analysts who build and deploy predictive models and need to explain their reasoning to stakeholders.

model-interpretability feature-attribution predictive-analytics machine-learning-explanation R-programming

Scores updated daily from GitHub, PyPI, and npm data. How scores work