shap and cf-shap

B extends A by adding counterfactual reasoning to SHAP's feature importance explanations, making them complements rather than competitors—you would use B's counterfactual framework on top of A's core Shapley value implementation.

shap
82
Verified
cf-shap
39
Emerging
Maintenance 20/25
Adoption 15/25
Maturity 25/25
Community 22/25
Maintenance 0/25
Adoption 6/25
Maturity 16/25
Community 17/25
Stars: 25,115
Forks: 3,481
Downloads:
Commits (30d): 21
Language: Jupyter Notebook
License: MIT
Stars: 21
Forks: 8
Downloads:
Commits (30d): 0
Language: HTML
License: Apache-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 cf-shap

jpmorganchase/cf-shap

Counterfactual SHAP: a framework for counterfactual feature importance

When you need to understand why a machine learning model made a specific decision, this tool helps you find the most influential factors. It takes your trained model and its predictions as input, then identifies the 'counterfactual' changes that would alter the prediction, explaining how much each feature contributed. This is for data scientists and ML practitioners who build and deploy models and need to explain their behavior.

model-explainability machine-learning-auditing AI-trustworthiness feature-importance responsible-AI

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