tinyshap 0.1.0

Minimal implementation of approximate Kernel SHAP algorithm

tinyshap

A minimal implementation of the SHAP algorithm using the KernelSHAP method. In less then 100 lines of code, this repo serves as an educational resource to understand how SHAP works without all the complexities of a production-level package.

Installation

pip install tinyshap

Example usage

from tinyshap import SHAPExplainer

# Train model
model = GradientBoostingRegressor()
model.fit(X_train, y_train)

# Explain predictions
explainer = SHAPExplainer(model.predict, X=X_train.mean().to_frame().T)
contributions = explainer.shap_values(X)

See complete notebook

Resources

• A Unified Approach to Interpreting Model Predictions (arXiv)
• Interpretable Machine Learning

Licence

MIT