shap and FastTreeSHAP

FastTreeSHAP is a specialized accelerator for the general-purpose SHAP library, optimizing Shapley value computation specifically for tree-based models that SHAP already supports.

shap
82
Verified
FastTreeSHAP
50
Established
Maintenance 20/25
Adoption 15/25
Maturity 25/25
Community 22/25
Maintenance 0/25
Adoption 11/25
Maturity 25/25
Community 14/25
Stars: 25,115
Forks: 3,481
Downloads:
Commits (30d): 21
Language: Jupyter Notebook
License: MIT
Stars: 554
Forks: 38
Downloads:
Commits (30d): 0
Language: Python
License: BSD-2-Clause
No risk flags
Stale 6m

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 FastTreeSHAP

linkedin/FastTreeSHAP

Fast SHAP value computation for interpreting tree-based models

This project helps data scientists, machine learning engineers, and researchers quickly understand why their tree-based models (like Random Forest or XGBoost) make specific predictions. It takes your trained tree model and a dataset, then efficiently calculates 'SHAP values' that show how much each input feature contributed to each prediction. This allows you to explain complex model behaviors in an understandable way, especially for large datasets.

machine-learning-explanation model-interpretability data-science-workflow predictive-modeling

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