tsitsimis/tinyshap

Python package providing a minimal implementation of the SHAP algorithm using the Kernel method

37
/ 100
Emerging

This helps data scientists and machine learning engineers understand why a predictive model makes a certain forecast. You input your trained machine learning model and the data you want to explain, and it outputs numerical values showing how much each input feature contributed to that specific prediction. This is for data science practitioners who need to peek inside the "black box" of their models.

No commits in the last 6 months. Available on PyPI.

Use this if you want to learn the fundamental mechanics of SHAP (SHapley Additive exPlanations) for model interpretability in a simplified, easy-to-understand implementation.

Not ideal if you need a robust, high-performance solution for explaining predictions in a production environment with complex models or large datasets.

Machine Learning Interpretability Model Explainability Data Science Education Predictive Analytics ML Model Debugging
Stale 6m
Maintenance 0 / 25
Adoption 4 / 25
Maturity 25 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Jupyter Notebook

License

MIT

Last pushed

May 27, 2023

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tsitsimis/tinyshap"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.