JoranMichiels/decomposition-shap
Explain model and feature dependencies by decomposition of SHAP values
When you're trying to understand why a machine learning model made a specific prediction, especially with real-world data where features often influence each other, this tool helps. It takes your model and data to explain how much each input factor directly impacts the outcome, and how much it influences other factors that then change the outcome. This is for data scientists, machine learning engineers, and researchers who need clear, defensible explanations of their models' decisions.
No commits in the last 6 months.
Use this if you need to explain individual predictions from your machine learning models, differentiating between a feature's direct influence on the model's output and its indirect influence through other related features.
Not ideal if you only need a general understanding of feature importance across an entire dataset, rather than detailed, decomposed explanations for specific predictions.
Stars
7
Forks
—
Language
Python
License
MIT
Category
Last pushed
Nov 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JoranMichiels/decomposition-shap"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shap/shap
A game theoretic approach to explain the output of any machine learning model.
mmschlk/shapiq
Shapley Interactions and Shapley Values for Machine Learning
iancovert/sage
For calculating global feature importance using Shapley values.
predict-idlab/powershap
A power-full Shapley feature selection method.
aerdem4/lofo-importance
Leave One Feature Out Importance