ModelOriented/hstats

Friedman's H-statistics

32
/ 100
Emerging

When analyzing a machine learning model, understanding how different input features interact to influence predictions is crucial. This tool helps you quantify the strength of these interactions, taking your trained model and input data to produce metrics that show how much variability in predictions is due to individual features and their combinations. It's designed for data scientists, machine learning engineers, and researchers who build and interpret predictive models.

Use this if you need to objectively measure and rank the interaction strength between features in your machine learning models to better understand their behavior.

Not ideal if your primary goal is to visualize interaction patterns without first quantifying their strength, or if your dataset is extremely large and you require highly robust estimates without sampling.

machine-learning-interpretability model-explanation feature-interaction predictive-modeling data-analysis
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 3 / 25

How are scores calculated?

Stars

34

Forks

1

Language

R

License

GPL-2.0

Category

mlr3-ecosystem

Last pushed

Jan 01, 2026

Commits (30d)

0

Get this data via API

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

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