smazzanti/mrmr

mRMR (minimum-Redundancy-Maximum-Relevance) for automatic feature selection at scale.

47
/ 100
Emerging

When building predictive models, you often have many data points (features) but only a few are truly useful. This tool helps data scientists and machine learning engineers automatically identify the smallest set of the most important features from large datasets. It takes your raw dataset and a target variable, then outputs a ranked list of the most relevant and least redundant features for your predictive task.

623 stars. No commits in the last 6 months.

Use this if you need to quickly and automatically identify a minimal yet highly effective set of features for a machine learning model, especially when dealing with large datasets or needing faster model training and better explainability.

Not ideal if your primary goal is to identify every single feature that has any relationship with your target variable, rather than focusing on a minimal, optimal set.

predictive-modeling data-preprocessing machine-learning-engineering marketing-analytics model-optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

623

Forks

90

Language

Python

License

MIT

Last pushed

Nov 19, 2024

Commits (30d)

0

Get this data via API

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

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