WillKoehrsen/feature-selector

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2228 stars · 763 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python library for feature selection that identifies features to remove from machine learning datasets using five methods: missing values, single unique values, collinear features, zero importance features, and low importance features. It includes visualization tools such as correlation heatmaps and feature importance plots.

Use cases

• remove collinear features from a dataset
• drop features with too many missing values
• identify zero importance features before training
• reduce dimensionality of a machine learning dataset
• visualize feature correlations in a dataframe
• prune low importance features to speed up model training

When to choose

• you want a simple, notebook-friendly feature selection workflow for tabular data
• you need to inspect and visualize feature importance and collinearity before modeling
• you work with pandas DataFrames and want automated removal of redundant columns

When to avoid

• you need feature selection for non-tabular data like text or images
• you require actively maintained tooling with modern dependency versions
• you need scalable feature selection for very large datasets beyond memory

Facets

library · maturity maintenance

machine-learning data-science data-visualization machine-learning data-science python feature-selection dimensionality-reduction jupyter-notebook lightgbm pandas

Member repositories

For agents

markdown · JSON · MCP: product_card(name="WillKoehrsen/feature-selector")