WillKoehrsen/feature-selector
A Python library for automated feature selection and dimensionality reduction in machine learning datasets using importance-based and statistical methods.
Velocity · 7d
+0.8
★ / day
Trend
→steady
star history
Feature Selector provides five methods to identify and remove low-value features: missing value thresholding, single unique value detection, collinearity-based removal, and importance-based filtering using LightGBM feature importances. It integrates with scikit-learn workflows and includes visualization utilities for inspecting dataset characteristics and feature importance distributions.