jundongl/scikit-feature

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1583 stars · 438 forks observed · 2026-08-28

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

scikit-feature is an open-source Python feature selection library built on scikit-learn, NumPy, and SciPy. It implements around 40 popular feature selection algorithms, including traditional, structural, and streaming methods, for research and applied use.

Use cases

• select the most informative features from a high-dimensional dataset
• reduce dimensionality before training a machine learning model
• compare different feature selection algorithms empirically
• apply streaming feature selection to evolving data
• find relevant features for a classification or regression task
• implement and benchmark new feature selection research

When to choose

• you need a broad collection of ready-to-use feature selection algorithms in Python
• you are doing academic research or comparative studies on feature selection
• your stack already uses scikit-learn, NumPy, and SciPy

When to avoid

• you need actively maintained code with recent bug fixes and modern packaging
• you only need simple built-in feature selection, which scikit-learn already provides
• you require commercial-friendly licensing, since it is GPL-2.0

Facets

library · maturity maintenance

machine-learning data-science machine-learning data-science python windows feature-selection scikit-learn dimensionality-reduction linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="jundongl/scikit-feature")