koaning/scikit-lego

Health v2 · maintenance only

Adoption not part of the score

1412 stars · 136 forks observed · 2026-10-19

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

scikit-lego is a Python library of extra building blocks—custom transformers, models, metrics, and datasets—that are fully compatible with scikit-learn pipelines. It consolidates commonly rewritten utilities into a tested, MIT-licensed package that adheres to scikit-learn's API standards.

Use cases

• add custom transformers to scikit-learn pipelines
• find scikit-learn compatible models like GMM classifier
• load example datasets for teaching machine learning
• evaluate model fairness with scikit-learn metrics
• add noise augmentation inside a pipeline
• extend scikit-learn without writing boilerplate transformers

When to choose

• you already use scikit-learn and need extra transformers, models, or metrics that fit the same API
• you want tested, reusable pipeline components instead of copy-pasting custom code
• you teach or demo machine learning and need small interesting datasets with fairness concerns

When to avoid

• you need deep learning or GPU-based modeling outside the scikit-learn ecosystem
• you require a library formally affiliated with or maintained by the scikit-learn project
• you need a full AutoML or end-to-end ML platform rather than pipeline building blocks

Facets

library · maturity active

machine-learning data-science testing machine-learning data-science python scikit-learn pipelines transformers fairness datasets

Member repositories

For agents

markdown · JSON · MCP: product_card(name="koaning/scikit-lego")