koaning/human-learn

Natural Intelligence is still a pretty good idea.

51
/ 100
Established

This project helps data analysts and domain experts create predictive models by drawing rules directly onto their data visualizations. You can input your dataset, interactively define classification, regression, or outlier detection rules by drawing shapes, and then export these human-crafted rules as a machine learning model. This allows those with deep domain knowledge to directly encode their insights into a model without needing to write complex code.

827 stars.

Use this if you are a domain expert with a strong intuition about patterns in your data and want to quickly create a model or define preprocessing steps by visually outlining those patterns.

Not ideal if you're looking for purely automated, black-box machine learning solutions that discover patterns without human input or if your dataset is too large or complex to visualize effectively for drawing rules.

data-analysis rule-based-modeling interactive-data-exploration predictive-modeling domain-expertise
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

827

Forks

56

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/koaning/human-learn"

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