koaning/human-learn
Natural Intelligence is still a pretty good idea.
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.
Stars
827
Forks
56
Language
Jupyter Notebook
License
MIT
Category
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.
Related frameworks
microsoft/ML-For-Beginners
12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all
jzsmoreno/likelihood
Code generated from the Machine Learning course to optimization tasks
john-science/scipy_con_2019
Tutorial Sessions for SciPy Con 2019
ethen8181/machine-learning
:earth_americas: machine learning tutorials (mainly in Python3)
x4nth055/pythoncode-tutorials
The Python Code Tutorials