MilesCranmer/PySR

High-Performance Symbolic Regression in Python and Julia

63
/ 100
Established

This tool helps scientists, engineers, and researchers discover the underlying mathematical equations that describe their data. You input your experimental or observational data (features and target values), and it outputs a list of simple, interpretable formulas that fit your data well. This is perfect for anyone trying to understand the fundamental relationships within their measurements rather than just predicting outcomes.

3,427 stars. Actively maintained with 8 commits in the last 30 days.

Use this if you need to find an explicit, human-readable formula to explain the patterns in your numerical data, especially when dealing with low-dimensional datasets or to simplify complex neural network models.

Not ideal if your primary goal is high-accuracy prediction without needing an interpretable formula, or if you are working with extremely high-dimensional, unstructured data like images or text.

scientific-modeling physics-discovery data-analysis equation-discovery interpretable-AI
No Package No Dependents
Maintenance 17 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

3,427

Forks

315

Language

Python

License

Apache-2.0

Last pushed

Mar 09, 2026

Commits (30d)

8

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MilesCranmer/PySR"

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