aangelopoulos/ppi_py

A package for statistically rigorous scientific discovery using machine learning. Implements prediction-powered inference.

53
/ 100
Established

This tool helps scientists and researchers make more accurate and reliable conclusions when using machine learning models to analyze data. It takes a small set of meticulously labeled "gold-standard" data, combined with a larger set of unlabeled data and model predictions, to produce better estimates and tighter confidence intervals for population statistics. The end-user is typically a domain expert or scientist who applies machine learning in fields like biology, astronomy, or social science, and needs statistically sound results.

279 stars.

Use this if you need to derive statistically rigorous insights and confidence intervals from your data, especially when you have limited gold-standard labels but abundant predictions from a machine learning model.

Not ideal if your primary goal is only model development or improving prediction accuracy, rather than making statistical inferences about a population.

scientific-discovery proteomics-analysis galaxy-classification gene-expression-analysis deforestation-monitoring
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

279

Forks

34

Language

Python

License

MIT

Last pushed

Feb 24, 2026

Commits (30d)

0

Get this data via API

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

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