NannyML/nannyml

nannyml: post-deployment data science in python

66
/ 100
Established

Implements proprietary algorithms—confidence-based performance estimation (CBPE) and direct loss estimation (DLE)—to estimate model performance without ground truth labels, while detecting data drift via PCA-based multivariate reconstruction. Model-agnostic architecture supports tabular classification and regression workflows, with capabilities to correlate performance degradation directly to underlying data shifts rather than triggering generic drift alerts.

2,128 stars and 33,718 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 2 / 25
Adoption 20 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

2,128

Forks

180

Language

Python

License

Apache-2.0

Last pushed

Jul 12, 2025

Monthly downloads

33,718

Commits (30d)

0

Dependencies

25

Get this data via API

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

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