NannyML/nannyml
nannyml: post-deployment data science in python
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.
Stars
2,128
Forks
180
Language
Python
License
Apache-2.0
Category
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.
Related frameworks
online-ml/river
🌊 Online machine learning in Python
IFCA-Advanced-Computing/frouros
Frouros: an open-source Python library for drift detection in machine learning systems.
Western-OC2-Lab/AutoML-Implementation-for-Static-and-Dynamic-Data-Analytics
Implementation/Tutorial of using Automated Machine Learning (AutoML) methods for static/batch...
mitre/menelaus
Online and batch-based concept and data drift detection algorithms to monitor and maintain ML...
etsi-ai/etsi-watchdog
Real-time data drift detection and monitoring for machine learning pipelines.