mitre/menelaus
Online and batch-based concept and data drift detection algorithms to monitor and maintain ML performance.
When your machine learning models are deployed, the real-world data they encounter can change over time, making your models less accurate or even wrong. This tool helps you monitor your live model's input data or performance metrics. It takes in either continuous streams of new data or batches of historical data and tells you when significant shifts occur, helping you decide when your model needs an update or retraining. It's for data scientists, ML engineers, or anyone responsible for the ongoing performance of deployed machine learning systems.
No commits in the last 6 months. Available on PyPI.
Use this if you need to automatically detect unexpected shifts in your live data or a decline in your ML model's performance, whether data arrives continuously or in batches.
Not ideal if you are looking for a tool to build or train your initial machine learning models, as this focuses solely on monitoring their stability after deployment.
Stars
68
Forks
7
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 27, 2023
Commits (30d)
0
Dependencies
5
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mitre/menelaus"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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.
NannyML/nannyml
nannyml: post-deployment data science in python
Western-OC2-Lab/AutoML-Implementation-for-Static-and-Dynamic-Data-Analytics
Implementation/Tutorial of using Automated Machine Learning (AutoML) methods for static/batch...
etsi-ai/etsi-watchdog
Real-time data drift detection and monitoring for machine learning pipelines.