Luminaire¶
This library focuses on anomaly detection in time series data. In particular, it supports monitoring data over comparible windows instead of tracking individual data points as outliers.
Logo |
|
---|---|
Website |
|
Repository |
|
Byline |
Luminaire is a python package that provides ML driven solutions for monitoring time series data. |
License |
Apache 2.0 |
Project age |
2 years 5 months |
Backers |
|
Lastest News (2022-07-26) |
0.4.0 Support up to Python 3.10; Support of latest versions of scipy, statsmodels and bayesian-changepoin-detection; Minor bug fixes and … more |
Size score (1 to 10, higher is better) |
1.75 |
Trend score (1 to 10, higher is better) |
4.75 |
Education Resources¶
URL |
Resource Type |
Description |
---|---|---|
Paper |
Paper providing an overview of Luminaire (IEEE Big Data, 2020) |
|
Paper |
Paper going into detail on Luminaire’s teporal state alignment algorithm (IEEE ICMLA, 2019) |
Git Commit Statistics¶
Statistics computed using Git data through November 30, 2022.
Statistic |
Lifetime |
Last 12 Months |
---|---|---|
Commits |
1,444 |
154 |
Lines committed |
1,195,750 |
4,132 |
Unique committers |
13 |
7 |
Core committers |
4 |
4 |
Similar Projects¶
Project |
Size Score |
Trend Score |
Byline |
---|---|---|---|
2.75 |
5.5 |
A Machine Learning Framework for Time Series Intelligence |
|
3.25 |
5.5 |
A Python package for Bayesian forecasting with object-oriented design and probabilistic models under the hood. |
|
3.5 |
6.5 |
Time series forecasting with PyTorch |
|
2.25 |
2.75 |
An Automated Time-series Outlier Detection System |
|
2.5 |
3.5 |
TSFRESH automatically extracts 100s of features from time series. |