An open source project from Data to AI Lab at MIT.
OrionA machine learning library for unsupervised time series anomaly detection.
Important Links :computer: Website Check out the Sintel Website for more information about the project. :book: Documentation Quickstarts, User and Development Guides, and API Reference. :star: Tutorials Checkout our notebooks :octocat: Repository The link to the Github Repository of this library. :scroll: License The repository is published under the MIT License. Community Join our Slack Workspace for announcements and discussions. OverviewOrion is a machine learning library built for unsupervised time series anomaly detection. With a given time series data, we provide a number of “verified” ML pipelines (a.k.a Orion pipelines) that identify rare patterns and flag them for expert review.
The library makes use of a number of automated machine learning tools developed under Data to AI Lab at MIT.
Read about using an Orion pipeline on NYC taxi dataset in a blog series:
Notebooks: Discover Orion through colab by launching our notebooks!
Quickstart Install with pipThe easiest and recommended way to install Orion is using pip:
pip install orion-ml
This will pull and install the latest stable release from PyPi.
In the following example we show how to use one of the Orion Pipelines.
Fit an Orion pipelineWe will load a demo data for this example:
from orion.data import load_signal
train_data = load_signal('S-1-train')
train_data.head()
which should show a signal with timestamp and value.
timestamp value
0 1222819200 -0.366359
1 1222840800 -0.394108
2 1222862400 0.403625
3 1222884000 -0.362759
4 1222905600 -0.370746
In this example we use aer pipeline and set some hyperparameters (in this case training epochs as 5).
from orion import Orion
hyperparameters = {
'orion.primitives.aer.AER#1': {
'epochs': 5,
'verbose': True
}
}
orion = Orion(
pipeline='aer',
hyperparameters=hyperparameters
)
orion.fit(train_data)
Detect anomalies using the fitted pipeline
Once it is fitted, we are ready to use it to detect anomalies in our incoming time series:
new_data = load_signal('S-1-new')
anomalies = orion.detect(new_data)
:warning: Depending on your system and the exact versions that you might have installed some WARNINGS may be printed. These can be safely ignored as they do not interfere with the proper behavior of the pipeline.
The output of the previous command will be a pandas.DataFrame containing a table of detected anomalies:
start end severity
0 1402012800 1403870400 0.122539
In every release, we run Orion benchmark. We maintain an up-to-date leaderboard with the current scoring of the verified pipelines according to the benchmarking procedure.
We run the benchmark on 12 datasets with their known grounth truth. We record the score of the pipelines on each datasets. To compute the leaderboard table, we showcase the number of wins each pipeline has over the ARIMA pipeline.
Pipeline Outperforms ARIMA AER 12 TadGAN 7 LSTM Dynamic Thresholding 9 LSTM Autoencoder 7 Dense Autoencoder 7 VAE 6 AnomalyTransformer 2 LNN 7 Matrix Profile 5 UniTS 6 TimesFM 7 GANF 5 Azure 0You can find the scores of each pipeline on every signal recorded in the details Google Sheets document. The summarized results can also be browsed in the following summary Google Sheets document.
ResourcesAdditional resources that might be of interest:
If you use AER for your research, please consider citing the following paper:
Lawrence Wong, Dongyu Liu, Laure Berti-Equille, Sarah Alnegheimish, Kalyan Veeramachaneni. AER: Auto-Encoder with Regression for Time Series Anomaly Detection.
@inproceedings{wong2022aer,
title={AER: Auto-Encoder with Regression for Time Series Anomaly Detection},
author={Wong, Lawrence and Liu, Dongyu and Berti-Equille, Laure and Alnegheimish, Sarah and Veeramachaneni, Kalyan},
booktitle={2022 IEEE International Conference on Big Data (IEEE BigData)},
pages={1152-1161},
doi={10.1109/BigData55660.2022.10020857},
organization={IEEE},
year={2022}
}
If you use TadGAN for your research, please consider citing the following paper:
Alexander Geiger, Dongyu Liu, Sarah Alnegheimish, Alfredo Cuesta-Infante, Kalyan Veeramachaneni. TadGAN - Time Series Anomaly Detection Using Generative Adversarial Networks.
@inproceedings{geiger2020tadgan,
title={TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks},
author={Geiger, Alexander and Liu, Dongyu and Alnegheimish, Sarah and Cuesta-Infante, Alfredo and Veeramachaneni, Kalyan},
booktitle={2020 IEEE International Conference on Big Data (IEEE BigData)},
pages={33-43},
doi={10.1109/BigData50022.2020.9378139},
organization={IEEE},
year={2020}
}
If you use Orion which is part of the Sintel ecosystem for your research, please consider citing the following paper:
Sarah Alnegheimish, Dongyu Liu, Carles Sala, Laure Berti-Equille, Kalyan Veeramachaneni. Sintel: A Machine Learning Framework to Extract Insights from Signals.
@inproceedings{alnegheimish2022sintel,
title={Sintel: A Machine Learning Framework to Extract Insights from Signals},
author={Alnegheimish, Sarah and Liu, Dongyu and Sala, Carles and Berti-Equille, Laure and Veeramachaneni, Kalyan},
booktitle={Proceedings of the 2022 International Conference on Management of Data},
pages={1855–1865},
numpages={11},
publisher={Association for Computing Machinery},
doi={10.1145/3514221.3517910},
series={SIGMOD '22},
year={2022}
}
New timesfm pipeline
mistune – Issue #605 by @sarahmishunits pipeline find_anomalies params – Issue #602 by @Linh-nkNew units pipeline
scikit-learn and fix MinMaxScaler – Issue #596 by @sarahmishunits pipelines – Issue #595 by @sarahmishSupport for python 3.10 and 3.11
Issues resolvedtest_core file – Issue #507 by @sarahmishSupport for python 3.9 and new Matrix Profile pipeline
Issues resolvedThis version introduces a new dataset to the benchmark.
Issues resolvedazure pipeline – Issue #436 by @sarahmishThis version uses ml-stars package instead of mlprimitives.
best_cost in find_anomalies primitive – Issue #403 by @sarahmishlstm_dynamic_threshold_gpu and lstm_autoencoder_gpu pipeline maintenance – Issue #373 by @sarahmishorion.evaluate uses fails when fitting – Issue #384 by @sarahmishopencv – Issue #372 by @sarahmishscikit-learn – Issue #367 by @sarahmishThis version introduces several new enhancements:
VAE, a Variational AutoEncoder model.regression_errors – Issue #352 by @dyuliubatch_size cannot be changed – Issue #313 by @sarahmishThis version fixes some of the issues in aer, ae, and tadgan pipelines.
window_size – Issue #300 by @sarahmishThis version introduce a new pipeline, namely AER, an AutoEncoder Regressor model.
This version deprecates the support of OrionDBExplorer, which has been migrated to sintel. As a result, Orion no longer requires mongoDB as a dependency.
This version introduces improvements and more testing.
Issues resolvedThis version supports multivariate timeseries as input. In addition to minor improvements and maintenance.
Issues resolvedsetuptools no longer supports lib2to3 breaking mongoengine - Issue #252 by @sarahmishwindow_size - Issue #87 by @sarahmishThis version adds new features to the benchmark function where users can now save pipelines, view results as they are being calculated, and allow a single evaluation to be compared multiple times.
Issues resolvedThis version introduces two new pipelines: LSTM AE and Dense AE. In addition to minor improvements, a bit of code refactoring took place to introduce a new primtive: reconstruction_errors.
BENCHMARK.md and the docs - Issue #148 by @sarahmishThis version includes the new style of documentation and a revamp of the README.md. In addition to some minor improvements in the benchmark code and primitives. This release includes the transfer of tadgan pipeline to verified.
timeseries_anomalies unittests - Issue #136 by @sarahmishfind_sequences in converting series to arrays - Issue #135 by @sarahmishMinor enhancements to benchmark
New benchmark and Azure primitive.
find_anomalies - Issue #101 by @sarahmishNew Evaluation sub-package and refactor TadGAN.
README.md and HISTORY.md - Issue #88 by @dyuliuscore_anomaly in Cyclegan primitive - Issue #86 by @dyuliuepoch meaning in Cyclegan primitive - Issue #85 by @sarahmishNew class and function based interfaces.
First Orion release to PyPI: https://pypi.org/project/orion-ml/
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4