Orion
Support for python 3.10 and 3.11
Update test_core file – Issue #507 by @sarahmish
test_core
update ARIMA primitive and pipeline – Issue #503 by @sarahmish
Update Dependency – Issue #497 & Issue #499 by @sarahmish
Update Python for Dependency Test – Issue #484 by @sarahmish
Add python 3.10 and 3.11 & drop 3.6 and 3.7 – Issue #477 by @sarahmish
LNN Pipeline – Issue #475 by @sarahmish
Support for python 3.9 and new Matrix Profile pipeline
Send pipeline names in benchmark arguments – Issue #466 by @sarahmish
Add continuation parameter for benchmark – Issue #464 by @sarahmish
Fix references in documentation – Issue #453 by @sarahmish
Update documentation – Issue #448 by @sarahmish
Add matrix profiling method – Issue #446 by @sarahmish
Support python 3.9 – Issue #408 by @sarahmish
This version introduces a new dataset to the benchmark.
Add UCR dataset to the benchmark – Issue #443 by @sarahmish
docker image build failed – Issue #439 by @sarahmish
Edit interval settings in azure pipeline – Issue #436 by @sarahmish
azure
This version uses ml-stars package instead of mlprimitives.
ml-stars
mlprimitives
Migrate to ml-stars – Issue #418 by @sarahmish
Updating best_cost in find_anomalies primitive – Issue #403 by @sarahmish
best_cost
find_anomalies
Retire lstm_dynamic_threshold_gpu and lstm_autoencoder_gpu pipeline maintenance – Issue #373 by @sarahmish
lstm_dynamic_threshold_gpu
lstm_autoencoder_gpu
Typo in xlsxwriter dependency specification – Issue #394 by @sarahmish
orion.evaluate uses fails when fitting – Issue #384 by @sarahmish
orion.evaluate
AER pipeline with visualization option – Issue #379 by @sarahmish
Move VAE from sandbox to verified – Issue #377 by @sarahmish
Pin opencv – Issue #372 by @sarahmish
opencv
Pin scikit-learn – Issue #367 by @sarahmish
scikit-learn
Fix VAE documentation – Issue #360 by @sarahmish
This version introduces several new enhancements:
Support to python 3.8
Migrating to Tensorflow 2.0
New pipeline, namely VAE, a Variational AutoEncoder model.
VAE
Add python 3.8 – Issue #342 by @sarahmish
VAE (Variational Autoencoders) pipeline implementation – Issue #349 by @dyuliu
Add masking option for regression_errors – Issue #352 by @dyuliu
regression_errors
Changes in TadGAN for tensorflow 2.0 – Issue #161 by @lcwong0928
Add an automatic dependency checker – Issue #320 by @sarahmish
TadGAN batch_size cannot be changed – Issue #313 by @sarahmish
batch_size
This version fixes some of the issues in aer, ae, and tadgan pipelines.
aer
ae
tadgan
Fix AER model predict error after loading – Issue #304 by @lcwong0928
Update AE to work with any window_size – Issue #300 by @sarahmish
window_size
Updated tadgan_viz.json – Issue #292 by @Hramir
This version introduce a new pipeline, namely AER, an AutoEncoder Regressor model.
AER
Add AER Model - Issue #286 by @lcwong0928
This version deprecates the support of OrionDBExplorer, which has been migrated to sintel. As a result, Orion no longer requires mongoDB as a dependency.
OrionDBExplorer
Update dependency - Issue #283 by @sarahmish
General housekeeping - Issue #278 by @sarahmish
Fix tutorial testing issue - Issue #276 by @sarahmish
Migrate OrionExplorer to Sintel - Issue #275 by @dyuliu
LSTM viz JSON pipeline added - Issue #271 by @Hramir
This version introduces improvements and more testing.
Adjusting builds for TadGAN - Issue #261 by @sarahmish
Testing tutorials, dependencies, and OS - Issue #251 by @sarahmish
This version supports multivariate timeseries as input. In addition to minor improvements and maintenance.
setuptools no longer supports lib2to3 breaking mongoengine - Issue #252 by @sarahmish
setuptools
lib2to3
mongoengine
Supporting multivariate input - Issue #248 by @sarahmish
TadGAN pipeline with visualization option - Issue #240 by @sarahmish
Support saving absolute path for add_signals and add_signal when using dbExplorer - Issue #202 by @sarahmish
dynamic scalability of TadGAN primitive based on window_size - Issue #87 by @sarahmish
This 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.
Dask issues in benchmark function & improvements - Issue #225 by @sarahmish
Numerical overflow when using contextual metrics - Issue #212 by @kronerte
This 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.
reconstruction_errors
Comparison of DTW library performance - Issue #205 by @sarahmish
Not able to pickle dump tadgan pipeline - Issue #200 by @sarahmish
New pipeline LSTM and Dense autoencoders - Issue #194 by @sarahmish
Readme - Issue #192 by @pvk-developer
Unable to launch cli - Issue #186 by @sarahmish
bullet points not formatted correctly in index.rst - Issue #178 by @micahjsmith
Update notebooks - Issue #176 by @sarahmish
Inaccuracy in README.md file in orion/evaluation/ - Issue #157 by @sarahmish
Dockerfile – docker does not find orion primitives automatically - Issue #155 by @sarahmish
Primitive documentation - Issue #151 by @sarahmish
Variable name inconsistency in tadgan - Issue #150 by @sarahmish
Sync leaderboard tables between BENCHMARK.md and the docs - Issue #148 by @sarahmish
BENCHMARK.md
This 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.
README.md
verified
Link with google colab - Issue #144 by @sarahmish
Add timeseries_anomalies unittests - Issue #136 by @sarahmish
timeseries_anomalies
Update find_sequences in converting series to arrays - Issue #135 by @sarahmish
find_sequences
Definition of error/critic smooth window in score anomalies primitive - Issue #132 by @sarahmish
Train-test split in benchmark enhancement - Issue #130 by @sarahmish
Minor enhancements to benchmark
Load ground truth before try-catch - Issue #124 by @sarahmish
Converting timestamp to datetime in Azure primitive - Issue #123 by @sarahmish
Benchmark exceptions - Issue #120 by @sarahmish
New benchmark and Azure primitive.
Implement a benchmarking function new feature - Issue #94 by @sarahmish
Add azure anomaly detection as primitive new feature - Issue #97 by @sarahmish
Critic and reconstruction error combination - Issue #99 by @sarahmish
Fixed threshold for find_anomalies - Issue #101 by @sarahmish
Add an option to have window size and window step size as percentages of error size - Issue #102 by @sarahmish
Organize pipelines into verified and sandbox - Issue #105 by @sarahmish
Ground truth parameter name enhancement - Issue #114 by @sarahmish
Add benchmark dataset list and parameters to s3 bucket enhancement - Issue #118 by @sarahmish
New Evaluation sub-package and refactor TadGAN.
Two bugs when saving signalrun if there is no event detected - Issue #92 by @dyuliu
File encoding/decoding issues about README.md and HISTORY.md - Issue #88 by @dyuliu
HISTORY.md
Fix bottle neck of score_anomaly in Cyclegan primitive - Issue #86 by @dyuliu
score_anomaly
Adjust epoch meaning in Cyclegan primitive - Issue #85 by @sarahmish
epoch
Rename evaluation to benchmark and metrics to evaluation - Issue #83 by @sarahmish
Scoring function for intervals of size one - Issue #76 by @sarahmish
New class and function based interfaces.
Implement the Orion Class - Issue #79 by @csala
Implement new functional interface - Issue #80 by @csala
First Orion release to PyPI: https://pypi.org/project/orion-ml/