v0.2.0

May 2023

Following this release the deprecation policy remains suspended. Future releases may have breaking changes, so it may be wise to set an upper bound on the package version.

Highlights

• aeon now supports Python 3.11!

• New estimators are available in the regression package, including InceptionTime (@hadifawaz1999) and FreshPRINCE (@dguijo)

• The distances module has been reworked, and the distances available are now faster (@chrisholder)

• The RandomDilatedShapeletTransform for collections of series is now available (@baraline)

• The ‘Getting Started’ page on the documentation has been rewritten with clearer introductions to each module

Enhancements

• [ENH] remove regression mentions of nested_univ (#279) @TonyBagnall

• [ENH] Bounding matrix for distances module (#305) @chrisholder

• [ENH] added inceptionTime as regressor (#260) @hadifawaz1999

• [ENH] Convert Catch22 and Catch22Wrapper to use numpy internally (#294) @TonyBagnall

• [ENH] Update euclidean and squared distance (#308) @chrisholder

• [ENH] Update distance alignment paths (#309) @chrisholder

• [ENH] Convert HOG1DTransformer and DerivativeSlopeTransformer to use numpy arrays internally (#261) @TonyBagnall

• [ENH] Convert DWTTransformer to use numpy format internally (#293) @TonyBagnall

• [ENH] RDST transformer (#310) @baraline

• [ENH] Update dtw distance (#316) @chrisholder

• [ENH] added ReduceLROnPlateau callback by default to InceptionTime deep classifier (#327) @hadifawaz1999

• [ENH] Introduce list of numpy arrays data type for classification/regression/clustering (#296) @TonyBagnall

• [ENH] refactor param_est to live in forecasting module (#330) @TonyBagnall

• [ENH] Removes nested dataframes from shape dtw (#329) @TonyBagnall

• [ENH] Add reduce on plateau learning rate decay for FCN ResNet and MLP deep classifiers (#351) @hadifawaz1999

• [ENH] Refactor pairwise distance (#357) @chrisholder

• [ENH] purge mentions of Panel in classification (#331) @TonyBagnall

• [ENH] Update ddtw distance (#319) @chrisholder

• [ENH] Update wdtw distance (#322) @chrisholder

• [ENH] Update wddtw distance (#323) @chrisholder

• [ENH] Update lcss distance (#332) @chrisholder

• [ENH] Update erp distance (#333) @chrisholder

• [ENH] Update edr distance (#366) @chrisholder

• [ENH] add model checkpoint to inceptionTime deep classifier (#362) @hadifawaz1999

• [ENH] Update twe distance (#367) @chrisholder

• [ENH] Update msm distance (#369) @chrisholder

• [ENH] Distance module cleanup (#372) @chrisholder

• [MNT] Remove any reference of pykalman (#380) @hadifawaz1999

• [ENH] removes the param_est package (#356) @TonyBagnall

• [ENH] added modelcheckpoint and reduce learning rate to inceptionTime regressor (#397) @hadifawaz1999

• [ENH] Add model checkpoint for the rest of the deep learning classifiers (#394) @hadifawaz1999

• [ENH] convert TSInterpolator to np-list/numpy3D (#388) @TonyBagnall

• [ENH] Adapt PlateauFinder to use numpy3D (#392) {user}`TonyBagnall

• [ENH] FreshPRINCERegressor, RotationForestRegressor and minor changes to FreshPRINCEClassifier (#384) @dguijo

• [ENH] remove more mentions of nested_univ (#295) @TonyBagnall

• [ENH] combine test_returns_self with test_fit_updates_state (#300) @TonyBagnall

• [ENH] Change data loaders and writers to minimize use of “nested_univ” input type (#355) @TonyBagnall

• [ENH] TruncationTransformer, PaddingTransformer and TSFresh internal type to np-list (#364) @TonyBagnall

Fixes

• [BUG] Fix test overwrite inception time classifier (#315) @hadifawaz1999

• [ENH] Update distance alignment paths (#309) @chrisholder

• [BUG] Forecasting base circular import (#328) @MatthewMiddlehurst

• [BUG] Fixes show_versions error (#353) @GuiArcencio

• [BUG] Fixes load_covid_3month returning a non-numeric y (#354) @GuiArcencio

• [ENH] Update twe distance (#367) @chrisholder

• [MNT] Remove any reference of pykalman (#380) @hadifawaz1999

• [BUG] fix tsfresh “kind” feature extractor (#400) @TonyBagnall

• [BUG] fix all_estimators to work with tags that are lists of strings not just single strings (#399) @TonyBagnall

Documentation

• [DOC] Change web documentation colours (#301) @MatthewMiddlehurst

• [DOC] New aeon logo and replacement for current usage (#298) @MatthewMiddlehurst

• [DOC] Update README (#303) @MatthewMiddlehurst

• [DOC] Fix rocket examples imports (#325) @hadifawaz1999

• [DOC] Remove meetup and sponsor cards from get involved (#344) @MatthewMiddlehurst

• & TonyBagnall [DOC] Remake get_started page (#346) @MatthewMiddlehurst

• [DOC] Add contrib.rocks image to contributors.md and lower all-contributors table/image size (#352) @MatthewMiddlehurst

• [MNT] docs update to fix readthedocs fail (#386) @TonyBagnall

• [DOC] Tidy up classification docs (#398) @TonyBagnall

• [DOC] Update section names in examples.md (#404) @GuzalBulatova

Maintenance

• [MNT] Update issue templates to use issue forms (#311) @MatthewMiddlehurst

• [MNT] Fix Binder Dockerfile (#306) @MatthewMiddlehurst

• [MNT] Update contributors.md (#312) @MatthewMiddlehurst

• [MNT] Cleanup the forecasting tests (#192) @lmmentel

• [MNT] Update file change action and cancel workflow (#339) @MatthewMiddlehurst

• [MNT] Remove test_fit_does_not_overwrite_hyper_params and test_methods_have_no_side_effects from config for most deep learners CNN MLP Encoder and FCN classifiers (#348) @hadifawaz1999

• [MNT] Remove the test_methods_have_no_side_effects for inceptionTime classifier from _config (#338) @hadifawaz1999

• [MNT] Fix workflow concurrency (#350) @MatthewMiddlehurst

• [MNT] Change update_contributors.yml to create PRs (#349) @MatthewMiddlehurst

• [MNT] Changes repo owner to aeon-toolkit in .all-contributorsrc (#359) @GuiArcencio

• [MNT] docs update to fix readthedocs fail (#386) @TonyBagnall

• [MNT] Add python 3.11 support (#191) @lmmentel

• [MNT] Remove any reference of pykalman (#380) @hadifawaz1999

• [MNT] Unstable extras (#365) @MatthewMiddlehurst

• [MNT] Remove the test_methods_have_no_side_effects for inceptionTime classifier from _config (#338) @hadifawaz1999

Contributors

@baraline, @chrisholder, @dguijo, @GuiArcencio, @GuzalBulatova, @hadifawaz1999, @lmmentel, @MatthewMiddlehurst, @TonyBagnall