v1.0.0

November 2024

aeon v1.0.0 is our first major release. It contains a large number of new features and removes a significant body of legacy code. We want to thank every contributor who has helped make this release possible.

This major release includes breaking changes that could not happen in a regular minor release. This includes the removal of the old forecasting wrapper-based code, the datatypes module and the previous transformer module. Our focus now is on writing more efficient code based on efficient array based bespoke implementations.

Highlights

  • Introduction of a new experimental forecasting module, replacing the old module (this is currently sparse, but we will expand on the framework and available estimators in the future.

  • Restructuring and expansion of the clustering module, including deep learning clustering.

  • Explicit split of the transformation module into series transformers and collection transformers.

  • Extended anomaly detection module.

  • Completely new testing suite.

  • Enhanced visualisation tools.

  • Improved documentation and examples.

  • Introduction of more multivariate capable deep learning estimators.

Anomaly Detection

Bug Fixes

Deprecation

Enhancements

Maintenance

Benchmarking

Deprecation

Documentation

  • [REF] Refactor performance_metrics into benchmarking.metrics and use a local version of sphinx-remove-toctrees (#2353) @MatthewMiddlehurst

Enhancements

Refactored

  • [REF] Refactor performance_metrics into benchmarking.metrics and use a local version of sphinx-remove-toctrees (#2353) @MatthewMiddlehurst

Other

  • [ENH] fix the zero_method of the wilcoxon sign rank test to “wilcox” in mcm (#2361) @TonyBagnall

Classification

Bug Fixes

  • [ENH] Remove soft dependency on pyfftw (#2213) @TonyBagnall

  • [BUG] Fixed subsampling in highly imbalances datasets giving subsamples with only a single class (#2305) @ferewi

Deprecation

Documentation

Enhancements

Maintenance

Clustering

Bug Fixes

  • [BUG[ Use clone estimator in BaseDeepClusterer to fix check_fit_updates_state fail (#2309) @hadifawaz1999

Documentation

  • [DOC] remove use of init_algorithm parameter in Clustering notebook (#2050) @TonyBagnall

Enhancements

Maintenance

Other

Datasets

Bug Fixes

Documentation

Enhancements

Maintenance

Distances

Bug Fixes

  • [BUG] Fix failing periodic tests (#2159) @chrisholder

  • [ENH, BUG] Fixes issue with lower bounding in SAX for TS length not divisible by the number of segments (#2214) @patrickzib

Enhancements

Maintenance

Refactored

  • [MNT] Change the “metric” parameter to “measure in the distance module (#2403) @chrisholder

  • [MNT] Distance module changed to method rather than metric (#2407) @chrisholder

Forecasting

Deprecation

Enhancements

Documentation

Networks

Deprecation

Enhancements

Maintenance

Regression

Deprecation

Documentation

Enhancements

Maintenance

Other

Transformations

Bug Fixes

Deprecation

Documentation

Enhancements

Maintenance

Other

Unit Testing

Bug Fixes

Deprecation

Documentation

Enhancements

Maintenance

Refactored

Other

Visualisations

Bug Fixes

Enhancements

Documentation

  • [ENH] Documented why rotational forest isn’t visualisable in the shapelet viz module (#2027) @IRKnyazev

Other

Bug Fixes

Deprecation

Documentation

Enhancements

Maintenance

Refactored

Contributors

The following have contributed to this release through a collective 212 GitHub Pull Requests:

@aadya940, @alexbanwell1, @aryanpola, @baraline, @chrisholder, @Cyril-Meyer, @danielroberts20, @Datadote, @emmanuel-ferdman, @ferewi, @fspinna, @georgejl7, @griegner, @hadifawaz1999, @IRKnyazev, @itsdivya1309, @kavya-r30, @LinGinQiu, @MatthewMiddlehurst, @Moonzyyy, @notaryanramani, @patrickzib, @pattplatt, @SebastianSchmidl, @Sharathchenna, @TonyBagnall