torchtime

Fixed

• Support for PyTorch 1.13.x to 2.0.x
• GitHub Actions badge

Changed

• Updated dependencies

Added

• Support for Python 3.10 and 3.11

Changed

• Adopt updated sktime version

Changed

• One-hot encoded PhysioNet2012 ICUType channel
• Updated pre-commit hooks

Added

• "zero" value imputation
• Download progress bars

Fixed

• overwrite_cache now re-downloads data
• scikit-learn dependency

Fixed

• Continuous deployment

Changed

• More efficient PhysioNet data set downscaling
• Updated documentation

Added

• PhysioNet2012 data set
• PhysioNet and UEA/UCR unit tests
• Utility function module
• Better console messages

Fixed

• Replace PhysioNet2019 missing data indicator with NaNs
• Code coverage badge

Changed

• Processed data are now cached in the .torchtime directory
• train_split and val_split arguments are renamed train_prop and val_prop respectively
• Introduced generic torchtime.data_TimeSeriesDataSet class behind the scenes - note training/validation/test data splits have changed for a given seed
• torchtime.collate.packed_sequence now returns both X and y as a PackedSequence object
• Expanded unit tests - note coverage is currently limited as PhysioNet2019 tests cannot be run under CI
• Updated documentation

Added

• impute argument to support missing data imputation using mean and forward imputation methods or a custom imputation function
• downscale argument to reduce the size of data sets for testing/model development
• torchtime.data.TensorTimeSeriesDataset class to create a data set from input tensors

Fixed

• Use float32/torch.float and int64/torch.long precision for all data sets
• Shape of y data in PhysioNet2019 data
• Bug when adding time delta channels without a missing data mask

Changed

• Simplified training/validation/test split approach
• Default file path for PhysioNet2019 data set is now data/physionet2019
• Refactored torchtime.data to share utility functions across data classes
• Expanded unit tests
• Updated documentation

Added

• Missing data simulation for UEA/UCR data sets
• Support appending missing data masks and time delta channels
• packed_sequence collate function
• Documentation now includes a tutorial
• Automated releases using GitHub Actions
• DOI

First release to PyPi