Benchmark time series data sets for PyTorch
MIT License
Bot releases are visible (Hide)
Published by github-actions[bot] over 1 year ago
Published by github-actions[bot] about 2 years ago
sktime
versionPublished by github-actions[bot] about 2 years ago
ICUType
channeloverwrite_cache
now re-downloads datascikit-learn
dependencyPublished by github-actions[bot] over 2 years ago
Published by github-actions[bot] over 2 years ago
NaNs
Published by github-actions[bot] over 2 years ago
.torchtime
directorytrain_split
and val_split
arguments are renamed train_prop
and val_prop
respectivelytorchtime.data_TimeSeriesDataSet
class behind the scenes - note training/validation/test data splits have changed for a given seedtorchtime.collate.packed_sequence
now returns both X
and y
as a PackedSequence objectimpute
argument to support missing data imputation using mean and forward imputation methods or a custom imputation functiondownscale
argument to reduce the size of data sets for testing/model developmenttorchtime.data.TensorTimeSeriesDataset
class to create a data set from input tensorsfloat32
/torch.float
and int64
/torch.long
precision for all data setsy
data in PhysioNet2019 dataPublished by github-actions[bot] over 2 years ago
data/physionet2019
torchtime.data
to share utility functions across data classespacked_sequence
collate functionPublished by philipdarke over 2 years ago
First release to PyPi