v0.14.0 - Some minor fixes

[0.14.0] - 2023-07-21

Fixed

• The convert event methods for the EgaitAddidas2014 dataset had a bug that the offset was not taken into account
  correctly.
• For two participants of the EgaitAddidas2014 dataset the offset between the systems was for some reason not consistent
  across all strides. We decided to ignore this, but warn the user about it.

Changed

• The mocap_sampling_rate_hz method of the Kluge2017 dataset is now called mocap_sampling_rate_hz_
  (with trailing underscore) to be consistent with the other datasets.

Added

• SensorPositionComparison2019 now has a method to get the marker trajectories per stride.

v0.13.0 - Fixed bad strides for egait-segmentation-validation

[0.13.0] - 2023-07-13

Fixed

• The egait segmentation validation dataset contained strides that had negative duration.
  We now remove them during loading.

v0.12.0 - New Egait Segmentation labels

[0.12.0] - 2023-04-27

Added

• New labels for the EgaitSegmentationValidation dataset have been created and are distributed with all future versions
  of the dataset.
  These new labels are now the default labels used by the dataset.
  The old labels can be accessed using the segmented_stride_list_original_ property.

v0.11.0 - Some sorting fixes

[0.11.0] - 2023-04-21

Fixed

• Fixed further potential cases where the index of datasets was not deterministically sorted.

Changed

• Config files are frozen now

v0.10.0 - config revamp

[0.10.0] - 2023-03-10

Fixed

• Fixed an issue that the index of EgaitParameterValidation2013 was not deterministically sorted.

Changed

• Removed pydantic as dependency and switched to custom logic to set configs.
  The use-facing API remains the same.

v0.9.0 - Adidas dataset

[0.9.0] - 2023-02-02

Added

• The EgaitParameterValidation2013 dataset now has the option to exclude participant "P52", which appears to have
  non-sensical imu data.
• The EgaitAdidas2014 dataset was added.
  The dataset is not publicly available yet, but will be soon and contains data from healthy participants walking
  through a Vicon motion capture system.
• A convert_segmented_stride_list was added to convert segmented event list to min_vel eventlists.

Changed

• The method convert_with_padding of the SensorPositionComparison2019 dataset is now called
  convert_events_with_padding.

v0.8.0 - global config

[0.8.0] - 2023-30-01

Added

• It is now possible to create a global config file containing the local path to the datasets.
  This allows you to use the datasets without having to specify the path to the dataset every time.
  Further, it means that you don't have to modify source code (just a config file) to run the examples and tests during
  development.
  See the README for more details.
  (#8)

v0.7.0

[0.7.0] - 2023-23-01

Added

• Support for the new alternative calibration files for the egait_parameter_validation_2013 dataset.
  Basically, we found out that the original calibration files were not that good and added new ones to the public
  dataset, that should result in significantly better results when calculating spatial gait parameters.
• All datasets now have images visualizing the applied coordinate system transformations.
• The stair pyshoe dataset has now a new index column describing the number of levels the participant walked during a
  single trail.

v0.6.0

Added

• The PyShoe Dataset (https://github.com/utiasSTARS/pyshoe)

Changed

• The sensor position dataset now reports the mocap distance in m instead of mm to be consistent with the use of SI
  units.

v0.5.0

Changed package name mad-datasets to gaitmap-datasets!
All old releases will still be available under the old name.
All new releases will be available under the new name.