Pymdma

Patch release with fixes for high memory consumption in k-nn manifold estimation metrics.

Added
- `n_workers` parameter in k-nn estimation functions

Changed
- Moved k-nn estimation functions from `general.utils` to `general.functional`

Fixed
- Computing argpartition on distance matrix chunks instead of the entire matrix
- Using sklearn's `pairwise_distances_chunked` instead of `pairwise_distances`
- Reserving memory for the distance matrices to avoid memory spikes

Minor patch release with Time Series standardization and documentation updates.

Changed
- Introduced `BaseTSExtractor` torch module for time_series
- Loading TSFEL config on class instanciation

Fixed
- Removed input layer logic from time_series example notebook (should not use internal methods or classes)

Minor patch release with reduced dependency tree and documentaion updates.

Added
- `convert_grayscale` option in `PSNR`metric
- Explicitely listing `SSIM` and `MSSIM` params
- Non deterministic warning for MSID documentation

Changed
- Renamed `MSSIM` to `MSSSIM`
- GIQA documentation to indicate QS and DS as in paper
- Removed unnecessary torchmetrics dependency for image

Fixed
- Added `np.isclose` verification in hypersphere estimation functions for synthetic evaluation

Minor patch release with new image features extraction method and documentation updates.

Added
- `extract_features_from_dataloader` method to the image `BaseExtractor` class

Changed
- Allowed for `numpy >= 2.0.0` in the requirements
- Allowed `pydantic>2.9.0` in the requirements
- Moved internal method in the image `BaseExtractor` to underscore method

Fixed
- Simplified the `StandardTransform` in images to work directly with tensors

Introduce new time-series metrics and documentation updates.

Added
- `DTW` metric for time-series synthetic data
- `CrossCorrelation` metric for time-series synthetic data
- Time-series example notebook
- PyPI ckassifiers for development status and machine learning topics
- Documentation page in pyproject.toml
- `fastdtw` dependency for the `DTW` metric

Changed
- removed `pydom` dependency from the `DOM` metric
- DOM metric now has a local implementation

Fixed
- PyPI security issues due to direct external `pydom` dependency

Taxonomy rework and documentation updates.

Added
- readthedocs slug in the README file
- References to tabular metrics

Changed
- Renamed `validation_type` to `validation_domain`
- Renamed `metric_group` to `metric_category`
- Renamed `metric_goal` to `metric_group`

Fixed
- Getting features from the last Linear layer of VGG models
- Simplified batch stacking in Image extractor method
- Updated hierarchy diagram in the documentation
- Using local seed in the `features_splitting` method to avoid global overrides that led to inconsistent results
- Removed ununsed text modules
- Added seed for the `cluster_into_bins` method in the `PrecisionRecallDistribution` metric. This ensures that the results are consistent across runs