sup3r.preprocessing.batch_handling.ValidationDataTemporalDC

class ValidationDataTemporalDC(data_handlers, batch_size=8, s_enhance=1, t_enhance=1, temporal_coarsening_method='subsample', hr_features_ind=None, smoothing=None, smoothing_ignore=None)[source]

Bases: ValidationDataDC

Iterator for data-centric temporal validation data

Parameters:

  • data_handlers (list[DataHandler]) – List of DataHandler instances

  • batch_size (int) – Size of validation data batches

  • s_enhance (int) – Factor by which to coarsen spatial dimensions of the high resolution data

  • t_enhance (int) – Factor by which to coarsen temporal dimension of the high resolution data

  • temporal_coarsening_method (str) – [subsample, average, total, min, max] Subsample will take every t_enhance-th time step, average will average over t_enhance time steps, total will sum over t_enhance time steps

  • hr_features_ind (list | np.ndarray | None) – List/array of feature channel indices that are used for generative output, without any feature indices used only for training.

  • smoothing (float | None) – Standard deviation to use for gaussian filtering of the coarse data. This can be tuned by matching the kinetic energy of a low resolution simulation with the kinetic energy of a coarsened and smoothed high resolution simulation. If None no smoothing is performed.

  • smoothing_ignore (list | None) – List of features to ignore for the smoothing filter. None will smooth all features if smoothing kwarg is not None

Methods

any()

Return True if any validation data exists

batch_next(high_res)

Assemble the next batch

get_handler_index()

Get random handler index based on handler weights

Attributes

N_SPACE_BINS

N_TIME_BINS

handler_weights

Get weights used to sample from different data handlers based on relative sizes

shape

Shape of full validation dataset across all handlers
BATCH_CLASS

alias of Batch

any()

Return True if any validation data exists

batch_next(high_res)

Assemble the next batch

Parameters:

high_res (np.ndarray) – 4D | 5D array (batch_size, spatial_1, spatial_2, features) (batch_size, spatial_1, spatial_2, temporal, features)

Returns:

batch (Batch)

get_handler_index()

Get random handler index based on handler weights

property handler_weights

Get weights used to sample from different data handlers based on relative sizes

property shape

Shape of full validation dataset across all handlers

Returns:

shape (tuple) – (spatial_1, spatial_2, temporal, features) With temporal extent equal to the sum across all data handlers time dimension