hookeai.miscellaneous.pruning.pruning_dataset.set_pruning_iter_dir

set_pruning_iter_dir(prun_datasets_dir, train_dataset, val_dataset, unused_dataset, test_dataset_dirs={}, dataset_basename='ss_paths_dataset')

Setup pruning iteration directory.

Parameters:

• prun_datasets_dir (str) – Pruned data sets directory.

• train_dataset (torch.utils.data.Dataset) – Time series training data set. Each sample is stored as a dictionary where each feature (key, str) data is a torch.Tensor(2d) of shape (sequence_length, n_features).

• val_dataset (torch.utils.data.Dataset) – Time series validation data set. Each sample is stored as a dictionary where each feature (key, str) data is a torch.Tensor(2d) of shape (sequence_length, n_features).

• unused_dataset (torch.utils.data.Dataset) – Time series unused data set. Each sample is stored as a dictionary where each feature (key, str) data is a torch.Tensor(2d) of shape (sequence_length, n_features).

• test_dataset_dirs (dict, default={}) – Testing data set directory (item, str) for each testing type (key, str).

• dataset_basename (str, defaut='ss_paths_dataset') – Data set file base name.

Returns:

• pruning_iter_dir (str) – Pruning iteration directory.

• model_directory (str) – Directory where model is stored.

• train_dataset_file_path (str) – Training data set file path.

• val_dataset_file_path (str) – Validation data set file path.

• test_dataset_file_paths (dict) – Testing data set file path (item, str) for each testing type (key, str).

• test_prediction_dirs (dict) – Directory (item, str) where samples predictions results files are stored for each testing type (key, str).