n_folds = args.cv if args.cv is not None else 1
if n_folds > 1:
fold_splits = load_cv_splits(args.dataset,
dataset_name,
n_folds,
train_ext=train_ext,
valid_ext=valid_ext,
test_ext=test_ext,
dtype=args.dtype)
else:
fold_splits = load_train_val_test_splits(args.dataset,
dataset_name,
x_only=False,
y_only=False,
train_ext=train_ext,
valid_ext=valid_ext,
test_ext=test_ext,
dtype=args.dtype)
print_fold_splits_shapes(fold_splits)
merged_fold_splits = []
for i, splits in enumerate(fold_splits):
logging.info('Processing fold {}\n'.format(i))
merged_splits = []
for j, split in enumerate(splits):
if split is not None:
split_x, split_y = split
test_ext=repr_test_x_ext,
dtype=args.repr_x_dtype)
if decode:
repr_fold_y_splits = load_cv_splits(args.repr_y,
dataset_name,
n_folds,
y_only=True,
train_ext=repr_train_y_ext,
valid_ext=repr_valid_y_ext,
test_ext=repr_test_y_ext,
dtype=args.repr_y_dtype)
else:
fold_splits = load_train_val_test_splits(args.dataset,
dataset_name,
train_ext=train_ext,
valid_ext=valid_ext,
test_ext=test_ext,
dtype=args.dtype)
repr_fold_x_splits = load_train_val_test_splits(args.repr_x,
dataset_name,
x_only=True,
train_ext=repr_train_x_ext,
valid_ext=repr_valid_x_ext,
test_ext=repr_test_x_ext,
dtype=args.repr_x_dtype)
if decode:
repr_fold_y_splits = load_train_val_test_splits(args.repr_y,
dataset_name,
y_only=True,
train_ext=repr_train_y_ext,
valid_ext=repr_valid_y_ext,