tensorflow_datasets/audio/dementiabank.py [46:103]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def _compute_split_boundaries(split_probs, n_items):
  """Computes boundary indices for each of the splits in split_probs.

  Args:
    split_probs: List of (split_name, prob), e.g. [('train', 0.6), ('dev', 0.2),
      ('test', 0.2)]
    n_items: Number of items we want to split.

  Returns:
    The item indices of boundaries between different splits. For the above
    example and n_items=100, these will be
    [('train', 0, 60), ('dev', 60, 80), ('test', 80, 100)].
  """
  if len(split_probs) > n_items:
    raise ValueError('Not enough items for the splits. There are {splits} '
                     'splits while there are only {items} items'.format(
                         splits=len(split_probs), items=n_items))
  total_probs = sum(p for name, p in split_probs)
  if abs(1 - total_probs) > 1E-8:
    raise ValueError('Probs should sum up to 1. probs={}'.format(split_probs))
  split_boundaries = []
  sum_p = 0.0
  for name, p in split_probs:
    prev = sum_p
    sum_p += p
    split_boundaries.append((name, int(prev * n_items), int(sum_p * n_items)))

  # Guard against rounding errors.
  split_boundaries[-1] = (split_boundaries[-1][0], split_boundaries[-1][1],
                          n_items)

  return split_boundaries


def _get_inter_splits_by_group(items_and_groups, split_probs, split_number):
  """Split items to train/dev/test, so all items in group go into same split.

  Each group contains all the samples from the same speaker ID. The samples are
  splitted so that all each speaker belongs to exactly one split.

  Args:
    items_and_groups: Sequence of (item_id, group_id) pairs.
    split_probs: List of (split_name, prob), e.g. [('train', 0.6), ('dev', 0.2),
      ('test', 0.2)]
    split_number: Generated splits should change with split_number.

  Returns:
    Dictionary that looks like {split name -> set(ids)}.
  """
  groups = sorted(set(group_id for item_id, group_id in items_and_groups))
  rng = np.random.RandomState(split_number)
  rng.shuffle(groups)

  split_boundaries = _compute_split_boundaries(split_probs, len(groups))
  group_id_to_split = {}
  for split_name, i_start, i_end in split_boundaries:
    for i in range(i_start, i_end):
      group_id_to_split[groups[i]] = split_name
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tensorflow_datasets/audio/savee.py [60:117]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def _compute_split_boundaries(split_probs, n_items):
  """Computes boundary indices for each of the splits in split_probs.

  Args:
    split_probs: List of (split_name, prob), e.g. [('train', 0.6), ('dev', 0.2),
      ('test', 0.2)]
    n_items: Number of items we want to split.

  Returns:
    The item indices of boundaries between different splits. For the above
    example and n_items=100, these will be
    [('train', 0, 60), ('dev', 60, 80), ('test', 80, 100)].
  """
  if len(split_probs) > n_items:
    raise ValueError('Not enough items for the splits. There are {splits} '
                     'splits while there are only {items} items'.format(
                         splits=len(split_probs), items=n_items))
  total_probs = sum(p for name, p in split_probs)
  if abs(1 - total_probs) > 1E-8:
    raise ValueError('Probs should sum up to 1. probs={}'.format(split_probs))
  split_boundaries = []
  sum_p = 0.0
  for name, p in split_probs:
    prev = sum_p
    sum_p += p
    split_boundaries.append((name, int(prev * n_items), int(sum_p * n_items)))

  # Guard against rounding errors.
  split_boundaries[-1] = (split_boundaries[-1][0], split_boundaries[-1][1],
                          n_items)

  return split_boundaries


def _get_inter_splits_by_group(items_and_groups, split_probs, split_number):
  """Split items to train/dev/test, so all items in group go into same split.

  Each group contains all the samples from the same speaker ID. The samples are
  splitted so that all each speaker belongs to exactly one split.

  Args:
    items_and_groups: Sequence of (item_id, group_id) pairs.
    split_probs: List of (split_name, prob), e.g. [('train', 0.6), ('dev', 0.2),
      ('test', 0.2)]
    split_number: Generated splits should change with split_number.

  Returns:
    Dictionary that looks like {split name -> set(ids)}.
  """
  groups = sorted(set(group_id for item_id, group_id in items_and_groups))
  rng = np.random.RandomState(split_number)
  rng.shuffle(groups)

  split_boundaries = _compute_split_boundaries(split_probs, len(groups))
  group_id_to_split = {}
  for split_name, i_start, i_end in split_boundaries:
    for i in range(i_start, i_end):
      group_id_to_split[groups[i]] = split_name
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -