[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

elk/extraction/dataset_preprocessing.py

@@ -8,19 +8,21 @@ def undersample(dataset: DatasetDict, label_column: str = "label"):
 
  Args:
  dataset (DatasetDict): The dataset to balance.
- label_column (str, optional): 
+ label_column (str, optional):
  The column containing the labels.
  Defaults to "label".
- 
+
  Returns:
  DatasetDict: The balanced dataset.
  """
  labels, counts = np.unique(dataset[label_column], return_counts=True)
 
  subsets = []
  for label in labels:
- subsets.append(dataset.filter(
- lambda x: x[label_column] == label).select(range(min(counts)))
+ subsets.append(
+ dataset.filter(lambda x: x[label_column] == label).select(
+ range(min(counts))
+ )
  )
 
  return concatenate_datasets(subsets).shuffle()