def _make_seed_labels()

in sourcecode/scoring/topic_model.py [0:0]

• 16 lines of code
• 7 McCabe index (conditional complexity)

  def _make_seed_labels(self, texts: np.ndarray) -> Tuple[np.ndarray, np.ndarray]:
    """Produce a label vector based on seed terms.

    Args:
      texts: array containing strings for topic assignment

    Returns:
      Tuple[0]: array specifying topic labels for texts
      Tuple[1]: array specifying texts that are unassigned due to conflicting matches.
    """
    labels = np.zeros(texts.shape[0], dtype=np.int64)
    conflictedTexts = np.zeros(texts.shape[0], dtype=bool)

    for i, text in enumerate(texts):
      matches = self._compiled_regex.finditer(text.lower())
      found_topics = set()
      for match in matches:
        found_topics.update([Topics[grp].value for grp in match.groupdict() if match.group(grp)])

      if len(found_topics) == 1:
        labels[i] = found_topics.pop()
      elif len(found_topics) > 1:
        labels[i] = Topics.Unassigned.value
        conflictedTexts[i] = True

    unassigned_count = np.sum(conflictedTexts)
    logger.info(f"  Notes unassigned due to multiple matches: {unassigned_count}")
    return labels, conflictedTexts