autointent.metrics.scoring_neg_ranking_loss#

autointent.metrics.scoring_neg_ranking_loss(labels, scores)#

Supports multilabel.

Compute the average number of label pairs that are incorrectly ordered given y_score weighted by the size of the label set and the number of labels not in the label set.

the ideal value is 0

Parameters:
  • labels (autointent.metrics.custom_types.LABELS_VALUE_TYPE) – ground truth labels for each utterance

  • scores (autointent.metrics.custom_types.SCORES_VALUE_TYPE) – for each utterance, this list contains scores for each of n_classes classes

Returns:

Score of the scoring metric

Return type:

float