autointent.metrics.scoring_neg_ranking_loss#

autointent.metrics.scoring_neg_ranking_loss(labels, scores)#

Calculate negative ranking loss for multilabel classification.

Computes average number of incorrectly ordered label pairs weighted by label set size. 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, scores for each of n_classes classes.

Returns:

Negative ranking loss score.

Return type: