autointent.metrics.scoring.scoring_roc_auc#
- autointent.metrics.scoring.scoring_roc_auc(labels, scores)#
Supports multiclass and multilabel cases.
Macro averaged roc-auc for utterance classification task, i.e.
\[\frac{1}{C}\sum_{k=1}^C ROCAUC(scores[:, k], labels[:, k])\]where
Cis the number of classes- 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: