autointent.metrics.scoring_map#

autointent.metrics.scoring_map(labels, scores)#

Calculate mean average precision (MAP) score for multilabel classification.

Measures precision at different ranking levels, averaged across all queries. The ideal value is 1, indicating perfect ranking.

Parameters:

labels (autointent.metrics.custom_types.LABELS_VALUE_TYPE) – Ground truth labels for each sample.
scores (autointent.metrics.custom_types.SCORES_VALUE_TYPE) – For each sample, scores for each of n_classes classes.

Returns:

Mean average precision score.

Return type: