autointent.metrics.scoring_hit_rate#

autointent.metrics.scoring_hit_rate(labels, scores)#

Calculate hit rate for multilabel classification.

Hit rate measures the fraction of cases where the top-ranked label is in the set of true labels for the instance.

$$\text{Hit Rate}=\frac{1}{N}\sum _{i=1}^N\mathbb{1}(y_{\text{top},i}\in y_{\text{true},i})$$

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:

Hit rate score.

Return type:

float