autointent.metrics.retrieval_hit_rate#

autointent.metrics.retrieval_hit_rate(query_labels, candidates_labels, k=None)#

Calculate the hit rate at position k.

The hit rate is calculated as:

\[\text{Hit Rate} = \frac{\sum_{i=1}^N \mathbb{1}(y_{\text{query},i} \in y_{\text{candidates},i}^{(1:k)})}{N}\]

where: - \(N\) is the total number of queries, - \(y_{\text{query},i}\) is the true label for the \(i\)-th query, - \(y_{\text{candidates},i}^{(1:k)}\) is the set of top-k predicted labels for the \(i\)-th query, - \(\mathbb{1}(\text{condition})\) is the indicator function that equals 1 if the condition is true and 0 otherwise.

Parameters:
  • query_labels (autointent.metrics.custom_types.LABELS_VALUE_TYPE) – For each query, this list contains its class labels

  • candidates_labels (autointent.metrics.custom_types.CANDIDATE_TYPE) – For each query, these lists contain class labels of items ranked by a retrieval model (from most to least relevant)

  • k (int | None) – Number of top items to consider for each query

Returns:

Score of the retrieval metric

Return type:

float