autointent.metrics.retrieval.retrieval_hit_rate#
- autointent.metrics.retrieval.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: