napkinxc.measures.recall_at_k¶
- napkinxc.measures.recall_at_k(Y_true, Y_pred, k=5, zero_division=0)[source]¶
Calculate recall at 1-k places. Recall at k is defined as:
\[r@k = \frac{1}{||\pmb{y}||_1} \sum_{l \in \text{rank}_k(\hat{\pmb{y}})} y_l \,,\]where \(\pmb{y} \in {0, 1}^m\) is ground truth label vector, \(\hat{\pmb{y}} \in \mathbb{R}^m\) is predicted labels score vector, and \(\text{rank}_k(\hat{\pmb{y}})\) returns the \(k\) indices of \(\hat{\pmb{y}}\) with the largest values, ordered in descending order.
- Parameters:
Y_true (ndarray, csr_matrix, list[list|set[int|str]]) – Ground truth provided as a matrix with non-zero values for true labels or a list of lists or sets of true labels.
Y_pred (ndarray, csr_matrix, list[list[int|str]], list[list[tuple[int|str, float]]) – Predicted labels provided as a matrix with scores or list of rankings as a list of labels or tuples of labels with scores (label, score). In the case of the matrix, the ranking will be calculated by sorting scores in descending order.
k (int, optional) – Calculate at places from 1 to k, defaults to 5
zero_division (float, optional) – Value to add when there is a zero division, typically set to 0, defaults to 0
- Returns:
Values of recall at 1-k places.
- Return type:
ndarray