c672738b39c8f739551da0d88991a2fedfba3e14,deeppavlov/models/ranking/metrics.py,,recall_at_k,#Any#Any#Any#,24

Before Change

    return recall_at_k(labels, predictions, k=10)

def recall_at_k(y_true, y_pred, k):
    labels = np.array(y_true)
    predictions = np.array(y_pred)
    predictions = np.argsort(predictions, -1)[:, :k]
    flags = np.zeros_like(predictions)
    for i in range(predictions.shape[0]):
        for j in range(predictions.shape[1]):
            if predictions[i][j] in np.arange(labels[i][j]):
                flags[i][j] = 1.
    return np.mean((np.sum(flags, -1) >= 1.).astype(float))

After Change

    predictions = np.flip(np.argsort(predictions, -1), -1)[:, :k]
    num_correct = 0
    for el in predictions:
        if 0 in el:
            num_correct += 1
    return float(num_correct) / num_examples

@register_metric("rank_response")
def rank_response(y_true, y_pred):

Instances