Calculate Dice Score for Classification

Problem

Calculate the Dice Score (Dice Coefficient) for binary classification. The Dice score is similar to the F1 score and measures overlap between predicted and actual positive labels.

Solution

def dice_score(y_true, y_pred):
    tp = sum(1 for t, p in zip(y_true, y_pred) if t == 1 and p == 1)
    fp = sum(1 for t, p in zip(y_true, y_pred) if t == 0 and p == 1)
    fn = sum(1 for t, p in zip(y_true, y_pred) if t == 1 and p == 0)

    denominator = 2 * tp + fp + fn
    if denominator == 0:
        return 1.0

    return round((2 * tp) / denominator, 4)

Explanation

1. Count TP, FP, and FN from the true and predicted labels.
2. Dice Score = 2 TP / (2 TP + FP + FN).
3. Equivalent to the F1 score for binary classification.
4. Ranges from 0 (no overlap) to 1 (perfect match).
5. Commonly used in image segmentation to measure overlap between predicted and ground-truth masks.

Complexity

• Time: O(n) where n is the number of samples
• Space: O(1)