Metrics · Medium

AUC

Measure pairwise ordering quality across positive and negative examples.

Task

Implement auc(labels: list[int], scores: list[float]) -> float. Compare every positive example with every negative example and return the probability that a randomly chosen positive receives a higher score.

Requirements

Count a positive-negative score tie as 0.5.
Return 0.0 when the input has no positive examples or no negative examples.
Do not assume scores are probabilities or already sorted.
Inputs have equal length and labels are binary.

Example

labels = [0, 1, 0, 1]
scores = [0.1, 0.9, 0.2, 0.8]

auc(labels, scores)
# 1.0