Hinge Loss

Problem

Compute the mean hinge loss for labels in {-1, +1}: (1/n) * sum(max(0, 1 - y_i * score_i)).

Empty input returns 0.0.

Hint

A sample is penalized only when its margin y*score is less than one.

case 1

in: [[1,-1],[0.5,0.5]]

expected: 1

case 2

in: [[1,1],[2,3]]

expected: 0

case 3

in: [[1,-1],[-1,-2]]

expected: 1

case 4

in: [[],[]]

expected: 0

Starter codePython

def hinge_loss(y_true, scores):
    # Your code here
    pass

4 test cases · run your code against them in the editor