Brier Score Decomposition

Problem

Return the mean squared error between predicted probabilities and 0/1 labels: mean((prob - label)^2). Return 0.0 for empty input.

case 1

in: [[0.9,0.1],[1,0]]

expected: 0.009999999999999998

case 2

in: [[0.5],[0]]

expected: 0.25

case 3

in: [[],[]]

expected: 0

case 4

in: [[1,0],[1,0]]

expected: 0

Starter codePython

def brier_score(probs, labels):
    # Your code here
    pass

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