MediumStatisticsst-412

Log Loss Binary

Problem

Binary log loss is -mean_i (y_i log(p_i) + (1 - y_i) log(1 - p_i)).

Given predicted probabilities (strictly between 0 and 1) and binary outcomes, return the log loss.

Hint

Only the probability assigned to the observed outcome counts.

case 1

in: [[0.8,0.2],[1,0]]

expected: 0.2231435513142097

case 2

in: [[0.5,0.5],[0,1]]

expected: 0.6931471805599453

case 3

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

expected: 0.10536051565782628

Starter codePython

def log_loss_binary(probs, outcomes):
    # Your code here
    pass

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