Balanced Accuracy

Problem

Compute balanced accuracy: the unweighted mean of recall over the classes present in y_true.

For each class, recall = TP / (TP + FN) counting that class as positive against all others. Empty input returns 0.0.

Hint

It is macro recall: average the per-class recalls equally, regardless of support.

case 1

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

expected: 0.75

case 2

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

expected: 1

case 3

in: [[0,1,2,2],[0,1,1,2]]

expected: 0.8333333333333334

case 4

in: [[],[]]

expected: 0

Starter codePython

def balanced_accuracy(y_true, y_pred):
    # Your code here
    pass

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