Surrogate Fidelity

Problem

Compute surrogate fidelity: the fraction of samples where the surrogate and black-box predictions agree.

Empty input returns 0.0.

Hint

Fidelity measures how faithfully the interpretable surrogate imitates the black box.

case 1

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

expected: 0.5

case 2

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

expected: 1

case 3

in: [[],[]]

expected: 0

Starter codePython

def surrogate_fidelity(blackbox_preds, surrogate_preds):
    # Your code here
    pass

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