Anchor Precision

Problem

Compute anchor precision: among instances covered by the anchor, the fraction whose prediction matches the anchor's.

Return 0.0 when nothing is covered or input is empty.

Hint

An anchor is only useful if the prediction rarely changes inside it.

case 1

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

expected: 0.6666666666666666

case 2

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

expected: 0

case 3

in: [[],[]]

expected: 0

Starter codePython

def anchor_precision(covered, same_prediction):
    # Your code here
    pass

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