Hard Negative Mining by Distance

Problem

Return the index of the hardest negative: among samples with label 0, the one with the smallest distance (ties keep the smallest index).

Return -1 if there is no negative sample.

Hint

The hardest negative is the one that is closest to the anchor.

case 1

in: [[0.9,0.2,0.5,0.1],[0,1,0,0]]

expected: 3

case 2

in: [[0.1,0.2],[1,1]]

expected: -1

case 3

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

expected: 0

Starter codePython

def hard_negative_index(distances, labels):
    # Your code here
    pass

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