Slice-Based Evaluation Gap

Problem

Report how much a data slice underperforms the overall metric.

Return round(slice_accuracy - overall_accuracy, 4).

case 1

in: [0.62,0.7]

expected: -0.08

case 2

in: [0.9,0.9]

expected: 0

case 3

in: [0.45,0.55]

expected: -0.1

Starter codePython

def slice_eval_gap(slice_accuracy, overall_accuracy):
    # Your code here
    pass

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