Feature Drift KS Statistic

Problem

Compute the two-sample Kolmogorov-Smirnov statistic between raw reference and current feature values. Evaluate the empirical CDF gap at every distinct value from both samples and return the maximum absolute difference. Return 0.0 when either sample is empty.

Hint

The KS statistic is the largest vertical gap between the two empirical CDFs.

Test cases

case 1

in: [[1,2,3,4],[1,2,3,5]]

expected: 0.25

case 2

in: [[1,2,3],[4,5,6]]

expected: 1

case 3

in: [[1,2,3],[1,2,3]]

expected: 0

case 4

in: [[1,2],[2,3]]

expected: 0.5

case 5

in: [[],[]]

expected: 0

Starter codePython

def feature_drift_ks(reference, current):
    # Your code here
    pass

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