Lloyd-Max One Update

Problem

Perform one Lloyd-Max iteration. Assign every sample to its nearest centroid, breaking ties toward the lower index, then move each centroid to the mean of the samples assigned to it. A centroid that receives no samples keeps its old value. Return the updated centroid list.

Hint

The assignment step uses the old centroids; the update step uses the new assignments.

Test cases

case 1

in: [[0,1,2,10],[0,5]]

expected: [1,10]

case 2

in: [[1,2,3,10,11,12],[2,11]]

expected: [2,11]

case 3

in: [[0,0.4,0.6,1],[0.25,0.75]]

expected: [0.2,0.8]

case 4

in: [[5],[0,10]]

expected: [5,10]

case 5

in: [[-3,-1,4,6],[0,5]]

expected: [-2,5]

Starter codePython

def lloyd_max_update(samples, centroids):
    # Your code here
    pass

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