Partition Accuracy vs Ground Truth

Problem

Measure how well a predicted partition matches ground truth labels by node-wise agreement.

Return the fraction of positions where predicted equals truth, or 0.0 when the lists are empty. predicted and truth are equal-length label lists.

Hint

Node-wise accuracy is strict about label identity, unlike NMI.

case 1

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

expected: 1

case 2

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

expected: 0.5

case 3

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

expected: 1

case 4

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

expected: 0

case 5

in: [[],[]]

expected: 0

Starter codePython

def partition_accuracy(predicted, truth):
    # Your code here
    pass

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