Confusion matrix

gistfile1.py

from collections import defaultdict

def confusion(trueLabels, clusterLabels):
    counts = defaultdict(lambda: defaultdict(int))
    allLabels = sorted(set(trueLabels + clusterLabels))
    for trueLabel, clusterLabel in zip(trueLabels, clusterLabels):
        counts[trueLabel][clusterLabel] += 1
    return allLabels, counts

Usage (with ugly printing) looks something like this

labels, counts = confusion([0, 0, 1], [1, 2, 1])

print '  ',
for label in labels:
    print label,
print

for trueLabel in labels:
    print '%s: ' % trueLabel,
    for clusterLabel in labels:
        print counts[trueLabel][clusterLabel],
    print

Producing

0 1 2
0:  0 1 1
1:  0 1 0
2:  0 0 0