Demo of affinity propagation clustering algorithm

Reference: Brendan J. Frey and Delbert Dueck, “Clustering by Passing Messages Between Data Points”, Science Feb. 2007

Script output:

Estimated number of clusters: 3
Homogeneity: 0.906
Completeness: 0.907
V-measure: 0.907
Adjusted Rand Index: 0.941
Adjusted Mutual Information: 0.906
Silhouette Coefficient: 0.771

Python source code: plot_affinity_propagation.py

print __doc__

import numpy as np
from sklearn.cluster import AffinityPropagation
from sklearn import metrics
from sklearn.datasets.samples_generator import make_blobs

##############################################################################
# Generate sample data
centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(n_samples=300, centers=centers, cluster_std=0.5)

##############################################################################
# Compute similarities
X_norms = np.sum(X ** 2, axis=1)
S = - X_norms[:, np.newaxis] - X_norms[np.newaxis, :] + 2 * np.dot(X, X.T)
p = 10 * np.median(S)

##############################################################################
# Compute Affinity Propagation
af = AffinityPropagation().fit(S, p)
cluster_centers_indices = af.cluster_centers_indices_
labels = af.labels_

n_clusters_ = len(cluster_centers_indices)

print 'Estimated number of clusters: %d' % n_clusters_
print "Homogeneity: %0.3f" % metrics.homogeneity_score(labels_true, labels)
print "Completeness: %0.3f" % metrics.completeness_score(labels_true, labels)
print "V-measure: %0.3f" % metrics.v_measure_score(labels_true, labels)
print "Adjusted Rand Index: %0.3f" % \
    metrics.adjusted_rand_score(labels_true, labels)
print "Adjusted Mutual Information: %0.3f" % \
    metrics.adjusted_mutual_info_score(labels_true, labels)
D = (S / np.min(S))
print ("Silhouette Coefficient: %0.3f" %
       metrics.silhouette_score(D, labels, metric='precomputed'))

##############################################################################
# Plot result
import pylab as pl
from itertools import cycle

pl.close('all')
pl.figure(1)
pl.clf()

colors = cycle('bgrcmykbgrcmykbgrcmykbgrcmyk')
for k, col in zip(range(n_clusters_), colors):
    class_members = labels == k
    cluster_center = X[cluster_centers_indices[k]]
    pl.plot(X[class_members, 0], X[class_members, 1], col + '.')
    pl.plot(cluster_center[0], cluster_center[1], 'o', markerfacecolor=col,
            markeredgecolor='k', markersize=14)
    for x in X[class_members]:
        pl.plot([cluster_center[0], x[0]], [cluster_center[1], x[1]], col)

pl.title('Estimated number of clusters: %d' % n_clusters_)
pl.show()