affinity_propogation.py

import json

import numpy as np
import scipy
from sklearn.cluster import AffinityPropagation
from sklearn import metrics
from sklearn.datasets 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, random_state=0
)

# #############################################################################
# Compute Affinity Propagation
# TODO: init preference with median similarity between initial samples
distances = scipy.spatial.distance.cdist(X, X)

# af = AffinityPropagation(preference=np.median(distances), random_state=0).fit(X)
af = AffinityPropagation(preference=-50, random_state=0).fit(X)
# af = AffinityPropagation(random_state=0).fit(X)
cluster_centers_indices = af.cluster_centers_indices_
labels = af.labels_

n_clusters_ = len(cluster_centers_indices)

# json.dump({'dvq_checkpoint': 'self.dvq_checkpoint',
#            'labels': af.labels_,
#            'cluster_centers': af.cluster_centers_indices_}, open('/tmp/dvq_compress', 'w'), )

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)
)
print(
    "Silhouette Coefficient: %0.3f"
    % metrics.silhouette_score(X, labels, metric="sqeuclidean")
)
print("Calinski Harabasz score: %0.3f",
      metrics.calinski_harabasz_score(X, labels)
)
print("Davies Bouldin score: %0.3f",
      metrics.davies_bouldin_score(X, labels)
)

# TODO: Jump method if needed https://github.com/v-iashin/JumpMethod/commits?author=v-iashin

# #############################################################################
# Plot result
import matplotlib.pyplot as plt
from itertools import cycle

plt.close("all")
plt.figure(1)
plt.clf()

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

plt.title("Estimated number of clusters: %d" % n_clusters_)
plt.show()