1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
|
"""
=============================================================
Bisecting K-Means and Regular K-Means Performance Comparison
=============================================================
This example shows differences between Regular K-Means algorithm and Bisecting K-Means.
While K-Means clusterings are different when with increasing n_clusters,
Bisecting K-Means clustering build on top of the previous ones.
This difference can visually be observed.
"""
import matplotlib.pyplot as plt
from sklearn.datasets import make_blobs
from sklearn.cluster import BisectingKMeans, KMeans
print(__doc__)
# Generate sample data
n_samples = 1000
random_state = 0
X, _ = make_blobs(n_samples=n_samples, centers=2, random_state=random_state)
# Number of cluster centers for KMeans and BisectingKMeans
n_clusters_list = [2, 3, 4, 5]
# Algorithms to compare
clustering_algorithms = {
"Bisecting K-Means": BisectingKMeans,
"K-Means": KMeans,
}
# Make subplots for each variant
fig, axs = plt.subplots(
len(clustering_algorithms), len(n_clusters_list), figsize=(15, 5)
)
axs = axs.T
for i, (algorithm_name, Algorithm) in enumerate(clustering_algorithms.items()):
for j, n_clusters in enumerate(n_clusters_list):
algo = Algorithm(n_clusters=n_clusters, random_state=random_state, n_init=3)
algo.fit(X)
centers = algo.cluster_centers_
axs[j, i].scatter(X[:, 0], X[:, 1], s=10, c=algo.labels_)
axs[j, i].scatter(centers[:, 0], centers[:, 1], c="r", s=20)
axs[j, i].set_title(f"{algorithm_name} : {n_clusters} clusters")
# Hide x labels and tick labels for top plots and y ticks for right plots.
for ax in axs.flat:
ax.label_outer()
ax.set_xticks([])
ax.set_yticks([])
plt.show()
|
