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
64
65
66
|
"""
=============================================
A demo of the mean-shift clustering algorithm
=============================================
Reference:
Dorin Comaniciu and Peter Meer, "Mean Shift: A robust approach toward
feature space analysis". IEEE Transactions on Pattern Analysis and
Machine Intelligence. 2002. pp. 603-619.
"""
import numpy as np
from sklearn.cluster import MeanShift, estimate_bandwidth
from sklearn.datasets import make_blobs
# %%
# Generate sample data
# --------------------
centers = [[1, 1], [-1, -1], [1, -1]]
X, _ = make_blobs(n_samples=10000, centers=centers, cluster_std=0.6)
# %%
# Compute clustering with MeanShift
# ---------------------------------
# The following bandwidth can be automatically detected using
bandwidth = estimate_bandwidth(X, quantile=0.2, n_samples=500)
ms = MeanShift(bandwidth=bandwidth, bin_seeding=True)
ms.fit(X)
labels = ms.labels_
cluster_centers = ms.cluster_centers_
labels_unique = np.unique(labels)
n_clusters_ = len(labels_unique)
print("number of estimated clusters : %d" % n_clusters_)
# %%
# Plot result
# -----------
import matplotlib.pyplot as plt
plt.figure(1)
plt.clf()
colors = ["#dede00", "#377eb8", "#f781bf"]
markers = ["x", "o", "^"]
for k, col in zip(range(n_clusters_), colors):
my_members = labels == k
cluster_center = cluster_centers[k]
plt.plot(X[my_members, 0], X[my_members, 1], markers[k], color=col)
plt.plot(
cluster_center[0],
cluster_center[1],
markers[k],
markerfacecolor=col,
markeredgecolor="k",
markersize=14,
)
plt.title("Estimated number of clusters: %d" % n_clusters_)
plt.show()
|
