Note

Go to the end to download the full example code. or to run this example in your browser via Binder

均值漂移聚类算法示例#

参考文献：

Dorin Comaniciu 和 Peter Meer, “Mean Shift: A robust approach toward feature space analysis”. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2002. 第603-619页.

import numpy as np

from sklearn.cluster import MeanShift, estimate_bandwidth
from sklearn.datasets import make_blobs

生成示例数据#

centers = [[1, 1], [-1, -1], [1, -1]]
X, _ = make_blobs(n_samples=10000, centers=centers, cluster_std=0.6)

计算使用MeanShift的聚类#

# 可以自动检测到以下带宽
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_)

number of estimated clusters : 3

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()