import numpy as np
from sklearn.cluster import MeanShift, estimate_bandwidth
from sklearn.datasets.samples_generator import make_blobs
# Generate sample data 创建数据集
centers = [[1, 1], [-1, -1], [1, -1]]
X, _ = make_blobs(n_samples=10000, centers=centers, cluster_std=0.6)
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_
import matplotlib.pyplot as plt
from itertools import cycle
plt.figure(1)
plt.clf()
colors = cycle("bgrcmykbgrcmykbgrcmykbgrcmyk")
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], col + ".")
plt.plot(cluster_center[0], cluster_center[1], "o", markerfacecolor=col,
markeredgecolor="k", markersize=14)
plt.title("Estimated number of clusters: %d" % n_clusters_)
plt.show()
『sklearn学习』MeanShift 聚类
最新推荐文章于 2024-09-16 17:40:00 发布
这篇博客介绍了如何利用sklearn库中的MeanShift进行聚类分析。首先,通过make_blobs创建了一个数据集,然后估计了合适的bandwidth。接着,应用MeanShift算法并进行拟合,获取聚类标签和中心。最后,使用matplotlib展示聚类结果,显示了估计的聚类数量。
摘要由CSDN通过智能技术生成