聚类-均值漂移

 1 from scipy.spatial import distance
 2 from sklearn.neighbors import NearestNeighbors
 3 from sklearn.cluster.dbscan_ import DBSCAN
 4 from sklearn.cluster.dbscan_ import dbscan
 5 import numpy as np
 6 from matplotlib import pyplot as plt
 7 from sklearn.cluster import MeanShift, estimate_bandwidth
 8 
 9 from sklearn.cluster.tests.common import generate_clustered_data
10 
11 min_samples = 10
12 eps = 0.0309
13 
14 X = generate_clustered_data(seed=1, n_samples_per_cluster=1000)
15 
16 #quantile 控制是否同一类别的距离
17 bandwidth = estimate_bandwidth(X, quantile=0.3, n_samples=len(X))
18 meanshift = MeanShift(bandwidth=bandwidth, bin_seeding=True)  # 构建对象
19 meanshift.fit(X)
20 labels = meanshift.labels_
21 
22 print(np.unique(labels))
23 
24 fig, ax = plt.subplots()
25 cluster_num = len(np.unique(labels))  # label的个数，即自动划分的族群的个数
26 for i in range(0, cluster_num):
27     x = []
28     y = []
29     for ind, label in enumerate(labels):
30         if label == i:
31             x.append(X[ind][0])
32             y.append(X[ind][1])
33     ax.scatter(x, y, s=1)
34 
35 plt.show()