sklearn.cluster使用

代码如下

import numpy as np  # 数据结构
import sklearn.cluster as skc  # 密度聚类
from sklearn import metrics   # 评估模型
import matplotlib.pyplot as plt  # 可视化绘图

data=[
    [-2.68420713,1.469732895],[-2.71539062,-0.763005825],[-2.88981954,-0.618055245],[-2.7464372,-1.40005944],[-2.72859298,1.50266052],
    [-2.27989736,3.365022195],[-2.82089068,-0.369470295],[-2.62648199,0.766824075],[-2.88795857,-2.568591135],[-2.67384469,-0.48011265],
    [-2.50652679,2.933707545],[-2.61314272,0.096842835],[-2.78743398,-1.024830855],[-3.22520045,-2.264759595],[-2.64354322,5.33787705],
    [-2.38386932,6.05139453],[-2.6225262,3.681403515],[-2.64832273,1.436115015],[-2.19907796,3.956598405],[-2.58734619,2.34213138],
    [1.28479459,3.084476355],[0.93241075,1.436391405],[1.46406132,2.268854235],[0.18096721,-3.71521773],[1.08713449,0.339256755],
    [0.64043675,-1.87795566],[1.09522371,1.277510445],[-0.75146714,-4.504983795],[1.04329778,1.030306095],[-0.01019007,-3.242586915],
    [-0.5110862,-5.681213775],[0.51109806,-0.460278495],[0.26233576,-2.46551985],[0.98404455,-0.55962189],[-0.174864,-1.133170065],
    [0.92757294,2.107062945],[0.65959279,-1.583893305],[0.23454059,-1.493648235],[0.94236171,-2.43820017],[0.0432464,-2.616702525],
    [4.53172698,-0.05329008],[3.41407223,-2.58716277],[4.61648461,1.538708805],[3.97081495,-0.815065605],[4.34975798,-0.188471475],
    [5.39687992,2.462256225],[2.51938325,-5.361082605],[4.9320051,1.585696545],[4.31967279,-1.104966765],[4.91813423,3.511712835],
    [3.66193495,1.0891728],[3.80234045,-0.972695745],[4.16537886,0.96876126],[3.34459422,-3.493869435],[3.5852673,-2.426881725],
    [3.90474358,0.534685455],[3.94924878,0.18328617],[5.48876538,5.27195043],[5.79468686,1.139695065],[3.29832982,-3.42456273]
]
X = np.array(data)

db = skc.DBSCAN(eps=1.5, min_samples=3).fit(X) #DBSCAN聚类方法 还有参数，matric = ""距离计算方法
labels = db.labels_  #和X同一个维度，labels对应索引序号的值 为她所在簇的序号。若簇编号为-1，表示为噪声

print('每个样本的簇标号:')
print(labels)

raito = len(labels[labels[:] == -1]) / len(labels)  #计算噪声点个数占总数的比例
print('噪声比:', format(raito, '.2%'))

n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)  # 获取分簇的数目

print('分簇的数目: %d' % n_clusters_)
print("轮廓系数: %0.3f" % metrics.silhouette_score(X, labels)) #轮廓系数评价聚类的好坏

#label的值是一个与X长度相同，里面为每一个X对应的簇Index

#label==i返回一个与X长度相同，值为True 或False的数组（若簇Index==i是True）

#one_cluster就是当前簇对应的X数据

for i in range(n_clusters_):

    print('簇 ', i, '的所有样本:')
    one_cluster = X[labels == i]
    print(one_cluster)
    plt.plot(one_cluster[:,0],one_cluster[:,1],'o')

plt.show()

解释