### K-Means (AgglomerativeClustering 为层次聚类使用,相应两行被替换) 向量距离聚类
#coding=utf-8
import numpy as np
import matplotlib.pyplot as plt
#from sklearn.cluster import KMeans
from sklearn.cluster import AgglomerativeClustering
#读取城市经纬度数据
X = []
f = open('files\\city.csv')
for v in f:
X.append([float(v.split(',')[2]),float(v.split(',')[3])])
#转换成numpy array
X = np.array(X)
#类簇的数量 - kmeans算法的参数
n_clusters = 5
#进行聚类
cls = KMeans(n_clusters).fit(X)
#cls = AgglomerativeClustering(linkage='ward',n_clusters=n_clusters).fit(X)
#聚类结果列表
cls.labels_
#画图
markers = ['^','x','o','*','+']
for i in range(n_clusters):
members = cls.labels_ == i
plt.scatter(X[members,0],X[members,1], s=60, marker=markers[i],c='b',alpha=0.5)
#print(members)
#print(X[members,1])
plt.title('')
plt.show()
### DBScan算法 密度聚类
#coding = utf-8
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import DBSCAN
X = [
[9670250,1392358258], #中国
[2980000,1247923065],