31个省市居民家庭收费调查

数据请见（电脑F盘）或（腾讯微云文件“Redhur的进阶“）的{python数据—test2}

北京,2959.19,730.79,749.41,513.34,467.87,1141.82,478.42,457.64
天津,2459.77,495.47,697.33,302.87,284.19,735.97,570.84,305.08
河北,1495.63,515.90,362.37,285.32,272.95,540.58,364.91,188.63
山西,1406.33,477.77,290.15,208.57,201.50,414.72,281.84,212.10
…

import numpy as np
from sklearn.cluster import KMeans
 
def loadData(filePath):
    fr = open(filePath,'r+',encoding='utf-8')
    lines = fr.readlines()
    retData = []
    retCityName = []
    for line in lines:
        items = line.strip().split(",")
        retCityName.append(items[0])
        retData.append([float(items[i]) for i in range(1,len(items))])
    return retData,retCityName
    
'''
retData大致的模样是：
[[2959.19, 730.79, 749.41, 513.34, 467.87, 1141.82, 478.42, 457.64],
[2459.77, 495.47, 697.33, 302.87, 284.19, 735.97, 570.84, 305.08]...] 

K-Means聚类算法默认用的是欧氏距离
'''

if __name__=='__main__':
    filepath = r'E:\快乐的程序猿\city.txt'
    data,cityName=loadData(filepath)  
    km=KMeans(n_clusters=4)          #n_cluster用于指定聚类中心的个数
    
    label=km.fit_predict(data)       
    #fit_predict()：计算簇中心以及为簇分配序号；
    #label：聚类后各数据所属的标签，大致是[2 0 3 3 3 1 3 3 2 0 0 1 0 3 1 3 1 1 2 1 1 0 1 1 0 0 3 3 3 3 3]的样子
    
    print(km.cluster_centers_) ##每个簇的每种消费的mean值
    print("--------------------------------------------------------------------")
    
    expenses=np.sum(km.cluster_centers_,axis=1)  #每个簇的平均总消费（）
    print(expenses)
    print("--------------------------------------------------------------------")
    
    CityCluster=[[],[],[],[]]      #将城市 按label分成设定的簇，将每个簇的城市输出
    for i in range(len(cityName)):
        CityCluster[label[i]].append(cityName[i])
    for i in range(len(CityCluster)):
        print("Expenses:{}.2f" .format(expenses[i]))
        print(CityCluster[i])