【聚类之K-Means】K-Means学习实例

数据介绍：现有1999年全国31个省份城镇居民家庭平均每人全年消费性支出的八个主要变量数据，这八个变量分别是：食品、衣着、家庭设备用品及服务、医疗保健、交通和通讯、娱乐教育文化服务、居住以及杂项商品和服务。利用已有数据，对31个省份进行聚类。

import numpy as np
from sklearn.cluster import KMeans

def loadData(filePath):
    fr = open(filePath, 'r+')       #读写打开一个文本文件
    lines = fr.readlines()          #一次读取整个文件（类似于.read()）
    retData = []                    #用来存储城市的各项消费信息
    retCityName = []                #用来存储城市名称
    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     #返回值：返回城市名称，以及该城市的各项消费信息

if __name__ == '__main__':
    data, cityName = loadData('31省市居民家庭消费水平-city.txt') #利用loadData方法读取数据
    # print(data)
    # print(cityName)
    km = KMeans(n_clusters=4,init='k-means++',max_iter=300)                                   #创建实例
    label = km.fit_predict(data)                                #调用Kmeans()fit_predict()方法计算簇中心以及为簇分配序号）进行计算，获得各数据所属的标签
    # print(label)
    # print(type(label))
    # print(km.cluster_centers_)
    expenses = np.sum(km.cluster_centers_, axis=1)             #聚类中心点的数值相加，也就是平均消费水平
    # print(expenses)
    # print(type(expenses))

    CityCluster = [[], [], [],[]]                  #将城市按label分成设定的簇
    for i in range(len(cityName)):
        CityCluster[label[i]].append(cityName[i])   #将每个簇的城市添加到CityCluster
    for i in range(len(CityCluster)):
        print("Expenses:%.2f" % expenses[i])        #将每个簇的平均花费输出，expense：聚类中心点的数值加和，也就是平均消费水平
        print(CityCluster[i])

附上数据文件（31省市居民家庭消费水平-city.txt）：

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
内蒙古,1303.97,524.29,254.83,192.17,249.81,463.09,287.87,192.96
辽宁,1730.84,553.90,246.91,279.81,239.18,445.20,330.24,163.86
吉林,1561.86,492.42,200.49,218.36,220.69,459.62,360.48,147.76
黑龙江,1410.11,510.71,211.88,277.11,224.65,376.82,317.61,152.85
上海,3712.31,550.74,893.37,346.93,527.00,1034.98,720.33,462.03
江苏,2207.58,449.37,572.40,211.92,302.09,585.23,429.77,252.54
浙江,2629.16,557.32,689.73,435.69,514.66,795.87,575.76,323.36
安徽,1844.78,430.29,271.28,126.33,250.56,513.18,314.00,151.39
福建,2709.46,428.11,334.12,160.77,405.14,461.67,535.13,232.29
江西,1563.78,303.65,233.81,107.90,209.70,393.99,509.39,160.12
山东,1675.75,613.32,550.71,219.79,272.59,599.43,371.62,211.84
河南,1427.65,431.79,288.55,208.14,217.00,337.76,421.31,165.32
湖南,1942.23,512.27,401.39,206.06,321.29,697.22,492.60,226.45
湖北,1783.43,511.88,282.84,201.01,237.60,617.74,523.52,182.52
广东,3055.17,353.23,564.56,356.27,811.88,873.06,1082.82,420.81
广西,2033.87,300.82,338.65,157.78,329.06,621.74,587.02,218.27
海南,2057.86,186.44,202.72,171.79,329.65,477.17,312.93,279.19
重庆,2303.29,589.99,516.21,236.55,403.92,730.05,438.41,225.80
四川,1974.28,507.76,344.79,203.21,240.24,575.10,430.36,223.46
贵州,1673.82,437.75,461.61,153.32,254.66,445.59,346.11,191.48
云南,2194.25,537.01,369.07,249.54,290.84,561.91,407.70,330.95
西藏,2646.61,839.70,204.44,209.11,379.30,371.04,269.59,389.33
陕西,1472.95,390.89,447.95,259.51,230.61,490.90,469.10,191.34
甘肃,1525.57,472.98,328.90,219.86,206.65,449.69,249.66,228.19
青海,1654.69,437.77,258.78,303.00,244.93,479.53,288.56,236.51
宁夏,1375.46,480.89,273.84,317.32,251.08,424.75,228.73,195.93
新疆,1608.82,536.05,432.46,235.82,250.28,541.30,344.85,214.40