2019-07-25【机器学习】无监督学习之聚类 K-Means算法实例 （1999年中国居民消费城市分类）

样本

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

import numpy as np
from sklearn.cluster import KMeans #导入聚类KMean算法

def loadData(filePath):
    fr = open(filePath, 'r+') #以读的方式打开
    lines = fr.readlines()
    retData = []
    retCityName = []
    for line in lines:
        #print(line)
        items = line.strip().split(",") #以，为分割返回列表，strip去除 \n
        #print(items)
        retCityName.append(items[0])#根据数据位置，添加城市名字
        retData.append([float(items[i]) for i in range(1, len(items))])
    return retData, retCityName

if __name__ == '__main__':
    data, cityName = loadData('city.txt') #导入数据
    km = KMeans(n_clusters=4) #聚类中心的个数
    label = km.fit_predict(data) #调用算法分标签，分为n_clusters=4类，默认调用欧式空间距离
    #print(label)
    #print(km.cluster_centers_)
    expenses = np.sum(km.cluster_centers_, axis=1) #求和费用
    #print(expenses)
    #print(expenses)
    CityCluster = [[], [], [], []] #二维数组,对应n_clusters=4
    for i in range(len(cityName)):
        CityCluster[label[i]].append(cityName[i]) #加入到数组

    for i in range(len(CityCluster)):
        print("Expenses:%.2f" % expenses[i])
        print(CityCluster[i])

　　输出结果