无监督学习之聚类1——Kmeans

Kmeans算法分析31省市消费水平

#coding=utf-8

import numpy as np
from sklearn.cluster import KMeans

def loadData(filepath):
    fr = open(filepath, ‘r+‘)
    lines = fr.readlines()
    retData = []
    retCityName = []
    for line in lines:
        items = line.strip().split(",")#以逗号为分割符读取数据
        retCityName.append(items[0]) #将城市名加到城市名数据列表中
        retData.append([float(items[i]) for i in range(1,len(items))])
        #将数据中的其他data转化为float后加到retData中
    return retData,retCityName

if __name__ == ‘__main__‘:
    data,cityName = loadData(‘F:\data\city.txt‘)
    km = KMeans(n_clusters=4) #分成的簇的数目
    label = km.fit_predict(data)#计算簇中心及为簇分配序号
    expenses = np.sum(km.cluster_centers_, axis=1) #axis按行求和

    CityCluster = [[],[],[],[]]#设置与簇数目对应的列表数来存储数据
    #将每个城市分成设定的簇
    for i in range(len(cityName)):
        CityCluster[label[i]].append(cityName[i]) #将每个簇的城市名输出
    #输出每个簇的平均消费
    for i in range(len(CityCluster)):
        print("Expenses: %.2f"%expenses[i])
        print(CityCluster[i])

　　运算后;

Expenses: 4512.27
[‘江苏‘, ‘安徽‘, ‘湖南‘, ‘湖北‘, ‘广西‘, ‘海南‘, ‘四川‘, ‘云南‘]
Expenses: 7754.66
[‘北京‘, ‘上海‘, ‘广东‘]
Expenses: 5678.62
[‘天津‘, ‘浙江‘, ‘福建‘, ‘重庆‘, ‘西藏‘]
Expenses: 3788.76
[‘河北‘, ‘山西‘, ‘内蒙古‘, ‘辽宁‘, ‘吉林‘, ‘黑龙江‘, ‘江西‘, ‘山东‘, ‘河南‘, ‘贵州‘, ‘陕西‘, ‘甘肃‘, ‘青海‘, ‘宁夏‘, ‘新疆‘]