聚类-31省市居民家庭消费水平-city

===分三类的=====

======分四类的========

直接写文件名，那么你的那个txt文件应该是和py文件在同一个路径的

============code===========

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(",")
        retCityName.append(items[0])
        retData.append([float(items[i]) for i in range(1,len(items))])
    for i in range(1,len(items)):
        return retData,retCityName
if __name__ == '__main__':
    data,cityName=loadData('city.txt')
    km = KMeans(n_clusters=3)
    label = km.fit_predict(data)
    expenses = np.sum(km.cluster_centers_,axis=1)
    #print(expense)
    CityCluster =[[],[],[]]
    for i in range(len(cityName)):
        CityCluster[label[i]].append(cityName[i])
    for i in range(len(CityCluster)):
        print("Expenses:%.2f"%expenses[i])
        print(CityCluster[i])
    =========

1. import numpy as np
2. from sklearn.cluster import KMeans
3. def loadData(filePath):
4. fr = open(filePath,'r+')
5. lines = fr.readlines()
6. retData = []
7. retCityName = []
8. for line in lines:
9. items = line.strip().split(",")
10. retCityName.append(items[0])
11. retData.append([float(items[i]) for i in range(1,len(items))])
12. return retData,retCityName
13. if __name__ == '__main__':
14. data,cityName = loadData('city.txt')
15. km = KMeans(n_clusters=4)
16. label = km.fit_predict(data)
17. expenses = np.sum(km.cluster_centers_,axis=1)
18. #print(expenses)
19. CityCluster = [[],[],[],[]]
20. for i in range(len(cityName)):
21. CityCluster[label[i]].append(cityName[i])
22. for i in range(len(CityCluster)):
23. print("Expenses:%.2f" % expenses[i])
24. print(CityCluster[i])