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. importnumpyasnp
2. fromsklearn.clusterimportKMeans
5. defloadData(filePath):
6. fr=open(filePath,'r+')
7. lines=fr.readlines()
8. retData=[]
9. retCityName=[]
10. forlineinlines:
11. items=line.strip().split(",")
12. retCityName.append(items[0])
13. retData.append([float(items[i])foriinrange(1,len(items))])
14. returnretData,retCityName
17. if__name__=='__main__':
18. data,cityName=loadData('city.txt')
19. km=KMeans(n_clusters=4)
20. label=km.fit_predict(data)
21. expenses=np.sum(km.cluster_centers_,axis=1)
22. #print(expenses)
23. CityCluster=[[],[],[],[]]
24. foriinrange(len(cityName)):
25. CityCluster[label[i]].append(cityName[i])
26. foriinrange(len(CityCluster)):
27. print("Expenses:%.2f"%expenses[i])
28. print(CityCluster[i])