Kmeans笔记

import numpy as np
from sklearn.cluster import KMeans
def loadData(filePath):
    fr = open(filePath,'r+') #r+指用于读写
    lines = fr.readlines()
    retData = []
    retCityName = []
    for line in lines:
        items = line.strip().split(',')  
        '''解读
        1.strip()去除首尾空格,strip(0)则是去除首尾的0
        2.split(',')在line中出现，的地方切片
        '''
        retCityName.append(items[0])
        retData.append([float(items[i]) for i in range(1,len(items))])
    return retCityName,retData
    
if __name__ =='__main__':
    cityName,data = loadData('31省市居民家庭消费水平-city.txt')
    km = KMeans(n_clusters = 3,n_init = 100)  #n_clusters调协聚类的k，
    #n_init是在k较小时，使用不同seed的次数，默认为10
    
    
    label = km.fit_predict(data) #加载聚类数值，并返回完成聚类后对应数据的标签
    expenses = np.sum(km.cluster_centers_,axis=1)
    print(km.cluster_centers_)
    print(np.sum(km.cluster_centers_,axis = 0))
    print(expenses)
    #print(expenses)
    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])