Python机器学习应用-Kmeans算法

import numpy as np
from sklearn.cluster import KMeans

def loadData(filePath):
    fr = open(filePath, 'r+')  # 读写打开一个文本文件
    lines = fr.readlines()
    retData = []  # 城市各个消费数据
    retCityName = []  # 城市名称
    for line in lines:
        items = line.strip().split(",")  # 以逗号为分隔
        retCityName.append(items[0])  # 返回第一个，即城市名称
        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')  # 导入文件，返回数据
    km = KMeans(n_clusters=5, init='k-means++', max_iter=300)  # 设值簇的数量为3,init为初始化方法，max_iter为最大迭代次数
    label = km.fit_predict(data)  # label：聚类后各数据所属的标签；fit_predict()计算簇中心以及为簇分配序号
    expenses = np.sum(km.cluster_centers_, axis=1)
    print(expenses)
    CityCluster = [[], [], [],[],[]]
    for i in range(len(cityName)):  # 即对每个城市进行遍历
        CityCluster[label[i]].append(cityName[i])
    for i in range(len(CityCluster)):
        print("Express:%.2f " % expenses[i])
        print(CityCluster[i])