sklearn

分类任务、回归任务、聚类任务、降维任务、模型选择、数据预处理

from sklearn.cluster import KMeans
import numpy as np

def loadData(filePath):
    fr = open(filePath,'r+',encoding='UTF-8')
    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))])

    #print(retData)
    #print(retCityName)
    
    return retData,retCityName


if __name__=='__main__':
    data,cityName = loadData('city.txt')
    
    km = KMeans(n_clusters=4)
    label = km.fit_predict(data)
    #print(label)   # data中每一条的类别
    #print(km.cluster_centers_) # 聚类中心
    expenses = np.sum(km.cluster_centers_,axis=1)

    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])