sklearn库kmeans实现实例

# -*- coding: utf-8 -*-from sklearn.cluster import KMeansfrom sklearn.externals import joblibimport numpyimport pandas as pddef kmeans(inputfile,n):

final = open(‘data/dataset.csv‘ , ‘r‘)

data = [line.strip().split(‘,‘) for line in final]    feature = [[float(x) for x in row[1]] for row in data]    # print feature    #调用kmeans类    clf = KMeans(n_clusters=n)  #给定类别个数为3    s = clf.fit(feature)    # print s    #聚类中心坐标    print ‘聚类中心‘,clf.cluster_centers_    #每个样本所属的簇    print ‘每个样本所属的簇‘,clf.labels_ #每个点的分类    #用来评估簇的个数是否合适，距离越小说明簇分的越好，选取临界点的簇个数    print clf.inertia_ #每个点到其簇的质心的距离之和    #进行预测    df = pd.read_csv(‘data/dataset1.csv‘)  #未添加类标签的数据集    label = clf.predict(feature)    labelpre = pd.DataFrame(label,columns=[‘label‘])    df[‘label‘] = labelpre  #将聚类之后的类标签添加到数据集中    # print clf.predict(feature)    print df    #保存模型    joblib.dump(clf , ‘data/km.pkl‘)

#载入保存的模型    clf = joblib.load(‘data/km.pkl‘)    print ‘clf‘,clf    ‘‘‘    #用来评估簇的个数是否合适，距离越小说明簇分的越好，选取临界点的簇个数    for i in range(5,30,1):        clf = KMeans(n_clusters=i)        s = clf.fit(feature)        print i , clf.inertia_    ‘‘‘kmeans(‘data/danger.csv‘,3)

原文地址：https://www.cnblogs.com/eternallql/p/8142990.html