轮廓系数

 

 

import numpy as npfrom sklearn.cluster import KMeansfrom pylab import *import codecsimport matplotlib.pyplot as pltfrom sklearn.metrics import calinski_harabaz_scoreimport pandas as pdfrom numpy.random import randomfrom sklearn import preprocessing from sklearn import metricsimport operator  data = []labels = []number1=10with codecs.open("red_nopca_nolabel.txt", "r") as f:    for line in f.readlines():        line1=line.strip()        line2 = line1.split(',')        x2 = []        for i in range(0,number1):            x1=line2[i]            x2.append(float(x1))        data.append(x2)        x2 = []        #label = line2[number1-1]        #labels.append(float(label))datas = np.array(data)'''kmeans_model = KMeans(n_clusters=3, random_state=1).fit(datas)labels = kmeans_model.labels_a = metrics.silhouette_score(datas, labels, metric='euclidean')print(a)'''silhouette_all=[]for k in range(2,25):    kmeans_model = KMeans(n_clusters=k, random_state=1).fit(datas)    labels = kmeans_model.labels_    a = metrics.silhouette_score(datas, labels, metric='euclidean')    silhouette_all.append(a)    #print(a)    print('这个是k={}次时的轮廓系数：'.format(k),a)    dic={}             #存放所有的互信息的键值对mi_num=2  for i in silhouette_all:    dic['k={}时轮廓系数'.format(mi_num)]='{}'.format(i)    mi_num=mi_num+1#print(dic)rankdata=sorted(dic.items(),key=operator.itemgetter(1),reverse=True)print(rankdata)