# coding: utf-8
import sys
import math
import re
import docx
from sklearn.cluster import AffinityPropagation
import nltk
from nltk.corpus import wordnet as wn
from nltk.collocations import *
import numpy as np
reload(sys)
sys.setdefaultencoding('utf8')
from sklearn.feature_extraction.text import CountVectorizer
#要聚类的数据
corpus = [
 'This is the first document.',#0
 'This is the second second document.',#1
 'And the third one.',#2
 'Is this the first document"cluster centroids:",centroid_list
print labels
max_centroid = 0
max_cluster_id = 0
cluster_menmbers_list = []
for i in range(0, n_clusters_):
 menmbers_list = []
 for j in range(0, len(labels)):
  if labels[j] == i:
   menmbers_list.append(j)
 cluster_menmbers_list.append(menmbers_list)
# print cluster_menmbers_list

#聚类结果
for i in range(0,len(cluster_menmbers_list)):
 print '第' + str(i) + '类' + '---------------------'
 for j in range(0,len(cluster_menmbers_list[i])):
  a = cluster_menmbers_list[i][j]
  print corpus[a]