Python如何使用k-means方法將列表中相似的句子歸類

# 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
#要聚類的數(shù)據(jù)
corpus = [
 'This is the first document.',#0
 'This is the second second document.',#1
 'And the third one.',#2
 'Is this the first document?',#3
 'I like reading',#4
 'do you like reading?',#5
 'how funny you are! ',#6
 'he is a good guy',#7
 'she is a beautiful girl',#8
 'who am i',#9
 'i like writing',#10
 'And the first one',#11
 'do you play basketball',#12
]
#將文本中的詞語轉(zhuǎn)換為詞頻矩陣
vectorizer = CountVectorizer()
#計(jì)算個(gè)詞語出現(xiàn)的次數(shù)
X = vectorizer.fit_transform(corpus)#獲取詞袋中所有文本關(guān)鍵詞
word = vectorizer.get_feature_names()
#類調(diào)用
transformer = TfidfTransformer()
#將詞頻矩陣X統(tǒng)計(jì)成TF-IDF值
tfidf = transformer.fit_transform(X)
#查看數(shù)據(jù)結(jié)構(gòu) tfidf[i][j]表示i類文本中的tf-idf權(quán)重
weight = tfidf.toarray()
# print weight
# kmeans聚類
from sklearn.cluster import KMeans
# print data
kmeans = KMeans(n_clusters=5, random_state=0).fit(weight)#k值可以自己設(shè)置，不一定是五類
# print kmeans
centroid_list = kmeans.cluster_centers_
labels = kmeans.labels_
n_clusters_ = len(centroid_list)
# print "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

#聚類結(jié)果
for i in range(0,len(cluster_menmbers_list)):
 print '第' + str(i) + '類' + '---------------------'
 for j in range(0,len(cluster_menmbers_list[i])):
  a = cluster_menmbers_list[i][j]
  print corpus[a]