python生成相似句子_Python 使用k-means方法将列表中相似的句子聚为一类

由于今年暑假在学习一些自然语言处理的东西，发现网上对k-means的讲解不是很清楚，网上大多数代码只是将聚类结果以图片的形式呈现，而不是将聚类的结果表示出来，于是我将老师给的代码和网上的代码结合了一下，由于网上有许多关于k-means算法基础知识的讲解，因此我在这里就不多讲解了，想了解详细内容的，大家可以自行百度，在这里我只把我的代码给大家展示一下。k-means方法的缺点是k值需要自己找，大家可以多换换k值，看看结果会有什么不同

# 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?‘,#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

]

#将文本中的词语转换为词频矩阵

vectorizer = CountVectorizer()

#计算个词语出现的次数

X = vectorizer.fit_transform(corpus)#获取词袋中所有文本关键词

word = vectorizer.get_feature_names()

#类调用

transformer = TfidfTransformer()

#将词频矩阵X统计成TF-IDF值

tfidf = transformer.fit_transform(X)

#查看数据结构 tfidf[i][j]表示i类文本中的tf-idf权重

weight = tfidf.toarray()

# print weight

# kmeans聚类

from sklearn.cluster import KMeans

# print data

kmeans = KMeans(n_clusters=5, random_state=0).fit(weight)#k值可以自己设置，不一定是五类

# 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]

运行结果：