当前位置:首页 >> 脚本专栏

Python使用gensim计算文档相似性

pre_file.py

#-*-coding:utf-8-*-
import MySQLdb
import MySQLdb as mdb
import os,sys,string
import jieba
import codecs
reload(sys)
sys.setdefaultencoding('utf-8')
#连接数据库
try:
  conn=mdb.connect(host='127.0.0.1',user='root',passwd='kongjunli',db='test1',charset='utf8')
except Exception,e:
  print e
  sys.exit()
#获取cursor对象操作数据库
cursor=conn.cursor(mdb.cursors.DictCursor) #cursor游标
#获取内容
sql='SELECT link,content FROM test1.spider;'
cursor.execute(sql)   #execute()方法,将字符串当命令执行
data=cursor.fetchall()#fetchall()接收全部返回结果行
f=codecs.open('C:\Users\kk\Desktop\hello-result1.txt','w','utf-8')
 
for row in data:    #row接收结果行的每行数据
  seg='/'.join(list(jieba.cut(row['content'],cut_all='False')))
  f.write(row['link']+' '+seg+'\r\n')
f.close()
 
cursor.close()
      #提交事务,在插入数据时必须

jiansuo.py

#-*-coding:utf-8-*-
import sys
import string
import MySQLdb
import MySQLdb as mdb
import gensim
from gensim import corpora,models,similarities
from gensim.similarities import MatrixSimilarity
import logging
import codecs
reload(sys)
sys.setdefaultencoding('utf-8')
 
con=mdb.connect(host='127.0.0.1',user='root',passwd='kongjunli',db='test1',charset='utf8')
with con:
  cur=con.cursor()
  cur.execute('SELECT * FROM cutresult_copy')
  rows=cur.fetchall()
  class MyCorpus(object):
    def __iter__(self):
      for row in rows:
        yield str(row[1]).split('/')
#开启日志
logging.basicConfig(format='%(asctime)s:%(levelname)s:%(message)s',level=logging.INFO)
Corp=MyCorpus()
#将网页文档转化为tf-idf
dictionary=corpora.Dictionary(Corp)
corpus=[dictionary.doc2bow(text) for text in Corp] #将文档转化为词袋模型
#print corpus
tfidf=models.TfidfModel(corpus)#使用tf-idf模型得出文档的tf-idf模型
corpus_tfidf=tfidf[corpus]#计算得出tf-idf值
#for doc in corpus_tfidf:
  #print doc
###
'''
q_file=open('C:\Users\kk\Desktop\q.txt','r')
query=q_file.readline()
q_file.close()
vec_bow=dictionary.doc2bow(query.split(' '))#将请求转化为词带模型
vec_tfidf=tfidf[vec_bow]#计算出请求的tf-idf值
#for t in vec_tfidf:
 # print t
'''
###
query=raw_input('Enter your query:')
vec_bow=dictionary.doc2bow(query.split())
vec_tfidf=tfidf[vec_bow]
index=similarities.MatrixSimilarity(corpus_tfidf)
sims=index[vec_tfidf]
similarity=list(sims)
print sorted(similarity,reverse=True)

encodings.xml

<"1.0" encoding="UTF-8"?>
<project version="4">
 <component name="Encoding">
  <file url="PROJECT" charset="UTF-8" />
 </component>
</project>

misc.xml

<"1.0" encoding="UTF-8"?>
<project version="4">
 <component name="ProjectLevelVcsManager" settingsEditedManually="false">
  <OptionsSetting value="true" id="Add" />
  <OptionsSetting value="true" id="Remove" />
  <OptionsSetting value="true" id="Checkout" />
  <OptionsSetting value="true" id="Update" />
  <OptionsSetting value="true" id="Status" />
  <OptionsSetting value="true" id="Edit" />
  <ConfirmationsSetting value="0" id="Add" />
  <ConfirmationsSetting value="0" id="Remove" />
 </component>
 <component name="ProjectRootManager" version="2" project-jdk-name="Python 2.7.11 (C:\Python27\python.exe)" project-jdk-type="Python SDK" />
</project>

modules.xml

<"1.0" encoding="UTF-8"?>
<project version="4">
 <component name="ProjectModuleManager">
  <modules>
   <module fileurl="file://$PROJECT_DIR$/.idea/爬虫练习代码.iml" filepath="$PROJECT_DIR$/.idea/爬虫练习代码.iml" />
  </modules>
 </component>
</project>