基于tfidf 以及 lsi 的文本相似度分析

本文主要为了计算文档之间的相似度。标准语聊为我们训练模型所需的，用户语料则用来测试与标准语聊的相似度
1、 数据预处理部分，见注释

对标准语聊进行处理如下

ws = open('d:/sentence.csv','r',encoding='gbk')
times = 0
import re
import jieba  
standard_data = [] ###标准语料
map_value = {}
seed = 0
from zhon.hanzi import punctuation
for i in ws.readlines():
    times += 1
    if times == 1:
        continue
    newline = i.strip().split(',')
    newline = re.sub("[A-Za-z0-9\[\`\~\!\@\#\$\^\&\*\(\)\=\|\{\}\'\:\;\'\,\[\]\.\<\>\/\?\~\！\@\#\\\&\*\%\-\_]", "", newline[0])
    newline = re.sub(' ','',newline)
    newline = re.sub("[%s]+" %punctuation, "", newline)
    standard_data.append(list(jieba.cut(newline)))
    seed += 1
    map_value[seed-1] =  newline
ws.close()

2、tf-idf

from gensim import corpora, models, similarities 

# 生成字典和向量语料  
dictionary = corpora.Dictionary(standard_data)  
# 通过下面一句得到语料中每一篇文档对应的稀疏向量（这里是bow向量）  
corpus = [dictionary.doc2bow(text) for text in standard_data]  


# corpus是一个返回bow向量的迭代器。下面代码将完成对corpus中出现的每一个特征的IDF值的统计工作  
tfidf_model = models.TfidfModel(corpus)  
corpus_tfidf = tfidf_model[corpus]  

####文档相似性的计算
map_value_user = {}
import jieba
import re
raw_data = []
w = open('d:/user_content_v2.txt','r',encoding= 'utf-8')
start = 0
for line in w.readlines():
    newline = line.strip()
    newline = re.sub(' ','',newline)
    newline2 = jieba.cut(newline)
    newline2 = list(newline2)
    map_value_user[start] = newline
    raw_data.append(newline2)
    start += 1


w.close()
index = similarities.MatrixSimilarity(corpus_tfidf) 
vec_bow =[dictionary.doc2bow(text) for text in raw_data]   #把用户语料转为词包
all_reult_sims = []
times_v2 = 0 
###对每个用户语聊与标准语聊计算相似度

for i in vec_bow:    
     #直接使用上面得出的tf-idf 模型即可得出商品描述的tf-idf 值
    sims = index[tfidf_model[i]]
    sims = sorted(enumerate(sims), key=lambda item: -item[1])
    result_sims = []    
    for i,j in sims:
        result_sims.append([map_value_user[times_v2],map_value[i],j])
    times_v2 += 1
    all_reult_sims.append(result_sims[:20])

3、lsi

lsi = models.LsiModel(corpus_tfidf)  
corpus_lsi = lsi[corpus_tfidf]  
####文档相似性的计算
map_value_user = {}
import jieba
import re
raw_data = []
w = open('d:/user_content_v2.txt','r',encoding= 'utf-8')
start = 0
for line in w.readlines():
    newline = line.strip()
    newline = re.sub(' ','',newline)
    newline2 = jieba.cut(newline)
    newline2 = list(newline2)
    map_value_user[start] = newline
    raw_data.append(newline2)
    start += 1


w.close()
index = similarities.MatrixSimilarity(corpus_lsi) 
vec_bow =[dictionary.doc2bow(text) for text in raw_data]   #把商品描述转为词包
all_reult_sims = []
times_v2 = 0 
for i in vec_bow:    
     #直接使用上面得出的tf-idf 模型即可得出商品描述的tf-idf 值
    sims = index[lsi[tfidf_model[i]]]
    sims = sorted(enumerate(sims), key=lambda item: -item[1])
    result_sims = []    
    for i,j in sims:
        result_sims.append([map_value_user[times_v2],map_value[i],j])
    times_v2 += 1
    all_reult_sims.append(result_sims[:20])