python_NLP实战之文本向量化

实战：网页文本向量化

1、词向量的训练

1.1 中文语料预处理

将xml->txt  繁->简 利用结巴进行分词

# -*- coding: utf-8 -*-
from gensim.corpora import WikiCorpus
import jieba
from langconv import *

def my_function():
    space = ' '
    i = 0
    l = []
    zhwiki_name = './data/zhwiki-latest-pages-articles.xml.bz2'
    f = open('./data/reduce_zhiwiki.txt', 'w')
    wiki = WikiCorpus(zhwiki_name, lemmatize=False, dictionary={})
    for text in wiki.get_texts():
        for temp_sentence in text:
            temp_sentence = Converter('zh-hans').convert(temp_sentence)
            seg_list = list(jieba.cut(temp_sentence))
            for temp_term in seg_list:
                l.append(temp_term)
        f.write(space.join(l) + '\n')
        l = []
        i = i + 1

        if (i %200 == 0):
            print('Saved ' + str(i) + ' articles')
    f.close()

if __name__ == '__main__':
    my_function()

1.2 利用gensim模块训练词向量

# -*- coding: utf-8 -*-
from gensim.models import Word2Vec
from gensim.models.word2vec import LineSentence
import logging

logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)

def my_function():
    wiki_news = open('./data/reduce_zhiwiki.txt', 'r')
    model = Word2Vec(LineSentence(wiki_news), sg=0,size=192, window=5, min_count=5, workers=9)
    model.save('zhiwiki_news.word2vec')

if __name__ == '__main__':
    my_function()

2、段落向量的训练

与训练词向量不同的是无需再对文档进行分词，直接将简体文本保留。doc2vec在训练时能够采用Tag信息更好地辅助训练（表明是同一类doc）输入文档多了一个tag属性。

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import gensim.models as g
from gensim.corpora import WikiCorpus
import logging
from langconv import *

#enable logging
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)

docvec_size=192
class TaggedWikiDocument(object):
    def __init__(self, wiki):
        self.wiki = wiki
        self.wiki.metadata = True
    def __iter__(self):
        import jieba
        for content, (page_id, title) in self.wiki.get_texts():
            yield g.doc2vec.LabeledSentence(words=[w for c in content for w in jieba.cut(Converter('zh-hans').convert(c))], tags=[title])

def my_function():
    zhwiki_name = './data/zhwiki-latest-pages-articles.xml.bz2'
    wiki = WikiCorpus(zhwiki_name, lemmatize=False, dictionary={})
    documents = TaggedWikiDocument(wiki)

    model = g.Doc2Vec(documents, dm=0, dbow_words=1, size=docvec_size, window=8, min_count=19, iter=5, workers=8)
    model.save('data/zhiwiki_news.doc2vec')

if __name__ == '__main__':
    my_function()

3、计算网页相似度

3.1 word2vec计算网页相似度

      基本方法：抽取文本中的关键词（结巴工具包里面的tfidf关键字提取），将关键词向量化，然后将得到的各个词向量相加，最后得到一个词向量总和代表文本的向量化表示，利用总的向量计算文本相似度。

# -*- coding: utf-8 -*-
import jieba.posseg as pseg
from jieba import analyse

def keyword_extract(data, file_name):
   tfidf = analyse.extract_tags
   keywords = tfidf(data)
   return keywords

def getKeywords(docpath, savepath):

   with open(docpath, 'r') as docf, open(savepath, 'w') as outf:
      for data in docf:
         data = data[:len(data)-1]
         keywords = keyword_extract(data, savepath)
         for word in keywords:
            outf.write(word + ' ')
         outf.write('\n')
def word2vec(file_name,model):
    with codecs.open(file_name, 'r') as f:
        word_vec_all = numpy.zeros(wordvec_size)
        for data in f:
            space_pos = get_char_pos(data, ' ')
            first_word=data[0:space_pos[0]]
            if model.__contains__(first_word):
                word_vec_all= word_vec_all+model[first_word]

            for i in range(len(space_pos) - 1):
                word = data[space_pos[i]:space_pos[i + 1]]
                if model.__contains__(word):
                    word_vec_all = word_vec_all+model[word]
        return word_vec_all

def simlarityCalu(vector1,vector2):
    vector1Mod=np.sqrt(vector1.dot(vector1))
    vector2Mod=np.sqrt(vector2.dot(vector2))
    if vector2Mod!=0 and vector1Mod!=0:
        simlarity=(vector1.dot(vector2))/(vector1Mod*vector2Mod)
    else:
        simlarity=0
    return simlarity

if __name__ == '__main__':
    model = gensim.models.Word2Vec.load('data/zhiwiki_news.word2vec')
    p1 = './data/P1.txt'
    p2 = './data/P2.txt'
    p1_keywords = './data/P1_keywords.txt'
    p2_keywords = './data/P2_keywords.txt'
    getKeywords(p1, p1_keywords)
    getKeywords(p2, p2_keywords)
    p1_vec=word2vec(p1_keywords,model)
    p2_vec=word2vec(p2_keywords,model)

    print(simlarityCalu(p1_vec,p2_vec))

 

3.2 doc2vec计算网页相似度

三步走：预处理->文档向量化->.计算文本相似

import gensim.models as g
import codecs
import numpy
import numpy as np

model_path = './data/zhiwiki_news.doc2vec'
start_alpha = 0.01
infer_epoch = 1000
docvec_size = 192


def simlarityCalu(vector1, vector2):
    vector1Mod = np.sqrt(vector1.dot(vector1))
    vector2Mod = np.sqrt(vector2.dot(vector2))
    if vector2Mod != 0 and vector1Mod != 0:
        simlarity = (vector1.dot(vector2)) / (vector1Mod * vector2Mod)
    else:
        simlarity = 0
    return simlarity


def doc2vec(file_name, model):
    import jieba
    doc = [w for x in codecs.open(file_name, 'r', 'utf-8').readlines() for w in jieba.cut(x.strip())]
    doc_vec_all = model.infer_vector(doc, alpha=start_alpha, steps=infer_epoch)
    return doc_vec_all


if __name__ == '__main__':
    model = g.Doc2Vec.load(model_path)
    p1 = './data/P1.txt'
    p2 = './data/P2.txt'
    P1_doc2vec = doc2vec(p1, model)
    P2_doc2vec = doc2vec(p2, model)
    print(simlarityCalu(P1_doc2vec, P2_doc2vec))