由于工作需要,接触自然语言处理,写一些笔记,请大家指教。
功能:
实现把文本库中和输入文本相似的文本输出。
工具:
Spyder,python3.6,codecs,jieba,gensim等模块。(需要自己安装相关模块,我使用的是pip安装)
程序:
# -*- coding: utf-8 -*-
"""
Spyder Editor
This is a temporary script file.
"""
import jieba
from gensim import corpora,models,similarities
import codecs
#构建停用词表
#stop_words = 'E:/zss/zss/资料/网站积累的源码/doc2vec_java-master/file/totalstop.txt'
#stopwords = codecs.open(stop_words,'rb').readlines()
#stopwords = [ w.strip() for w in stopwords ]
#stop_flag = ['x', 'c', 'u','d', 'p', 't', 'uj', 'm', 'f', 'r']
#读取训练词库
Train_test = 'E:/zss/zss/资料/网站积累的源码/doc2vec_java-master/file/test.txt'
Traintest = codecs.open(Train_test,'rb').readlines()
Traintest = [w.strip() for w in Traintest]
# 分词完毕得到结果
Traintest_word = []
for word in Traintest:
words_list = [words for words in jieba.cut(word)]
&n