[文本语义相似] 基于tf-idf的余弦距离

import os
import jieba
import pickle
import logging
import numpy as np
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import CountVectorizer 
 
 
class StopWords(object):
    '''
    '''
    def __init__(self, stopwords_file=stopwords_file ):
        self.stopwords = set( [ word.strip() for word in open(stopwords_file, 'r') ] )
    
    def del_stopwords(self, words):
        return [ word for word in words if word not in self.stopwords ]
 
stop_word = StopWords()
 
# 是否分词、  及其停用词语
def _seg_word(words_list, jieba_flag=True, del_stopword=False):
    if jieba_flag:
        word_list = [[stop_word.del_stopwords(words) if del_stopword else word for word in j