使用python进行文本预处理和提取特征的实例

如下所示：

<strong><span style="font-size:14px;">文本过滤</span></strong>

result = re.sub(r'[^\u4e00-\u9fa5,。？！，、；：“ ”‘ '（ ）《 》〈 〉]', "", content)#只保留中文和标点

result = re.sub(r'[^\u4e00-\u9fa5]', "",content)#只保留中文 
result = re.sub(r'[^\0-9\.\u4e00-\u9fa5,。？！，、；：“ ”‘ '（ ）《 》〈 〉]', "", content)#只保留中文和标点和数字 
result = re.sub(r'[^\u4e00-\u9fa5,A-Za-z0-9]', "",content)#只保留中文、英文和数字

文本去除两个以上空格

content=re.sub(r'\s{2,}', '', content)

bas4编码变成中文

def bas4_decode(bas4_content): 
 decodestr= base64.b64decode(bas4_content) 
 result = re.sub(r'[^\0-9\.\u4e00-\u9fa5,。？！，、；：“ ”‘ '（ ）《 》〈 〉]', "", decodestr.decode())#只保留中文和标点和数字 
 return result

文本去停用词

def text_to_wordlist(text): 
 result = re.sub(r'[^\u4e00-\u9fa5]', "",text) 
 f1_seg_list = jieba.cut(result)#需要添加一个词典，来弥补结巴分词中没有的词语，从而保证更高的正确率 
 f_stop = codecs.open(".\stopword.txt","r","utf-8") 
 try: 
  f_stop_text = f_stop.read() 
 finally: 
  f_stop.close() 
 f_stop_seg_list = f_stop_text.split() 
 
 test_words = [] 
 
 for myword in f1_seg_list: 
  if myword not in f_stop_seg_list: 
   test_words.append(myword) 
    
 return test_words

文本特征提取

import jieba 
import jieba.analyse 
import numpy as np 
#import json 
import re

def Textrank(content):
 result = re.sub(r'[^\u4e00-\u9fa5]', "",content)
 seg = jieba.cut(result) 
 jieba.analyse.set_stop_words('stopword.txt')
 keyList=jieba.analyse.textrank('|'.join(seg), topK=10, withWeight=False) 
 return keyList

def TF_IDF(content):
 result = re.sub(r'[^\u4e00-\u9fa5]', "",content)
 seg = jieba.cut(result) 
 jieba.analyse.set_stop_words('stopword.txt')
 keyWord = jieba.analyse.extract_tags( 
  '|'.join(seg), topK=10, withWeight=False, allowPOS=())#关键词提取，在这里对jieba的tfidf.py进行了修改 
 return keyWord