自然语言处理3---TFIDF

# -*- coding:utf-8 -*-

'''
将tfidf写入txt文件
'''
import string
import sys
import codecs

reload(sys)
import os
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer, TfidfTransformer

if __name__ == '__main__':

    # =====================1、构造样本的目录文件名称======================

    # 根目录文件
    root_file = '.\Reduced_internet_preprocess'
    # 目录列表
    text_dir_list = []
    # 遍历根目录文件
    for root, dir, files in os.walk(root_file):
        # 构造文件目录
        for f in files:
            text_init_dir = root + '\\' + f
            text_dir_list.append(text_init_dir)

    # =================== 2、从文件导入停