中文文本分类

import os
path =r'C:\Users\Administrator\Desktop\0369data'

def readfile(path):
    for root,dirs,files in os.walk(path):
            #print(root)
            #print(dirs)
        for f in files:
            fn = os.path.join(root,f)
#             size = os.path.getsize(fn)
#             print(fn,size)
            genInfo(fn)

import numpy as np
def genInfo(path):
    classfity = fn.split('\\')[-2] # 获取类别
    with open(fn,'r',encoding='utf-8') as f:
        content = f.read() # 获取文本
        
# import jieba
# import jieba.posseg as psg 
# file_path = r'C:\Users\Administrator\Desktop\stopsCN.txt'
# fo = open(file_path,'r',encoding='utf-8').read()

# stops = np.loadtxt(file_path,dtype=str,delimiter=r'\t',encoding='utf-8')
# stops.shape
# tokens=[token for token in tokens if token not in stops]
# tokens

 

转载于:https://www.cnblogs.com/hodafu/p/10113126.html