将分好词的文本文件转换持久化为Bunch类形式

# encoding: utf-8

import sys
import os
import jieba
import importlib
importlib.reload(sys)
from sklearn.datasets.base import Bunch
import pickle

bunch = Bunch(target_name=[],label=[],filenams=[],contents=[])

def savefile(savepath,content):
    fp = open(savepath,"w",encoding='gb2312',errors='ignore')
    fp.write(content)
    fp.close()

def readfile(path):
    fp = open(path,"r",encoding='gb2312',errors='ignore')
    content = fp.read()
    fp.close()
    return content

wordbag_path = "F://研究生项目//Bunch分词后的文本语料库//train_set.dat"
seg_path = "F://研究生项目//Bunch分词后的文本语料库/"

catelist = os.listdir(seg_path)
bunch.target_name.extend(catelist)   #将类别信息保存到Bunch对象中
for mydir in catelist:
    class_path = seg_path+mydir+"/"
    file_list = os.listdir(class_path)
    for file_path in file_list:
        fullname = class_path+"/"+file_path
        bunch.label.append(mydir)     #保存当前文件的分类标签
        bunch.filenams.append(fullname)    #保存当前文件的文件路径
        bunch.contents.append(readfile(fullname).strip())    #保存文件的词向量


#Bunch对象持久化
file_obj = open(wordbag_path,"wb+")
pickle.dump(bunch,file_obj)
file_obj.close()
print("构建文本结束了")