Python贝叶斯算法进行文本主客观分析（采用文本双词模型）

from __future__ import division
import re
from numpy import ones, array
from numpy.lib.scimath import log
from nltk import *

def loadDataSet():
    obj=open("obj_train_data.txt",'r')
    sbj=open("sbj_train_data.txt",'r')
    lst_all=[]
    classVec=[]
    for i in range(2000):
        classVec.append(i%2)
    for i in range(1000):
        str0=obj.readline()
        str1=sbj.readline()
        regEx0=re.compile('\\W*')
        regEx1=re.compile('\\W*')
        lst_obj=regEx0.split(str0)
        lst_sbj=regEx1.split(str1)
        each_lst_obj=[]
        each_lst_obj.append([tok.lower() for tok in lst_obj if len(tok)>0])
        lst_all.append(bigramGenerate(each_lst_obj[0]))
        each_lst_sbj=[]
        each_lst_sbj.append([tok.lower() for tok in lst_sbj if len(tok)>0])
        lst_all.append(bigramGenerate(each_lst_sbj[0]))
    return lst_all,cla