conn = sqlite3.connect(‘expData2.db‘)
conn.text_factory = str
rows = conn.execute(‘select * from articles ‘).fetchall()
conn.close()

rmvList = [‘x‘,‘y‘,‘uj‘]  #移除部分无用词

f1=codecs.open(‘forum_all.txt‘,‘w‘,‘utf-8‘)
j = 1
for row in rows:
     wList = ‘‘
     words = row[2] + row[5]
     keys = jieba.posseg.cut(words)
     for k in keys:
          if k.flag not in rmvList:
               wList += ‘ ‘ + k.word
     f1.write(wList)
     f1.write(‘\n‘)

     j += 1
     if j%1000 ==0:
          print ‘Write %dk records...‘ %(j/1000)

f1.close()
print ‘Completed.‘

def classNB_txt():
    C, X, Y = loadDataSet()
    print ‘Building trainning matrix....‘
    trainMat1d = []
    trainMat2d = []
    for postinDoc in X:
        ary = array(setOfWords2Vec(C, postinDoc))
        trainMat2d.append(ary)
    print ‘Building trainning matrix completed‘

    clf = GaussianNB().fit(trainMat2d, Y)
    f = codecs.open(‘forum_all.txt‘, ‘r‘)
    #fw = codecs.open(‘forum_all_result.txt‘, ‘w‘)
    lines = f.readlines()
    totalNum = len(lines)
    j = 1

    thisDoc = []
    for line in lines:
        ar = line.split(‘ ‘)
        thisDoc.append( setOfWords2Vec(C, ar))

    aryDoc = np.array(thisDoc)
    r = clf.predict(aryDoc)
    f.close()
    print ‘Completed.‘
    l = list(r)
    #ary = [[x] for x in l ]
    #print ary
    print ‘XB: %d‘ %(l.count(1))
    print ‘PS: %d‘ % (l.count(2))
    print ‘PC: %d‘ % (l.count(3))