def Stem(self):
#????
fin = open('../file/pos_signature.txt', 'r')
fout = open('../file/stem_signature.txt', 'w+')
while True:
line = fin.readline()
if line:
if '***' in line:
fout.write(line)
elif '---------' in line:
fout.write(line)
else:
num, line = line.split(':', 1)
line = self.RemSingleWord(line)#???????
line = self.CleanStopWords(line)#????
line = self.CleanLines(line)#???
line = line.split()
word_list = []
s = nltk.stem.SnowballStemmer('english')
for w in line:
w = s.stem(w)
word_list.append(w)
line = ' '.join(word_list)
fout.write(num + ':' + line + '\n')
else:
break
评论列表
文章目录