小编Far*_*ood的帖子

我有两个目录,我想从中读取他们的文本文件并标记它们,但我不知道如何通过它TaggedDocument.我认为它可以用作TaggedDocument([Strings],[Labels]),但这显然不起作用.

这是我的代码:

from gensim import models
from gensim.models.doc2vec import TaggedDocument
import utilities as util
import os
from sklearn import svm
from nltk.tokenize import sent_tokenize
CogPath = "./FixedCog/"
NotCogPath = "./FixedNotCog/"
SamplePath ="./Sample/"
docs = []
tags = []
CogList = [p for p in os.listdir(CogPath) if p.endswith('.txt')]
NotCogList = [p for p in os.listdir(NotCogPath) if p.endswith('.txt')]
SampleList = [p for p in os.listdir(SamplePath) if p.endswith('.txt')]
for doc in CogList:
     str = open(CogPath+doc,'r').read().decode("utf-8")
     docs.append(str)
     print docs
     tags.append(doc)
     print "###########" …