hello all
when i run the code :
# -*- coding: cp1256 -*-
from nltk.tagger import *
from nltk.corpus import brown
from nltk.tokenizer import WhitespaceTokenizer
# Tokenize ten texts from the Brown Corpus
train_tokens = []
xx=Token(TEXT=open('fataha2.txt').read())
WhitespaceTokenizer().tokenize(xx)
for l in xx:
    train_tokens.append(l)
#Initialise and train a unigram tagger
mytagger = UnigramTagger(SUBTOKENS='WORDS')
for tok in train_tokens: mytagger.train(tok)
#Once a UnigramTagger has been trained, the tag() method can be used to tag new text:
text_token = Token(TEXT="ÇáÍãÏ ááå ÑÈ ÇáÚÇáãíä")
WhitespaceTokenizer(SUBTOKENS='WORDS').tokenize(text_token)
mytagger.tag(text_token)
print 'The first example : Using Unigram Tagger the reseults are : 'print
acc = tagger_accuracy(mytagger, train_tokens)
print ' With Accuracy :Accuracy = %4.1f%%,' % (100 * acc)
 
i got the following error :
Traceback (most recent call last):
  File "F:\MSC first Chapters\unigramgtag1.py", line 14, in -toplevel-
    for tok in train_tokens: mytagger.train(tok)
  File "C:\Python24\Lib\site-packages\nltk\tagger\__init__.py", line 324, in train
    assert chktype(1, tagged_token, Token)
  File "C:\Python24\Lib\site-packages\nltk\chktype.py", line 316, in chktype
    raise TypeError(errstr)
TypeError:
  Argument 1 to train() must have type: Token
      (got a str)
 
please i want a help on how to recover this error , in other words how can i convert between type string and token , as im still new in python
thanks in advance
 


Yahoo! FareChase - Search multiple travel sites in one click.
-- 
http://mail.python.org/mailman/listinfo/python-list

Reply via email to