gistfile1.py

from sussex_nltk.corpus_readers import ReutersCorpusReader
from sussex_nltk.tag import twitter_tag_batch
from nltk import pos_tag
from nltk.tokenize import word_tokenize

number_of_sentences = 10     #Number of sentences to sample and display
rcr = ReutersCorpusReader()  #Create a corpus reader

sentences = rcr.sample_raw_sents(number_of_sentences)  #Sample some sentences

#Tag with twitter specific tagger
# - it also tokenises for you in a twitter specific way
twitter_tagged = twitter_tag_batch(sentences)   

#Tag with NLTK's maximum entropy tagger         
nltk_tagged = [pos_tag(word_tokenize(sentence)) for sentence in sentences]  

#Print each sentence
for raw, twitter_sentence, nltk_sentence in zip(sentences,twitter_tagged,nltk_tagged):
    print "-----------------Sentence----------------"
    print "Raw:\n  %s " % raw
    print "Twitter tagged:"
    for token, tag in twitter_sentence:
        print "  %s\t%s" % (token,tag)
    print "NLTK tagged:"
    for token, tag in nltk_sentence:
        print "  %s\t%s" % (token,tag)