gistfile1.py

from sussex_nltk.corpus_readers import TwitterCorpusReader
from sussex_nltk.parse import dep_parse_sentences_arceager
from nltk.tokenize import word_tokenize
from nltk import pos_tag

tcr = TwitterCorpusReader()

# Get some (here 30) un-tokenised sentences from tweets
sents = tcr.sample_raw_sents(30) 

# Tokenise and PoS tag the sentences
# Notice the round brackets instead of square brackets. This is a generator 
# expression. It acts quite like a list, but instead of computing all list 
# elements and storing all in memory, it only does one at a time.
# Therefore "tagged_sents" is a generator, not a list
tagged_sents = (pos_tag(word_tokenize(sentence)) for sentence in sents) 

# Dependency parse the sentences
parsed_sents = dep_parse_sentences_arceager(tagged_sents)

# Now you can inspect the results by printing the sentences as in the 
# previous section'''
for sentence in parsed_sents:
    print "-----"
    print sentence