gistfile1.py

from sussex_nltk import untag_sequence, extract_by_pos

all_tags = r".+"
all_nouns = r"N+"
all_verbs = r"V+"
all_adjectives = r"J+"

example_tagged_words = [('The', 'DT'), ('little', 'JJ'), ('badgers', 'NNS'), ('ate', 'VBP'), ('some', 'DT'), ('jam', 'NN')]

#Decide on some patterns to match
unigram_regex = [all_nouns, all_adjectives]

#Extract only those words that match the given patterns, and untag them
features = untag_sequence(extract_by_pos(example_tagged_words, unigram_regex))

print features