# Ling/CSE 472, Spring 2009
# Assignment 3, part I
# alltags.py

# import the Natural Language Toolkit
import nltk

# get a tagged corpus
tagged_sents = nltk.corpus.treebank.tagged_sents()

# split it into a training set and a test set
size = int(len(tagged_sents) * 0.9)
train_sents = tagged_sents[:size]
test_sents = tagged_sents[size:]

# train a bigram tagger
default_tagger = nltk.DefaultTagger('NN')
unigram_tagger = nltk.UnigramTagger(train_sents, backoff=default_tagger)
bigram_tagger = nltk.BigramTagger(train_sents, backoff=unigram_tagger)

# evaluate the accuracy and print the results
print nltk.tag.accuracy(bigram_tagger, test_sents)