def __init__(self,
train=None,
model=None,
backoff=None,
cutoff=0,
verbose=False):
NgramTagger.__init__(self, 1, train, model, backoff, cutoff, verbose)
def getNgramTaggerAccuracy(n, trainingSet, testingSet):
# trains and returns the accuracy of the NgramTagger given a value of n
# get untagged sentences and gold POS tags
testingUntaggedSentences = [[taggedWord[0] for taggedWord in sentence] for sentence in testingSet]
testingGoldPOSTags = [[taggedWord[1] for taggedWord in sentence] for sentence in testingSet]
# train tagger
ngramTagger = NgramTagger(n, trainingSet)
# test tagger and get predicted POS tags
ngramTaggedSentences = ngramTagger.tag_sents(testingUntaggedSentences)
ngramTaggedSentencesPOSTags = [[taggedWord[1] for taggedWord in sentence] for sentence in ngramTaggedSentences]
# calculate and return accuracy
return calculateAccuracy(testingGoldPOSTags, ngramTaggedSentencesPOSTags)
def getNgramTaggerAccuracy(n, trainingSet, testingSet):
# trains and returns the accuracy of the NgramTagger given a value of n
# get untagged sentences and gold POS tags
testingUntaggedSentences = [[taggedWord[0] for taggedWord in sentence]
for sentence in testingSet]
testingGoldPOSTags = [[taggedWord[1] for taggedWord in sentence]
for sentence in testingSet]
# train tagger
ngramTagger = NgramTagger(n, trainingSet)
# test tagger and get predicted POS tags
ngramTaggedSentences = ngramTagger.tag_sents(testingUntaggedSentences)
ngramTaggedSentencesPOSTags = [[taggedWord[1] for taggedWord in sentence]
for sentence in ngramTaggedSentences]
# calculate and return accuracy
return calculateAccuracy(testingGoldPOSTags, ngramTaggedSentencesPOSTags)
def test_ngram_taggers(self):
unitagger = UnigramTagger(self.corpus, backoff=self.default_tagger)
bitagger = BigramTagger(self.corpus, backoff=unitagger)
tritagger = TrigramTagger(self.corpus, backoff=bitagger)
ntagger = NgramTagger(4, self.corpus, backoff=tritagger)
encoded = self.encoder.encode(ntagger)
decoded = self.decoder.decode(encoded)
self.assertEqual(repr(ntagger), repr(decoded))
self.assertEqual(repr(tritagger), repr(decoded.backoff))
self.assertEqual(repr(bitagger), repr(decoded.backoff.backoff))
self.assertEqual(repr(unitagger), repr(decoded.backoff.backoff.backoff))
self.assertEqual(repr(self.default_tagger),
repr(decoded.backoff.backoff.backoff.backoff))
def __init__(self, *args, **kwargs):
NgramTagger.__init__(self, 4, *args, **kwargs)
def __init__(self, *args, **kwargs): NgramTagger.__init__(self, 4, *args, **kwargs)
def ngram_tagger(n, train_data, backoff=None):
Ngram_Tagger = NgramTagger(n, train_data, backoff=backoff)
return (Ngram_Tagger)
