def test_tag(self):
baseline = BaselineTagger(self.tagged_sents)
y = baseline.tag('el gato come pescado .'.split())
self.assertEqual(y, 'D N V N P'.split())
y = baseline.tag('el perro come salame .'.split())
self.assertEqual(y, 'D nc0s000 V nc0s000 P'.split())
def test_tag_word(self):
baseline = BaselineTagger(self.tagged_sents)
for w, t in zip('el gato come pescado .'.split(), 'D N V N P'.split()):
self.assertEqual(t, baseline.tag_word(w))
for w, t in zip('el perro come salame .'.split(),
'D nc0s000 V nc0s000 P'.split()):
self.assertEqual(t, baseline.tag_word(w))
def test_tag(self):
baseline = BaselineTagger(self.tagged_sents)
y = baseline.tag('el gato come pescado .'.split())
self.assertEqual(y, 'D N V N P'.split())
y = baseline.tag('el perro come salame .'.split())
self.assertEqual(y, 'D N V N P'.split())
def test_tag_word(self):
baseline = BaselineTagger(self.tagged_sents)
for w, t in zip('el gato come pescado .'.split(), 'D N V N P'.split()):
self.assertEqual(t, baseline.tag_word(w))
for w, t in zip('el perro come salame .'.split(), 'D N V N P'.split()):
self.assertEqual(t, baseline.tag_word(w))
def test_unknown(self):
baseline = BaselineTagger(self.tagged_sents)
known = {'el', 'gato', 'come', 'pescado', '.', 'la', 'gata', 'salmón'}
for w in known:
self.assertFalse(baseline.unknown(w))
unknown = {'perro', 'salame'}
for w in unknown:
self.assertTrue(baseline.unknown(w))
def test_unknown(self):
baseline = BaselineTagger(self.tagged_sents)
known = {'el', 'gato', 'come', 'pescado', '.', 'la', 'gata', 'salmón'}
for w in known:
self.assertFalse(baseline.unknown(w))
unknown = {'perro', 'salame'}
for w in unknown:
self.assertTrue(baseline.unknown(w))
opts = docopt(__doc__)
# load the data
print("Loading corpus data...")
files = 'CESS-CAST-(A|AA|P)/.*\.tbf\.xml'
corpus = SimpleAncoraCorpusReader('corpus/ancora-2.0/', files)
sents = list(corpus.tagged_sents())
# order of the model
m = str(opts['-m'])
# train the model
filename = opts['-o']
if m == "base":
print("Baseline Model selected")
model = BaselineTagger(tagged_sents=sents)
elif m == "mlhmm":
n = int(opts['-n'])
print("Maximum Likelihood Hidden Markov Model selected, n=%d" % n)
model = MLHMM(n=n, tagged_sents=sents, addone=True)
elif m == 'memm':
n = int(opts['-n'])
c = str(opts['-c'])
if c not in ['logreg', 'nb', 'svc']:
print("Bad classifier type, use --help option for help")
exit()
print("Maximum Entropy Markov Model selected, n=%d, c=%s" % (n, c))
model = MEMM(n=n, tagged_sents=sents, classifier=c)
else:
print("Bad model type, use --help option for help")
exit()
