def tag(self, sent, tagregex=True, deftag='XX', verbose=False):
kalimat = sent.encode('utf-8')
## :> --___<<IMPORTANT>>___--
## Untuk beberapa hal default tagger harus dibiarkan 'XX'
## dengan tujuan identifikasi Entitas
backoff_tagger = DefaultTagger(deftag)
if tagregex:
text = self.regexTokenizer(kalimat.lower().strip())
regexp_tagger = RegexpTagger(patterns.regex_patterns,backoff=backoff_tagger)
unigram_tagger = UnigramTagger(self.reader_train, backoff=regexp_tagger)
else:
text = self.wordTokenizer(kalimat.lower().strip())
unigram_tagger = UnigramTagger(self.reader_train, backoff=backoff_tagger)
bigram_tagger = BigramTagger(self.reader_train, backoff=unigram_tagger)
trigram_tagger = TrigramTagger(self.reader_train, backoff=bigram_tagger)
"""
# Menggunakan dataset pan localization bahasa indonesia "UI-1M-tagged.txt"
# kombinasi proses tagging diatas menghasilkan tingkat akurasi:
# dengan regextagger: < 77%
# tanpa regextagger : > 83%
"""
if verbose:
# Semakin besar dokumen, semakin lama proses perhitungan akurasi
# disarankan hanya untuk testing
print "Calculating Tagger Accuracy..."
self.tagAccuracy = trigram_tagger.evaluate(self.test_sent)
print "Accuracy is: %4.2f %%" % (100.0 * self.tagAccuracy)
return trigram_tagger.tag(text)
def tag(self, sent, tagregex=True, deftag='XX', verbose=False):
kalimat = sent.encode('utf-8')
text = self.regexTokenizer(kalimat.lower().strip())
## :> --___<<IMPORTANT>>___--
## Untuk beberapa hal default tagger harus dibiarkan 'XX'
## dengan tujuan identifikasi Entitas
backoff_tagger = DefaultTagger(deftag)
if tagregex:
regexp_tagger = RegexpTagger(patterns.regex_patterns,backoff=backoff_tagger)
unigram_tagger = UnigramTagger(self.reader_train, backoff=regexp_tagger)
else:
unigram_tagger = UnigramTagger(self.reader_train, backoff=backoff_tagger)
bigram_tagger = BigramTagger(self.reader_train, backoff=unigram_tagger)
trigram_tagger = TrigramTagger(self.reader_train, backoff=bigram_tagger)
"""
# Menggunakan dataset pan localization bahasa indonesia "UI-1M-tagged.txt"
# kombinasi proses tagging diatas menghasilkan tingkat akurasi:
# dengan regextagger: 77%
# tanpa regextagger : > 90%
"""
if verbose:
# Semakin besar dokumen, semakin lama proses perhitungan akurasi
# disarankan hanya untuk testing
print ("Calculating Tagger Accuracy...")
self.tagAccuracy = trigram_tagger.evaluate(self.test_sent)
print ("Accuracy is: %s" % (self.tagAccuracy))
return trigram_tagger.tag(text)
def train_trigram(data):
trigram_tagger = TrigramTagger(data)
with open(os.path.join(PACKDIR, "nib_marburg", "trigram.pickle"),
"wb") as f:
pickle.dump(trigram_tagger, f)
res = trigram_tagger.tag(
"uns ist in alten mæren wunders vil geseit".split(" "))
print(res)
def unigram_trigram_tagger(train_sentences):
return TrigramTagger(
train_sentences,
backoff=UnigramTagger(
train_sentences,
backoff=DefaultTagger("NN")
)
)
def ngramtagging(train): #PROSES POS TAGGING
train_data = []
train_data.append(train)
backoff_tagger = DefaultTagger('nn')
unigram_tagger = UnigramTagger(train_data, backoff = backoff_tagger)
bigram_tagger = BigramTagger(train_data, backoff = unigram_tagger)
trigram_tagger = TrigramTagger(train_data, backoff = bigram_tagger)
return trigram_tagger
def __init__(self, *args, **kwargs):
SequentialBackoffTagger.__init__(self, *args, **kwargs)
self.dist = FreqDist()
tagged_brown_path = os.path.join(os.path.dirname(__file__),
'../data/brown_clawstags.pickle')
train_sents = pickle.load(open(tagged_brown_path, 'rb'))
# make sure all tuples are in the required format: (TAG, word)
train_sents = [[t for t in sentence if len(t) == 2]
for sentence in train_sents]
# default_tagger = DefaultTagger('nn')
wn_tagger = WordNetTagger()
names_tagger = NamesTagger(wn_tagger)
coca_tagger = COCATagger(names_tagger)
bigram_tagger = BigramTagger(train_sents, backoff=coca_tagger)
trigram_tagger = TrigramTagger(train_sents, backoff=bigram_tagger)
# doesn't include self cause it's a dumb tagger (would always return None)
self._taggers = trigram_tagger._taggers
def train(self, templates=None, verbose=True):
"""Train a new Brill tagger."""
if templates is None:
templates = brill.nltkdemo18()
random.seed(len(self.tagged_data_list))
random.shuffle(self.tagged_data_list)
cutoff = int(self.dev_size * self.train_size)
training_data = self.tagged_data_list[:cutoff]
test_data = self.tagged_data_list[cutoff:self.dev_size]
# very simple regular expression tagger
regex_tagger = RegexpTagger([(r'^-?[0-9]+(.[0-9]+)?$', 'PUNCT'),
(r'.*', 'N')])
if verbose == True:
print "Regular expression tagger accuracy:\n{}\n".format(
regex_tagger.evaluate(test_data))
# unigram tagger
unigram_tagger = UnigramTagger(train=training_data,
backoff=regex_tagger)
if verbose == True:
print "Unigram tagger accuracy:\n{}\n".format(
unigram_tagger.evaluate(test_data))
# bigram tagger
bigram_tagger = BigramTagger(train=training_data,
backoff=unigram_tagger)
if verbose == True:
print "Bigram tagger accuracy:\n{}\n".format(
bigram_tagger.evaluate(test_data))
# trigram tagger
trigram_tagger = TrigramTagger(train=training_data,
backoff=bigram_tagger)
if verbose == True:
print "Trigram tagger accuracy:\n{}\n".format(
trigram_tagger.evaluate(test_data))
# first iteration
trainer = BrillTaggerTrainer(initial_tagger=trigram_tagger,
templates=templates)
brill_tagger = trainer.train(train_sents=training_data,
max_rules=self.max_rules,
min_score=self.min_score)
if verbose == True:
print "Initial Brill tagger accuracy:\n{}\n".format(
brill_tagger.evaluate(test_data))
# folding
for i in range(0, self.num_groups):
# random splitting
random.seed(len(self.tagged_data_list))
random.shuffle(self.tagged_data_list)
cutoff = int(self.dev_size * self.train_size)
training_data = self.tagged_data_list[:cutoff]
test_data = self.tagged_data_list[cutoff:self.dev_size]
# note that .train method returns a BrillTagger() object
brill_tagger = trainer.train(train_sents=training_data,
max_rules=self.max_rules,
min_score=self.min_score)
if verbose == True:
print "Brill tagger accuracy, fold {}:\n{}\n".format(
i + 1, brill_tagger.evaluate(test_data))
def train(self, templates=None, verbose=True):
"""Train a new Brill tagger."""
if templates is None:
templates = brill.nltkdemo18()
random.seed(len(self.tagged_data_list))
random.shuffle(self.tagged_data_list)
cutoff = int(self.dev_size * self.train_size)
training_data = self.tagged_data_list[:cutoff]
test_data = self.tagged_data_list[cutoff:self.dev_size]
# very simple regular expression tagger
regex_tagger = RegexpTagger([
(r'^-?[0-9]+(.[0-9]+)?$', 'PUNCT'),
(r'.*', 'N')
])
if verbose == True:
print "Regular expression tagger accuracy:\n{}\n".format(
regex_tagger.evaluate(test_data))
# unigram tagger
unigram_tagger = UnigramTagger(train=training_data,
backoff=regex_tagger)
if verbose == True:
print "Unigram tagger accuracy:\n{}\n".format(
unigram_tagger.evaluate(test_data))
# bigram tagger
bigram_tagger = BigramTagger(train=training_data,
backoff=unigram_tagger)
if verbose == True:
print "Bigram tagger accuracy:\n{}\n".format(
bigram_tagger.evaluate(test_data))
# trigram tagger
trigram_tagger = TrigramTagger(train=training_data,
backoff=bigram_tagger)
if verbose == True:
print "Trigram tagger accuracy:\n{}\n".format(
trigram_tagger.evaluate(test_data))
# first iteration
trainer = BrillTaggerTrainer(initial_tagger=trigram_tagger,
templates=templates)
brill_tagger = trainer.train(train_sents=training_data,
max_rules=self.max_rules,
min_score=self.min_score)
if verbose == True:
print "Initial Brill tagger accuracy:\n{}\n".format(
brill_tagger.evaluate(test_data))
# folding
for i in range(0, self.num_groups):
# random splitting
random.seed(len(self.tagged_data_list))
random.shuffle(self.tagged_data_list)
cutoff = int(self.dev_size * self.train_size)
training_data = self.tagged_data_list[:cutoff]
test_data = self.tagged_data_list[cutoff:self.dev_size]
# note that .train method returns a BrillTagger() object
brill_tagger = trainer.train(train_sents=training_data,
max_rules=self.max_rules,
min_score=self.min_score)
if verbose == True:
print "Brill tagger accuracy, fold {}:\n{}\n".format(
i+1, brill_tagger.evaluate(test_data))
