def no_backoff_taggers(test, train, corpus='floresta'):
default_tagger = default_tagger_corpus(corpus)
info('training {} taggers without backoff'.format(corpus))
info('this may take a while...\n')
info(default_tagger)
default_score = default_tagger.evaluate(test)
print('accuracy score: {}\n'.format(default_score))
# unigram tagger
uni_tagger = UnigramTagger(train)
# bigram tagger
bi_tagger = BigramTagger(train)
# trigram tagger
tri_tagger = TrigramTagger(train)
info(uni_tagger)
uni_score = uni_tagger.evaluate(test)
print('accuracy score: {}\n'.format(uni_score))
info(bi_tagger)
bi_score = bi_tagger.evaluate(test)
print('accuracy score: {}\n'.format(bi_score))
info(tri_tagger)
tri_score = tri_tagger.evaluate(test)
print('accuracy score: {}\n'.format(tri_score))
def pos_tag(self):
tokenize_obj = NLTKTokenize(self.options)
res = tokenize_obj.tokenize()
tokens = res['result']
tags = []
# Performs Bigram / Unigram / Regex Tagging
if self.options.get('tagger') in ['unigram', 'bigram', 'regex']:
trainer = self.options['train'] if self.options.get(
'train') in TRAINERS else DEFAULT_TRAIN
train = brown.tagged_sents(categories=trainer)
# Create your custom regex tagging pattern here
regex_tag = RegexpTagger([(r'^[-\:]?[0-9]+(.[0-9]+)?$', 'CD'),
(r'.*able$', 'JJ'),
(r'^[A-Z].*$', 'NNP'), (r'.*ly$', 'RB'),
(r'.*s$', 'NNS'), (r'.*ing$', 'VBG'),
(r'.*ed$', 'VBD'), (r'.*', 'NN')])
current = os.path.dirname(os.path.abspath(__file__))
# Unigram tag training data load / dump pickle
pkl_name = current + '/trained/unigram_' + trainer + '.pkl'
if os.path.isfile(pkl_name):
with open(pkl_name, 'rb') as pkl:
unigram_tag = load(pkl)
else:
unigram_tag = UnigramTagger(train, backoff=regex_tag)
with open(pkl_name, 'wb') as pkl:
dump(unigram_tag, pkl, -1)
# Bigram tag training data load / dump pickle
if self.options['tagger'] == 'bigram':
pkl_name = current + '/trained/bigram_' + trainer + '.pkl'
if os.path.isfile(pkl_name):
with open(pkl_name, 'rb') as pkl:
bigram_tag = load(pkl)
else:
bigram_tag = BigramTagger(train, backoff=unigram_tag)
with open(pkl_name, 'wb') as pkl:
dump(bigram_tag, pkl, -1)
tags = bigram_tag.tag(tokens) # Bigram tagging performed here
elif self.options['tagger'] == 'unigram':
tags = unigram_tag.tag(
tokens) # Unigram tagging performed here
else:
tags = regex_tag.tag(tokens) # Regex tagging performed here
# Performs default pos_tag
elif self.options.get('tagger', DEFAULT_TAGGER) == 'pos':
tags = pos_tag(tokens)
return self._dump(tags)
def backoff_taggers(test, train, save, corpus='floresta'):
default_tagger = default_tagger_corpus(corpus)
info('training {} taggers with backoff'.format(corpus))
info('this may take a while...\n')
info(default_tagger)
default_score = default_tagger.evaluate(test)
print('accuracy score: {}\n'.format(default_score))
# UNIGRAM TAGGER WITH BACKOFF
uni_tagger_backoff = UnigramTagger(train, backoff=default_tagger)
# BIGRAM TAGGER WITH BACKOFF
bi_tagger_backoff = BigramTagger(train, backoff=uni_tagger_backoff)
# TRIGRAM TAGGER WITH BACKOFF
tri_tagger_backoff = TrigramTagger(train, backoff=bi_tagger_backoff)
info(uni_tagger_backoff)
uni_backoff_score = uni_tagger_backoff.evaluate(test)
print('accuracy score: {}\n'.format(uni_backoff_score))
info(bi_tagger_backoff)
bi_backoff_score = bi_tagger_backoff.evaluate(test)
print('accuracy score: {}\n'.format(bi_backoff_score))
info(tri_tagger_backoff)
tri_backoff_score = tri_tagger_backoff.evaluate(test)
print('accuracy score: {}\n'.format(tri_backoff_score))
if not save:
return
accuracy_dict = {}
accuracy_dict['uni'] = uni_backoff_score
accuracy_dict['bi'] = bi_backoff_score
accuracy_dict['tri'] = tri_backoff_score
# Saving our Trigram-tagger with backoff
if uni_backoff_score == max(accuracy_dict.values()):
tagger_file = '{}_unigram_tagger_backoff.pkl'.format(corpus)
output = open(tagger_file, 'wb')
dump(uni_tagger_backoff, output, -1)
elif bi_backoff_score == max(accuracy_dict.values()):
tagger_file = '{}_bigram_tagger_backoff.pkl'.format(corpus)
output = open(tagger_file, 'wb')
dump(bi_tagger_backoff, output, -1)
elif tri_backoff_score == max(accuracy_dict.values()):
tagger_file = '{}_trigram_tagger_backoff.pkl'.format(corpus)
dump(tri_tagger_backoff, output, -1)
output.close()
info('saving %s...\n', tagger_file)
def __init__(self, mode, train_sents):
if mode == TRIGRAM:
self.tagger = UnigramTagger(train_sents)
self.tagger = BigramTagger(train_sents, backoff=self.tagger)
self.tagger = TrigramTagger(train_sents, backoff=self.tagger)
elif HDM:
self.tagger = HiddenMarkovModelTagger.train(train_sents)
def __init__(self, train=None, default=None, name=None):
self.name = name
# As found on page 199 of the nltk book
regexps = [
(r'.*ing$', 'VBG'), # gerunds
(r'.*ed$', 'VBD'), # simple past
(r'.*es$', 'VBZ'), # 3rd singular present
(r'.*ould$', 'MD'), # modals
(r'.*\'s$', 'NN$'), # possessive nouns
(r'.*s$', 'NNS'), # plural nouns
(r'^-?[0-9]+(.[0-9]+)?$', 'CD'), # cardinal numbers
]
self.default = default
self.regex = RegexpTagger(regexps, backoff=self.default)
self.unigram = UnigramTagger(train=train, backoff=self.regex)
self.bigram = BigramTagger(train=train, backoff=self.unigram)
def get_pos_tagger():
from nltk.corpus import brown
regexp_tagger = nltk.RegexpTagger([
(r'^-?[0-9]+(.[0-9]+)?$', 'CD'), # cardinal numbers
(r'(The|the|A|a|An|an)$', 'AT'), # articles
(r'.*able$', 'JJ'), # adjectives
(r'.*ness$', 'NN'), # nouns formed from adjectives
(r'.*ly$', 'RB'), # adverbs
(r'.*s$', 'NNS'), # plural nouns
(r'.*ing$', 'VBG'), # gerunds
(r'.*ed$', 'VBD'), # past tense verbs
(r'.*', 'NN') # nouns (default)
])
brown_train = brown.tagged_sents()
unigram_tagger = UnigramTagger(brown_train, backoff=regexp_tagger)
bigram_tagger = BigramTagger(brown_train, backoff=unigram_tagger)
trigram_tagger = TrigramTagger(brown_train, backoff=bigram_tagger)
# Override particular words
main_tagger = nltk.RegexpTagger(
[(r'(A|a|An|an)$', 'ex_quant'),
(r'(Every|every|All|all)$', 'univ_quant')],
backoff=trigram_tagger)
return main_tagger
def train_tagger(corpus_name, corpus): """ Train the taggers and saves them Args: corpus_name: name of the corpus used to create the tagger corpus: corpus for creating the tagger """ #List of n-gram taggers names complete_names = [corpus_name + '_' + x for x in N_GRAM_NAMES] # Training UnigramTagger tagger1 = UnigramTagger(corpus) utilities.save_pickle(tagger1, complete_names[0], TAGGER_EXTENSION, TAGGER_PATH) print "UnigramTagger trained with", corpus_name # Training BigramTagger tagger2 = BigramTagger(corpus) utilities.save_pickle(tagger2, complete_names[1], TAGGER_EXTENSION, TAGGER_PATH) print "BigramTagger trained with", corpus_name # Training TrigramTagger tagger3 = TrigramTagger(corpus) utilities.save_pickle(tagger3, complete_names[2], TAGGER_EXTENSION, TAGGER_PATH) print "TrigramTagger trained with", corpus_name
def __init__(self, train_sents, to_detect_list, n_gram=1):
train_data = [[(t, c) for w, t, c in sent] for sent in train_sents]
self.tagger = UnigramTagger(train_data)
if n_gram > 1:
self.tagger = BigramTagger(train_data, backoff=self.tagger)
if n_gram > 2:
self.tagger = TrigramTagger(train_data, backoff=self.tagger)
self.to_detect_list = to_detect_list
def TrainTaggers(training, testing):
global results
Unigram = UnigramTagger(training, backoff = default)
print('unigram trained')
Bigram = BigramTagger(training, backoff = Unigram)
print('bigram trained')
Trigram = TrigramTagger(training, backoff = Bigram)
print('trigram trained')
results += [Trigram.evaluate(testing)]
def train(self, model_path):
corpus = [[(token.lower(), tag) for token, tag in sent]
for sent in CORPUS]
unigram_tagger = UnigramTagger(corpus, backoff=DefaultTagger('UNK'))
bigram_tagger = BigramTagger(corpus, backoff=unigram_tagger)
with open(model_path, "wb") as model_file:
pickle.dump(bigram_tagger, model_file)
def find_combined_taggers_accuracy(train_set, test_set):
# finding most used tag
train_words = [word for sent in train_set for word in sent]
train_set_tags = [tag for (word, tag) in train_words]
most_frequent_tag = FreqDist(train_set_tags).max()
default_tagger = DefaultTagger(most_frequent_tag)
# default tagger
default_tagger_result = default_tagger.evaluate(test_set)
print("Default Tagger accuracy: ", default_tagger_result)
# regex tagger
patterns = [
(r'.*ing$', 'VBG'), # gerunds
(r'.*ed$', 'VBD'), # simple past
(r'.*es$', 'VBZ'), # 3rd singular present
(r'.*ould$', 'MD'), # modals
(r'.*\'s$', 'NN$'), # possessive nouns
(r'.*s$', 'NNS'), # plural nouns
(r'^-?[0-9]+(\.[0-9]+)?$', 'CD'), # cardinal numbers
(r'.*', 'NN') # nouns (default)
]
regex_tagger = RegexpTagger(patterns)
regex_tagger_result = regex_tagger.evaluate(test_set)
print("Regex Tagger Accuracy: ", regex_tagger_result)
# unigram tagger with default tagger as backoff
unigram_tagger = UnigramTagger(train_set, backoff=default_tagger)
unigram_tagger_result = unigram_tagger.evaluate(test_set)
print("Unigram Tagger accuracy (Backoff = Default Tagger): ",
unigram_tagger_result)
# bigram tagger with different backoffs
bigram_tagger = BigramTagger(train_set)
bigram_tagger_backoff_unigram = BigramTagger(train_set,
backoff=unigram_tagger)
bigram_tagger_backoff_regex = BigramTagger(train_set, backoff=regex_tagger)
bigram_tagger_result = bigram_tagger.evaluate(test_set)
bigram_tagger_backoff_regex_result = bigram_tagger_backoff_regex.evaluate(
test_set)
bigram_tagger_backoff_unigram_result = bigram_tagger_backoff_unigram.evaluate(
test_set)
print("Bigram Tagger Accuracy: ", bigram_tagger_result)
print("Bigram Tagger Accuracy (Backoff = Regex Tagger): ",
bigram_tagger_backoff_regex_result)
print("Bigram Tagger Accuracy (Backoff = Unigram Tagger): ",
bigram_tagger_backoff_unigram_result)
def __init__(self, train_sents):
"""Show parameters.
train_sents: trained sentences which have already been tagged.
using Brown, conll2000, and TreeBank corpus.
"""
t0 = DefaultTagger('NN')
t1 = UnigramTagger(train_sents, backoff=t0)
t2 = BigramTagger(train_sents, backoff=t1)
self.tagger = TrigramTagger(train_sents, backoff=t2)
def ngram_tag_with_backoff():
fd = FreqDist(brown.words(categories='news'))
#Get the most frequent tag of each word in the corpus
cfd = ConditionalFreqDist(brown.tagged_words(
categories='news')) #, backoff=nltk.DefaultTagger('NN'))
#Get the first 100 most common words
most_freq_words = fd.most_common(1000000)
#Create a dictionary in form of a tuple (word, most_likely_tag)
likely_tags = dict(
(word, cfd[word].max()) for (word, _) in most_freq_words)
#Unigram means tag by using its most frequency tag (no context needed) just like unigram in the Ngram topic
lookup_tagger = UnigramTagger(model=likely_tags)
#With Backoff
train_len = int(len(brown_tagged_sents) * 0.9)
print(brown_tagged_sents[train_len:])
bigram_tagger = BigramTagger(brown_tagged_sents[:train_len],
backoff=lookup_tagger)
score = bigram_tagger.evaluate(brown_tagged_sents[train_len:])
print(score)
def train_tagger(corpus_name, corpus):
""" Function to train tagger. """
# Training UnigramTagger.
uni_tag = UnigramTagger(corpus)
save_tagger('{}_unigram.tagger'.format(corpus_name), uni_tag)
# Training BigramTagger.
bi_tag = BigramTagger(corpus, backoff=uni_tag)
save_tagger('{}_bigram.tagger'.format(corpus_name), bi_tag)
_msg = str("Tagger trained with {} using "
"UnigramTagger and BigramTagger.").format(corpus_name)
print(_msg, file=sys.stderr)
def create_tagger(sents,patterns=PATTERNS,maxngram=4):
'''Обучение Backoff tagger на каком-либо корпусе предложений'''
train = sents
def_tagger = DefaultTagger('NN')
re_tagger = RegexpTagger(patterns, backoff=def_tagger)
uni_tagger = UnigramTagger(train, backoff=re_tagger)
bi_tagger = BigramTagger(train, backoff=uni_tagger)
tri_tagger = TrigramTagger(train, backoff=bi_tagger)
ngram_tagger = NgramTagger(maxngram, train, backoff=tri_tagger)
return ngram_tagger
class BigramChunker(ChunkParserI):
def __init__(self, train_sentences):
train_data = [[(t, c) for w, t, c in tree2conlltags(sent)]
for sent in train_sentences]
self.tagger = BigramTagger(train_data)
def parse(self, sentence):
pos_tags = [pos for (word, pos) in sentence]
tagged_pos_tags = self.tagger.tag(pos_tags)
chunk_tags = [chunk_tag for (pos, chunk_tag) in tagged_pos_tags]
conll_tags = [(word, pos, chunk_tag) for ((word, pos), chunk_tag) in zip(sentence, chunk_tags)]
return conlltags2tree(conll_tags)
def get_tagger(type="StandfordPOSTagger"):
if type == "Custom":
brown_tagged_sents = brown.tagged_sents(categories='news',
tagset='universal')
t0 = DefaultTagger('NOUN')
t1 = UnigramTagger(brown_tagged_sents, backoff=t0)
t2 = BigramTagger(brown_tagged_sents, backoff=t1)
else:
t2 = StanfordPOSTagger(
'data/./models/wsj-0-18-bidirectional-distsim.tagger',
'3rdparty_libs/stanford-postagger.jar')
return t2
def __init__(self):
if os.path.exists('tagger_spanish.pickle'):
with open('tagger_spanish.pickle', 'r') as file_obj:
self.tagger = pickle.load(file_obj)
else:
print 'tagger_spanish.pickle not found. Training tagger... may take a few minutes...'
from nltk import UnigramTagger, BigramTagger, TrigramTagger
from nltk.corpus import cess_esp
sents = cess_esp.tagged_sents()
unigram_tagger = UnigramTagger(sents)
bigram_tagger = BigramTagger(sents, backoff=unigram_tagger) # uses unigram tagger in case it can't tag a word
self.tagger = unigram_tagger
with open('tagger_spanish.pickle', 'w') as file_obj:
pickle.dump(self.tagger, file_obj) # Dump trained tagger
class BigramChunker(ChunkParserI):
def __init__(self, train_sentences):
train_data = [[(t, c) for w, t, c in tree2conlltags(sent)]
for sent in train_sentences]
self.tagger = BigramTagger(train_data)
def parse(self, sentence):
pos_tags = [pos for (word, pos) in sentence]
tagged_pos_tags = self.tagger.tag(pos_tags)
chunk_tags = [chunk_tag for (pos, chunk_tag) in tagged_pos_tags]
conll_tags = [(word, pos, chunk_tag)
for ((word, pos),
chunk_tag) in zip(sentence, chunk_tags)]
return conlltags2tree(conll_tags)
def trained_tagger():
"""Returns a trained trigram tagger
existing : set to True if already trained tagger has been pickled
"""
# Aggregate trained sentences for N-Gram Taggers
train_sents = nltk.corpus.brown.tagged_sents()
train_sents += nltk.corpus.conll2000.tagged_sents()
train_sents += nltk.corpus.treebank.tagged_sents()
t0 = DefaultTagger('NN')
t1 = UnigramTagger(train_sents, backoff=t0)
t2 = BigramTagger(train_sents, backoff=t1)
trigram_tagger = TrigramTagger(train_sents, backoff=t2)
pickle.dump(trigram_tagger, open(r'DataBase/trained_tagger.pkl', 'wb'))
return trigram_tagger
def train_and_save_bigram_tagger():
train_text = brown.tagged_sents()
regexp_tagger = RegexpTagger([
(r'^-?[0-9]+(.[0-9]+)?$', 'CD'), # cardinal numbers
(r'(The|the|A|a|An|an)$', 'AT'), # articles
(r'.*able$', 'JJ'), # adjectives
(r'.*ness$', 'NN'), # nouns formed from adjectives
(r'.*ly$', 'RB'), # adverbs
(r'.*s$', 'NNS'), # plural nouns
(r'.*ing$', 'VBG'), # gerunds
(r'.*ed$', 'VBD'), # past tense verbs
(r'.*', 'NN') # nouns (default)
])
unigram_tagger = UnigramTagger(train_text, backoff=regexp_tagger)
bigram_tagger = BigramTagger(train_text, backoff=unigram_tagger)
output = open('../taggers/bigram_tagger.pkl', 'wb')
dump(bigram_tagger, output, -1)
output.close()
def trained_tagger():
"""Returns a trained trigram tagger
existing : set to True if already trained tagger has been pickled
"""
if os.path.exists(os.path.join(os.getcwd(),
r"DataBase/trained_tagger.pkl")):
print("Trained Tagger File already Exists..")
return
# Aggregate trained sentences for N-Gram Taggers
train_sents = nltk.corpus.brown.tagged_sents()
train_sents += nltk.corpus.conll2000.tagged_sents()
train_sents += nltk.corpus.treebank.tagged_sents()
t0 = DefaultTagger('NN')
t1 = UnigramTagger(train_sents, backoff=t0)
t2 = BigramTagger(train_sents, backoff=t1)
trigram_tagger = TrigramTagger(train_sents, backoff=t2)
pickle.dump(trigram_tagger, open(r'DataBase/trained_tagger.pkl', 'wb'))
def __init__(self, train_sents, load=False):
if load:
print 'Loading saved tagger...',
self.load()
print 'done.'
else:
time_start = time.time()
print 'Training the tagger...'
tag_counts = Counter([t for s in train_sents for w, t in s])
default_tag = argmax(tag_counts)
def_tgr = DefaultTagger(default_tag)
af_tgr = AffixTagger(train_sents, affix_length=-3, backoff=def_tgr)
uni_tgr = UnigramTagger(train_sents, backoff=af_tgr)
bi_tgr = BigramTagger(train_sents, backoff=uni_tgr)
tri_tgr = TrigramTagger(train_sents, backoff=bi_tgr)
self.tgr = tri_tgr
print 'Done.'
time_stop = time.time()
print 'Training time: {0:.2f}s'.format(time_stop - time_start)
def prepare_toolset():
toolset = {}
patterns = [(r'^[\.1-9]+$', 'NUM'), (r'^[^a-zA-Z]+$', '.'),
(r'^[^a-zA-Z]*[a-zA-Z]+[-\'][a-zA-Z]+[^a-zA-Z]*$', 'NOUN'),
(r'^.*[a-zA-Z]+[^-a-zA-Z]+[a-zA-Z]+.*$', '.')]
train_set = brown.tagged_sents(
categories='learned', tagset='universal') + brown.tagged_sents(
categories='news', tagset='universal') + brown.tagged_sents(
categories='reviews', tagset='universal')
utgr = UnigramTagger(train=train_set, backoff=DefaultTagger('NN'))
btgr = BigramTagger(train=train_set, backoff=utgr)
ttgr = TrigramTagger(train=train_set, backoff=btgr)
toolset['tgr'] = RegexpTagger(regexps=patterns, backoff=ttgr)
toolset['sw'] = stopwords.words('english')
toolset['lr'] = WordNetLemmatizer()
toolset['wntg'] = {
'NOUN': wordnet.NOUN,
'VERB': wordnet.VERB,
'ADJ': wordnet.ADJ,
'ADV': wordnet.ADV,
'X': wordnet.NOUN
}
print('Tools Ready')
return toolset
def train_brill_tagger(train_data):
# Modules for creating the templates.
from nltk import UnigramTagger
# The brill tagger module in NLTK.
from nltk.tag.brill_trainer import BrillTaggerTrainer
from nltk import BigramTagger,UnigramTagger,TrigramTagger
import nltk
from pickle import dump
#unigram_tagger = UnigramTagger(train_data)
templates=nltk.tag.brill.fntbl37()
#Regular expression (Regex) Tagger as a default tagger
default_tagger = nltk.RegexpTagger(
[(r'^[Jj]ing', 'ABN'),
(r'^[pP]yn', 'CAV'),
(r'^[nN]ga$', '1PSG'),
(r'^[pP]hi$', '2PG'),
(r'^[pP]ha$', '2PF'),
(r'^[mM]e$', '2PM'),
(r'^[iI]$', '3PSG'),
(r'^[bB]an$', 'INP'),
(r'^[Kk]a$', '3PSF'),
(r'^[uU]$', '3PSM'),
(r'^[kK]i$', '3PPG'),
(r'(sha|da|na|hapoh|halor|ha|naduh|shaduh|hapdeng|haduh)$', 'IN'),
(r'(bad|ruh|namar|hynrei|tangba|katba|katta)$', 'COC'),
(r'(lada|haba|khnang|ynda)$', 'SUC'),
(r'(katkum|kat|pat|wat|tang|lang)$', 'AD'),
(r'(bun|baroh)$', 'QNT'),
(r'^-?[0-9]+(.[0-9]+)?$', 'CN'),
(r'(dei|long|don)$', 'CO'),
(r'^[jJ]ong$', 'POP'),
(r'^[sS]hah$', 'PAV'),
(r'^[lL]ah$', 'MOD'),
(r'^[lL]a$', 'VST'),
(r'(ym|em|khlem|nym|kam)$', 'NEG'),
(r'^hi$', 'EM'),
(r'.*lade$', 'RFP'),
(r'(dang|nang)$', 'VPP'),
(r'([uU]n|[kK]an|[kK]in|[sS]a|[yY]n|[nN]gin|[pP]hin)$', 'VFT'),
(r'(.*ngut|.*tylli)$', 'ADJ'),
(r'^[bB]a$', 'COM'),
(r'^\W+$', 'SYM'),
(r'[^a-z\W]a$', 'IN'),
(r'([vV]ote|[bB]ye|[cC]onstituency|[sS]outh)$', 'FR'),
(r'.*', 'CMN')
])
t0 = default_tagger
print(train_data)
t1 = UnigramTagger(train_data,backoff=t0)
t2 = BigramTagger(train_data,backoff=t1)
t3 = TrigramTagger(train_data,backoff=t2)
trainer = BrillTaggerTrainer(initial_tagger=t3,
templates=templates, trace=3,
deterministic=True)
brill_tagger = trainer.train(train_data,max_rules=10)
# Saving the Tagger for future use
output = open('t2.pkl', 'wb')
dump(t3, output, -1)
output.close()
return brill_tagger
def __init__(self, train_sents):
t0 = DefaultTagger('NN')
t1 = UnigramTagger(train_sents, backoff=t0)
t2 = BigramTagger(train_sents, backoff=t1)
self.tagger = TrigramTagger(train_sents, backoff=t2)
f.close()
tmp = open("/tmp/proper.txt", "w")
from nltk import DefaultTagger, UnigramTagger, BigramTagger
from nltk.corpus import brown
# This section is recompiled from the Natural Language Processing Book: http://nltk.googlecode.com/svn/trunk/doc/book/book.html
brown_news_tagged = brown.tagged_sents(categories='news') # Automatic tagging of a sentence, based on Brown News corpus
size = int(len(brown_news_tagged) * 0.9)
brown_news_train = brown_news_tagged[:size]
unigram_tagger = UnigramTagger(brown_news_train)
# Uses BigramTagger -- if it fails, it uses the UnigramTagger -- if it fails, it uses DefaultTagger
t0 = DefaultTagger('NN')
t1 = UnigramTagger(brown_news_train, backoff=t0)
tagger = BigramTagger(brown_news_train, backoff=t1)
for line in text:
tagged = tagger.tag(line.split(" "))
is_np = re.compile(r"NP")
for w in tagged:
if (is_np.match(w[1])):
#print w[0]
tmp.write(w[0] + "\n")
tmp.close()
# Sort list and remove duplicates
os.system("cat /tmp/proper.txt | sort | uniq")
#b)
#using regex from nltk.org/book/chp05.html, 4.2
patterns = [
(r'.*ing$', 'VBG'), #gerunds
(r'.*ed$', 'VBD'), #simple past
(r'.*es$', 'VBZ'), # 3rd singular present
(r'.*ould$', 'MD'), #modal
(r'.*\'s$', 'NN$'), # possessive nouns
(r'.*s$', 'NNS'), #plural nouns
(r'^-?[0-9]+(\.[0-9]+)?$', 'CD'), # cardinal numbers
(r'.*', 'NN') #nouns (default)
]
regexp_tagger = RegexpTagger(patterns)
uniB = UnigramTagger(brownT90, backoff=defaultTB90)
biB = BigramTagger(brownT90, backoff=uniB)
triB = TrigramTagger(brownT90, backoff=biB)
uniC = UnigramTagger(chatT50, backoff=defaultTChat50)
biC = BigramTagger(chatT50, backoff=uniC)
triC = TrigramTagger(chatT50, backoff=uniC)
print("Regextag50/50: ", regexp_tagger.evaluate(brownT50))
print("Default: ", defaultTB90.evaluate(brownT50))
print("Bigram Brown 50/50: ",
BigramTagger(brownT50, backoff=defaultTB50).evaluate(brownT50))
print("Default: ", defaultTB50.evaluate(brownT50))
print("Bigram Brown 90/10: ",
BigramTagger(brownT90, backoff=defaultTB90).evaluate(brownT90))
# In[17]:
display()
# ## N-Gram Tagger
# Unigram taggers assign to each wort $w_n$ the tag $t_n$, which is the most frequent tag for $w_n$ in the training corpus. N-Gram taggers are a generalization of Unigram-Taggers. During training they determine for each combination of $N-1$ previous tags $t_{n-1},t_{n-2},...$ and the current word $w_n$ the most frequent tag $t_n$. Tagging is then realized, by inspecting the $n-1$ previous tags and the current word $w_n$ and assigning the most frequent tag, which appeared for this combination in the training corpus.
# 
# In[18]:
baseline=nltk.DefaultTagger('NOUN')
unigram = UnigramTagger(train=train_sents,backoff=baseline)
bigram = BigramTagger(train=train_sents,backoff=unigram)
# In[19]:
bigram.evaluate(test_sents)
# # Find most frequent nouns
# The most frequent nouns usually provide information on the subject of a text. Below, the most frequent nouns of an already tagged text of the *Treebank*-corpus are determined. Let's see if we can conclude the text's subject.
# In[20]:
from nltk.corpus import treebank
def createModel(self):
model_name=None
try:
unigrams=self.buildUnigrams()
N=len(self.corpusSents)
toTraining=round(self.training_portion*N)
#logging.info("Sentencias totales:" + str(N))
training=self.corpusSents[:toTraining]
test=self.corpusSents[toTraining:]
post_patterns=[]
for regex,post in self.regex_list:
try:
regex=regex.decode('utf-8')
except:
pass
post_patterns.append((regex,post))
for regex,post in self.config.items('postaggers.regex'):
post_patterns.append((regex.decode('utf-8'),post))
regexpTagger = RegexpTagger(post_patterns)
unigramTagger = UnigramTagger(unigrams+training,backoff=regexpTagger)
bigramTagger= BigramTagger(training, backoff=unigramTagger)
trigramTagger = TrigramTagger(training, backoff=bigramTagger)
NTagger=NgramTagger(self.max_ngrams,training,backoff=trigramTagger)
print("Sentencias de entrenamiento para n-taggers:" + str(len(training)))
print("Sentencias de entrenamiento para unitaggers:" + str(len(unigrams)))
print("Cantidad de palabras ADICIONALES de DICCIONARIOS para el unitagger:" + str(len(unigrams)))
print("Sentencias para testing:" + str(len(test)))
print("Expresiones regulares para el Tagger:")
for post_regex in post_patterns:
print post_regex
if self.training_portion!=1:
score_ut=unigramTagger.evaluate(test)
score_bt=bigramTagger.evaluate(test)-0.002
score_tt=trigramTagger.evaluate(test)
score_nt=NTagger.evaluate(test)
scores=[score_ut,score_bt,score_tt,score_nt]
tagger_names=["uTagger","biTagger","triTagger","NTagger"]
taggers=[unigramTagger,bigramTagger,trigramTagger,NTagger]
bestTagger_index= scores.index(max(scores))
best_msg=max(scores),tagger_names[bestTagger_index]
fname=self.taggers_path + tagger_names[bestTagger_index]
if os.path.isfile(fname+self.tagger_extension_file):
fname=fname+str(len(listdir(self.taggers_path)))+self.tagger_extension_file
else:
fname=self.taggers_path + tagger_names[bestTagger_index]+self.tagger_extension_file
model=taggers[bestTagger_index]
f = open(fname,'wb')
pickle.dump(model, f)
f.close()
print ("Guardando el tagger :" + fname)
#logging.info("Guardando el mejor tagger :" + fname)
model_name=fname
except Exception,e:
print "ERRPR EN POS TAGGER GENERATOR:",str(e)
pdb.set_trace()
def __init__(self, train_sentences):
train_data = [[(t, c) for w, t, c in tree2conlltags(sent)]
for sent in train_sentences]
self.tagger = BigramTagger(train_data)
def __init__(self, train_sentences):
train_data = [[(t, c) for w, t, c in tree2conlltags(sent)]
for sent in train_sentences]
self.tagger = BigramTagger(train_data)
def createModel(self):
model_name = None
try:
unigrams = self.buildUnigrams()
N = len(self.corpusSents)
toTraining = round(self.training_portion * N)
#logging.info("Sentencias totales:" + str(N))
training = self.corpusSents[:toTraining]
test = self.corpusSents[toTraining:]
post_patterns = []
for regex, post in self.regex_list:
try:
regex = regex.decode('utf-8')
except:
pass
post_patterns.append((regex, post))
for regex, post in self.config.items('postaggers.regex'):
post_patterns.append((regex.decode('utf-8'), post))
regexpTagger = RegexpTagger(post_patterns)
unigramTagger = UnigramTagger(unigrams + training,
backoff=regexpTagger)
bigramTagger = BigramTagger(training, backoff=unigramTagger)
trigramTagger = TrigramTagger(training, backoff=bigramTagger)
NTagger = NgramTagger(self.max_ngrams,
training,
backoff=trigramTagger)
print("Sentencias de entrenamiento para n-taggers:" +
str(len(training)))
print("Sentencias de entrenamiento para unitaggers:" +
str(len(unigrams)))
print(
"Cantidad de palabras ADICIONALES de DICCIONARIOS para el unitagger:"
+ str(len(unigrams)))
print("Sentencias para testing:" + str(len(test)))
print("Expresiones regulares para el Tagger:")
for post_regex in post_patterns:
print post_regex
if self.training_portion != 1:
score_ut = unigramTagger.evaluate(test)
score_bt = bigramTagger.evaluate(test) - 0.002
score_tt = trigramTagger.evaluate(test)
score_nt = NTagger.evaluate(test)
scores = [score_ut, score_bt, score_tt, score_nt]
tagger_names = ["uTagger", "biTagger", "triTagger", "NTagger"]
taggers = [unigramTagger, bigramTagger, trigramTagger, NTagger]
bestTagger_index = scores.index(max(scores))
best_msg = max(scores), tagger_names[bestTagger_index]
fname = self.taggers_path + tagger_names[bestTagger_index]
if os.path.isfile(fname + self.tagger_extension_file):
fname = fname + str(len(listdir(
self.taggers_path))) + self.tagger_extension_file
else:
fname = self.taggers_path + tagger_names[
bestTagger_index] + self.tagger_extension_file
model = taggers[bestTagger_index]
f = open(fname, 'wb')
pickle.dump(model, f)
f.close()
print("Guardando el tagger :" + fname)
#logging.info("Guardando el mejor tagger :" + fname)
model_name = fname
except Exception, e:
print "ERRPR EN POS TAGGER GENERATOR:", str(e)
pdb.set_trace()
nltk.download('averaged_perceptron_tagger')
from nltk.corpus import wordnet as wn
from nltk.corpus import treebank, conll2000, brown, conll2002
from nltk import DefaultTagger, UnigramTagger, BigramTagger
wordnet_lemmatizer = nltk.stem.WordNetLemmatizer()
# The code below trains bigram part of speech tagger from various datasets.
train_sents = treebank.tagged_sents() + brown.tagged_sents() + conll2000.tagged_sents() + conll2002.tagged_sents()
edited_train = []
for sent in train_sents:
edited_train.append([(word.lower(),tag) for (word,tag) in sent])
t0 = DefaultTagger(None)
et1 = UnigramTagger(edited_train, backoff = t0)
et2 = BigramTagger(edited_train, backoff = et1)
# The function below converts bigram pos to wordnet pos for lemmatization
def penn_to_wn(tag):
nltk_wn_pos = {'J':wn.ADJ,'V':wn.VERB,'N':wn.NOUN,'R':wn.ADV}
try:
return nltk_wn_pos[tag[0]]
except:
return None
# The list below is a list of unwanted tokens
unwanted_tokens = ['"','!', '"', '#', '$', '%', '&', "'", '(', ')', '*', '+', ',', '-', '.', '/','”','“','–',"'s",
':', ';', '<', '=', '>', '?', '@', '[', '\\', ']', '^', '_', '`', '{', '|', '}', '~']
# The function below filters unwanted tokens from the given tokenList
def filterUnwantedCharacters(tokenList):
