def __init__(self, backoff=None):
"""Setup for SequentialBackoffLemmatizer()
:param backoff: Next lemmatizer in backoff chain.
"""
LemmatizerI.__init__(self)
SequentialBackoffTagger.__init__(self, backoff)
def __init__(self, list_of_drugs, backoff=None):
SequentialBackoffTagger.__init__(self, backoff)
drug_list = [ x.strip() for x in open(list_of_drugs, 'r')]
self.drugs = {}
# HashTable it for O(1) lookup
for drug in drug_list:
self.drugs[drug] = 1
def __init__(self, backoff=None):
"""Setup for SequentialBackoffLemmatizer()
:param backoff: Next lemmatizer in backoff chain.
"""
LemmatizerI.__init__(self)
SequentialBackoffTagger.__init__(self, backoff)
def __init__(self, list_of_drugs, backoff=None):
SequentialBackoffTagger.__init__(self, backoff)
drug_list = [x.strip() for x in open(list_of_drugs, 'r')]
self.drugs = {}
# HashTable it for O(1) lookup
for drug in drug_list:
self.drugs[drug] = 1
def __init__(self, *args, **kwargs):
SequentialBackoffTagger.__init__(self, *args, **kwargs)
coca_path = os.path.join(os.path.dirname(__file__),
'../data/coca_500k.csv')
coca_list = csv.reader(open(coca_path), delimiter='\t')
self.tag_map = dict()
for row in coca_list:
freq = int(row[0])
word = row[1].strip()
pos = row[2].strip()
self.insertPair(word, pos, freq)
def __init__(self, *args, **kwargs):
SequentialBackoffTagger.__init__(self, *args, **kwargs)
# maps wordnet tags to claws7 tags
self.wordnet_tag_map = {
'n': 'nn',
's': 'jj',
'a': 'jj',
'r': 'rr',
'v': 'vv0'
}
self.wordnet = wordnet
def __init__(self, *args, **kwargs):
SequentialBackoffTagger.__init__(self, *args, **kwargs)
self.dist = FreqDist()
# train_sents = brown.tagged_sents()
train_sents = pickle.load(open("pickles/brown_clawstags.pickle"))
# 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(default_tagger)
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 __init__(self: object, backoff: object, verbose: bool = False):
"""
Setup for SequentialBackoffLemmatizer
:param backoff: Next lemmatizer in backoff chain
:param verbose: Flag to include which lemmatizer assigned in a given tag in the return tuple
"""
SequentialBackoffTagger.__init__(self, backoff=None)
# Setup backoff chain
if backoff is None:
self._taggers = [self]
else:
self._taggers = [self] + backoff._taggers
self.VERBOSE = verbose
self.repr = reprlib.Repr()
self.repr.maxlist = 1
self.repr.maxdict = 1
def __init__(self: object, backoff: object, verbose: bool = False):
"""
Setup for SequentialBackoffLemmatizer
:param backoff: Next lemmatizer in backoff chain
:type verbose: bool
:param verbose: Flag to include which lemmatizer assigned in
a given tag in the return tuple
"""
SequentialBackoffTagger.__init__(self, backoff=None)
# Setup backoff chain
if backoff is None:
self._taggers = [self]
else:
self._taggers = [self] + backoff._taggers
self.VERBOSE = verbose
self.repr = reprlib.Repr()
self.repr.maxlist = 1
self.repr.maxdict = 1
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 __init__(self, train=None):
self._morph = pymorphy2.MorphAnalyzer()
SequentialBackoffTagger.__init__(self, None)
def __init__(self, *args, **kwargs):
SequentialBackoffTagger.__init__(self, *args, **kwargs)
def __init__(self, train=None):
self._morph = pymorphy2.MorphAnalyzer()
SequentialBackoffTagger.__init__(self, None)
