def filter_pos_infinitive(self, s, category_list=[], allowed=False):
'''
Filters grammatical categories (pos:Part-of-Speech tags) from a string
and converts to infinitive, predicative and singularized forms words:
If allowed is set to True it only allows POS in category_list.
If allowed is set to False it allows all POS except those in category_list
POS that can be in category list:
nouns = ['NN', 'NNS', 'NNP', 'NNPS']
verbs = ['VB', 'VBD', 'VBG', 'VBN', 'VBP', 'VBZ']
adjectives = ['JJ','JJR','JJS']
determiners = ['DT']
conjunctions = ['IN', 'CC']
adverbs = ['RB','RBR', 'RBS']
modals = ['MD']
utterances = ['UH']
In:
(s:string, category_list:list of strings, allowed:boolean)
Out:
(string)
'''
if isinstance(s, str):
s = unicode(s, "utf-8", "xmlcharrefreplace")
list = []
pos_list = self.pos_tagging(s)
if len(category_list) == 0:
return s
if allowed == False:
for pos in pos_list:
if pos.split(':')[1] not in category_list:
if pos.split(':')[1] in ['NNS']:
word = singularize(pos.split(':')[0])
list.append(word)
elif pos.split(':')[1] in ['VB', 'VBD', 'VBG', 'VBN', 'VBP', 'VBZ']:
word = conjugate(pos.split(':')[0], INFINITIVE)
list.append(word)
elif pos.split(':')[1] in ['JJ','JJR','JJS']:
word = predicative(pos.split(':')[0])
list.append(word)
else:
list.append(pos.split(':')[0])
else:
for pos in pos_list:
if pos.split(':')[1] in category_list:
if pos.split(':')[1] in ['NNS']:
word = singularize(pos.split(':')[0])
list.append(word)
elif pos.split(':')[1] in ['VB', 'VBD', 'VBG', 'VBN', 'VBP', 'VBZ']:
word = conjugate(pos.split(':')[0], INFINITIVE)
list.append(word)
elif pos.split(':')[1] in ['JJ','JJR','JJS']:
word = predicative(pos.split(':')[0])
list.append(word)
else:
list.append(pos.split(':')[0])
return u' '.join(list)
def pos_tagging_infinitive(self, s):
'''
Grammatical category of each word a.k.a. Part-of-Speech (pos) tagging,
but transformming adjectives to predicative form, singularizing nouns and
verbs to infinitive form
ej. ella:PRP maneja:VBD carros:NNS rojos:JJ
PRP: Possesive pronoun ---> ella
VBD: Verb in past tense ----> manejar(infinitive)
NNS: Noun in plural --------> carro (singularized)
JJ: adjective --------------> rojo (predicative)
In:
(s:string) string text
Out:
(list) list with grammatical categories in the form 'word:category'
'''
categories = parse(s)
list = []
if isinstance(s, str):
s = unicode(s, "utf-8", "xmlcharrefreplace")
for x in categories.split():
for y in x:
if y[1] in ['NNS']:
word = singularize(y[0])
list.append(word+":NN")
elif y[1] in ['VB', 'VBD', 'VBG', 'VBN', 'VBP', 'VBZ']:
word = conjugate(y[0], INFINITIVE)
list.append(word+":VB")
elif y[1] in ['JJ','JJR','JJS']:
word = predicative(y[0])
list.append(word+":JJ")
else:
list.append(y[0]+':'+y[1])
return list
def test_predicative(self):
# Assert the accuracy of the predicative algorithm ("horribles" => "horrible").
from pattern.db import Datasheet
test = {}
for w, lemma, tag, f in Datasheet.load(os.path.join(PATH, "corpora", "wordforms-es-davies.csv")):
if tag == "j": test.setdefault(lemma, []).append(w)
i, n = 0, 0
for pred, attr in test.items():
attr = sorted(attr, key=len, reverse=True)[0]
if es.predicative(attr) == pred:
i += 1
n += 1
self.assertTrue(float(i) / n > 0.92)
print("pattern.es.predicative()")
def test_predicative(self):
# Assert the accuracy of the predicative algorithm ("horribles" => "horrible").
from pattern.db import Datasheet
test = {}
for w, lemma, tag, f in Datasheet.load(os.path.join(PATH, "corpora", "wordforms-es-davies.csv")):
if tag == "j": test.setdefault(lemma, []).append(w)
i, n = 0, 0
for pred, attr in test.items():
attr = sorted(attr, key=len, reverse=True)[0]
if es.predicative(attr) == pred:
i += 1
n += 1
self.assertTrue(float(i) / n > 0.92)
print "pattern.es.predicative()"
def unify_tokens(self):
"""
Singuralizes nouns, conjugates verbs to infinitive and passes adjectives to
predicative form in tokens
:return: Tokens
"""
if self._analysis is None:
raise Exception('It\'s necessary execute first analize')
for i in range(len(self._tokens)):
if self._analysis[i][1][0] == 'n':
self._tokens[i] = singularize(self._tokens[i])
elif self._analysis[i][1][0] == 'v':
self._tokens[i] = conjugate(self._tokens[i], INFINITIVE)
elif self._analysis[i][1][0] == 'a':
self._tokens[i] = predicative(self._tokens[i])
return self._tokens
def unify_tokens(self):
"""
Singuralizes nouns, conjugates verbs to infinitive and passes adjectives to
predicative form in tokens
:return: Tokens
"""
if self._analysis is None:
raise Exception('It\'s necessary execute first analize')
for i in range(len(self._tokens)):
if self._analysis[i][1][0] == 'n':
self._tokens[i] = singularize(self._tokens[i])
elif self._analysis[i][1][0] == 'v':
self._tokens[i] = conjugate(self._tokens[i], INFINITIVE)
elif self._analysis[i][1][0] == 'a':
self._tokens[i] = predicative(self._tokens[i])
return self._tokens
def adjetives():
print(predicative('hermosos'))
print(attributive('hermoso', gender=FEMALE + PLURAL))
def standard_value(value):
clean_value=predicative(value.lower().strip())
return clean_value
