def main(text, model_CWI, treshold, CWI_NER, SSSG_WSD, metode, model_SR):
definition = []
#CWI
hasil_CWI = []
if CWI_NER:
hasil_CWI = cwi_main.complexWordIdentificationNER(
text, model_CWI, treshold)
else:
hasil_CWI = cwi_main.complexWordIdentification(text, model_CWI,
treshold)
print("CWI ## Hasil ", hasil_CWI)
##SSSG
hasil_SSSG = []
tenses = []
if SSSG_WSD:
for word in hasil_CWI:
try:
tenses.append(en.verb_tense(word[0].lower()))
except:
tenses.append("")
tmp = sssg_main.get_synset(metode, word[0], text)
try:
print("SSSG ## Definition", word[0], ":",
sssg_main.get_word_definition(tmp))
definition.append(word[0] + " : " +
sssg_main.get_word_definition(tmp))
except:
print("SSSG ## Definition", word[0])
try:
tmp = sssg_main.get_word_synonym(tmp)
except:
tmp = [word[0]]
hasil_SSSG.append([tmp, word[1]])
else:
for word in hasil_CWI:
hasil_SSSG.append(
[sssg_main.get_word_synonym_noWSD(word[0]), word[1]])
print("SSSG ## Hasil", hasil_SSSG)
##SR
hasil_SR = []
for words in hasil_SSSG:
tmp = sr_main.wordRanking(model_SR, words[0])
print(tmp, words)
try:
hasil_SR.append([tmp[0][0], words[1]])
except:
continue
print("SR ## Hasil", hasil_SR)
##Hasil
hasil_text = text.split()
i = 0
for word in hasil_SR:
try:
hasil_text[word[1]] = en.verb_conjugate(word[0], tense=tenses[i])
except:
hasil_text[word[1]] = word[0]
i += 1
hasil_text = " ".join(hasil_text)
#Output
print("")
print(text)
print(hasil_text)
return hasil_text, definition
# main(text, model_CWI, treshold, CWI_NER, SSSG_WSD, metode, model_SR)
def conjugate(self, word, tense="infinitive", negate=False):
return verb_lib.verb_conjugate(word, tense, negate)
def get_synonyms(self):
spacy_module = spacy.load('en')
doc = spacy_module("".join([
" " +
i if not i.startswith("'") and i not in string.punctuation else i
for i in self.token_sent
]).strip())
for token in doc:
if str(token) == self.word:
self.lemma = token.lemma_
import requests
THEASURUS_KEY = "Get your theasurus key from https://words.bighugelabs.com/site/api"
r = requests.get(url='http://words.bighugelabs.com/api/2/' +
THEASURUS_KEY + '/' + self.lemma + '/json')
if r.status_code != 404:
try:
if 'V' in self.pos:
self.synonyms = r.json()["verb"]["syn"]
self.tense = verb.verb_tense(self.word)
elif 'N' in self.pos:
try:
self.synonyms = r.json()["noun"]["syn"] + r.json(
)["noun"]["sim"]
except:
self.synonyms = r.json()["noun"]["syn"]
elif 'J' in self.pos:
try:
self.synonyms = r.json()["adjective"]["syn"] + r.json(
)["adjective"]["sim"]
except:
self.synonyms = r.json()["adjective"]["syn"]
elif 'RB' in self.pos:
try:
self.synonyms = r.json()["adverb"]["syn"] + r.json(
)["adverb"]["sim"]
except:
self.synonyms = r.json()["adverb"]["syn"]
except:
total_list = []
for pos in r.json():
for type_ in r.json()[pos]:
total_list.append(r.json()[pos][type_])
self.synonyms = [
item for sublist in total_list for item in sublist
]
self.synonyms = [x.split(' ') for x in self.synonyms]
temp_set = []
for word in self.synonyms:
temp_set.append(word[0])
temp_set = set(temp_set)
temp_set = [[x] for x in temp_set]
self.synonyms = temp_set
if self.is_plural == True:
p = inflect.engine()
all_synonyms = []
for synonym in self.synonyms:
new_synonyms = []
for word in synonym:
if p.singular_noun(word) is False:
new_synonyms.append(plural.noun_plural(word))
else:
new_synonyms.append(word)
all_synonyms.append(new_synonyms)
self.synonyms = all_synonyms
if self.tense != None:
tense_synonyms = []
for x in self.synonyms:
multi_word = []
for element in x:
try:
multi_word.append(
(verb.verb_conjugate(element,
tense=self.tense,
negate=False)))
except:
multi_word.append(element)
tense_synonyms.append(multi_word)
self.synonyms = tense_synonyms
def get_synonyms(self):
spacy_module = spacy.load('en_core_web_sm')
doc = spacy_module("".join([
" " +
i if not i.startswith("'") and i not in string.punctuation else i
for i in self.token_sent
]).strip())
for token in doc:
if str(token) == self.word:
self.lemma = token.lemma_
if self.lemma == None:
self.synonyms = []
return
import requests
##6c6bbfe357c61dcc40b628419778ebd7
##ce218b46b8d46a30bebc843f4da120d8
r = requests.get(
url=
'http://words.bighugelabs.com/api/2/6c6bbfe357c61dcc40b628419778ebd7/'
+ self.lemma + '/json')
if r.status_code != 404:
try:
#print("----------")
#print(r.json())
if type(r.json()) == list:
self.synonyms = r.json()
elif 'V' in self.pos:
self.synonyms = r.json()["verb"]["syn"]
self.tense = verb.verb_tense(self.word)
elif 'N' in self.pos:
try:
self.synonyms = r.json()["noun"]["syn"] + r.json(
)["noun"]["sim"]
except:
self.synonyms = r.json()["noun"]["syn"]
elif 'J' in self.pos:
try:
self.synonyms = r.json()["adjective"]["syn"] + r.json(
)["adjective"]["sim"]
except:
self.synonyms = r.json()["adjective"]["syn"]
elif 'RB' in self.pos:
try:
self.synonyms = r.json()["adverb"]["syn"] + r.json(
)["adverb"]["sim"]
except:
self.synonyms = r.json()["adverb"]["syn"]
except:
total_list = []
for pos in r.json():
for type_ in r.json()[pos]:
total_list.append(r.json()[pos][type_])
self.synonyms = [
item for sublist in total_list for item in sublist
]
if self.synonyms == None:
return
self.synonyms = [x.split(' ') for x in self.synonyms]
temp_set = []
for word in self.synonyms:
temp_set.append(word[0])
temp_set = set(temp_set)
temp_set = [[x] for x in temp_set]
self.synonyms = temp_set
if self.is_plural == True:
p = inflect.engine()
all_synonyms = []
for synonym in self.synonyms:
new_synonyms = []
for word in synonym:
if p.singular_noun(word) is False:
new_synonyms.append(plural.noun_plural(word))
else:
new_synonyms.append(word)
all_synonyms.append(new_synonyms)
self.synonyms = all_synonyms
if self.tense != None:
tense_synonyms = []
for x in self.synonyms:
multi_word = []
for element in x:
try:
multi_word.append(
(verb.verb_conjugate(element,
tense=self.tense,
negate=False)))
except:
multi_word.append(element)
tense_synonyms.append(multi_word)
self.synonyms = tense_synonyms