def get_stopwords(self):
lang = self.args.get('lang_code')
return StopWords.get_stop_words(lang)
grams = self.generate_ngrams(tokens, 3)
grams.extend(self.generate_ngrams(tokens, 2))
for word in grams:
if word not in stop_tokens:
doc_grams.append(space_join(word))
pattern = r'<VERB>?<ADV>*<VERB>+'
doc = textacy.Doc(sentence, lang=model)
lists = textacy.extract.pos_regex_matches(doc, pattern)
verbs_list = []
for l in lists:
verb_tokens = l.lemma_.split()
for verb in verb_tokens:
if verb not in stop_tokens and self.is_valid_word(verb):
verbs_list.append(verb)
return doc_grams, unigrams, verbs_list
def generate_ngrams(self, tokens, n):
return list(ngrams(tokens, n))
if __name__ == "__main__":
a = 'How does the e-monies NEFT service differ from RGTS and EFT?'
from StopWords import StopWords
from StringProcessor import StringProcessor
a = StringProcessor().normalize(a, 'en')
en = StopWords.get_stop_words('en')
cl = PhraseFinder()
print(cl.find_phrases(a, en))
