files_path = "..\\corpus\\SFU_Spanish_Review_Corpus\\lavadoras"
errs = 0
pol_dict = {}
inputt = open('diccionario_polaridades.pk1', 'rb')
pol_dict = load(inputt)
inputt.close()
def lemmatize_sent(sent):
return utils.lemmatize_text(
utils.remove_unalphabetic_words(nltk.word_tokenize(sent)))
sents = []
for file_name in utils.find_all_files_in_path('*.txt', files_path):
sents += nltk.sent_tokenize(
open(file_name).read().replace('\n\n', '.').replace('\n', '.'))
print('aspect', 'pos', 'neg')
for aspect in aspects:
aspect_sent_avg_pos_count = 0
aspect_sent_avg_neg_count = 0
sents_of_aspect_count = 0
for sent in sents:
lemmatized_sent = lemmatize_sent(sent)
if (aspect in sent) or (aspect in lemmatized_sent):
sent_pos_count = 0
sent_neg_count = 0
sents_of_aspect_count += 1
for word in lemmatized_sent:
"""
import utils
from _pickle import load
from bs4 import BeautifulSoup as Soup
import gensim
import gensim.corpora as corpora
ruta_archivos = "..\\corpus\\corpusCine\\corpusCriticasCine"
sustantivos = []
inputt = open('UnigramTagger_cess_esp.pkl','rb')
unigram_tagger = load(inputt)
inputt.close()
errs = 0
data_lemmatized = []
for xml_file_name in utils.find_all_files_in_path('*.xml',ruta_archivos):
try:
handler = open(xml_file_name).read()
soup = Soup(handler,'lxml')
review = soup.find('review')
data_lemmatized.append(utils.normalize_text(review.get_text()))
except:
errs += 1
id2word = corpora.Dictionary(data_lemmatized)
corpus = [id2word.doc2bow(text) for text in data_lemmatized]
# Build LDA model
lda_model = gensim.models.ldamodel.LdaModel(corpus=corpus,
id2word=id2word,
num_topics=8,
Created on Sun Jun 2 13:58:15 2019
@author: Turing
"""
import utils
import nltk
from _pickle import load
from nltk.probability import FreqDist
ruta_archivos = "..\\corpus\\SFU_Spanish_Review_Corpus\\lavadoras"
sustantivos = []
inputt = open('UnigramTagger_cess_esp.pkl', 'rb')
unigram_tagger = load(inputt)
inputt.close()
for file_name in utils.find_all_files_in_path('*.txt', ruta_archivos):
oraciones = nltk.sent_tokenize(open(file_name).read().replace('\n', '.'))
palabras_etiquetas = unigram_tagger.tag(nltk.word_tokenize(oraciones[-1]))
sustantivos_archivo = [
sustantivo for sustantivo, tag in palabras_etiquetas
if tag.startswith('n')
]
sustantivos_archivo = utils.lemmatize_text(sustantivos_archivo)
sustantivos += sustantivos_archivo
#print(sustantivos)
fd = FreqDist(sustantivos)
print([word for word, freq in fd.most_common(10)])
sustantivos = []
errs = 0