def getdataready(self,filename):
service = self.service
this = self.entity
data = service.openfile_as_soup(filename)
prepro_file = 'word2vec.prepro'
this = Service.savefile(Service.append_words(service.read_data(data,filename)),prepro_file)
print('컨트롤러에서도' + prepro_file + '생성됌표시')
return this
def loop2():
txt='tojiText.txt'
context = './data/'
stopwordTxt= 'stopword.txt'
wordlist=Service.make_wordlist(context,txt,stopwordTxt)
fontpath = 'malgun.ttf'
filename = 'tojiWordCloud.png'
imageFile ='alice_color.png'
wordDict = dict(wordlist)
Service.makeWordCloud(context,wordDict,imageFile,fontpath,filename)
filename = 'tojiBarChart.png'
Service.makeBarChart(context,wordlist,filename)
def loop3():
context = './data/'
prepro_file = 'word2vec.prepro'
filename = '문재인대통령신년사.txt'
model_filename = 'word2vec.model'
Service.create_word2vec(context,filename,prepro_file,model_filename)
model = word2vec.Word2Vec.load(model_filename)
print(type(model))
# most_similar : positive에 명시된 단어에 대하여 유사도가 높은 항목을
# topn 개만 보여 주세요.
bargraph = model.wv.most_similar(positive=['국민'], topn=10)
print(bargraph)
piegraph = model.wv.most_similar(positive=['남북'], topn=5)
print(piegraph)
Service.showGraph(bargraph)
Service.makePie(piegraph)
def __init__(self):
self.service =Service()
self.entity = Entity()
def data_analysis(self):
entity = Entity()
service = Service()
entity.fname = 'kr-Report_2018.txt'
entity.context = './data/'
service.extract_token(entity)
service.extract_hanguel()
service.conversion_token()
service.compound_noun()
entity.fname = 'stopwords.txt'
service.extract_stoword(entity)
service.filtering_text_with_stopword()
service.frequent_text()
entity.fname = 'D2Coding.ttf'
service.draw_wordcloud(entity)
def loop1():
sentence = '세일즈 우먼인 아름다운 그녀가 아버지 가방에 들어 가시나 ㅎㅎ'
Service.sentence_pos(sentence)
Service.pos_to_noun(sentence)
def loop1():
sentence = '일등급 품질인 맛있는 딸기가 비닐 하우스에 들어가시나 ㅎㅎ'
Service.sentence_pos(sentence)
Service.pos_to_noun(sentence)