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)