무회blog

0003-Doc2vec ,방식으로 텍스트 ,코사인 유사도, 구하기-003-02¶ In [1]: # Word2Vec embedding # from gensim.models import Word2Vec from gensim.models.word2vec import Word2Vec from gensim.models import KeyedVectors from gensim.summarization import summarize from rank_bm25 import BM25Okapi from nltk import sent_tokenize, word_tokenize from konlpy.tag import Hannanum from konlpy.tag import Kkma hannanum = Hannanum() i..

In [1]: from gensim import models from collections import defaultdict from gensim import corpora from gensim import similarities import pandas as pd import time, timeit, os, sys , re , math from datetime import datetime from nltk import sent_tokenize, word_tokenize from konlpy.tag import Hannanum hannanum = Hannanum() from kiwipiepy import Kiwi kiwi = Kiwi() kiwi.prepare() # BM25 를 사용하여 코사인 유사도에..

002 - word2vec 방식으로 텍스트 코사인 유사도 구하기¶ In [1]: # Word2Vec embedding # from gensim.models import Word2Vec from gensim.models.word2vec import Word2Vec from gensim.models import KeyedVectors from gensim.summarization import summarize from rank_bm25 import BM25Okapi from nltk import sent_tokenize, word_tokenize from konlpy.tag import Hannanum from konlpy.tag import Kkma hannanum = Hannanum() import pa..

002 - word2vec 방식으로 텍스트 코사인 유사도 구하기¶ In [1]: # Word2Vec embedding # from gensim.models import Word2Vec from gensim.models.word2vec import Word2Vec from gensim.models import KeyedVectors from gensim.summarization import summarize from rank_bm25 import BM25Okapi from nltk import sent_tokenize, word_tokenize from konlpy.tag import Hannanum from konlpy.tag import Kkma hannanum = Hannanum() import pa..

class Cleaning_Text: def listToText(inputList): returnText = '' for i in inputList: returnText = returnText + i rt2 = Cleaning_Text.text_cleaning(returnText) return rt2 ## # step_4, 공통 코드 , 텍스트 클리닝 def text_cleaning(text): ################################## gensim 사용을 위한 정규표현식 200624 hangul_path9 = '[가-힣]+\.' # 한글로 포함되다 . hangul_path0 = '[가-힣]+\.[가-힣]{1}' # 한글 . + 한글 처리 h..