SILVERCitYz

참고자료: https://towardsdatascience.com/word2vec-from-scratch-with-numpy-8786ddd49e72 import re def tokenize(text): # obtains tokens with a least 1 alphabet pattern = re.compile(r'[A-Za-z]+[\w^\']*|[\w^\']*[A-Za-z]+[\w^\']*') return pattern.findall(text.lower()) def mapping ( text ) : word_to_id = {} id_to_word = {} for i, word in enumerate(set(text)) : word_to_id[word] = i id_to_word[i] = word ret..