#手作り C=np.array([ [0,1,0,0,0,0,0], [1,0,1,0,1,1,0], [0,1,0,1,0,0,0], [0,0,1,0,1,0,0], [0,1,0,1,0,0,0], [0,1,0,0,0,0,1], [0,0,0,0,0,1,0], ],dtype=np.int32) print(C[0]) print(C[4]) print(C[wordtoid['goodbye']]) vocab_size=len(wordtoid) C=create_to_matrix(corpus,vocab_size,window_size=1) #similarity c0=C[wordtoid['you']] c1=C[wordtoid['i']] print(cos_similarity(c0,c1)) #most_similar most_similar('you',wordtoid,idtoword,C,top=5) #ppmi W=ppmi(C) np.set_printoptions(precision=3) print('covariance matrix') print(C)
import sys sys.path.append('c:\\Users\\ryosh\\Python\\learn') from common.util import preprocess, create_to_matrix, most_similar text = 'You say goodbye and I say hello.' corpus, word_to_id, id_to_word = preprocess(text) vocab_size = len(word_to_id) C = create_to_matrix(corpus, vocab_size) most_similar('you', word_to_id, id_to_word, C, top=5)