Word2Vec模块
from gensim.models import Word2Vec,KeyedVectors#训练model=Word2Vec([a,b,c],size,window,min_count,workers)#a,b,c 是分词后的list#size是embedding size#min_count是最小词频#保存model.wv.save_word2vec_format('...bin',binary=Ture)#加载model=KeyedVectors.laod_word2vec_format('...bin',binary=Ture,unicode_erros='ignore')#vocab查看model.vocab.keys()#embedding 查询model[word]#相似度查询model.similarity(word1,word2)#近义词和反义词相似度最接近的词查询model.most_similar(positive,negative,top)#计算与其他word相似度最低的model.doesnt_match([word1,word2,..])
若有收获，就点个赞吧
0 人点赞
