#coding:utf8
from gensim.models.word2vec import Word2Vec
from gensim.models.word2vec import LineSentence
import AIKnowledgeMap.nlp.Word2Vec.getPath as getPath
def train(filepath):
sentences = LineSentence(filepath)
model = Word2Vec(sentences,size=100,window=8,min_count=10,sg=1,workers=4)
model.save(getPath.get_root()+"/model/WordEmbedding_chs_100d.vec")
for v,s in model.most_similar("三"):
print(v,s)
def loadModel(filepath):
#model = KeyedVectors().load_word2vec_format(filepath,binary=False)
model = Word2Vec.load(filepath)
return model
if __name__=="__main__":
#train("D:/wiki_space.txt")
''''''
model = loadModel(getPath.get_root()+"/model/WordEmbedding_chs_100d.vec")
for v,s in model.most_similar("3"):
print(v,s)
