对word2vec训练的model的结果操作笔记

存储、加载模型的方法如下:

>>> model.save('/tmp/mymodel')
>>> new_model = gensim.models.Word2Vec.load('/tmp/mymodel')
 
 

使用模型 
Word2vec支持数种单词相似度任务:

model.most_similar(positive=['woman', 'king'], negative=['man'], topn=1)
[('queen', 0.50882536)]
model.doesnt_match("breakfast cereal dinner lunch".split())
'cereal'
model.similarity('woman', 'man')
.73723527
 
 
1
2
3
4
5
6
 
 
1
2
3
4
5
6

可以通过以下方式来得到单词的向量:

model['computer']  # raw NumPy vector of a word
array([-0.00449447, -0.00310097,  0.02421786, ...], dtype=float32)