在python上使用gensim Word2Vec的不同模型 [英] Different models with gensim Word2Vec on python
问题描述
我正在尝试应用在python gensim库中实现的word2vec模型.我有一个句子列表(每个句子是一个单词列表).
I am trying to apply the word2vec model implemented in the library gensim in python. I have a list of sentences (each sentences is a list of words).
例如,让我们有:
sentences=[['first','second','third','fourth']]*n
我实现了两个相同的模型:
and I implement two identical models:
model = gensim.models.Word2Vec(sententes, min_count=1,size=2)
model2=gensim.models.Word2Vec(sentences, min_count=1,size=2)
我意识到,取决于n的值,模型有时是相同的,有时是不同的.
I realize that the models sometimes are the same, and sometimes are different, depending on the value of n.
例如,如果n = 100,我得到
For instance, if n=100 I obtain
print(model['first']==model2['first'])
True
同时,对于n = 1000:
while, for n=1000:
print(model['first']==model2['first'])
False
怎么可能?
非常感谢!
推荐答案
查看 gensim
文档,运行 Word2Vec
时会有一些随机性:
Looking at the gensim
documentation, there is some randomization when you run Word2Vec
:
seed
=用于随机数生成器.每个单词的初始向量都以单词+ str(seed)的串联哈希值作为种子.请注意,对于完全确定性可重现的运行,还必须将模型限制为单个工作线程,以消除OS线程调度中的排序抖动.
seed
= for the random number generator. Initial vectors for each word are seeded with a hash of the concatenation of word + str(seed). Note that for a fully deterministically-reproducible run, you must also limit the model to a single worker thread, to eliminate ordering jitter from OS thread scheduling.
因此,如果要获得可重复的结果,则需要设置种子:
Thus if you want to have reproducible results, you will need to set the seed:
In [1]: import gensim
In [2]: sentences=[['first','second','third','fourth']]*1000
In [3]: model1 = gensim.models.Word2Vec(sentences, min_count = 1, size = 2)
In [4]: model2 = gensim.models.Word2Vec(sentences, min_count = 1, size = 2)
In [5]: print(all(model1['first']==model2['first']))
False
In [6]: model3 = gensim.models.Word2Vec(sentences, min_count = 1, size = 2, seed = 1234)
In [7]: model4 = gensim.models.Word2Vec(sentences, min_count = 1, size = 2, seed = 1234)
In [11]: print(all(model3['first']==model4['first']))
True
这篇关于在python上使用gensim Word2Vec的不同模型的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!