#!/usr/bin/env python

from gensim.models import Word2Vec

sentences = [['first', 'sentence'], ['second', 'sentence']]
# train word2vec on the two sentences
model = gensim.models.Word2Vec(sentences, min_count=1)

#or with different options
model = Word2Vec(sentences, size=100, window=5, min_count=5, workers=4)

#Persist a model to disk with:
model.save(fname)


#Advanced users can load a model and continue training it with more sentences: 
model = gensim.models.Word2Vec.load('/tmp/mymodel')
model.train(more_sentences)
 

A more effective way...load sentences from a text file:

 

#!/usr/bin/env python

from gensim.models import Word2Vec

   
class MySentences(object):
 def __init__(self, dirname):
     self.dirname = dirname

 def __iter__(self):
     for fname in os.listdir(self.dirname):
         for line in open(os.path.join(self.dirname, fname)):
             yield line.split()
sentences = MySentences('/some/directory') # a memory-friendly iterator
model = gensim.models.Word2Vec(sentences)

Load an existing model, for example the “text8” corpus that can be downloaded from http://mattmahoney.net/dc/text8.zip .

 

#!/usr/bin/env python

from gensim.models import Word2Vec

   
#model = Word2Vec.load(path/to/your/model)

#model = Word2Vec.load_word2vec_format('/tmp/vectors.txt', binary=False)  # C text format
model = Word2Vec.load_word2vec_format('GoogleNews-vectors-negative300.bin', binary=True)  # C binary format

Some examples of use:

 

  
print model.similarity('france', 'spain')


print model.most_similar_cosmul(positive=['baghdad', 'england'], negative=['london'])


print model.n_similarity(['sushi', 'shop'], ['japanese', 'restaurant'])

print model.n_similarity(['restaurant', 'japanese'], ['japanese', 'restaurant'])

print model.n_similarity(['sushi'], ['restaurant']) == model.similarity('sushi', 'restaurant')

print model.most_similar(positive=['woman', 'king'], negative=['man'], topn=1)
print model.doesnt_match("breakfast cereal dinner lunch".split())
print model.similarity('woman', 'man')

model.most_similar(['man'])