Python Gensim Word2vec

Getting started

• 系统及包的版本
• ubuntu 16.04
• Python 3.5
• Numpy 1.14.0
• Scipy 1.1.0
• gensim 3.4.0
• jieba 0.39

Install Gensim

pip3 install gensim

Demo

1. 英文

import gensim
from gensim.models import Word2Vec

# define training data
sentences = [['this','is','first','sentence','for','word2vec'],
            ['this','is','the','second','sentence'],
            ['yet','another','sentence'],
            ['one','more','sentence'],
            ['and','the','final','sentence']]

# train model: 2 approaches
print('----------------------------------------------')
# approach 1: using Word2Vec directly
model = Word2Vec(sentences, min_count=1, size=100)
# appraoch 2: 3 steps
model = Word2Vec(size=100, min_count=1) # build a null model
model.build_vocab(sentence) # build vocabs
model.train(sentence,total_examples=model.corpus_count, epochs=model.epochs) # train the model
print('------------------------