gensim word2vec

fromgensim.models import Word2Vec

sys.argv.append('train_200000_split.utf8')
sys.argv.append('ner_training_word2vec_200001.model')
sys.argv.append('ner_training_word2vec_200001.vector')

input_file, output_model_file, output_vector_file = sys.argv[1:4]

sentences=[]
for line in open(input_file, 'r', encoding='utf-8'):
    sentences.append(line.split(' '))

model = Word2Vec(sentences, size=128, window=5, min_count=5,
        workers=multiprocessing.cpu_count())

# trim unneeded model memory = use(much) less RAM
#model.init_sims(replace=True)
model.save(output_model_file)
model.save_word2vec_format(output_vector_file, binary=False)

end_time = time.time()
print("used time : %d s" % (end_time - start_time))

#使用word2vec
w2vModel = Word2Vec.load(word2vec_model_file)
print(word2vec_model_file)
print(w2vModel.layer1_size)
embeddingDim = w2vModel.layer1_size #vector_size
embeddingUnknown = [0 for i in range(embeddingDim)]
embeddingWeights = np.zeros((vocabSize + 3, embeddingDim))
for word, index in vocab.items():
    if word in w2vModel:
        e = w2vModel[word]
        print(word)
    else:
        print('not in model:',word)
        e = embeddingUnknown
    # print(e)
    embeddingWeights[index, :] = e