train_vector_model.py 文件源码

def trainDoc2Vector(sentence_count, vector_dimension):
    # train and save the model
    sentences = TaggedLineDocument('sources/splited_words.txt')
    model = Doc2Vec(sentences, size=vector_dimension, window=8, min_count=2, workers=multiprocessing.cpu_count())
    model.train(sentences, total_examples=sentence_count, epochs=model.iter)
    model.save('result/doc2vec.model')
    # save vectors
    out = open('result/doc2vec.vector', mode='w+', encoding='utf-8')
    for index in range(0, sentence_count, 1):
        docvec = model.docvecs[index]
        out.write(' '.join(str(f) for f in docvec) + "\n")

    out.close()