gensim之word2vec增量训练

word2vec增量训练
python word2vec_add.py patent.model new_patent.txt patent_new.model patent_new.vector

import logging
import os.path
import sys
from gensim.models import Word2Vec
from gensim.models.word2vec import LineSentence

if __name__ == '__main__':
    program = os.path.basename(sys.argv[0])

    logger = logging.getLogger(program)
    logging.basicConfig(format='%(asctime)s: %(levelname)s: %(message)s')
    logging.root.setLevel(level=logging.INFO)

    logging.info('running %s' % ' '.join(sys.argv))

    if len(sys.argv) < 5:
        print(globals()['__doc__'] % locals())

    '''
    	model_path:已有模型对，对应patent.model
        inp:增加分好词的数据，对应new_patent.txt
        output_model:新保存的模型，对应patent_new.model
        output_txt:保存的词向量，对应patent_new.vector
    '''
    model_path, inp, output_model, output_txt = sys.argv[1:4]

    sentences = LineSentence(inp)
    model = Word2Vec.load(model_path)
    
    model.build_vocab(sentences, update=True)
    model.train(sentences, total_examples=2000000, epochs=5)
    model.save(output_model)
    
    model.wv.save_word2vec_format(output_txt, binary=False)