gensim之word2vec训练词向量

pip install gensim
python word2vec.py patent.txt patent.model patent.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) < 4:
        print(globals()['__doc__'] % locals())

    '''
        inp:分好词的数据，对应patent.txt
        output_model:保存的模型，对应patent.model 
        output_txt:保存的词向量，patent.vector
    '''
    inp, output_model, output_txt = sys.argv[1:4]

    model = Word2Vec(LineSentence(inp), size=768, window=5, sg=1, min_count=2)
    model.save(output_model)
    model.wv.save_word2vec_format(output_txt, binary=False)