In [ ]:

    

# -*- coding: utf-8 -*-

import sys
sys.path.append('path to normal python')
import logging
import os.path
import multiprocessing

from gensim.models import Word2Vec
from gensim.models import word2vec
#from gensim import models

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)
    logger.info("running %s" % ' '.join(sys.argv))

    inp = '/home/jeffmxh/word2vec/news_seg_all.txt'
    outp1 = 'sougou_news.model'
    outp2 = 'sougou_news.vector'
    sentences = word2vec.Text8Corpus(inp)
    model = Word2Vec(sentences, size=300, window=5, min_count=5, workers=multiprocessing.cpu_count())

    # trim unneeded model memory = use(much) less RAM
    #model.init_sims(replace=True)
    model.save(outp1)
    model.save_word2vec_format(outp2, binary=False)