1.下载维基百科数据
https://dumps.wikimedia.org/zhwiki/latest/
2.预处理文件:将压缩的文件转化成.txt文件
添加脚本文件process.py,代码如下:
import logging
import os.path
import sys
from gensim.corpora import WikiCorpus
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))
# check and process input arguments
if len(sys.argv) < 3:
print(globals()['__doc__'] % locals())
sys.exit(1)
inp, outp = s