word2vector体验

参见：http://www.52nlp.cn/%E4%B8%AD%E8%8B%B1%E6%96%87%E7%BB%B4%E5%9F%BA%E7%99%BE%E7%A7%91%E8%AF%AD%E6%96%99%E4%B8%8A%E7%9A%84word2vec%E5%AE%9E%E9%AA%8C

1  install python3 opencc

 brew install python3 opencc

2 download zhwiki-latest-pages-articles2.xml.bz2

3 抽取xml为文本文字

python process.py zhwiki-latest-pages-articles2.xml.bz2 test.txt

4 optional
opencc -i  test.txt -o test_simple.txt -c t2s.json
5
  from test_simple.txt (test.txt)  to testjieba.txt by TestJieba.py 
import jieba
import jieba.analyse
import jieba.posseg as pseg
import codecs,sys
def cut_words(sentence):
    #print sentence
    return " ".join(jieba.cut(sentence)).encode('utf-8')
f=codecs.open('test.txt','r',encoding="utf8")
target = codecs.open("testjieba.txt", 'w',encoding="utf8")
print ('open files')
line_num=1
line = f.readline()
while line:
    print('---- processing ', line_num, ' article----------------')
    line_seg = " ".join(jieba.cut(line))
    target.writelines(line_seg)
    line_num = line_num + 1
    line = f.readline()
f.close()
target.close()
exit()
while line:
    curr = []
    for oneline in line:
        #print(oneline)
        curr.append(oneline)
    after_cut = map(cut_words, curr)
    target.writelines(after_cut)
    print ('saved',line_num,'articles')
    exit()
    line = f.readline1()
f.close()
target.close()

# python Testjieba.py

5

python word2vec_model.py testjieba.txt wiki.zh.text.model wiki.zh.text.vector
import logging
import os.path
import sys
import multiprocessing
from gensim.corpora import WikiCorpus
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)
    logger.info("running %s" % ' '.join(sys.argv))
    # check and process input arguments
    if len(sys.argv) < 4:
        print (globals()['__doc__'] % locals())
        sys.exit(1)
    inp, outp1, outp2 = sys.argv[1:4]
    model = Word2Vec(LineSentence(inp), size=400, window=5, min_count=5, workers=multiprocessing.cpu_count())
    model.save(outp1)
    model.model.wv.save_word2vec_format(outp2, binary=False)
#python word2vec_model.py testjieba.txt wiki.zh.text.model wiki.zh.text.vector
#opencc -i test.txt -o test_simple.txt -c t2s.json