Merge branch 'master' of http://git.yaozhitech.com/yufeng/machine_learn

lda/train_lda.py

@@ -54,6 +54,7 @@ for line in lines:
     abstract = html.sub('', abstract, )
     train.append([word for word in jieba.cut(abstract)])
     article_info.append({"article_id":i,"__url":data[1]})
+print(article_info[:10])
 lines=[]
 print("解析结束")
 dictionary = corpora.Dictionary(train)