Yes,

 

We already used ALS in our production environment, we also want to try SVD++ 
but it has no python interface.

 

Any idea? Thanks

 

-Allen

 

发件人: Yanbo Liang [mailto:yblia...@gmail.com] 
发送时间: 2015年12月3日 10:30
收件人: 张志强(旺轩)
抄送: dev@spark.apache.org
主题: Re: query on SVD++

 

You means the SVDPlusPlus in GraphX? If you want to use SVD++ to train CF 
model, I recommend you to use ALS which is more efficiency and has python 
interface.

 

2015-12-02 11:21 GMT+08:00 张志强(旺轩) <zzq98...@alibaba-inc.com>:

Hi All,

 

I came across the SVD++ algorithm implementation in Spark code base, but I was 
wondering why we didn’t expose the scala api interface to python?

Any plan to do this?

 

BR,

-Allen Zhang

 

Reply via email to