spark-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From YiZhi Liu <javeli...@gmail.com>
Subject Re: Ability to offer initial coefficients in ml.LogisticRegression
Date Tue, 03 Nov 2015 04:04:21 GMT
Hi Holden,

Yep the issue id is correct. It seems that you're waiting for
SPARK-11136 which Jayant is working on?

Best,
Yizhi

2015-11-03 11:14 GMT+08:00 Holden Karau <holden@pigscanfly.ca>:
> Hi YiZhi,
>
> I've been waiting on the shared param to go in (I think it was kmeans) so we
> could have a common API. I think the issue is SPARK-7852 but I am on mobile
> right now.
>
> Cheers,
>
> Holden :)
>
>
> On Monday, November 2, 2015, DB Tsai <dbtsai@dbtsai.com> wrote:
>>
>> Hi YiZhi,
>>
>> Sure. I think Holden already created a JIRA for this. Please
>> coordinate with Holden, and keep me in the loop. Thanks.
>>
>> Sincerely,
>>
>> DB Tsai
>> ----------------------------------------------------------
>> Web: https://www.dbtsai.com
>> PGP Key ID: 0xAF08DF8D
>>
>>
>> On Mon, Nov 2, 2015 at 7:32 AM, YiZhi Liu <javelinjs@gmail.com> wrote:
>> > Hi Tsai,
>> >
>> > Is it proper if I create a jira and try to work on it?
>> >
>> > 2015-10-23 10:40 GMT+08:00 YiZhi Liu <javelinjs@gmail.com>:
>> >> Thank you Tsai.
>> >>
>> >> Holden, would you mind posting the JIRA issue id here? I searched but
>> >> found nothing. Thanks.
>> >>
>> >> 2015-10-23 1:36 GMT+08:00 DB Tsai <dbtsai@dbtsai.com>:
>> >>> There is a JIRA for this. I know Holden is interested in this.
>> >>>
>> >>>
>> >>> On Thursday, October 22, 2015, YiZhi Liu <javelinjs@gmail.com>
wrote:
>> >>>>
>> >>>> Would someone mind giving some hint?
>> >>>>
>> >>>> 2015-10-20 15:34 GMT+08:00 YiZhi Liu <javelinjs@gmail.com>:
>> >>>> > Hi all,
>> >>>> >
>> >>>> > I noticed that in ml.classification.LogisticRegression, users
are
>> >>>> > not
>> >>>> > allowed to set initial coefficients, while it is supported
in
>> >>>> > mllib.classification.LogisticRegressionWithSGD.
>> >>>> >
>> >>>> > Sometimes we know specific coefficients are close to the final
>> >>>> > optima.
>> >>>> > e.g., we usually pick yesterday's output model as init coefficients
>> >>>> > since the data distribution between two days' training sample
>> >>>> > shouldn't change much.
>> >>>> >
>> >>>> > Is there any concern for not supporting this feature?
>> >>>> >
>> >>>> > --
>> >>>> > Yizhi Liu
>> >>>> > Senior Software Engineer / Data Mining
>> >>>> > www.mvad.com, Shanghai, China
>> >>>>
>> >>>>
>> >>>>
>> >>>> --
>> >>>> Yizhi Liu
>> >>>> Senior Software Engineer / Data Mining
>> >>>> www.mvad.com, Shanghai, China
>> >>>>
>> >>>> ---------------------------------------------------------------------
>> >>>> To unsubscribe, e-mail: dev-unsubscribe@spark.apache.org
>> >>>> For additional commands, e-mail: dev-help@spark.apache.org
>> >>>>
>> >>>
>> >>>
>> >>> --
>> >>> - DB
>> >>>
>> >>> Sent from my iPhone
>> >>
>> >>
>> >>
>> >> --
>> >> Yizhi Liu
>> >> Senior Software Engineer / Data Mining
>> >> www.mvad.com, Shanghai, China
>> >
>> >
>> >
>> > --
>> > Yizhi Liu
>> > Senior Software Engineer / Data Mining
>> > www.mvad.com, Shanghai, China
>
>
>
> --
> Cell : 425-233-8271
> Twitter: https://twitter.com/holdenkarau
>



-- 
Yizhi Liu
Senior Software Engineer / Data Mining
www.mvad.com, Shanghai, China

---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscribe@spark.apache.org
For additional commands, e-mail: dev-help@spark.apache.org


Mime
View raw message