Nonparamtric - Semiparametric API

Previous Topic Next Topic
 
classic Classic list List threaded Threaded
6 messages Options
Reply | Threaded
Open this post in threaded view
|

Nonparamtric - Semiparametric API

Vincent Grunert
Hi,

I am just working on non- and semiparametric models and came to realize that there
is quite a bit of potential for developement in that area.

It would be great to develop a kernel, polynomial etc. regression API.

Anybody else interested?

bw

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.
Reply | Threaded
Open this post in threaded view
|

Re: Nonparamtric - Semiparametric API

Milan Bouchet-Valat
Le vendredi 04 septembre 2015 à 08:35 -0700, Vincent Grunert a écrit :

> Hi,
>
> I am just working on non- and semiparametric models and came to
> realize that there
> is quite a bit of potential for developement in that area.
>
> It would be great to develop a kernel, polynomial etc. regression
> API.
>
> Anybody else interested?
I suspect many people would be interested in using it. Or probably your
question was about people interested in developing it? ;-)

More seriously, I think you'll find people to discuss the API to
integrate it with the rest of the stats packages. Have a look at the
issues at https://github.com/JuliaStats/Roadmap.jl/issues
and in particular at the one about regression.

You can open a more specific issue about semi- and non-parametric
regression, with a draft design if you want feedback.


Regards

> bw
> --
> You received this message because you are subscribed to the Google
> Groups "julia-stats" group.
> To unsubscribe from this group and stop receiving emails from it,
> send an email to [hidden email].
> For more options, visit https://groups.google.com/d/optout.

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.
Reply | Threaded
Open this post in threaded view
|

Re: Nonparamtric - Semiparametric API

Vincent Grunert
In reply to this post by Vincent Grunert
Well my question was actually both, interest and interest in development.

The point is that I was tying to run a simple kernel regression and as far as I aware of,
the KernelDensity package does not provide an interface to these kind of computations.

I have not developed a larger project like this myself yet. Hence I would need someone with
experience development of such an API. I would definitely participate in the programming but to do it right, there should be someone with
experience in developing an API. 

Thanks for the recommendation. I will post my request there.

On Friday, September 4, 2015 at 5:35:56 PM UTC+2, Vincent Grunert wrote:
Hi,

I am just working on non- and semiparametric models and came to realize that there
is quite a bit of potential for developement in that area.

It would be great to develop a kernel, polynomial etc. regression API.

Anybody else interested?

bw

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.
Reply | Threaded
Open this post in threaded view
|

Re: Nonparamtric - Semiparametric API

jock.lawrie
Also take a look at KernelEstimator.jl
Not sure how actively maintained this package is but is may provide some API hints.
Perhaps combine your efforts?


On Saturday, September 5, 2015 at 7:42:09 PM UTC+10, Vincent Grunert wrote:
Well my question was actually both, interest and interest in development.

The point is that I was tying to run a simple kernel regression and as far as I aware of,
the KernelDensity package does not provide an interface to these kind of computations.

I have not developed a larger project like this myself yet. Hence I would need someone with
experience development of such an API. I would definitely participate in the programming but to do it right, there should be someone with
experience in developing an API. 

Thanks for the recommendation. I will post my request there.

On Friday, September 4, 2015 at 5:35:56 PM UTC+2, Vincent Grunert wrote:
Hi,

I am just working on non- and semiparametric models and came to realize that there
is quite a bit of potential for developement in that area.

It would be great to develop a kernel, polynomial etc. regression API.

Anybody else interested?

bw

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.
Reply | Threaded
Open this post in threaded view
|

Re: Nonparamtric - Semiparametric API

Vincent Grunert
Thanks for the tipp.

On Monday, September 7, 2015 at 1:55:26 AM UTC+2, [hidden email] wrote:
Also take a look at <a href="https://github.com/panlanfeng/KernelEstimator.jl" target="_blank" rel="nofollow" onmousedown="this.href=&#39;https://www.google.com/url?q\75https%3A%2F%2Fgithub.com%2Fpanlanfeng%2FKernelEstimator.jl\46sa\75D\46sntz\0751\46usg\75AFQjCNEUhWyVYzha1Fw8xkKDaTbBDbg5sA&#39;;return true;" onclick="this.href=&#39;https://www.google.com/url?q\75https%3A%2F%2Fgithub.com%2Fpanlanfeng%2FKernelEstimator.jl\46sa\75D\46sntz\0751\46usg\75AFQjCNEUhWyVYzha1Fw8xkKDaTbBDbg5sA&#39;;return true;">KernelEstimator.jl
Not sure how actively maintained this package is but is may provide some API hints.
Perhaps combine your efforts?


On Saturday, September 5, 2015 at 7:42:09 PM UTC+10, Vincent Grunert wrote:
Well my question was actually both, interest and interest in development.

The point is that I was tying to run a simple kernel regression and as far as I aware of,
the KernelDensity package does not provide an interface to these kind of computations.

I have not developed a larger project like this myself yet. Hence I would need someone with
experience development of such an API. I would definitely participate in the programming but to do it right, there should be someone with
experience in developing an API. 

Thanks for the recommendation. I will post my request there.

On Friday, September 4, 2015 at 5:35:56 PM UTC+2, Vincent Grunert wrote:
Hi,

I am just working on non- and semiparametric models and came to realize that there
is quite a bit of potential for developement in that area.

It would be great to develop a kernel, polynomial etc. regression API.

Anybody else interested?

bw

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.
Reply | Threaded
Open this post in threaded view
|

Re: Nonparamtric - Semiparametric API

Lanfeng Pan
KernelEstimator.jl provides the regular as well as bounded kernel density estimate. There are also local constant and local linear regression estimator. 

Currently there is no semi-parametric support. 


Best,
Lanfeng



On Monday, September 7, 2015 at 1:00:47 AM UTC-5, Vincent Grunert wrote:
Thanks for the tipp.

On Monday, September 7, 2015 at 1:55:26 AM UTC+2, [hidden email] wrote:
Also take a look at <a href="https://github.com/panlanfeng/KernelEstimator.jl" rel="nofollow" target="_blank" onmousedown="this.href=&#39;https://www.google.com/url?q\75https%3A%2F%2Fgithub.com%2Fpanlanfeng%2FKernelEstimator.jl\46sa\75D\46sntz\0751\46usg\75AFQjCNEUhWyVYzha1Fw8xkKDaTbBDbg5sA&#39;;return true;" onclick="this.href=&#39;https://www.google.com/url?q\75https%3A%2F%2Fgithub.com%2Fpanlanfeng%2FKernelEstimator.jl\46sa\75D\46sntz\0751\46usg\75AFQjCNEUhWyVYzha1Fw8xkKDaTbBDbg5sA&#39;;return true;">KernelEstimator.jl
Not sure how actively maintained this package is but is may provide some API hints.
Perhaps combine your efforts?


On Saturday, September 5, 2015 at 7:42:09 PM UTC+10, Vincent Grunert wrote:
Well my question was actually both, interest and interest in development.

The point is that I was tying to run a simple kernel regression and as far as I aware of,
the KernelDensity package does not provide an interface to these kind of computations.

I have not developed a larger project like this myself yet. Hence I would need someone with
experience development of such an API. I would definitely participate in the programming but to do it right, there should be someone with
experience in developing an API. 

Thanks for the recommendation. I will post my request there.

On Friday, September 4, 2015 at 5:35:56 PM UTC+2, Vincent Grunert wrote:
Hi,

I am just working on non- and semiparametric models and came to realize that there
is quite a bit of potential for developement in that area.

It would be great to develop a kernel, polynomial etc. regression API.

Anybody else interested?

bw

--
You received this message because you are subscribed to the Google Groups "julia-stats" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].
For more options, visit https://groups.google.com/d/optout.