hi Joly,
I actually have a few questions:
Firstly, regarding the implementation of sparse functions. _tree.pxy is the
back end cython code to handle the operations Splitting, Evaluating
impurities at nodes and then constructing the tree. The basic
implementation that i have in mind is that we duplicate the splitter
classes and The tree architecture itself. At each leaf node we might have a
sparse matrix representing the output data and at every non-leaf node,
splitting should be done on the sparse matrix at that node and produce few
other nodes with sparse output. So the project boils down to implementing
good access and construction methods for sparse matrices in cython. I just
want to know if this is a possible implementation criterion ?. And i would
also like to know the implementation plan that you have in mind ?
Secondly, In my previous mail i have shown you my contributions. I would
just like to know if the patches are upto the mark for a selection. If they
are, i will turn my attention to the DT sparse problem, else i will work on
the issues a bit more.
On Tue, Mar 11, 2014 at 1:12 PM, Arnaud Joly <a.j...@ulg.ac.be> wrote:
> Thanks for your contribution.
>
> Keep up!
>
> Arnaud
>
> On 10 Mar 2014, at 23:51, vamsi kaushik <kaushik.varana...@gmail.com>
> wrote:
>
> My name is actually Varanasi Vamsi Kaushik(yeah its pretty long).
>
> And i have already contributed a little.
> Please take a look at :
>
> https://github.com/scikit-learn/scikit-learn/pull/2905
>
> and also:
> https://github.com/scikit-learn/scikit-learn/pull/2895
> https://github.com/scikit-learn/scikit-learn/issues/2727
>
> cheers,
> kaushik
>
>
> On Tue, Mar 11, 2014 at 3:13 AM, vamsi kaushik <
> kaushik.varana...@gmail.com> wrote:
>
>> hi Arnaud,
>>
>> Vamsi kaushik is actually me.
>> Thanks for your reply, i'll get to the issue soon
>>
>> cheers,
>> vamsi kaushik
>>
>>
>> On Mon, Mar 10, 2014 at 3:16 PM, Arnaud Joly <a.j...@ulg.ac.be> wrote:
>>
>>> Hi,
>>>
>>> Anything concerning the GSOC should pass by the scikit-learn
>>> mailing list.
>>>
>>> Thanks for your interest in the subject. If you intend to apply for a
>>> GSOC, I suggest you to read
>>>
>>> https://github.com/scikit-learn/scikit-learn/wiki/Google-summer-of-code-%28GSOC%29-2014<https://github.com/scikit-learn/scikit-learn/wiki/Google-summer-of-code-(GSOC)-2014>
>>> and start contributing to scikit-learn.
>>>
>>> Right now, three people have shown interest for this topic: Maheshakya
>>> (who is now
>>> applying for a GSOC about LSH), Vamsi Kaushik and you. Several
>>> candidates may apply for the
>>> same subject. However it is likely that if a GSOC is awarded for a given
>>> subject, only the best proposal will
>>> be selected.
>>>
>>> Best regards,
>>> Arnaud
>>>
>>>
>>> On 28 Feb 2014, at 22:33, João <joaopalo...@gmail.com> wrote:
>>>
>>> Hi Arnaud,
>>>
>>> While browsing the current GSoC projects I saw an interesting one for
>>> which you are assigned as mentor: "Add scipy.sparse matrix support to the
>>> Decision Tree".
>>>
>>> I am considering applying for this project as I have already faced the
>>> necessity of sparse matrices in sklearn and the outcome was not totally
>>> satisfactory.
>>> Right now I am participating in a kaggle contest (
>>> http://www.kaggle.com/c/lshtc/) and facing several difficulties even
>>> with algorithms that already support spase matrices (even simple algorithms
>>> such as NB). In general I get some memory error and sometimes segfaults.
>>>
>>> I would be happy if I could implement the necessary support for DT (and
>>> related algorithms such as random forest and extra trees) and, if the time
>>> constraint allows, improve as much as possible the general support for
>>> sparse matrices.
>>>
>>> With this email, I want to show my interest and ask you if there are
>>> already any candidates for this place.
>>>
>>> Best regards,
>>> --
>>> João
>>>
>>>
>>>
>>>
>>> ------------------------------------------------------------------------------
>>> Learn Graph Databases - Download FREE O'Reilly Book
>>> "Graph Databases" is the definitive new guide to graph databases and
>>> their
>>> applications. Written by three acclaimed leaders in the field,
>>> this first edition is now available. Download your free book today!
>>> http://p.sf.net/sfu/13534_NeoTech
>>> _______________________________________________
>>> Scikit-learn-general mailing list
>>> Scikit-learn-general@lists.sourceforge.net
>>> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>>>
>>>
>>
>
> ------------------------------------------------------------------------------
> Learn Graph Databases - Download FREE O'Reilly Book
> "Graph Databases" is the definitive new guide to graph databases and their
> applications. Written by three acclaimed leaders in the field,
> this first edition is now available. Download your free book today!
>
> http://p.sf.net/sfu/13534_NeoTech_______________________________________________
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>
>
>
>
> ------------------------------------------------------------------------------
> Learn Graph Databases - Download FREE O'Reilly Book
> "Graph Databases" is the definitive new guide to graph databases and their
> applications. Written by three acclaimed leaders in the field,
> this first edition is now available. Download your free book today!
> http://p.sf.net/sfu/13534_NeoTech
> _______________________________________________
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>
>
------------------------------------------------------------------------------
Learn Graph Databases - Download FREE O'Reilly Book
"Graph Databases" is the definitive new guide to graph databases and their
applications. Written by three acclaimed leaders in the field,
this first edition is now available. Download your free book today!
http://p.sf.net/sfu/13534_NeoTech
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
