[pymvpa] RFE memory issue

Thorsten Kranz thorstenkranz at googlemail.com
Sat Nov 20 13:21:17 UTC 2010


Hi Yaroslav,

thank you for your quick and precise reply. I'll try your proposals on
monday. But one question remains for me: what is the adequate way to
group things together in chunks? All samples with the same label in
one chunk? I must say that I didn't really make use of chunks up to
now...

Greetings,

Thotsten

2010/11/19 Yaroslav Halchenko <debian at onerussian.com>:
> Welcome Thorsten,
>
>
> On Fri, 19 Nov 2010, Thorsten Kranz wrote:
>>         rfesvm_split = SplitClassifier(LinearCSVMC())
>>         >...<
>> on a dataset with 66500 features:
>>         Dataset / float64 379 x 66500 uniq: 379 chunks 17 labels
>
> The reason is -- SplitClassifier by default uses NFoldSplitter and you
> have 379 chunks... Also due to its nature SplitClassifier constructs and
> keeps all those 379 classifiers (1 per split) in memory... so you can do
> counting ;-)
>
> workarounds:
> - reduce number of chunks by groupping trials together
> - use OddEven or HalfSplitter within rfesvm_split instead of NFold
>
> also
>
> - why not give a try to SMLR?
>  at least it should be much faster than "correctly" RFEed SVM, like you
>  are trying to do.... you might also like to use SMLR just for the sake
>  of feature selection prior using SVM (pair-wised voted), effectively
>  replacing RFE with SMLR as a feature selection step
>
>> Is the number of labels (17) the problem?
> not directly, although it contributes, since SVM does pair-wise
> classification, thus effectively constructs 17*16/2 = 136 binary classifiers
>
>> history is needed, errors and
>> nfeatures shouldn't be too big...
> yeap
>
> --
>                                  .-.
> =------------------------------   /v\  ----------------------------=
> Keep in touch                    // \\     (yoh@|www.)onerussian.com
> Yaroslav Halchenko              /(   )\               ICQ#: 60653192
>                   Linux User    ^^-^^    [175555]
>
>
>
> _______________________________________________
> Pkg-ExpPsy-PyMVPA mailing list
> Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org
> http://lists.alioth.debian.org/mailman/listinfo/pkg-exppsy-pymvpa
>



More information about the Pkg-ExpPsy-PyMVPA mailing list