[pymvpa] _clf_internals question

[Per B. Sederberg]

The other thing I was unable to prevent was the printout from R when
you load the GLMNET package.  I wish rpy or R had a way to suppress
those messages, but I couldn't find it...

P

On Wed, May 27, 2009 at 3:51 PM, Per B. Sederberg <persed at princeton.edu> wrote:
> On Wed, May 27, 2009 at 3:44 PM, Yaroslav Halchenko
> <debian at onerussian.com> wrote:
>> well... unittests were failing not due to convergence issues, but
>> because the _R was treated as classifier unless you explicitely provided
>> 'regression=True' to it. That caused unittests to fail while checking
>> the .confusion in regression tests.
>
>
> Ahhh cool, did you fix that??  I was having trouble figuring out what
> to add to the code to make the _R version be a regression to pymvpa...
>
> Thanks,
> P
>
>
>
>>
>> I am yet to explore glmnet on real data ;)
>>
>> On Wed, 27 May 2009, Per B. Sederberg wrote:
>>
>>> Indeed, I couldn't prevent non-convergence errors, so some unit tests
>>> fail, but I have had no issue with either classification or regression
>>> on actual data.  Have you?
>>
>> --
>>                                  .-.
>> =------------------------------   /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
>>
>