Hi Peter
As recommended by you I'll switch to the master immediately and check with
it.
But I am unclear on flattening Y_1.Should it done or kept as 2D ?
Thank you so much.And yes, Congratulations for Win in Kaggle Competition!!
Regards
Nikit Saraf
On Fri, Jul 6, 2012 at 1:55 AM, Peter Prettenh
Ok, I strongly recommend using the current master because I added some
bugfixes w.r.t. input verification after the 0.11 release.
I added some more test cases for input verification and another fix (I
didn't flatten the ``y`` array and you are passing a 2d ``Y_1``).
I included them in this PR [1] w
Hi Peter
It is most probably 0.11.I'm not so sure, It can be older version too.
Regards
Nikit Saraf
On Fri, Jul 6, 2012 at 1:39 AM, Peter Prettenhofer <
[email protected]> wrote:
> Nikit,
> which version of sklearn do you use? master or 0.11?
>
> best,
> Peter
>
> 2012/7/5 Nikit S
Nikit,
which version of sklearn do you use? master or 0.11?
best,
Peter
2012/7/5 Nikit Saraf :
> Hi Peter
>
> Thanks for the reply.
>
> dtype of Y_1 is 'string64' and its shape is (12137,1)
> dtype of X_1 is 'float64" and its shape is (12137,100)
>
> And here is the example of 10 cases http://
Hi Peter
Thanks for the reply.
dtype of Y_1 is 'string64' and its shape is (12137,1)
dtype of X_1 is 'float64" and its shape is (12137,100)
And here is the example of 10 cases http://paste.ubuntu.com/1077028/
It would be great if you could point out where I'm going wrong.Thank you so
much for t
Hi Nikit,
thanks for reporting - I added a test case for symbolic class labels
and it works ok (class labels get mapped to internal class ids prior
to fitting; see gradient_boosting.py:629:631) - I think the source of
the error is something different.
Can you check the dtype and shape of ``Y_1``?
I was trying to train a Character Recognition Model with the help of
GradientBoostingClassifier. When i tried to run, it gave me the following
error :-
Traceback (most recent call last):
File "charRecog.py", line 23, in
clf = GradientBoostingClassifier().fit(X_1,Y_1)
File
"/usr/local/lib/
On Thu, Jul 5, 2012 at 10:24 AM, Gael Varoquaux
wrote:
> Do you have any plans to generate notebooks from enhanced valid Python
> code? I would find that really handy as it would open the door to proving
> notebook-like functionality without really depending on the notebook for
> the development w
Olivier, Gael,
Thanks for the detailed suggestions.
The tutorial I'm preparing for is on Monday, July 16, so I'll be putting
in a lot of effort in the next couple weeks. I think for present
purposes, I'll plan to keep the tutorial and examples in the old
paradigm of rst + source code with skel
On Thu, Jul 05, 2012 at 10:19:49AM -0700, Fernando Perez wrote:
> We've tried to make sure the format is as version control-friendly as
> possible, within the limits of accepting that it's json.
Do you have any plans to generate notebooks from enhanced valid Python
code? I would find that really
On Thu, Jul 5, 2012 at 9:34 AM, Gael Varoquaux
wrote:
> I am very clearly -1 on this suggestion for several reasons:
You guys should definitely find a policy that works well for sklearn.
I just want to provide some info here, not push for using notebooks in
your default setup:
> a. I worry very
On Thu, Jul 05, 2012 at 06:47:35PM +0200, Olivier Grisel wrote:
> None of this is doctested. And I don't want to put pollute the code
> with boilerplate to make that testable. It's up to the teacher to
> check that those exercises still work prior to using them in an
> interactive session.
I afrai
On Fri, Jul 06, 2012 at 01:44:43AM +0900, Mathieu Blondel wrote:
>This is how I did it in my calibration plot PR too:
>[2]https://github.com/scikit-learn/scikit-learn/pull/882
I am so far behind on PR reviewing :(. I hadn't looked at that so far. I
am only starting to catch up with mail.
The tutorial itself and inline examples can stay in sphinx + doctests.
I agree this is a great format for online publishing and maintenance
checks using doctests.
But converting the 3 or 4 short exercises in notebook format would be great:
Here is the current code for the exercise snippets in my
On Fri, Jul 6, 2012 at 12:31 AM, Gael Varoquaux <
[email protected]> wrote:
> I must admit that so far I have been frowning away from adding code that
> does any plotting to scikit-learn. I tend to be worried about the
> maintenance code for such code. However, maybe having code that s
On Wed, Jul 04, 2012 at 11:43:38AM +0200, Olivier Grisel wrote:
> > Thanks -- I will pick up this "lucky to succeed once" fix ;)
> I think that using the numpy.random singleton (or any other mutable
> singleton) in scikit-learn tests should be considered a failure in
> itself as it breaks the test
On Tue, Jul 03, 2012 at 12:24:43PM -0700, Jake Vanderplas wrote:
> I turned in the first draft of my PhD thesis yesterday,
Congratulations!
> Should the loaders be moved to sklearn.datasets, so the data can be
> used for general examples which are not associated with the tutorial?
> Or do you thi
On Jul 5, 2012, at 17:31 , Gael Varoquaux wrote:
> On Thu, Jul 05, 2012 at 05:08:13PM +0200, Peter Prettenhofer wrote:
>> Indeed would be great to have a component to generate learning curves
>> in sklearn - I have some custom code lying around but it's rather
>> ugly...
>
> I must admit that so
On 07/05/2012 04:31 PM, Gael Varoquaux wrote:
> On Thu, Jul 05, 2012 at 05:08:13PM +0200, Peter Prettenhofer wrote:
>> Indeed would be great to have a component to generate learning curves
>> in sklearn - I have some custom code lying around but it's rather
>> ugly...
> I must admit that so far I h
On Thu, Jul 05, 2012 at 04:57:25PM +0200, Peter Prettenhofer wrote:
> Model selection is my nemesis - little can be gained, everything lost :-)
Agreed!
> In the end I did 5x 5-fold CV - the error std between the repetitions
> was around 0.005.
I am a big fan of using ShuffleSplit to reduce the v
On Thu, Jul 05, 2012 at 05:08:13PM +0200, Peter Prettenhofer wrote:
> Indeed would be great to have a component to generate learning curves
> in sklearn - I have some custom code lying around but it's rather
> ugly...
I must admit that so far I have been frowning away from adding code that
does an
2012/7/5 Peter Prettenhofer :
> 2012/7/5 Olivier Grisel :
>> 2012/7/5 Emanuele Olivetti :
>>> On 07/05/2012 09:45 AM, Andreas Mueller wrote:
Hey Peter.
Pretty awesome feat! Thanks for all the work you put into the ensemble
module!
A blog post about this competition would re
2012/7/5 Peter Prettenhofer :
> 2012/7/5 Olivier Grisel :
>> 2012/7/5 Emanuele Olivetti :
>>> On 07/05/2012 08:49 AM, Olivier Grisel wrote:
2012/7/5 Peter Prettenhofer :
> ...
>
> I've to check with the competition organizers whether its ok to put
> the source code on github -
2012/7/5 Olivier Grisel :
> 2012/7/5 Emanuele Olivetti :
>> On 07/05/2012 08:49 AM, Olivier Grisel wrote:
>>> 2012/7/5 Peter Prettenhofer :
...
I've to check with the competition organizers whether its ok to put
the source code on github - I'll keep you posted.
>>> If so that wo
2012/7/5 Olivier Grisel :
> 2012/7/5 Emanuele Olivetti :
>> On 07/05/2012 09:45 AM, Andreas Mueller wrote:
>>> Hey Peter.
>>> Pretty awesome feat! Thanks for all the work you put into the ensemble
>>> module!
>>>
>>> A blog post about this competition would really be great :)
>>>
>>> I was wonderin
2012/7/5 Emanuele Olivetti :
> On 07/05/2012 08:49 AM, Olivier Grisel wrote:
>> 2012/7/5 Peter Prettenhofer :
>>> ...
>>>
>>> I've to check with the competition organizers whether its ok to put
>>> the source code on github - I'll keep you posted.
>> If so that would be a great blog post topic. Loo
2012/7/5 Emanuele Olivetti :
> On 07/05/2012 09:45 AM, Andreas Mueller wrote:
>> Hey Peter.
>> Pretty awesome feat! Thanks for all the work you put into the ensemble
>> module!
>>
>> A blog post about this competition would really be great :)
>>
>> I was wondering, was there much difference in perf
On 07/05/2012 08:49 AM, Olivier Grisel wrote:
> 2012/7/5 Peter Prettenhofer :
>> ...
>>
>> I've to check with the competition organizers whether its ok to put
>> the source code on github - I'll keep you posted.
> If so that would be a great blog post topic. Looking forward to it.
>
Hi,
For what
On 07/05/2012 09:45 AM, Andreas Mueller wrote:
> Hey Peter.
> Pretty awesome feat! Thanks for all the work you put into the ensemble
> module!
>
> A blog post about this competition would really be great :)
>
> I was wondering, was there much difference in performance between GBRT
> and RF?
Hi,
I
Thanks very much for the wrap up Vlad. Could you please document how
to use the %memit and %mrun tools in the performance chapter of the
scikit-learn documentation?
http://scikit-learn.org/stable/developers/performance.html
Those are great tools BTW. Also continuous monitoring of memory usage
in
Hello friends,
As the midterm evaluation is approaching, I pushed the pedal to the metal and
my blog and github profile have seen a lot of activity recently.
I would like to link to everything from one place, and that place will be this
e-mail. So this is what happened:
-- I wrote a couple of m
Congratulations Peter! Excellent work as always!
Vlad
On Jul 5, 2012, at 00:48 , Emanuele Olivetti wrote:
> Dear All,
>
> As some of you may have already noticed, Peter (Prettenhofer) has
> just won a the "Online Product Sales" competition on kaggle.com
> beating 365 teams:
> http://www.kaggle.
If you get an OK - that would be absolutely amazing, especially if you
broke it down and explained the different tweaks.
Speaking for myself - I am only super interested in seeing how you set up
the grid search on the EC3 instances :)
Congratulations on a fantastic job, and this will draw a lot m
On Thu, Jul 5, 2012 at 4:45 PM, Andreas Mueller wrote:
> Hey Peter.
> Pretty awesome feat! Thanks for all the work you put into the ensemble
> module!
>
> A blog post about this competition would really be great :)
>
> I was wondering, was there much difference in performance between GBRT
> and RF
Hey Peter.
Pretty awesome feat! Thanks for all the work you put into the ensemble
module!
A blog post about this competition would really be great :)
I was wondering, was there much difference in performance between GBRT
and RF?
We should do a "hall of fame" on the website listing citations an
Congratulations!!! Very well done
2012/7/5 Olivier Grisel
> 2012/7/5 Peter Prettenhofer :
> > Hi everybody,
> >
> > thanks a lot for your congratulations. It has been a tight race indeed
> > and I have to consider myself lucky that I ended up on the first place
> > - as Olivier already said scor
2012/7/5 Peter Prettenhofer :
> Hi everybody,
>
> thanks a lot for your congratulations. It has been a tight race indeed
> and I have to consider myself lucky that I ended up on the first place
> - as Olivier already said score differences among the top teams are
> really small.
>
> Anyways, it's a
37 matches
Mail list logo
