fix application performance issues faster with Applications Manager
> Applications Manager provides deep performance insights into multiple tiers of
> your business applications. It resolves application problems quickly and
> reduces your MTTR. Get your free trial!
> https://a
16;z
> ___
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
Gael Varoquaux
Researcher, INRIA Parietal
NeuroSpin/CEA Saclay , Bat 145, 91191 Gif
On Sat, Mar 26, 2016 at 05:31:36PM -0400, Sebastian Raschka wrote:
> I wouldn’t fundamentally change the random forest algorithm in scikit-learn
> using ideas from xgboost, since it wouldn’t be a random forest anymore, then.
> Please don’t get me wrong, I’d also like to see a more efficient (pred
reduces your MTTR. Get your free trial!
> https://ad.doubleclick.net/ddm/clk/302982198;130105516;z
> ___
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit
Sounds good to me !
Gaël
Sent from my phone. Please forgive brevity and mis spelling
On Apr 4, 2016, 20:20, at 20:20, Andreas Mueller wrote:
>I don't know to much about this but that seems to be the default:
>https://guides.github.com/activities/citable-code/
>
>On 04/02/20
We can use zenodo for this. Is that what you are suggesting?
Gaël
Sent from my phone. Please forgive brevity and mis spelling
On Apr 1, 2016, 16:10, at 16:10, Andreas Mueller wrote:
>Hi all.
>I realized there is no DOI for scikit-learn releases.
>Should we create one? I've been talking with
On Mon, Mar 07, 2016 at 10:54:53AM -0500, Andreas Mueller wrote:
> I'm not sure about the naming of the package. As long as there is no active
> involvement of the scikit-learn developers in this
> package, I'd rather not have "our" name on it.
> Gael?
I don't know about this. I see the point of n
Site24x7 APM Insight: Get Deep Visibility into Application Performance
> APM + Mobile APM + RUM: Monitor 3 App instances at just $35/Month
> Monitor end-to-end web transactions and take corrective actions now
> Troubleshoot
On Wed, Mar 02, 2016 at 11:34:17AM -0800, Jacob Schreiber wrote:
> Reinforcement learning is an exciting field of machine learning, and you're
> right that it seems underrepresented in Python. However, I don't think that it
> falls within the strict scope of the scikit-learn API.
Indeed. There's
On Thu, Feb 25, 2016 at 10:18:07AM -0800, Matthew Brett wrote:
> Who did you contact for Python.org? We moved our (brain imaging)
> mailing lists last year or so, it was pretty quick and easy. I
> contacted postmas...@python.org . Maybe it's worth trying again?
We contacted postmaster twice,
> For any particular application (I did bag of visual words), creating an
> implementation using the kmeans or sparse coding in scikit-learn
> is only a couple of lines (you can find my visual bow for per-superpixel
> descriptors here https://github.com/amueller/segmentation/blob/master/bow.py#
> L
40
> ___
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
Gael Varoquaux
t; Hi
> I would like to know if :
> https://github.com/scikit-learn/scikit-learn/blob/master/sklearn/
> feature_selection/mutual_info_.py
> supports Y to be a matrix. From what I see it seems like Y can only be a
> column vector.
--
Gael Varoquaux
Resear
arn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
Gael Varoquaux
Researcher, INRIA Parietal
NeuroSpin/CEA Saclay , Bat 145, 91191 Gif-sur-Yvette France
Phone: ++ 33-1-69-
On Wed, Jan 27, 2016 at 04:13:58PM -0800, Mika S wrote:
> Is it possible to update an LDA model online incrementally in scikit learn
> (stable or dev version)?
Yes. Use the "partial_fit" method.
Gaël
--
Site24x7 APM Insi
> Maybe we should implement that?
+1
--
Site24x7 APM Insight: Get Deep Visibility into Application Performance
APM + Mobile APM + RUM: Monitor 3 App instances at just $35/Month
Monitor end-to-end web transactions and take
le APM + RUM: Monitor 3 App instances at just $35/Month
> Monitor end-to-end web transactions and take corrective actions now
> Troubleshoot faster and improve end-user experience. Signup Now!
> http://pubads.g.doubleclick.net/gampad/clk?id=267308311&iu=/4140
> ___
> Scikit-learn-genera
On Mon, Jan 04, 2016 at 01:22:12PM -0500, Andreas Mueller wrote:
> I'm not sure I'm for dropping 2.6 for the sake of dropping 2.6.
I agree. I find the attitude of the post that I mentionned a bit
annoying: dropping support for the sake of forcing people to move isn't a
good thing. It should bring
Happy new year everybody,
As a new year resolution, I suggest that we drop Python 2.6
compatibility.
For an argumentation in this favor, see
http://www.snarky.ca/stop-using-python-2-6 (I don't buy everything there,
but the core idea is there).
For us, this will mean more usage of context manager
On Fri, Jan 01, 2016 at 08:41:56PM +0100, Marco De Nadai wrote:
> I would expose it through a score function. In this way it can be called to
> evaluate 2 models (let's say model A with 4 params and model B with 10).
> Moreover, this could also be called by feature_selection.RFECV.
OK, but BIC is
Marco De Nadai wrote:
> Hello everyone,
> I'm new to sklearn. Is there any reason behind the absence of Bayesian
> information criterion (BIC) and Akaike information criterion (AIC) in sklearn
> (especially for model/feature selection).
> Thanks :)
--
Gael Varoquaux
R
ning in scikit-learn?" which will expand on "Will you
> add GPU support"?
> If you agree, I'll raise an issue!
> On Wed, Dec 16, 2015 at 4:26 PM, Gael Varoquaux
>
> wrote:
> Hi Arasu,
> Deep learning requires a rich vocabulary to define an architectu
ts neural nets package.
> If so, could you please point me to some related tasks that I can start
> contributing on?
> Thank you!
--
Gael Varoquaux
Researcher, INRIA Parietal
NeuroSpin/CEA Saclay , Bat 145, 91191 Gif-sur-Yvette France
Phone: ++ 33-1-69-08-79-68
; ___
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
Gael Varoquaux
Researcher, INRIA Parietal
NeuroSpin/CEA Saclay , Bat 14
ormat to load/store
> > different datasets without duplicating the effort in many places.
> > On Wed, 9 Dec 2015 at 19:58 Andreas Mueller wrote:
> > On 12/09/2015 01:48 PM, Gael Varoquaux wrote:
> > > On Wed, Dec 09, 2015 at 12:33:55PM -0500, Andreas Mueller wrote:
> >
On Wed, Dec 09, 2015 at 06:17:02PM +, Luca Puggini wrote:
> I would really like to have an easy way to import public datasets.
So would I. But is scikit-learn the right place to solve this problem?
Gaël
--
_
On Wed, Dec 09, 2015 at 12:33:55PM -0500, Andreas Mueller wrote:
> I guess we use the matlab data with is not required by mldata.
> We could add code that tries to fetch the matlab, and if that doesn't
> work uses the hdf5,
I'd rather not. I'd rather we just have a good error message.
G
---
> hello pandora's box ;)
> I thought we don't want to have time-series specific code?
I agree. We should strive to make something like this pluggeable into
scikit-learn, but not have in inside.
--
Go from Idea to Many App
> How about adding a "Need Review(s?)(er?)" tag?
For me, it's the '[MRG]' in the PR name.
--
Go from Idea to Many App Stores Faster with Intel(R) XDK
Give your users amazing mobile app experiences with Intel(R) XDK.
Use
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
Gael Varoquaux
Researcher, INRIA Parietal
NeuroSpin/CEA Saclay , Bat 145, 91191 Gif-sur-Yvette France
Phone: ++ 33-1-69-08-79-68
http://gael-v
Newton is never d**2 because every body uses a truncated Newton, which is in
effect linear in d.
Gaël
Sent from my phone. Please forgive brevity and mis spelling
On Nov 8, 2015, 18:51, at 18:51, Sebastian Raschka wrote:
>
>> On Nov 8, 2015, at 11:32 AM, Raphael C wrote:
>>
>> In terms of c
+1. My position on that list doesn't reflect the amount of code I have
contributed: it over estimates it compared to people who have made large pull
requests and squashed. It also doesn't account at all for any reviewing.
Sent from my phone. Please forgive brevity and mis spelling
On Nov 6, 2
> ___
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
Gael Varoquaux
Researcher, INRIA Parietal
NeuroSpin/CEA
On Thu, Nov 05, 2015 at 07:05:11AM +, Raphael C wrote:
> https://github.com/szilard/benchm-ml
> The upshot is that in some cases it seems that the scikit-learn
> versions have room for improvement.
The various main lessons that I can see from those results are:
* Linear models (aka LogisticR
Why didn't you use "git revert" rather than rewriting history?
Thanks for working on the release, by the way!
Gaël
Sent from my phone. Please forgive brevity and mis spelling
On Oct 31, 2015, 17:10, at 17:10, Andy wrote:
>Hey.
>Just in case anyone was working on 0.17.X for some reason:
>I ne
> I don't think it is so bad to code. Perhaps I could do a related projects repo
> first and then see if something similar can be moved in officially?
Sounds like a good idea to me.
--
rn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
Gael Varoquaux
Researcher, INRIA Parietal
NeuroSpin/CEA Saclay , Bat 145, 91191 Gif-sur-Yvette France
Phone: ++ 33-1-69-08-79-68
http
> I had similar issues when I was running code on our clusters. I think that
> software & hardware architecture may also be a factor to be considered. What I
> observed was that the memory usage was growing over time. I added a few lines
> to manually clear the garbage collection, which solved the
and 3.5 for Windows and Mac OS
> X
> are now available on PyPI.
--
Gael Varoquaux
Researcher, INRIA Parietal
NeuroSpin/CEA Saclay , Bat 145, 91191 Gif-sur-Yvette France
Phone: ++ 33-1-69-08-79-68
http://gael-varoquaux.infohttp://twitter.com/Gael
On Wed, Oct 14, 2015 at 01:18:19PM +, Luca Puggini wrote:
> I was expecting OCSVM to be not too much influenced by the increasing number
> of
> variables even if some of them are irrelevant.
I am not: it's based on an RBF kernel. These things are not well behaved
in high dimensions.
Gaël
--
We should probably should document this in the docstring.
Sent from my phone. Please forgive brevity and mis spelling
On Oct 9, 2015, 04:42, at 04:42, Jacob Schreiber
wrote:
>Okay this makes sense. Upon reflection, the splitters all only take
>pointers to the datasets, so that shouldn't have
On Thu, Oct 01, 2015 at 11:10:51AM +0200, Maryam Tavakol wrote:
> My problem however is the size of data in terms of number of samples.
> The features are engineered and are only 80. I wanted to try training
> on bigger set of data for improvement.
I would use the BIRCH clustering method in an onl
Dear Pythonistas,
We have just released a new version of the "scipy lecture notes":
http://www.scipy-lectures.org/
These are a consistent set of materials to learn the core aspects of the
scientific Python ecosystem, from beginner to expert. They are written
and maintained by a set of volunteers
to both.
> Cheers,
> Alex
> --
> ___
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/li
On Thu, Sep 10, 2015 at 09:52:44AM -0400, Andy wrote:
> I feel it is quite awkward if the function and the estimator have
> different requirements on X.
That's a point of view. But they are different things, so I am not sure
that this point of view is universal.
> And your statement "they are fo
On Wed, Sep 09, 2015 at 02:10:05PM -0400, Andreas Mueller wrote:
> I see two possible ways forward:
> a) Make the functions private and deprecate the public interface, like
> k_means, lars_path,
These functions are important for reuse in an algorithmic setting: if I
am doing an algorithm tha
apps and tools
> in one place.
> SourceForge users - Click here to start your Free Trial of Datadog now!
> http://pubads.g.doubleclick.net/gampad/clk?id=241902991&iu=/4140
> _______
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.source
ikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
> --
> ___
> Scikit-learn-general mailing list
> Scikit-learn-gen
On Tue, Aug 25, 2015 at 01:06:11PM -0400, Andreas Mueller wrote:
> For speed regression tests, it has happened that things got slower, in
> particular with innocent looking things like input validation.
> I think it would be good to have some tests that ensure that we don't
> get too much slower.
> Is it required that an algorithm, which is implemented in Scikit-Learn, scales
> well wrt n_samples?
The requirement is 'be actually useful', which is something that is a bit
hard to judge :).
I think that K-medoids is bordeline on this requirement, probably on the
right side of the border. I
t specify `n_jobs` parameter which is 1 in default. Is this an
> expected behavior?
> If I want to release GIL, can I use OpenMP module in Cython? Or is that a task
> of Joblib?
> Any input on this is highly appreciated.
> Best regards,
--
Gael Varoquaux
Researcher,
On Tue, Jul 28, 2015 at 08:59:15PM +0200, bthirion wrote:
> Note that Jacob Schreiber is already working on it.
> https://github.com/scikit-learn/scikit-learn/pull/5010
Indeed, and he has a few other PRs going in this direction. You should
interact on the PRs with him.
---
.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
Gael Varoquaux
Researcher, INRIA Parietal
NeuroSpin/CEA Saclay , Bat 145, 91191 Gif-sur-Yvette France
Phone: ++ 33-1-69-08-79-68
http://gael-varoquaux.info
ured For All Businesses. Start Your Cloud Today.
> https://www.gigenetcloud.com/
> ___
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
Gael Varoquaux
Resear
On Mon, Jul 06, 2015 at 04:55:07PM -0400, Deepak Subburam wrote:
> I have some time to contribute, and would like to implement a
> sample_weight option to the fit() method of
> sklearn.cross_decomposition.PLSRegression, handling any other knock-on
> effects. Let me know if you think this is not
On Wed, Jul 01, 2015 at 11:04:30AM -0400, Andreas Mueller wrote:
> Theano uses __setstate__ and __getstate__ and they seem to be happy with
> that.
As long as we don't change the data model that works easily, but then so
does pickle. If when chage the data model, which we have done a few time,
we
Hi Sam,
I agree that a meta estimator would be the way to go. However, the question is:
are these techniques used widely enough to warrant inclusion in scikit-learn? I
have the impression that they are used much less than agglomerative approaches.
I have myself used them in the past with succe
Hi GSOC students,
And welcome. I hope that you will have a fun and productive summer.
To communicate well on your project, and to help you draw big picture from
your work, the PSF requires that blog every week on your project.
Can you send me the URL of your blog, so that I add it to plane
Anaconda is not provided by the scikit-learn developers. Please ask the
anaconda people.
Best,
Gaël
Sent from my phone. Please forgive brevity and mis spelling
On May 9, 2015, 04:25, at 04:25, nafise mehdipoor
wrote:
>Dear All,I want to install anaconda or any other version of python wi
> I thought that was discouraged and X.reshape(-1, 1) was suggested?
> (The newaxis makes it be neigher C nor F contiguous)
Indeed, sorry.
G
--
One dashboard for servers and applications across Physical-Virtual-Cloud
W
ri, May 1, 2015 at 7:58 PM, Gael Varoquaux
> wrote:
> I strongly advice raising an error. Very very very strongly.
> Being lax about ambiguous inputs makes prototyping and interactive usage
> easier: less typing, and the systems gets it right most of the time.
> Howe
Hi scikit-learn people,
The Euroscipy deadline has been extended: it will close on May 15th:
https://www.euroscipy.org/2015/
I would like to invite anybody who is interested to submit talks on
machine in Python. Euroscipy is an interesting venue that is centered on
people doing numerics and scien
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
Gael Varoquaux
Researcher, INRIA Parietal
Neuro
On Wed, Apr 29, 2015 at 11:28:29AM -0400, josef.p...@gmail.com wrote:
> related question: Does scikit-learn do any autoscaling of the
> penalities?
> I'm just looking into the scaling of penalties for statsmodels. Without
> scaling the data or scaling the penalties, the penalized estimator
> might
rmance metrics, stats and reports that give you Actionable Insights
> Deep dive visibility with transaction tracing using APM Insight.
> http://ad.doubleclick.net/ddm/clk/290420510;117567292;y
> ___
> Scikit-learn-general mailing list
> Scikit-learn-general
Hi list,
Please bare with me: a workshop announcment that is relevant to what we
do:
Workshop on Machine Learning Open Source Software 2015: Open Ecosystems
The ICML Workshop on Machine Learning Open Source Software (MLOSS) will
held in Lille, France on the 10th of July, 2015.
Important Dates:
> source=Sourceforge_BPM_Camp_5_6_15&utm_medium=email&utm_campaign=VA_SF
> ___
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
On Mon, Apr 13, 2015 at 06:23:28PM -0400, Andreas Mueller wrote:
> I'm not sure if this is joblib related or sklearn related, though.
It would be very useful having a traceback. Right now, it is impossible
to know where the problem comes from.
G
--
> I’m now in Paris, and I have done the preparations for the sprint tomorrow.
> However, I’ve been looking around on the website, and I cannot find the time
> that it is starting. Can anyone tell me please?
People will be there at 9. I'll be there later, say 10, as I have an
errand to run before
ed that the description in
the SMAC paper is quite vague, and that we will have to dig in referenced
papers and code to understand what is really being done. Maybe that
simply reflects my lack of understanding of the field :).
Gaël
> On 03/28/2015 01:29 PM, Gael Varoquaux wrote:
> > Sorr
> Just FYI, someday when the Github move happens there are a few tweaks
> to the build that will have to happen - Github has some special rules
> on folder names. I had to make some mods to the build for
> sklearn-theano, it wasn't awful but took a while to figure out
Yes, these problems have been
case studies, tutorials and more. Take a look and join the
> conversation now. http://goparallel.sourceforge.net/
> ___
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/li
__
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
Gael Varoquaux
Researcher, INRIA Parietal
Laboratoire de Neuro-Imagerie
Sorry for the slow reply,
On Fri, Mar 27, 2015 at 11:49:46AM -0400, hamzeh alsalhi wrote:
> I have revised my proposal to focus only on SMAC and to prioritize SMAC RF
> because it can be worked on independently GP.
I actually believed that GP were an easier route forward.
The way I would have t
Take a look and join the
> conversation now. http://goparallel.sourceforge.net/
> ___
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
Gael Varoquaux
Researcher, INRIA Pariet
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
Gael Varoquaux
Researcher, INRIA Parietal
Laboratoire de Neuro-Imagerie Assistee par Ordinateur
to this release!
> Cheers!
--
Gael Varoquaux
Researcher, INRIA Parietal
Laboratoire de Neuro-Imagerie Assistee par Ordinateur
NeuroSpin/CEA Saclay , Bat 145, 91191 Gif-sur-Yvette France
Phone: ++ 33-1-69-08-79-68
http://gael-varoquaux.infohttp://twitter
> It would be nice to do something else instead of crash and burn, but for the
> moment that's on the user.
I think that in recent Python versions segfault can be captured.
--
Dive into the World of Parallel Programming T
> 1. For the part Implementing VBGMM, do you mean it would be better if I add
> specific functions to be implemented? @Andreas.
My question is: why do you think that, by coding it from scratch rather
than trying to understand the existing one and improving it, you'll do a
better job? The guy who
I am very afraid of the time sink that this will be.
Sent from my phone. Please forgive brevity and mis spelling
On Mar 25, 2015, 19:47, at 19:47, Andreas Mueller wrote:
>I think you could bench on other problems, but maybe focus on the ones
>in scikit-learn.
>Deep learning people might be h
On Tue, Mar 24, 2015 at 07:39:17PM -0400, Vlad Niculae wrote:
> 1. The design of multiple metric support is important and would bring an
> immense usability gain.
But it will also require a framework of its own. I would say that this is
to be considered in a second step.
G
-
> I think the problem with matrix-like Y is that Y would be symmetric. Thus for
> doing cross-validation one would need to select both rows and columns.
Correct. Then ideed it's off limits. These are specifically the kind of
problem I would like not to have to worry about. The combination of all
t
On Tue, Mar 24, 2015 at 09:04:28PM -0400, Vlad Niculae wrote:
> There were two API issues and I think both need thought. The first is the
> matrix-like Y which at the moment overlaps semantically with multilabel and
> multioutput-multiclass (though I think it could be seen as a form of
> multi-t
On Wed, Mar 25, 2015 at 03:25:40AM +0300, Artem wrote:
> You mean matrix-like y?
matrix-like y (ie y 2D: n_sample, n_features) is already covered in our
API, so I see no problem with it.
--
Dive into the World of Parallel
On Wed, Mar 25, 2015 at 11:22:51AM +0900, Mathieu Blondel wrote:
> The part I am most enthusiastic about is fixing the CV generators, though this
> could be a merge nightmare since we are in the process of changing the API. We
> need it to figure out which modifications are most likely to get in fi
> Don't you think that I could also benchmark models that are not
> implemented in sklearn? For instance, I could write a wrapper
> DeepNet(...) with fit() and predict(), and which uses internally theano
> to build a ANN? In this way, I could benchmark complex deep networks
> beyond what will b
On Tue, Mar 24, 2015 at 04:58:20PM +0100, Alexandre Gramfort wrote:
> how different is it from
> http://scikit-learn.org/stable/modules/generated/sklearn.cross_validation.LeaveOneLabelOut.html
> ?
Well, LeaveOneLabelOut should be modified to be able not to do an
exhaustive set (which scales pretty
> To make this more concrete, the MetricLearner().metric_ estimator would
> require specialised set_params or clone behaviour, I assume. I.e. it
> involves hacking API fundamentals.
It's more a general principle of "freeze": to be able to settle down on
something that we _know_ works and is robus
> So I just thought: what if metric learners will have an attribute `metric`
Before adding features and API entries, I'd really like to focus on
having a 1.0 release, with a fixed API that really solves the problems
that we currently are trying to solve.
In other words, I would like to get in an
On Mon, Mar 23, 2015 at 07:56:33AM +0100, Michael Eickenberg wrote:
> > I think it is somewhat different from cosine similarity.
> Then you'll have to tell me how, because I am being dense and I don't see
> the difference.
> Both are scalar products of two normalized data vectors.
> P
On Mon, Mar 23, 2015 at 10:27:00AM +0530, Vinayak Mehta wrote:
> > I believe that it is the same thing as cosine similarity. If that's
> > indeed the case, you could add a note in the cosine similarity docstring
> > to stress it.
> I think it is somewhat different from cosine similarity.
Then you
On Sun, Mar 22, 2015 at 05:51:23PM +0530, Vinayak Mehta wrote:
> I wanted to discuss about the possibility of adding PCS Measure to
> sklearn.metrics. I could open a PR if we go forward with this. :)
I believe that it is the same thing as cosine similarity. If that's
indeed the case, you could add
On Sun, Mar 22, 2015 at 11:59:17AM +1100, Joel Nothman wrote:
> FWIW It'll require some changes to cross-validation routines.
I'd rather we try not to add new needs and usecases to these before we
release 1.0. We are already having a hard time covering in a homogeneous
way all the possible options
w. http://goparallel.sourceforge.net/
> _______
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
Gael Varoquaux
Researcher, INRIA Pari
hub for
> all
> things parallel software development, from weekly thought leadership blogs
> to
> news, videos, case studies, tutorials and more. Take a look and join the
> conversation now. http://goparallel.sourceforge.net/
> _
> Does anybody know of further optimization approaches that were not
> mentioned below and that we could consider?
Maybe parallel computing. A grid search is an embarrassingly parallel
problem. A Bayesian optimization is not. We have the necessary framework
only to tackle embarrassingly parallel
On Wed, Mar 18, 2015 at 07:21:18PM +0300, Artem wrote:
> As to what y should look like, it depends on what we'd like the algorithm to
> do. We can go with usual y vector consisting of feature labels. Actually, LMNN
> is done this way, the optimization objective depends on the equality of labels
> o
On Wed, Mar 18, 2015 at 11:32:05AM -0400, Andreas Mueller wrote:
> Do you have an idea of what y would look like?
Me. Not sure, no. I haven't looked at the corresponding literature.
G
> Also +1 on what you said (but you knew that ;)
> On 03/18/2015 11:27 AM, Gael Varoquaux wro
into the World of Parallel Programming The Go Parallel Website, sponsored
> by Intel and developed in partnership with Slashdot Media, is your hub for all
> things parallel software development, from weekly thought leadership blogs to
> news, videos, case studies, tutorials and more. Take
On Tue, Mar 17, 2015 at 01:12:05AM +, Sturla Molden wrote:
> c-means can be faster as it does not need to evaluate trancendental
> functions, e.g. if fuzzy memberships are computed with a Bartlet window,
> but it might still yield almost the same result.
Being faster is a good thing. Do you ha
1 - 100 of 1267 matches
Mail list logo
