Re: [Scikit-learn-general] Sklearn slides / lecture notes

On Mon, Jul 23, 2012 at 11:13:30PM +0100, Andreas Mueller wrote: >I just stumbled across [1]these lecture notes by Fabian and Gael. >I was wondering why there is no link to it. Or is it obsolete now that >there is a tutorial in the docs? They are a shortened version of the tutorial. Ma

Re: [Scikit-learn-general] Sklearn slides / lecture notes

My recent scipy tutorial is online - I'm going to add it to the documentation once the video is up http://astroML.github.com/sklearn_tutorial/ The source is at http://github.com/astroML/sklearn_tutorial Good luck with the talk at PyCon! Jake On 07/23/2012 03:13 PM, Andreas Mueller wrote:

Re: [Scikit-learn-general] Is there a quick and simple way to get the R^2 from a LogisticRegression using cross-validation

Thanks. That appears to be working (I put metrics.r2_score in there). On 23 July 2012 14:52, Gael Varoquaux wrote: > On Mon, Jul 23, 2012 at 10:56:53AM +1000, Robert Layton wrote: > >Sorry for what will probably turn out to be an overly simple question. > >Is there a simple way to get th

[Scikit-learn-general] Sklearn slides / lecture notes

Hi everybody. I just stumbled acrossthese lecture notes by Fabian and Gael . I was wondering why there is no link to it. Or is it obsolete now that there is a tutorial in the docs? I'll be holding a sklearn/ML talk at PyCon DE i

Re: [Scikit-learn-general] issue with GB and MultinomialDeviance

On 07/23/2012 11:49 AM, Peter Prettenhofer wrote: > 2012/7/23 Emanuele Olivetti : >> [..] >> >> As you can see the solution is very simple and just based on >> np.logaddexp.reduce() >> instead of np.exp().sum(), plus np.nan_to_num() and a little rearrangement. >> I can prepare a pull request if yo

Re: [Scikit-learn-general] issue with GB and MultinomialDeviance

On 07/23/2012 11:38 AM, Gael Varoquaux wrote: > Thanks a lot for your investigation work. It's very useful. > > On Mon, Jul 23, 2012 at 11:32:24AM +0200, Emanuele Olivetti wrote: >> As you can see the solution is very simple and just based on >> np.logaddexp.reduce() instead of np.exp().sum(), plus

Re: [Scikit-learn-general] Supporting users on stackoverflow

2012/7/23 Jaques Grobler : > thanks for that.. btw, I just fixed those links. Should be fine now Thanks for the fix, and sorry for not having checked the rendering myself... -- Olivier http://twitter.com/ogrisel - http://github.com/ogrisel ---

Re: [Scikit-learn-general] Supporting users on stackoverflow

thanks for that.. btw, I just fixed those links. Should be fine now 2012/7/23 Olivier Grisel > 2012/7/23 Andreas Müller : > > How does the online edit UI work? I didn't know that existed... > > Click on the "Edit" button on > https://github.com/scikit-learn/scikit-learn/blob/master/doc/support.r

Re: [Scikit-learn-general] issue with GB and MultinomialDeviance

2012/7/23 Emanuele Olivetti : > [..] > > As you can see the solution is very simple and just based on > np.logaddexp.reduce() > instead of np.exp().sum(), plus np.nan_to_num() and a little rearrangement. > I can prepare a pull request if you are interested. Hi Emanuele, Absolutely, that would be

Re: [Scikit-learn-general] Supporting users on stackoverflow

netiher, actually.. interested.. :) 2012/7/23 Andreas Müller > How does the online edit UI work? I didn't know that existed... > > - Ursprüngliche Mail - > Von: "Olivier Grisel" > An: [email protected] > Gesendet: Montag, 23. Juli 2012 10:22:48 > Betreff: Re: [S

Re: [Scikit-learn-general] Supporting users on stackoverflow

2012/7/23 Andreas Müller : > How does the online edit UI work? I didn't know that existed... Click on the "Edit" button on https://github.com/scikit-learn/scikit-learn/blob/master/doc/support.rst But based on this experience I would advertise against it whenever you need RST rendering. It's good

Re: [Scikit-learn-general] issue with GB and MultinomialDeviance

Thanks a lot for your investigation work. It's very useful. On Mon, Jul 23, 2012 at 11:32:24AM +0200, Emanuele Olivetti wrote: > As you can see the solution is very simple and just based on > np.logaddexp.reduce() instead of np.exp().sum(), plus np.nan_to_num() > and a little rearrangement. As fa

[Scikit-learn-general] issue with GB and MultinomialDeviance

Hi, During the weekend I was trying to play with GradientBoostingClassifier and a dataset with a large number of classes. I observed an issue during ".fit()", due to the MultinomialDeviance class code (sklearn v0.11): /usr/lib/pymodules/python2.7/sklearn/ensemble/gradient_boosting.py:299: Ru

Re: [Scikit-learn-general] Supporting users on stackoverflow

How does the online edit UI work? I didn't know that existed... - Ursprüngliche Mail - Von: "Olivier Grisel" An: [email protected] Gesendet: Montag, 23. Juli 2012 10:22:48 Betreff: Re: [Scikit-learn-general] Supporting users on stackoverflow 2012/7/23 Jaques Grob

Re: [Scikit-learn-general] Supporting users on stackoverflow

no problem, I'll do it quick ;) 2012/7/23 Olivier Grisel > 2012/7/23 Jaques Grobler : > > I see the link to the stackoverflow page is already on the development > > website's support section.. > > Just needs to be made into a proper link.. actually, I'd like to touch up > > the support page, if

Re: [Scikit-learn-general] Supporting users on stackoverflow

2012/7/23 Jaques Grobler : > I see the link to the stackoverflow page is already on the development > website's support section.. > Just needs to be made into a proper link.. actually, I'd like to touch up > the support page, if nobody's doing that already? Yeah I did the change yesterday via the

Re: [Scikit-learn-general] Supporting users on stackoverflow

Ja, it's there, but there are things like `_. showing on the page.. which needs a ` at the front unless that's done and will show on the updated page 2012/7/23 Andreas Müller > Didn't Olivier just do that? Maybe there is still so

Re: [Scikit-learn-general] Supporting users on stackoverflow

Didn't Olivier just do that? Maybe there is still some to improve, though. - Ursprüngliche Mail - Von: "Jaques Grobler" An: [email protected] Gesendet: Montag, 23. Juli 2012 09:50:14 Betreff: Re: [Scikit-learn-general] Supporting users on stackoverflow I see the

Re: [Scikit-learn-general] Supporting users on stackoverflow

I see the link to the stackoverflow page is already on the development website's support section.. Just needs to be made into a proper link.. actually, I'd like to touch up the support page, if nobody's doing that already? 2012/7/21 denis > On 24/06/2012 14:42, Olivier Grisel wrote: > > Hi all,