Re: [Scikit-learn-general] GSOC proposal update: Optimizing sparse linear models using coordinate descent and strong rules

On 20 April 2012 09:05, Olivier Grisel wrote: > > References > > - Does Google expect full referencing style? If so, put that in. > > Google does not care (it's an abstract entity devoid of morality and > judgment... so far), PSF mentors that review the proposals might car > but most GSoC project

Re: [Scikit-learn-general] GSOC proposal update: Optimizing sparse linear models using coordinate descent and strong rules

> References > - Does Google expect full referencing style? If so, put that in. Google does not care (it's an abstract entity devoid of morality and judgment... so far), PSF mentors that review the proposals might car but most GSoC projects are not scientific anyway, hence most of them don't have

Re: [Scikit-learn-general] GSOC proposal update: Optimizing sparse linear models using coordinate descent and strong rules

Hi! It looks great, if you would like some minor comments, here they are: *Abstract* - I suggest focusing on the what you will do first, then the where ("linear models, to be implemented in sklearn", rather than "this is sklearn, I'm going to do linear models"). - "This task includes high test co

Re: [Scikit-learn-general] ROC curve

> Thank's Immanuel, would like to use python, but I study this alternative. my feeling is that it is not that hard to reimplement so if you do, please do not hesite to share the code with a gist or better a pull request. Alex --

Re: [Scikit-learn-general] ROC curve

Yes! Olivier, as the Immanuel said. There is already a multi-class approach to. Thank's Immanuel, would like to use python, but I study this alternative. Regards, On 19 April 2012 12:56, Immanuel B wrote: > Hi, > > the ROC curve has indeed been extended to the multiclass case. > for example:

Re: [Scikit-learn-general] ROC curve

Hi, the ROC curve has indeed been extended to the multiclass case. for example: A simplified extension of the Area under the ROC to the multiclass domain http://homepage.tudelft.nl/a9p19/papers/prasa_06_vuc.pdf I have used the R pROC package for that, maybe that’s an option.

Re: [Scikit-learn-general] ROC curve

Le 19 avril 2012 07:32, Paulo Henrique Junqueira Amorim a écrit : > Hi, > > I'm trying to plot ROC curve from multiple multiclass. It seems to me that > the library does not, how could get around it? the data I have are these: > > precision    recall  f1-score   support > 0  

[Scikit-learn-general] ROC curve

Hi, I'm trying to plot ROC curve from multiple multiclass. It seems to me that the library does not, how could get around it? the data I have are these: precisionrecall f1-score support 0 0.00 0.00 0.00 1 1 1.00 1.00 1.

Re: [Scikit-learn-general] GSOC proposal update: Optimizing sparse linear models using coordinate descent and strong rules

Done, thanks for pointing out the urgency I wasn't aware of it. 2012/4/19 Olivier Grisel : > Le 19 avril 2012 03:41, Immanuel B a écrit : >> Hello all, >> >> I rewrote the timeline part of my proposal in order to make it better >> readable and provide clearer definitions for the steps I intend to

Re: [Scikit-learn-general] GSOC proposal update: Optimizing sparse linear models using coordinate descent and strong rules

Le 19 avril 2012 03:41, Immanuel B a écrit : > Hello all, > > I rewrote the timeline part of my proposal in order to make it better > readable and provide clearer definitions for the steps I intend to follow. > > I would be greatfull for any comments be it on content, formulation or > anything >

[Scikit-learn-general] GSOC proposal update: Optimizing sparse linear models using coordinate descent and strong rules

Hello all, I rewrote the timeline part of my proposal in order to make it better readable and provide clearer definitions for the steps I intend to follow. I would be greatfull for any comments be it on content, formulation or anything else before I update my proposal on the GSOC site. https://d