Re: [Scikit-learn-general] Feature selection: floating search algorithm

Hi Nikolay, On Wed, Oct 8, 2014 at 10:03 PM, Nikolay Mayorov wrote: > Hi! > > Do you think scikit-learn will benefit from the general algorithm of feature > selection as described by P.Pudil et al. in "Floating search methods in > feature selection"? > > It is a wrapper method which alternates f

[Scikit-learn-general] Feature selection: floating search algorithm

Hi! Do you think scikit-learn will benefit from the general algorithm of feature selection as described by P.Pudil et al. in "Floating search methods in feature selection"? It is a wrapper method which alternates feature additions and removals (starting from empty or full set of features.

Re: [Scikit-learn-general] Regarding ROC from multiple classifiers

Hi Shalu. Can you show your code or explain what you tried and didn't work? Cheers, Andy On 10/07/2014 07:03 PM, shalu jhanwar wrote: Hi Scikit Users, I want to make a ROC curve to compare various classifiers. Can anybody tell me how to plot it? I am already familiar of plotting ROC using c

Re: [Scikit-learn-general] feature union

On 10/08/2014 02:35 AM, Joel Nothman wrote: > You can even just edit the file directly at > https://github.com/scikit-learn/scikit-learn/blob/master/examples/feature_stacker.py > Done. Not sure what I was thinking. -- Mee

Re: [Scikit-learn-general] cross_val_score crashes python every time

Generic python cannot use all cores efficiently when using threads because of the Global Interpreter Lock [1]. This is why people use multiprocessing instead of threading. multiprocessing can be quite complex to use properly though. I would advise you to use the joblib wrapper instead. Please see

Re: [Scikit-learn-general] using svmlight trained file with nltk

Oh yeah, sorry for mistake. On Wed, Oct 8, 2014 at 3:12 PM, Lars Buitinck wrote: > 2014-10-08 11:32 GMT+02:00 Karimkhan Pathan : > > can I use this trained file with nltk to classify `plain input text`? > > This is the scikit-learn mailing list. You should be asking on the NLTK ML. > > > ---

Re: [Scikit-learn-general] using svmlight trained file with nltk

2014-10-08 11:32 GMT+02:00 Karimkhan Pathan : > can I use this trained file with nltk to classify `plain input text`? This is the scikit-learn mailing list. You should be asking on the NLTK ML. -- Meet PCI DSS 3.0 Complia

[Scikit-learn-general] using svmlight trained file with nltk

I have 114MB sized model file which is trained using svmlight. file looks like : *SVM-light Version V6.020 # kernel type3 # kernel parameter -d1 # kernel parameter -g1 # kernel parameter -s1 # kernel parameter -rempty# kernel parameter -u69