I am bit relunctant to support normalize as to be consistent it should be done everywhere including for example in SVM models. Also normalization with unit standard deviation is not always what you want to do: if you have an outlier coefficient it will collapse the good values to 0. hence you might want a "robust" scaling, also for fMRI we often scale by subject or session and not globally etc. To me there many good ways of scaling / normalizing and I prefer to let the user use a proper pipeline than support only a specific normalization everywhere. The only issue I see with the scaling pipeline is that it breaks with sparse data as centering breaks sparsity but an estimator can be smart enough to take care of normalizing without actually centering the data (cf. lasso coordinate descent).
anyone can give some input from other packages in R or else to say how it is handled? is normalization present and active everywhere? Alex On Sat, Nov 10, 2012 at 6:30 PM, Gael Varoquaux <gael.varoqu...@normalesup.org> wrote: > On Wed, Oct 31, 2012 at 06:10:13PM +0100, Alexandre Gramfort wrote: >> fine with me but do you push the logic further to any linear estimator ? >> For example in Ridge we also have normalize=False by default. > > Should normalize be on by default in Ridge, or should it not, based on > your experience of linear models? I have a hard time to tell. > > G > > > ------------------------------------------------------------------------------ > Everyone hates slow websites. So do we. > Make your web apps faster with AppDynamics > Download AppDynamics Lite for free today: > http://p.sf.net/sfu/appdyn_d2d_nov > _______________________________________________ > Scikit-learn-general mailing list > Scikit-learn-general@lists.sourceforge.net > https://lists.sourceforge.net/lists/listinfo/scikit-learn-general ------------------------------------------------------------------------------ Everyone hates slow websites. So do we. Make your web apps faster with AppDynamics Download AppDynamics Lite for free today: http://p.sf.net/sfu/appdyn_d2d_nov _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
