Re: [scikit-learn] VOTE: scikit-learn governance document

+1 On Tue, 19 Feb 2019 at 20:40, Fabian Pedregosa wrote: > > +1 (not sure if my previous email went through) > > On Tue, Feb 19, 2019 at 11:31 AM Andreas Mueller wrote: >> >> >> >> On 2/19/19 10:55 AM, Paolo Losi wrote: >> > +1 if my opinion matters >> > >> Thank you and it does :) >> >> >>

Re: [scikit-learn] VOTE: scikit-learn governance document

Hi Andy, I read through to document. Even though I have not been really active these past months/years, I think it summarizes well our governance model. +1. Gilles On Sat, 9 Feb 2019 at 12:01, Adrin wrote: > > +1 > > Thanks for the work you've put in it! > > On Sat, Feb 9, 2019, 03:00 Andreas

Re: [scikit-learn] Breiman vs. scikit-learn definition of Feature Importance

, though. > Probably not even the ExtraTrees. > I really need to get around to reading your thesis :-/ > Do you recommend using max_features=1 with ExtraTrees? > On 05/05/2018 05:21 AM, Gilles Louppe wrote: > > Hi, > > > > See also chapters 6 and 7 of http://arxiv.or

Re: [scikit-learn] Breiman vs. scikit-learn definition of Feature Importance

Hi, See also chapters 6 and 7 of http://arxiv.org/abs/1407.7502 for another point of view regarding the "issue" with feature importances. TLDR: Feature importances as we have them in scikit-learn (i.e. MDI) are provably **not** biased, provided trees are built totally at random (as in ExtraTrees w

Re: [scikit-learn] Label encoding for classifiers and soft targets

Hi Javier, In the particular case of tree-based models, you case use the soft labels to create a multi-output regression problem, which would yield an equivalent classifier (one can show that reduction of variance and the gini index would yield the same trees). So basically, reg = RandomForestRe