Great work indeed! Thanks to everybody involved! BTW: I find Gael's suggestion to include comparisons of different methods and giving rule of thumbs on how to choose between them a great idea. Maybe we could adopt that throughout the scikit... (something like Table 10.1 in ESLII, Section 'Off-the-shelve procedures for Data Mining' comes into my mind)
2011/9/16 Matthieu Brucher <[email protected]>: > Excellent, indeed! > > Perhaps a small enhancement: Isomap is not an extension of MDS, it is "just" > another MDS. The classical MDS is PCA, and Isomap is a metric MDS (it's the > official term found in the litterature). > > Cheers et keep up the good work! > > Matthieu > > 2011/9/16 xinfan meng <[email protected]> >> >> Fantastic indeed! >> >> BTW, the illustration picture in >> http://scikit-learn.sourceforge.net/dev/auto_examples/manifold/plot_compare_methods.html >> seems to be positioned incorrectly. >> >> On Thu, Sep 15, 2011 at 10:45 PM, Gael Varoquaux >> <[email protected]> wrote: >>> >>> I am just writting an email advertising the manifold learning part of the >>> scikit, and I linked to the docs: >>> http://scikit-learn.sourceforge.net/dev/modules/manifold.html >>> >>> All I must say it: wow fantastic docs. I remembered that it was good, but >>> coming back to it makes me think that it is absolutely an ideal example >>> of good docs: >>> >>> - A leading self-explaining summary figure (with the code generating it, >>> of course) >>> - An outline that match quite clearly the different main topics of the >>> example >>> - Each part giving intuitions and an example, before discussing the >>> computational complexity >>> - Practical tips (very important) >>> >>> The only thing that I could see that could be added would be a table >>> comparing the different methods and giving rule of thumbs on how to >>> choose between them. >>> >>> Great work, Jake and the others! You rock absolutely. Thank you so much, >>> in the name of the users who will read these docs, and never actually >>> come on the mailing list to thank you. >>> >>> Gael >>> >>> >>> ------------------------------------------------------------------------------ >>> Doing More with Less: The Next Generation Virtual Desktop >>> What are the key obstacles that have prevented many mid-market businesses >>> from deploying virtual desktops? How do next-generation virtual >>> desktops >>> provide companies an easier-to-deploy, easier-to-manage and more >>> affordable >>> virtual desktop model.http://www.accelacomm.com/jaw/sfnl/114/51426474/ >>> _______________________________________________ >>> Scikit-learn-general mailing list >>> [email protected] >>> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general >> >> >> >> -- >> Best Wishes >> -------------------------------------------- >> Meng Xinfan（蒙新泛） >> Institute of Computational Linguistics >> Department of Computer Science & Technology >> School of Electronic Engineering & Computer Science >> Peking University >> Beijing, 100871 >> China >> >> >> ------------------------------------------------------------------------------ >> BlackBerry® DevCon Americas, Oct. 18-20, San Francisco, CA >> http://p.sf.net/sfu/rim-devcon-copy2 >> _______________________________________________ >> Scikit-learn-general mailing list >> [email protected] >> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general >> > > > > -- > Information System Engineer, Ph.D. > Blog: http://matt.eifelle.com > LinkedIn: http://www.linkedin.com/in/matthieubrucher > > ------------------------------------------------------------------------------ > BlackBerry® DevCon Americas, Oct. 18-20, San Francisco, CA > http://p.sf.net/sfu/rim-devcon-copy2 > _______________________________________________ > Scikit-learn-general mailing list > [email protected] > https://lists.sourceforge.net/lists/listinfo/scikit-learn-general > > -- Peter Prettenhofer ------------------------------------------------------------------------------ BlackBerry® DevCon Americas, Oct. 18-20, San Francisco, CA http://p.sf.net/sfu/rim-devcon-copy2 _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
