2013/12/4 abhishek <[email protected]>:
> hi Olivier,
>
> Thanks for the reply.
>
> In my case each row of X contains two normal distributions (one 1-D and
> second 2-D).
> So a row of X looks like this : [ [mean1(1x1)] [variance1(1x1)] [mean2
> (1x2)] [variance2(2x2)] ]
> In case of normal distributions, do you think features will be preserved if
> i flatten mean2 and variance2 ?

I have no idea of what you are trying to do so I cannot answer that question.

To me a meaningful feature is a description of a physical quantity: a
price in dollars, a pixel intensity in an picture, a duration in
seconds, a date of an event described by the hour of the day, the day
of the week, the week of the year, a temperature in degrees, the
frequency of a given word in the text body of a email, a category
assignment (e.g. ) for the object beeing described...

-- 
Olivier
http://twitter.com/ogrisel - http://github.com/ogrisel

------------------------------------------------------------------------------
Sponsored by Intel(R) XDK 
Develop, test and display web and hybrid apps with a single code base.
Download it for free now!
http://pubads.g.doubleclick.net/gampad/clk?id=111408631&iu=/4140/ostg.clktrk
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general

Reply via email to