Re: Information-theoretic functions (David Bateman)

On Mon, 2006-11-20 at 19:21 +0100, Joseph Wakeling wrote:
> -----BEGIN PGP SIGNED MESSAGE-----
> Hash: SHA1
> 
> Muthiah Annamalai wrote:
> > I think you can look at the CVS online via source-forge's
> > website. The link to the information theory toolbox is at:
> > http://octave.cvs.sourceforge.net/octave/octave-forge/main/info-theory/inst/
> > 
> > I think of the functions you have presented, infogain.m is something
> > that is not in the toolbox. I suggest to you to please look through the
> > source files already in info-theory toolbox, and see if you can rework
> > the infogain.m. 
> 
> Thanks for the link.  It looks like in fact our functions are
> complementary: for example your entropy.m function calculates
> information entropy from the set of probabilities, whereas mine takes a
> sequence (or two sequences) and calculates, first the probabilities,
> then the resulting entropy (or joint entropy).
> 
> So, why don't I rewrite my functions to interact with yours? For
> example, I can write entropy_seq(x) which takes a sequence, calculates
> the probabilities, and then calls your function entropy() to get the answer.
> 
> Best wishes,
> 
>     -- Joe
> 
> 
Sounds good!
Thanks
Muthu


> -----BEGIN PGP SIGNATURE-----
> Version: GnuPG v1.4.3 (GNU/Linux)
> Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org
> 
> iD8DBQFFYfIzcjylL0sfzuERAnQXAJ4l0RvVGYRbsHI1jqwqCFdLtPXn4QCfRcO1
> iqX4KfRVAGuvfQOC1ZEktTA=
> =jJq+
> -----END PGP SIGNATURE-----