Re: K means.

[Søren Hauberg]

fre, 09 12 2011 kl. 08:00 +0100, skrev Søren Hauberg:
> My current version works like
> 
>   clusters = kmeans (data, initial_clusters);
> 
> whereas Matlab's work like
> 
>   clusters = kmeans (data, number_of_clusters);
> 
> I think we should at least match this before putting it into the
> statistics package. But otherwise, I see no problems with not having all
> the options available that Matlab has.

The attached version has a more compatible API. It's not perfect, but it
seems to work fairly well.

Søren

kmeans.m
Description: Text Data