On 24 April 2012 18:01, Daniel Ward wrote:
> No problem. I will get some documentation together. I also added a couple
> more options since then. I will pull the changes down to see
> the preferred format.
>
> I will try to get another patch to you in a couple of days. I will be making
> the appro
On 20 April 2012 05:56, Daniel Ward wrote:
> I have attacked the patch.
>
> This will expand the returned items to closer match the Matlab kmeans. It
> will also add the 'emptyaction' property with the 'singleton' value. This
> will allow for the kmeans algorithm to handle empty cluster better. It
