I've not tried this particular use case personally but it should be possible. NamedVectors flow transparently through k-means and Dirichlet, indeed they should be transparent in all Vector clustering. When you run the final clustering (-cl) step with Dirichlet, this will use the final iteration's cluster centers and a distance-based assignment using the distance measure you specify. You can select the most likely assignment or one that is pdf-based.
On Oct 7, 2013, at 10:36 AM, Taner Diler <[email protected]> wrote: > Hi, > > Is it possible to get dirichlet clustering result with named vector as in > k-means? > > with named vector in k-means, I can get files located in clusters.
