Re: [Gretl-users] clustering

Am 21.06.2018 um 09:27 schrieb Sven Schreiber: Sorry to answer to myself, but it seems not. I'm attaching a function that uses gretl's internal kernel density estimate to cluster the input data based on that. The idea is that all values "around" a peak in the density belong to the same cluster (or group, or region). So the number of estimated peaks determines the number of clusters. Quoting the comment in the function: Maps the input values in z to clusters defined as the neighborhoods     around the local maxima of the estimated (kernel) density.     Each cluster range goes from one (local) minimum to the next.     If the density is single-peaked, there is only one pseudo-cluster,     and the result is a vector of ones.     Returns a vector of the same length as z where each observed value     is replaced with the assigned cluster number 1..K. (Clusters are     ordered ascending.) I'm sure there is a fancy name in the literature out there for this type of algorithm, and I'm happy to learn it. Also I'm glad for any feedback as to what are optimal/reasonable/common choices for the kernel smoothing parameter in such an application. A test call to use the function is something like this: <hansl> # random test input for densclust: clear include densclust.inp    # put the attached file in the same path matrix z = 0.5 * mnormal(100,1) - 4 z |= 2 * mnormal(50,1) + 2 # different cluster region around 2 z |= mnormal(50,1) + 8 # and another one around 8 # test call: matrix m = densclust(z) eval z ~ m # same thing with capturing the interim results matrix tt dd densclust(z, ,,, &tt, &dd) print tt gnuplot 2 1 --matrix=dd --output=display </hansl> thanks, sven