Weka is very weak in clustering. In fact, clustering in Weka practically does not exist. Implementations, for example. OPTICS - these are, in fact, external programs that are just called, but not integrated at all. Perhaps you should take a look at ELKI, http://elki.dbs.ifi.lmu.de/ , which is similar to Weka for detecting clustering and outlier detection (it has no classification, though - this is where Weka is strong). This one doesn't have a CURE yet. But a dozen other clusters and visualizations for them.
Anony-mousse
source share