[R] Brute-force clustering

[syrvn]

Hi all,

I use heatmap.2 for clustering and as you know you can choose between
several distance functions and clustering algorithms. Trying all
combinations isn't too bad but I have two further parameters and whenever I
change one of these I need do redo all cluster combinations. It probably
takes weeks to test all possible
combinations that's why I would like to use a kind of brute-force solution
to test all combinations.

One major issue is that I have 20 different cases c1-c20 and I need c1-c5 to
be in one cluster and c6-c8 in a different one and so on. So after trying a
certain combination I somehow need to check whether the cases fall into the
same clusters.

Cheers
-- 
View this message in context: http://r.789695.n4.nabble.com/Brute-force-clustering-tp2296897p2296897.html
Sent from the R help mailing list archive at Nabble.com.