Extracting information from Agglomerate.
- To: mathgroup at smc.vnet.net
- Subject: [mg87470] Extracting information from Agglomerate.
- From: "W_Craig Carter" <ccarter at mit.edu>
- Date: Fri, 11 Apr 2008 01:45:02 -0400 (EDT)
Hello,
I am beginning to explore Agglomerate. I'd like to extract information
about which elements of
a cluster are indicated by the dissimilarity measure. (I am fairly new to
discrete math)
For example,
alist = RandomReal[{0, 100}, {5, 3}];
Agglomerate[alist, Linkage -> "Single"]
For any cluster with non-trivial subclusters,
is it possible to extract the particular points of the subclusters that are
producing the nearest two points? It seems it must be computed, but hidden.
I'd like to get those points and not have to traverse the subclusters to
find them.
Thanks, Craig
--
W. Craig Carter