Subject: syntheticcontroldata clustering example failure due to combiner

  Adil Aijaz 2009-06-10, 17:49
  Jeff Eastman 2009-06-10, 23:30
  Jeff Eastman 2009-06-11, 00:04
  Jeff Eastman 2009-06-11, 03:54
  Jeff Eastman 2009-06-11, 03:59
  Adil Aijaz 2009-06-11, 16:49
  Benson Margulies 2009-06-11, 17:06
  Jeff Eastman 2009-06-11, 17:22
  Jeff Eastman 2009-06-11, 17:32
For L_2 centroids, you just have to have the mapper emit a trivial sum and a
count (of 1).  The combiner should take a list of vector sums and counts and
produce a combined sum and count.

Then the reducer will get a sums and counts and it should add them together
and divide by the count.

(just like n-dimensional word count!)

On Thu, Jun 11, 2009 at 9:49 AM, Adil Aijaz <[EMAIL PROTECTED]> wrote:
--
Ted Dunning, CTO
DeepDyve

111 West Evelyn Ave. Ste. 202
Sunnyvale, CA 94086
http://www.deepdyve.com
858-414-0013 (m)
408-773-0220 (fax)
  Ted Dunning 2009-06-11, 20:03