Rapid-I Forum » General Community » Data Mining » k-means convergence
Pages: [1]
« previous next »
  Print  
Author Topic: k-means convergence  (Read 727 times)
mahi.aw
Newbie
*
Posts: 1
« on: June 30, 2011, 07:17:33 PM »
Hi all,,
Need your suggestions on k-means clustering..

i am trying to cluster the data using k-means..
but somehow my algorithm terminates after 4-5 steps..i do not know whether this is normal behavior of k-means algorithm or something wrong in my code or understanding of algorithm by me?
data set is in the range 0-2.

looking for suggestions??
Logged
Ingo Mierswa
Administrator
Hero Member
*****
Posts: 1207



WWW
« Reply #1 on: July 01, 2011, 05:51:51 PM »
Hi,

well, this is nothing too unusual. If the data is "easy" to cluster, the number of clusters fits well (and usually is small), then convergence is indeed often reached quite fast. I can, however, not say more without seeing the data, sorry.

Cheers,
Ingo
Logged
Did you try our new Marketplace? Upload or download new Extensions, add comments, and organize your operators. Have a look at  http://marketplace.rapid-i.com
Pages: [1]
  Print  
« previous next »
 
Jump to: