BookmarkSubscribeRSS Feed
himali
Calcite | Level 5

Hi,

 

I am trying to run fastclus and want to understand how does these options work in a PROC FASTCLUS. Does maxiter option override replace option or there is a difference in these two?

Proc fastclus data=all
out = cluster_exp
radius = .0001
delete = 1000
maxiter = 10000
maxclusters = 15 
Converge=0.001
replace = none;
var Factor:;
run;

 

1 REPLY 1
Rick_SAS
SAS Super FREQ

See the Overview section of the doc to see the algoritm.  When I read the doc, it sounds like the MAXITER= and the REPLACE= option are independent.  The MAXITER= option specifies how many times you should repeat Step 3 if the algorithm. The REPLACE= option specifies how Step 3 occurs.  

 

I've never used the REPLACE= option, but to me the doc says that your code will use random seeds.as the initial cluster centers. Because you've set REPLACE=NONE,  those centers will not change for the next 10,000 iterations.  

Ready to join fellow brilliant minds for the SAS Hackathon?

Build your skills. Make connections. Enjoy creative freedom. Maybe change the world. Registration is now open through August 30th. Visit the SAS Hackathon homepage.

Register today!
What is ANOVA?

ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 1 reply
  • 1243 views
  • 0 likes
  • 2 in conversation