KCLUS Procedure

(View the complete code for this example.)

This example uses the same data table that is loaded into your CAS session in Example 16.1.

You can find the number of clusters in the data table by specifying NOC=ABC in the PROC KCLUS statement as follows:

data mylib.iris;
   set sashelp.iris;
run;

proc kclus data=mylib.iris maxclusters=9 seed=1234
           NOC=ABC(B=10 minclusters=2 align=PCA criterion=FIRSTPEAK);
   input SepalLength SepalWidth PetalLength PetalWidth;
   ods output ABCStats=ABCStats1;
run;

PROC KCLUS generates several ODS tables, some of which are shown in Output 16.2.1 through Output 16.2.4.

Output 16.2.1 shows the parameters that are used in the aligned box criterion (ABC) method.

Output 16.2.2 shows the statistics that are obtained for each candidate number of clusters.

When you use the NOC= option, the KCLUS procedure first estimates the number of clusters, k, and then it displays the cluster analysis results for each of the k clusters as shown in Output 16.2.4.