/* Two different clustering approaches generated  */
/* different data sets, bestxy and best 8; we match */
/* merge these data sets to compare the clusters    */

/* Both data sets use clusname as the cluster ID; we */
/* need to reassign the name for one of them to avoid */
/* confusion in the merge   */

data best3;
input point_id clusname;
datalines;
1      3
2      2
3      1
4      3
5      3
6      1
7      2
8      2
9      2
10      2
11      1
12      1
13      3
14      3
15      1
16      1
17      2
18      2
19      2
20      3
21      1
22      2
23      3
24      2
25      1
26      1
27      2
28      2
29      3
30      2
31      1
32      3
33      3
34      3
35      3
36      1
37      3
38      1
39      3
40      1
41      2
42      2
43      3
44      3
45      3
46      3
47      1
48      3
49      1
50      3
;
run;
data best3xy;
input point_id clusname;
datalines;
1     2
2     3
3     2
4     2
5     3
6     3
7     1
8     1
9     3
10     2
11     3
12     3
13     1
14     2
15     3
16     1
17     1
18     1
19     1
20     2
21     3
22     1
23     2
24     1
25     3
26     2
27     1
28     1
29     2
30     2
31     1
32     2
33     2
34     1
35     2
36     3
37     2
38     3
39     3
40     3
41     1
42     2
43     1
44     2
45     3
46     2
47     3
48     1
49     3
50     2
;
run;
data best3n; set best3;
clusn=clusname;
drop clusname;
/* Sort then merge by point_id        */
/* We're simply copying over the old data  */
proc sort data=best3n; by point_id;
proc sort data=best3xy; by point_id;
data compa;
merge best3n best3xy; by point_id;
/* A simple two-way table compares the cluster methods  */
proc freq data=compa;	
label clusn='Method 1' clusname='Method 2';
table clusn*clusname;
run;