If you do not have SAS/OR .
data test;
input Company$ PairedCompany$;
datalines;
A C
A E
A F
A G
B H
B I
B J
C A
C E
C F
C G
D K
D L
E A
E C
E F
E G
;
data have;
set test;
rename Company=from PairedCompany=to;
run;
data full;
set have end=last;
if _n_ eq 1 then do;
declare hash h();
h.definekey('node');
h.definedata('node');
h.definedone();
end;
output;
node=from; h.replace();
from=to; to=node;
output;
node=from; h.replace();
if last then h.output(dataset:'node');
drop node;
run;
data want(keep=node household);
declare hash ha(ordered:'a');
declare hiter hi('ha');
ha.definekey('count');
ha.definedata('last');
ha.definedone();
declare hash _ha(hashexp: 20);
_ha.definekey('key');
_ha.definedone();
if 0 then set full;
declare hash from_to(dataset:'full(where=(from is not missing and to is not missing))',hashexp:20,multidata:'y');
from_to.definekey('from');
from_to.definedata('to');
from_to.definedone();
if 0 then set node;
declare hash no(dataset:'node');
declare hiter hi_no('no');
no.definekey('node');
no.definedata('node');
no.definedone();
do while(hi_no.next()=0);
household+1; output;
count=1;
key=node;_ha.add();
last=node;ha.add();
rc=hi.first();
do while(rc=0);
from=last;rx=from_to.find();
do while(rx=0);
key=to;ry=_ha.check();
if ry ne 0 then do;
node=to;output;rr=no.remove(key:node);
key=to;_ha.add();
count+1;
last=to;ha.add();
end;
rx=from_to.find_next();
end;
rc=hi.next();
end;
ha.clear();_ha.clear();
end;
stop;
run;
data final_want;
if _n_=1 then do;
if 0 then set want;
declare hash h(dataset:'want');
h.definekey('node');
h.definedata('household');
h.definedone();
end;
set test;
h.find(key:company);
drop node;
run;
... View more