我以 Haikuo Bian 的回答为起点，开发了一种稍微复杂一些的算法，该算法似乎适用于我迄今为止尝试过的所有测试用例。它可能会进一步优化，但它可以在我的 PC 上在一秒钟内处理 20000 行，同时只使用几 MB 内存。输入数据集不需要按任何特定顺序排序，但正如所写，它假设每一行至少出现一次，id1
测试用例：
/* Original test case */
data have;
input id1 id2;
cards;
1 4
1 5
2 5
2 6
3 7
4 1
5 1
5 2
6 2
7 3
;
run;
/* Revised test case - all in one group with connecting row right at the end */
data have;
input ID1 ID2;
/*Make sure each row has id1 < id2*/
if id1 > id2 then do;
t_id2 = id2;
id2 = id1;
id1 = t_id2;
end;
drop t_id2;
cards;
2 5
4 8
2 4
2 6
3 7
4 1
9 1
3 2
6 2
7 3
;
run;
/*Full scale test case*/
data have;
do _N_ = 1 to 20000;
call streaminit(1);
id1 = int(rand('uniform')*100000);
id2 = int(rand('uniform')*100000);
if id1 < id2 then output;
t_id2 = id2;
id2 = id1;
id1 = t_id2;
if id1 < id2 then output;
end;
drop t_id2;
run;
代码：
option fullstimer;
data _null_;
length id group 8;
declare hash h();
rc = h.definekey('id');
rc = h.definedata('id');
rc = h.definedata('group');
rc = h.definedone();
array ids(2) id1 id2;
array groups(2) group1 group2;
/*Initial group guesses (greedy algorithm)*/
do until (eof);
set have(where = (id1 < id2)) end = eof;
match = 0;
call missing(min_group);
do i = 1 to 2;
rc = h.find(key:ids[i]);
match + (rc=0);
if rc = 0 then min_group = min(group,min_group);
end;
/*If neither id was in a previously matched group, create a new one*/
if not(match) then do;
max_group + 1;
group = max_group;
end;
/*Otherwise, assign both to the matched group with the lowest number*/
else group = min_group;
do i = 1 to 2;
id = ids[i];
rc = h.replace();
end;
end;
/*We now need to work through the whole dataset multiple times
to deal with ids that were wrongly assigned to a separate group
at the end of the initial pass, so load the table into a
hash object + iterator*/
declare hash h2(dataset:'have(where = (id1 < id2))');
rc = h2.definekey('id1','id2');
rc = h2.definedata('id1','id2');
rc = h2.definedone();
declare hiter hi2('h2');
change_count = 1;
do while(change_count > 0);
change_count = 0;
rc = hi2.first();
do while(rc = 0);
/*Get the current group of each id from
the hash we made earlier*/
do i = 1 to 2;
rc = h.find(key:ids[i]);
groups[i] = group;
end;
/*If we find a row where the two ids have different groups,
move the id in the higher group to the lower group*/
if groups[1] < groups[2] then do;
id = ids[2];
group = groups[1];
rc = h.replace();
change_count + 1;
end;
else if groups[2] < groups[1] then do;
id = ids[1];
group = groups[2];
rc = h.replace();
change_count + 1;
end;
rc = hi2.next();
end;
pass + 1;
put pass= change_count=; /*For information only :)*/
end;
rc = h.output(dataset:'want');
run;
/*Renumber the groups sequentially*/
proc sort data = want;
by group id;
run;
data want;
set want;
by group;
if first.group then new_group + 1;
drop group;
rename new_group = group;
run;
/*Summarise by # of ids per group*/
proc sql;
select a.group, count(id) as FREQ
from want a
group by a.group
order by freq desc;
quit;
有趣的是，如果 id1 已经匹配，则在初始阶段不检查 id2 组的建议优化实际上在这个扩展算法中减慢了一些速度，因为这意味着在随后的阶段中必须做更多的工作，如果id2 位于编号较低的组中。例如。我之前进行的试运行的输出：
使用“优化”：
pass=0 change_count=4696
pass=1 change_count=204
pass=2 change_count=23
pass=3 change_count=9
pass=4 change_count=2
pass=5 change_count=1
pass=6 change_count=0
NOTE: DATA statement used (Total process time):
real time 0.19 seconds
user cpu time 0.17 seconds
system cpu time 0.04 seconds
memory 9088.76k
OS Memory 35192.00k
没有：
pass=0 change_count=4637
pass=1 change_count=182
pass=2 change_count=23
pass=3 change_count=9
pass=4 change_count=2
pass=5 change_count=1
pass=6 change_count=0
NOTE: DATA statement used (Total process time):
real time 0.18 seconds
user cpu time 0.16 seconds
system cpu time 0.04 seconds