写在前面。
新手小白，疏漏在所难免，如果您看完有所指正，那我会很感谢您。如果您看完有所收获，那是我的荣幸。
SAS编程实践---宏：按系统术语和首选术语分层次计算受试者发生不良反应（AE）例数和例次
其实是对上述文章的完善，上面文章没有最后的代码汇总，也没解释参数意义。
有读者要应用的话需要一块一块复制代码，很费劲，还可能复制漏了，实在是不方便。
因此本文主要内容是上篇文章的示例数据生成代码和宏代码汇总版本。
示例数据生成代码
proc delete data = work._ALL_;
run;
%let seed1 = 666666;
data adae;
do ii = 1 to 3;
armn = ii;
arm = cats("第",put(ii, best.) ,"组");
do jj = 1 to 100;
usubjid = cats( "X",put(ii, best.) ,"-", put(jj, z3.));
soc = cats( "SOC",put(ranbin( &seed1., 5, 0.2) + 1, best.) );
pt = cats( "PT", compress(soc, , "kd") , put(ranbin( &seed1., 10, 0.1) + 1, best.) );
AESEVN = ranbin( &seed1., 4, 0.5) + 1;
AESEV = cats(AESEVN, "级");
output;
end;
end;
run;
data adsl;
do ii = 1 to 3;
armn = ii;
arm = cats("第",put(ii, best.) ,"组");
do jj = 1 to 100;
usubjid = cats( "X",put(ii, best.) ,"-", put(jj, z3.));
output;
end;
end;
run;
宏代码汇总版本
%macro AESOCPT(
libin= ,
dtin = ,
adsl = ,
usubjid = ,
l1var = ,
l2var = ,
grpvarn = ,
rowsumyn = ,
colsumyn = ,
libout = ,
dtout = );
/*******************************************************************************************
Purpose：按系统术语、首选术语和严重程度分层次计算受试者发生不良反应（AE）例数和例次
libin：输入数据集所在逻辑库，如work；
dtin：用于分析的输入数据集，可以跟筛选条件，也可以提前处理好，如adlb(where = FASFL = "是")；
adsl：adsl数据集，用于确定受试者数量；
usubjid：受试者编号，用于确定受试者数量；
l1var：层级1的变量，如器官系统术语，AEBODSYS；
l2var：层级2的变量，如首选术语，AEDECOD；
grpvarn：受试者实验分组变量，数值型；
rowsumyn：指定是否计算合计列，取值限定为Y或者N；
colsumyn：指定是否计算首行合计，取值限定为Y或者N；
libout：输出数据集所在逻辑库，如work；
dtout：输出数据集名称，如Table1；
**************************************************************************************************/
*_1. pre-processing;
*_1.1 macro variables;
*subjid number;
proc sql noprint;
select count(distinct &grpvarn.) , count(distinct &usubjid.) into: grpnum, : SUBN999 from &adsl.;
quit;
%put 受试者数量：&SUBN999. 分组数量：&grpnum.;
%do xx = 1 %to &grpnum.;
proc sql noprint;
select count(distinct &usubjid.) into:SUBN&xx. from &adsl. where &grpvarn. = &xx.;
quit;
%put &grpvarn. = &xx.组的受试者数量： &&SUBN&xx.;
%end;
*_1.2 input datasets processing;
data stdt0;
set &libin..&dtin.;
run;
proc sort data=stdt0 out=&l1var._ nodupkey;
by &l1var.;
run;
data &l1var.n;
set &l1var._;
&l1var.n = _N_;
proc sort;
by &l1var.;
run;
proc sort data=stdt0;
by &l1var.;
run;
*_1.2.1 for times of case;
data times1;
merge stdt0
&l1var.n;
by &l1var.;
run;
data times2;
set times1;
&l1var. = "合计";
&l1var.n = 0;
&l2var. = "合计";
run;
*_1.2.2 for number of case;
data case1;
merge stdt0
&l1var.n;
by &l1var.;
run;
proc sort data=case1 out=cs1nodup nodup dupout=cs1dup;
by &usubjid. &l1var.n &l1var. &l2var.;
run;
proc sort data=case1 out=cs2nodup nodup dupout=cs2dup;
by &usubjid. &l1var.n &l1var.;
run;
data case2;
set cs2nodup;
&l1var. = "合计";
&l1var.n = 0;
&l2var. = "合计";
run;
*_2.stat step;
*_2.1 number of case;
%do aa = 1 %to &grpnum.;
proc sql noprint;
create table ST_&aa. as
select &l1var.n, &l1var., "合计" as &l2var.,
cats(sum(&grpvarn. = &aa.), "(", put(sum(&grpvarn. = &aa.)/&&SUBN&aa.*100, 8.2), ")") as CASE_&aa.,
sum(&grpvarn. > 0) + 0.2 as seq1
from cs1nodup
group by &l1var.n, &l1var.
union
select &l1var.n, &l1var., &l2var.,
cats(sum(&grpvarn. = &aa.), "(", put(sum(&grpvarn. = &aa.)/&&SUBN&aa.*100, 8.2), ")") as CASE_&aa.,
sum(&grpvarn. > 0) +0.1 as seq1
from cs1nodup
group by &l1var.n, &l1var., &l2var.
union
select &l1var.n, &l1var., "合计" as &l2var.,
cats(sum(&grpvarn. = &aa.), "(", put(sum(&grpvarn. = &aa.)/&&SUBN&aa.*100, 8.2), ")") as CASE_&aa.,
sum(&grpvarn. > 0) + 1 as seq1
from case2
group by &l1var.n, &l1var.
;
quit;
proc sort data= ST_&aa.;
by &l1var.n &l1var. &l2var.;
run;
%end;
*_2.2 times of case;
%do aa = 1 %to &grpnum.;
proc sql noprint;
create table ST_&aa._ as
select &l1var.n, &l1var., "合计" as &l2var.,
cats(sum(&grpvarn. = &aa.)) as CASE_&aa._ ,
sum(&grpvarn. > 0) + 0.2 as seq2
from times1
group by &l1var.n, &l1var.
union
select &l1var.n, &l1var., &l2var.,
cats(sum(&grpvarn. = &aa.)) as CASE_&aa._ ,
sum(&grpvarn. > 0) +0.1 as seq2
from times1
group by &l1var.n, &l1var., &l2var.
union
select &l1var.n, &l1var., "合计" as &l2var.,
cats(sum(&grpvarn. = &aa.)) as CASE_&aa._ ,
sum(&grpvarn. > 0) + 1 as seq2
from times2
group by &l1var.n, &l1var.
;
quit;
proc sort data= ST_&aa._;
by &l1var.n &l1var. &l2var.;
run;
%end;
*_2.3 caculation of each row;
%if %sysfunc(upcase(&rowsumyn.) ) = %str(Y) %then
%do;
%put WARNING: 已经计算每行合计;
*_2.3.1 caculation of each row for number of case;
proc sql noprint;
create table ST_99 as
select &l1var.n, &l1var., "合计" as &l2var., 1 as idid,
cats(sum(&grpvarn. > 0), "(", put(sum(&grpvarn. > 0)/&SUBN999.*100, 8.2), ")") as CASE_99,
sum(&grpvarn. > 0) + 0.2 as seq1
from cs1nodup
group by &l1var.n, &l1var.
union
select &l1var.n, &l1var., &l2var., 2 as idid,
cats(sum(&grpvarn. > 0), "(", put(sum(&grpvarn. > 0)/&SUBN999.*100, 8.2), ")") as CASE_99,
sum(&grpvarn. > 0) + 0.1 as seq1
from cs1nodup
group by &l1var.n, &l1var., &l2var.
union
select &l1var.n, &l1var., "合计" as &l2var., 3 as idid,
cats(sum(&grpvarn. > 0), "(", put(sum(&grpvarn. > 0)/&SUBN999.*100, 8.2), ")") as CASE_99,
sum(&grpvarn. > 0) + 1 as seq1
from case2
group by &l1var.n, &l1var.
;
run;
proc sort data= ST_99;
by &l1var.n &l1var. &l2var.;
run;
*_2.3.2 caculation of each row for times of case;
proc sql noprint;
create table ST_99_ as
select &l1var.n, &l1var., "合计" as &l2var., 1 as idid,
cats(sum(&grpvarn. > 0) ) as CASE_99_,
sum(&grpvarn. > 0) + 0.2 as seq2
from times1
group by &l1var.n, &l1var.
union
select &l1var.n, &l1var., &l2var., 2 as idid,
cats(sum(&grpvarn. > 0) ) as CASE_99_,
sum(&grpvarn. > 0) + 0.1 as seq2
from times1
group by &l1var.n, &l1var., &l2var.
union
select &l1var.n, &l1var., "合计" as &l2var., 3 as idid,
cats(sum(&grpvarn. > 0) ) as CASE_99_,
sum(&grpvarn. > 0) + 1 as seq2
from times2
group by &l1var.n, &l1var.
;
run;
proc sort data= ST_99_;
by &l1var.n &l1var. &l2var.;
run;
%end;
%else
%do;
%put WARNING: 不计算每行合计;
%end;
*_2.4 caculation of each column;
data _0&dtout.;
merge ST_:
;
by &l1var.n &l1var. &l2var.;
%if %sysfunc(upcase(&colsumyn.) ) = %str(Y) %then
%do;
%put WARNING: 已经计算每列合计;
%end;
%else
%do;
%put WARNING: 不计算每列合计;
if &l1var.n = 0 then
delete;
%end;
proc sort;
by &l1var.n descending seq1 descending seq2;
run;
run;
*_3 processing step of stat;
data _1&dtout.;
set _0&dtout.;
by &l1var.n descending seq1 descending seq2;
if first.&l1var.n or first.&l1var. then
&l1var. = &l1var.;
else &l1var. = " "||&l2var.;
keep &l1var. CASE_:;
run;
* _4.output steps;
proc contents data= _1&dtout. out= _1outs noprint;
proc sort;
by varnum;
run;
proc sql noprint;
select count(distinct NAME) , NAME into:varn,:col1-:col99 from _1outs;
quit;
data &libout..&dtout.;
set _1&dtout.;
%do ii = 1 %to &varn.;
if &&col&ii. = "0(0.00)" then
&&col&ii. ="0";
%let jj = %eval(&ii. - 1);
rename &&col&ii. = C&jj.;
%end;
run;
proc datasets lib=work noprint;
delete &l1var._ &l1var.n times: case: cs: st: _:;
run;
%mend;
%AESOCPT(libin=work ,
dtin = adae ,
adsl = adsl ,
usubjid = usubjid ,
l1var =soc ,
l2var = pt,
grpvarn = armn,
rowsumyn = Y,
colsumyn =Y ,
libout =work ,
dtout = table);
以上。
