Question

我知道标题很难理解，我很抱歉。找不到更好的方法来解释我的问题。

我有这样的事情：

 DATA HAVE;
 INPUT POLID PRODID TOSNUM PREMID X_INSURER_SERIAL_NO;
 DATALINES;
13102100206 310 0 20 .
13102100207 310 0 20 .
13102100207 310 0 21 .
13102100207 310 1 1 .
13102100207 310 1 2 .
13102100207 310 1 3 .
13102100207 310 1 20 .
13102100207 310 1 21 .
13102100207 310 2 1 .
13102100207 310 2 2 .
13102100207 310 2 20 .
13102100207 310 2 21 .
13102100207 310 3 1 .
13102100207 310 3 2 .
13102100207 310 3 9 .
13102100207 310 3 20 .
13102100207 310 3 21 .
13102100209 310 500 20 5
13102100210 310 100 20 1
13102100210 310 101 21 1
13102100210 310 100 1 1
13102100210 310 101 2 1
13102100210 310 101 3 1
13102100211 310 100 20 1
13102100211 310 101 21 1
13102100211 310 200 1 2
13102100211 310 201 2 2
13102100211 310 201 3 2
;RUN;

我需要做的是，

如果在当前行中缺少则添加premid，但在每个polid + prodid的前一行中都存在。

例如， polid = 13102100207，prodid = 310。

当tosnum = 1时，我有5种不同的preid（1,2,3,20,21）。当tosnum = 2时，我有4种不同的preid（1,2,20,21）。 premid = 3缺失。

我需要添加这个样本，并在每次添加样本时在fictive_ind列中添加1。

例如，

polid = 13102100206 只有一行，而且，计算中不包括，因为它没有以前的tosnum。

当X_INSURER_SERIAL_NO没有丢失时，它应该替换tosnum。

所以，例如，polid = 13102100210 sholud也可以从计算中排除，因为它没有任何其他先前的值（x_insurer_serial_no总是等于1）。

这就是我所做的：

首先，当x_insurer_serial_no没有丢失时替换tosnum：

PROC SQL;
CREATE TABLE AAA
AS
SELECT DISTINCT POLID, PRODID , 
CASE WHEN X_INSURER_SERIAL_NO = . THEN TOSNUM ELSE X_INSURER_SERIAL_NO END as  X_INSURER_SERIAL_NO 
FROM HAVE 
;QUIT;

然后，

我使用下面的代码，找出是否包含或排除计算中的polid sholud：

PROC SQL;
CREATE TABLE BBB AS
SELECT POLID, PRODID, COUNT(*) AS COUNT
FROM AAA
GROUP BY 
POLID, PRODID
;QUIT;

我只接受count> 1的计算行。

PROC SQL;
CREATE TABLE ABC AS
SELECT * FROM HAVE 
WHERE 
CATS(POLID,PRODID) IN 
SELECT CATS(POLID,PRODID) FROM BBB
WHERE COUNT>1;
QUIT;

现在我找到循环的最小值和最大值：

proc sql;
select min(TOSNUM), max(TOSNUM) ,  max(TOSNUM) -  min(TOSNUM) into: min_TOSNUM, :max_TOSNUM, :diff
from abc;
quit;

然后循环：

％macro fictive_premid（min_TOSNUM =，diff =）;

proc sql; 创建表fictive_premid 选择POLID，PRODID，TOSNUM，PREMID，0作为FICTIVE_IND 来自abc 其中TOSNUM =＆amp; min_TOSNUM; 退出;

%do i =  &min_TOSNUM %to %eval(&diff-1) ;
    proc sql;
    create table fictive_premid_t as
    select * from 
    (
    select polid, prodid, %eval(&i+1) as TOSNUM, premid, 1 as FICTIVE_IND
    from fictive_premid
    where TOSNUM = &i
    except
    select polid, prodid, %eval(&i+1) as TOSNUM , premid,  1 as FICTIVE_IND
    from abc
    where TOSNUM = %eval(&i+1)
    )
    union 
    select polid, prodid,%eval(&i+1) as TOSNUM, premid, 0 as FICTIVE_IND
    from abc
    where TOSNUM = %eval(&i+1);
    quit;

    proc append base=fictive_premid data=fictive_premid_t; run;

%end;


by polid prodid TOSNUM  premid
%mend;


%fictive_premid (min_TOSNUM = &min_TOSNUM, diff = &diff );

现在，

我的问题，例如，当＆amp; i的值= 4时和polid = 13102100207 ....

最后tosnum等于3，我得到6个新行，其中tosnum = 4，fictive_ind = 1。发生这种情况，当然直到＆amp; i达到＆amp; diff。

的值

请问你，

是一种在到达最后一个tosnum或x_insurer_serial_no时停止itterating的方法。

非常感谢您的帮助。

Hopefuly我很好地解释了我的需求。

Answer 1

如果我理解你的问题，我认为这可以做你想要的。这取决于TOSNUM值是增量值（即1,2,3或4,5,6），没有跳过。

/*Overwrite TOSNUM with X_INSURER_SERIAL_NO
  if it exists*/
data have;
set have;
tosnum = coalesce(X_INSURER_SERIAL_NO,TOSNUM);
run;

proc sort data=have;
by POLID PRODID TOSNUM PREMID;
run;

proc sql noprint;
/*Find polid values to delete*/
create view dist as
select distinct polid,
       prodid,
       tosnum
    from have;

create table toDelete as
    select polid,
           count(*) as count
        from dist
        group by polid
        having count = 1;

/*Delete single values*/
delete from have
    where polid in
        ( select polid from toDelete );

create table lastTosnum as
select POLID, PRODID, max(TOSNUM)+1 as Tosnum
    from have
    group by POLID, PRODID;
quit;

/*Increment TOSNUM by 1*/
data nextVals;
set have(drop=X_INSURER_SERIAL_NO );
TOSNUM = tosnum + 1;
run;

/*Delete the last TOSNUM from the set above*/
proc sql noprint;
delete from nextVals as nv
    where nv.tosnum in
        (select tosnum
            from lastTosnum as lts
            where lts.polid = nv.polid
              and lts.prodid = nv.prodid
        );
quit;

/*Merge to get the final set.*/
data want;
merge have (in=h) nextVals (in=next);
by POLID PRODID TOSNUM PREMID;

if next and ^h then
    fictive_ind = 1;
else 
    fictive_ind = 0;
/*decrement tosnum*/
tosnum = tosnum-1;

run;

使用以前的行向当前键添加行

1 个答案: