哈希合并宏 - 使用文件记录指示器 "HASH + point = Key"

Hash Merge Macro - using a file record indicator "HASH + point = Key"

希望将此宏更新为 HASH + point = key。对于我们的一个数据运行,我们已经开始超出当前版本的此宏的内存限制。我寻求帮助的原因是因为我没有太多时间并且从未真正分析过这段代码,因为它直到最近才成为我流程的一部分。

https://www.lexjansen.com/nesug/nesug11/ld/ld01.pdf,我真正不明白的是 RID 是如何设置的以及如何将它合并到我们的宏中。我什至不知道我们当前的宏是否可以这样做。

如有任何帮助,我们将不胜感激。

%macro hashmerge2(varnm,onto,from,byvars,obsqty);

%let data_vars   = %trim   (&varnm);
%let data_vars_a = %sysfunc(tranwrd(&data_vars.,%str( ),%str(" , ")));
%let data_vars_b = %sysfunc(tranwrd(&data_vars.,%str( ), %str(,)));
%let data_key    = %trim   (&byvars);
%let data_key    = %sysfunc(tranwrd(&data_key.,%str( ), %str(" , ")));

%if %index(&varnm,' ') > 0 %then %let varnm3=%substr(%substr(&varnm,1,%index(&varnm,' ')),1,4);
%else %let varnm3=%substr(&varnm,1,4);


data &onto(drop=rc) miss&varnm3(drop=rc);
if 0 then set &onto &from(keep=&varnm. &byvars.);

 declare hash h_merge (dataset: "&from.");

 rc = h_merge.DefineKey  ("&data_key.");
 rc = h_merge.DefineData ("&data_vars_a.");
 rc = h_merge.DefineDone ();


 do until (eof);
   set &onto end = eof;
   call missing(&data_vars_b.);
   rc = h_merge.find ();
   if rc = 0 then do;
      output &onto;
      from = "&from.";
   end;
   else do;
      output miss&varnm3 &onto;
      from = "&onto.";
   end;
 end;

stop;
run;

%mend;

所以我认为这就是您要查找的内容,但它仍然需要将 "lookup" table 中的所有键值加载到哈希对象中。但它可以节省 space,而不是同时加载非关键变量,它只需要加载与关键变量匹配的观察值。

%macro hash_merge_point
/*-----------------------------------------------------------------------------
Merge variables ONTO large table FROM small table using POINT= dataset option.
-----------------------------------------------------------------------------*/
(varnm  /* Space delimited list of variable to retrieve */
,onto   /* Dataset to update */
,from   /* Dataset to get values from */
,byvars /* Space delimited list of key variables to match on */
);
%local missds key_vars;
%let missds=%scan(&varnm,1,%str( ));
%let missds=miss%substr(&missds,1,%sysfunc(min(28,%length(&missds))));

%let key_vars="%sysfunc(tranwrd(%sysfunc(compbl(&byvars)),%str( )," "))";

data &onto(drop=rc) &missds(drop=rc);
  if 0 then set &onto &from(keep=&varnm. &byvars.);

  declare hash h_merge ();
  rc = h_merge.DefineKey  (&key_vars);
  rc = h_merge.DefineData ('_point');
  rc = h_merge.DefineDone ();
  do _point=1 to _nobs;
    set &from(keep=&byvars) point=_point nobs=_nobs;
    rc = h_merge.add();
  end;

  do until (eof);
    set &onto end = eof;
    rc = h_merge.find ();
    if rc = 0 then do;
      set &from (keep=&varnm) point=_point;
      from = "&from.";
      output &onto;
    end;
    else do;
      call missing(of &varnm);
      from = "&onto.";
      output ;
    end;
  end;

stop;
run;

%mend hash_merge_point;

所以这是一个简单的例子:

data lookup;
  input id age sex .;
cards;
1 10 F
2 20 .
4 30 M
;
data master ;
  input id wt ;
cards;
1 100
2 150
3 180
4 200
;

%hash_merge_point
/*-----------------------------------------------------------------------------
Merge variables ONTO large table FROM small table using POINT= dataset option.
-----------------------------------------------------------------------------*/
(varnm=age sex  /* Space delimited list of variable to retrieve */
,onto=master   /* Dataset to update */
,from=lookup  /* Dataset to get values from */
,byvars=id /* Space delimited list of key variables to match on */
);

如果目标 table 已经有合并创建的变量(所以你只想覆盖当前值)那么你可以使用 MODIFY 语句而不是 SET 语句来修改数据集地方。但是在尝试此操作之前,您可能需要确保备份了 table。另请注意,如果您想要源标志,即 from 变量,则该变量也需要存在。

所以有了这个更新的主控table:

data master ;
  input id wt ;
  length age 8 sex  from ;
cards;
1 100
2 150
3 180
4 200
;

而这个版本的宏:

%macro hash_merge_point
/*-----------------------------------------------------------------------------
Merge variables ONTO large table FROM small table using POINT= dataset option.
-----------------------------------------------------------------------------*/
(varnm  /* Space delimited list of variable to retrieve */
,onto   /* Dataset to update */
,from   /* Dataset to get values from */
,byvars /* Space delimited list of key variables to match on */
);
%local key_vars;
%let key_vars="%sysfunc(tranwrd(%sysfunc(compbl(&byvars)),%str( )," "))";

data &onto;
  if 0 then set &onto (keep=&byvars.);

  declare hash h_merge ();
  rc = h_merge.DefineKey  (&key_vars);
  rc = h_merge.DefineData ('_point');
  rc = h_merge.DefineDone ();
  do _point=1 to _nobs;
    set &from(keep=&byvars) point=_point nobs=_nobs;
    rc = h_merge.add();
  end;

  do until (eof);
    modify &onto end = eof;
    rc = h_merge.find ();
    if rc = 0 then do;
      set &from (keep=&varnm) point=_point;
      from = "&from.";
    end;
    else from = "&onto.";
    replace;
  end;

stop;
run;

%mend hash_merge_point;

如果您运行此代码:

proc print data=master; 
 title 'BEFORE';
run;

%hash_merge_point
/*-----------------------------------------------------------------------------
Merge variables ONTO large table FROM small table using POINT= dataset option.
-----------------------------------------------------------------------------*/
(varnm=age sex  /* Space delimited list of variable to retrieve */
,onto=master   /* Dataset to update */
,from=lookup  /* Dataset to get values from */
,byvars=id /* Space delimited list of key variables to match on */
);

proc print data=master; 
  title 'AFTER';
run;

你得到这个结果: