idge-实际上它与请求完全匹配。要求只保留在同一小时内有200次或更多观测的记录。您可以使用子查询将其重新表述为联接，但为什么不让SAS自动为您执行此操作？@Tom，为什么不使用having语句呢？无需子查询，无需混乱和缓慢的重新合并。。。。 data

---

idge-实际上它与请求完全匹配。要求只保留在同一小时内有200次或更多观测的记录。您可以使用子查询将其重新表述为联接，但为什么不让SAS自动为您执行此操作？@Tom，为什么不使用

having

语句呢？无需子查询，无需混乱和缓慢的重新合并。。。。

data lib.data;
    set lib.data;
    retain I; by date hour;
    if first.date or first.hour then I=1; else I=I+1;
run;

proc sql;
    create table lib.data1
    as select a.*,  max(I) as N 
    from lib.data as a  
    group by date, hour
    order by date, hour;
quit; 

data lib.data (drop= i n);
    set lib.data;
if n < 200 then delete;
run;

data lib.data (drop= counter rc);
    set lib.data;
    by date hour;
    retain counter 0;

    If _N_ =1 then do;
        declare hash hs(multidata:'yes');
        hs.definekey('date','hour');
        hs.definedone();
    end;
/*if first record in hour zero counter*/
    if first.hour then do;
        counter=0;
    end;
/*increment counter*/
    counter = counter+1;
/*if counter less then 200 add record to hash table*/
    if counter < 200 then do;
        hs.add();
    end;
    /*if counter=200 output current record and record from hash*/
    if counter = 200 then do;
        output;
        rc = hs.find();
        do while(rc=0);
            output;
            rc= hs.find_next();
        end;
    end;
    /*if counter greater then 200 output current record*/
    if counter > 200 then output;
/*if last record in hour clear hash*/
    if last.hour then do;
        hs.clear();
    end;
run;

data want ;
  do until (last.hour);
    set lib.data;
    by date hour;
    n=sum(n,1);
  end;
  do until (last.hour);
    set lib.data;
    by date hour;
    if n >= 200 then output;
  end;
run;

proc sql;
create table want as
select
    a.*
from
    lib.data  a
    join
    (select 
        date,
        hour,
        count(*)
    from
        lib.data
    group by date, hour
    having count(*) >= 200)  b
        on
        a.date = b.date and
        a.hour = b.hour
;
quit;