data employees(drop=i);
   length empid $20;
   array first_names{20} $15 _temporary_ ("Paul", "Allan", "Thomas", "Michael", "Chris", "David", "John", "Jerry", "James", "Robert",
                                          "William", "Richard", "Bob", "Daniel", "Paul", "George", "Larry", "Eric", "Charles", "Stephen");
   array last_names{20} $15 _temporary_ ("Smith", "Johnson", "Williams", "Jones", "Brown", "Miller", "Wilson", "Moore", "Taylor", "Hall",
                                        "Anderson", "Jackson", "White", "Harris", "Martin", "Thompson", "Robinson", "Lewis", "Walker", "Allen");
   call streaminit(123);
   do i=1 to 50e6;
      first_name=first_names[ceil(rand("Uniform")*20)];
      last_name=last_names[ceil(rand("Uniform")*20)];
      empid=compress(uuidgen(), '-');
      output;
   end;
run;

proc surveyselect data=employees out=temp(keep=empid) seed=123 noprint                
     method=srs
     sampsize=500000;
run;

data emphours;
   set temp;
   hours=round(rand('Uniform', 10, 100), 0.01);
   sickdays=ceil(rand("Uniform")*10);
   seniority=ceil(rand("Uniform")*30);
run;

proc datasets lib=work nolist;
   delete temp;
run;quit;