libname hercules  's:\courses\stat-renaes\stat404';

* this cleaning is shown in several steps with the last DATA step being the all-in-one clean;


title 'Uncleaned data';
proc print data=hercules.nonsales;
run;
title; * this cancels the previous title (as long as it is not a numbered title);

data work.clean;
   set hercules.nonsales; 
   Country=upcase(Country);
run;

title 'Cleaned Countries';
proc print data=work.clean;
   var Employee_ID Job_Title Country;
run;
title;


data work.clean;
   set hercules.nonsales; 
   Country=upcase(Country);
   if Employee_ID=120106 then Salary=26960;
   if Employee_ID=120115 then Salary=26500;
   if Employee_ID=120191 then Salary=24015;
run;

title "Cleaned Salaries 1";
proc print data=work.clean;
   var Employee_ID Salary Job_Title Country;
run;
title;

data work.clean;
   set hercules.nonsales; 
   if Employee_ID=120106 then Salary=26960;
   else if Employee_ID=120115 then Salary=26500;
   else if Employee_ID=120191 then Salary=24015;
run;

title 'Cleaned Countries and Salaries 2';
proc print data=work.clean;
   var Employee_ID Salary Job_Title Country;
run;
title;

*multiple steps;
data work.clean;
   set hercules.nonsales; 
   Country=upcase(Country);
   if Employee_ID=120106 then Salary=26960;
   else if Employee_ID=120115 then Salary=26500;
   else if Employee_ID=120191 then Salary=24015;
   else if Employee_ID=120107 then 
           Hire_Date='21JAN1995'd;
   else if Employee_ID=120111 then 
           Hire_Date='01NOV1978'd;
   else if Employee_ID=121011 then 
           Hire_Date='01JAN1998'd;
run;

title 'Cleaned Countries, salaries and dates';
proc print data=work.clean;
   var Employee_ID Salary Job_Title Country Hire_Date;
run;
title;