rawEmpDS = load '/user/akhanolk/joinProject/data/employees_active/part-e' using PigStorage(',') as (empNo:chararray,dOB:chararray,lName:chararray,fName:chararray,gender:chararray,hireDate:chararray,deptNo:chararray); empDS = foreach rawEmpDS generate empNo,fName,lName,gender,deptNo; sortedEmpDS = ORDER empDS by empNo; rawSalDS = load '/user/akhanolk/joinProject/data/salaries_history/part-sh' using PigStorage(',') as (empNo:chararray,salary:long,fromDate:chararray,toDate:chararray); filteredSalDS = filter rawSalDS by toDate == '9999-01-01'; salDS = foreach filteredSalDS generate empNo, salary; sortedSalDS = ORDER salDS by empNo; joinedDS = join sortedEmpDS by empNo, sortedSalDS by empNo using 'merge'; finalDS = foreach joinedDS generate sortedEmpDS::empNo,sortedEmpDS::fName,sortedEmpDS::lName,sortedEmpDS::gender,sortedEmpDS::deptNo,sortedSalDS::salary; store finalDS into '/user/akhanolk/joinProject/output/pig-RSJ';