# load emp.csv into HDFS with hadoop:
#   hadoop fs -mkdir /emp7 
#   hadoop fs -chmod 777 /emp7 
#   hadoop fs -put /tmp/emp.csv /emp7

time pig <<EOF
a1 = load '/emp7/emp.csv' using PigStorage(',') as (empno: int, ename: chararray, deptno: int);
a2 = load '/emp7/emp.csv' using PigStorage(',') as (empno: int, ename: chararray, deptno: int);
a3 = load '/emp7/emp.csv' using PigStorage(',') as (empno: int, ename: chararray, deptno: int);
a4 = load '/emp7/emp.csv' using PigStorage(',') as (empno: int, ename: chararray, deptno: int);
a5 = load '/emp7/emp.csv' using PigStorage(',') as (empno: int, ename: chararray, deptno: int);
a6 = load '/emp7/emp.csv' using PigStorage(',') as (empno: int, ename: chararray, deptno: int);
a7 = load '/emp7/emp.csv' using PigStorage(',') as (empno: int, ename: chararray, deptno: int);
b = filter a1 by deptno==10;
c = join b by deptno, a2 by deptno, a3 by deptno, a4 by deptno, a5 by deptno, a6 by deptno, a7 by deptno;
d = group c all;
e = foreach d generate COUNT(c);
dump e;
quit;
EOF