first create data file emp111.txt in ur LFS
2. MOVE to HDFS
3. OPen vi editor type Pig Script
4. vi pig1.pig
bag1= load 'emp111.txt' using PigStorage(',')as (eno:int,ename:chararray,sal:int);
bag2= filter bag1 by sal > 34000;
store bag2 into 'pigoutput11' using PigStorage(',');
5. execute script
pig pig1.pig
-------------------------------------------------
avg salary group by clause
-----------------------------------------
bag1= load 'emp11.txt' using PigStorage(',')as (eno:int,ename:chararray,sal:int,dname:chararray);
bag2= group bag1 by dname;
bag3= foreach bag2 generate bag1.dname, AVG(bag1.sal);
store bag4 into 'avgop2' using PigStorage(',');
---------------------------------------------------------------------
A= load 'emp11.txt' using PigStorage(',')as (eno:int,ename:chararray,sal:int,dname:chararray);
B= group A by dname;
C= foreach B generate SUM(A.sal);
dump C;
-----------------------------------------------------------------------------------
bag1= load 'emp22.txt' using PigStorage(',')as (eno:int,ename:chararray,sal:int,dname:chararray);
bag2= group bag1 all;
bag3= foreach bag2 generate SUM(bag1.sal);
store bag3 into 'sumop' using PigStorage(',');
No comments:
Post a Comment