pig scripts

 first create  people_data.txt file

Alice,30,New York Bob,25,California Charlie,35,Texas David,30,California Eva,20,New York Frank,40,California Grace,30,Texas Hannah,45,New York Ivy,25,California Jack,20,Texas

--------------------------

copy data to hadoop directory

> hadoop fs -put people_data.txt people_data.txt

---------------------------------------

write pig script

pig1.pig

people= LOAD 'people_data.txt' USING PigStorage(',')as (name:chararray, age:int, city:chararray);

dump people;

-------------------------------------------

-----------------------------------------

pig2.pig

people= LOAD 'people_data.txt' USING PigStorage(',')as (name:chararray, age:int, city:chararray);

filtered_data = FILTER people BY age > 30;

dump filtered_data;

-----------------------------------------------------------

pig3.pig

people= LOAD 'people_data.txt' USING PigStorage(',')as (name:chararray, age:int, city:chararray);

Group_data = GROUP people by city;

dump Group_data;

----------------------------------------------------

pig4.pig

people= LOAD 'people_data.txt' USING PigStorage(',')as (name:chararray, age:int, city:chararray);

sort_age = ORDER people BY age DESC;

dump sort_age;

--------------------------------------------------------

pig5.pig

people_data.txt:

sql
John, 30, New York
Alice, 25, Los Angeles
Bob, 35, Chicago
Charlie, 28, New York

city_data.txt:

sql
New York, 8000000, New York
Los Angeles, 4000000, California
Chicago, 2700000, Illinois
San Francisco, 870000, California

Now, let's perform the join on the city field.

Pig Script:

pig
-- Load the people data
people = LOAD 'people_data.txt' USING PigStorage(',') AS (name:chararray, age:int, city:chararray);

-- Load the city data
city_data = LOAD 'city_data.txt' USING PigStorage(',') AS (city:chararray, population:int, state:chararray);

-- Perform the join on the 'city' field
joined_data = JOIN people BY city, city_data BY city;

-- Display the result of the join
DUMP joined_data;


----------------------------------