AI & DS PIG EXPERIMENT

 first create these files in your terminal using cat command

cat > employees.csv

     1, John Doe, 101, 50000

     2, Jane Smith, 102, 60000

     3, Jim Brown, 101, 55000

     4, Jake White, 103, 70000

 

    cat > departments.csv

     101, HR

     102, Engineering

     103, Marketing

move to hadoop directory

>hadoop fs -put employees.csv emp.csv

>hadoop fs -put departments.csv dept.csv

> vi pig1.pig

employees = LOAD 'emp.csv' USING PigStorage(',') AS (employee_id:int, name:chararray,

     department_id:int, salary:float);

dump employees;

> pig pig1.pig

> vi pig2.pig

departments = LOAD 'dept.csv'        USING    PigStorage(',')   AS   (department_id:int,

     department_name:chararray);

dump departments;

>pig pig2.pig

>vi pig3.pig

    employees = LOAD 'emp.csv' USING PigStorage(',') AS (employee_id:int, name:chararray,

     department_id:int, salary:float);

     high_salary_employees = FILTER employees BY salary > 55000;

     dump high_salary_employees;

>pig pig3.pig

TRY these scripts 

-- Project only the name and salary of high salary employees

     projected_employees = FOREACH high_salary_employees GENERATE name, salary;

 

     -- Group employees by department_id

     grouped_employees = GROUP employees BY department_id;

 

     -- Join employees with departments to get department names

     joined_data = JOIN employees BY department_id, departments BY department_id;

 

     -- Sort employees by salary in descending order

     sorted_employees = ORDER employees BY salary DESC;

 

     -- Store the results of the sorted employees

     STORE sorted_employees INTO 'sorted_employees_output' USING PigStorage(',');