> hdfs dfs -put /etc/passwd /user/cloudera > pig -x mapreduce > clear grunt> A= load ‘/user/cloudera/passwd’ using PigStorage(‘:’); grunt> dumb A;   # execute map reduce jobs grunt> B= foreach A generate $0, $4, $5 ; grunt> dumb B;   # execute map reduce jobs grunt> store B into ‘file.out’   # store in hdfs

create table CustomerFact ( Customer_id INTEGER, order_item_id INTEGER ) partitioned by ( customer_key  INTEGER ) stored as PARQUET insert into table CustomerFact2 select category_id from categories; select customer_id from customers ; select order_item_id from order_items ; — Most popular product categories select c.category_name, count(order_item_quantity) as count from order_items oi inner join products p on oi.order_item_product_id