DROP TABLE IF EXISTS lineitem;
DROP TABLE IF EXISTS q1_pricing_summary_report;

-- create tables and load data
Create external table lineitem (L_ORDERKEY INT, L_PARTKEY INT, L_SUPPKEY INT, L_LINENUMBER INT, L_QUANTITY DOUBLE, L_EXTENDEDPRICE DOUBLE, L_DISCOUNT DOUBLE, L_TAX DOUBLE, L_RETURNFLAG STRING, L_LINESTATUS STRING, L_SHIPDATE STRING, L_COMMITDATE STRING, L_RECEIPTDATE STRING, L_SHIPINSTRUCT STRING, L_SHIPMODE STRING, L_COMMENT STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' STORED AS TEXTFILE LOCATION '/tpch/lineitem';

-- create the target table
CREATE TABLE q1_pricing_summary_report ( L_RETURNFLAG STRING, L_LINESTATUS STRING, SUM_QTY DOUBLE, SUM_BASE_PRICE DOUBLE, SUM_DISC_PRICE DOUBLE, SUM_CHARGE DOUBLE, AVE_QTY DOUBLE, AVE_PRICE DOUBLE, AVE_DISC DOUBLE, COUNT_ORDER INT);

set mapred.min.split.size=536870912;

-- the query
INSERT OVERWRITE TABLE q1_pricing_summary_report 
SELECT 
  L_RETURNFLAG, L_LINESTATUS, SUM(L_QUANTITY), SUM(L_EXTENDEDPRICE), SUM(L_EXTENDEDPRICE*(1-L_DISCOUNT)), SUM(L_EXTENDEDPRICE*(1-L_DISCOUNT)*(1+L_TAX)), AVG(L_QUANTITY), AVG(L_EXTENDEDPRICE), AVG(L_DISCOUNT), COUNT(1) 
FROM 
  lineitem 
WHERE 
  L_SHIPDATE<='1998-09-02' 
GROUP BY L_RETURNFLAG, L_LINESTATUS 
ORDER BY L_RETURNFLAG, L_LINESTATUS;