DROP TABLE IF EXISTS lineitem;
DROP TABLE IF EXISTS u4_gby_distinct;

-- create the tables and load the 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 result tables
create table u4_gby_distinct(l_partkey int, t_sum_quantity double);

-- the query
insert overwrite table u4_gby_distinct
select 
  l_orderkey, avg(distinct L_QUANTITY) as t_sum_quantity
from 
  lineitem
group by l_orderkey
order by l_orderkey desc
limit 10;