Hive lab13

Hive Lab 13 : Eliminating Duplicates and Unions (merging)

[training@localhost ~]$ cat dupes
101,aaa,10000
101,bbb,20000
101,aaa,10000
101,aaa,10000
101,aaa,10000
102,bbb,40000
103,cccc,50000
102,bbb,40000
102,bbb,40000
[training@localhost ~]$ 

hive> create database hdp;
OK
Time taken: 1.702 seconds
hive> use hdp;
OK
Time taken: 0.018 seconds
hive> create table info(id int, name string, 
    >   sal int)
    >  row format delimited fields terminated 
    >  by ',';
OK
Time taken: 0.439 seconds
hive> 

hive> load data local inpath 'dupes'
    >  into table info;
Copying data from file:/home/training/dupes
Copying file: file:/home/training/dupes
Loading data to table hdp.info
OK
Time taken: 0.209 seconds
hive> select * from info;
OK
101     aaa     10000
101     bbb     20000
101     aaa     10000
101     aaa     10000
101     aaa     10000
102     bbb     40000
103     cccc    50000
102     bbb     40000
102     bbb     40000
Time taken: 0.201 seconds
hive> 
hive> select distinct(id),name,sal
    >   from info;