Search This Blog

Sunday 26 February 2017

buckets in hive

>create table bucket1(id int,name string)
    > clustered by(id) into 5 buckets;  

> create table user(id int,name string)
    > row format delimited                
    > fields terminated by ','            
    > lines terminated by '\n'            
    > stored as textfile;


SET hive.exec.dynamic.partition= true;
SET hive.exec.dynamic.partition.mode= nonstrict;
SET  hive.enforce.bucketing=true;


1,aaa
2,bbb
3,ccc
4,ddd
4,eee
5,fff
13,ggg
12,hhh
13,kkk
6,rrr
17,ppp
18,wer
8,qwe

 load data local inpath 'users.txt'  overwrite into table user;


------------------------------------------
hive> insert overwrite table  bucket1            
    > select id,name from user;  
-----------------------------------------

[training@localhost ~]$ hadoop fs -cat  /user/hive/warehouse/emp.db/bucket1/000000_0



THE user data splitted in to different buckets by corresponding hash mapping

No comments:

Post a Comment

Hadoop Analytics

NewolympicData

  Alison Bartosik 21 United States 2004 08-29-04 Synchronized Swimming 0 0 2 2 Anastasiya Davydova 21 Russia 2004 0...