Practice Questions:
******************************************************************************
Important Hdfs command
***********************************************************************************
1 calculate check sum :- Hadoop fs -checksum /user/a1.txt
2 Health check of file : hdfs fsck /
3 status of dataNode : hdfs dfsadmin -report
4 replication factor of system.log : Hadoop fs -stat %r /data/logs/system.log
5 check owner : Hadoop fs -ls /data/logs/system.log
6 Hadoop fs -stat %b /data/logs/system.log
7 first n line : Hadoop fs -cat /user/a.txt | head -n 10
8 last n line : Hadoop fs -cat /user/a.txt | tail -n 10
9 change grup ownership : Hadoop fs -chgrp admin /data/a.txt
10 appending data : Hadoop fs -appendToFile /local/logs/newdata.log
/user/logs/complete.log
11 list the file or directory : Hadoop fs -ls /
12 make directory : Hadoop fs -mkdir /admin
13 upload file from local to hdfs : Hadoop fs (-put or -copyFromLocal) (path of
local) (path of hdfs)
14 upload file from hdfs to local : Hadoop fs -get (path of hdfs) (path of local)
14 remove file or directory : Hadoop fs -rm /user/a.txt
******************************************************************************
Important Hive command
***********************************************************************************
1 check available database : show databases;
2 create Database : create databse nameofdb;
3 Use Database : use nameofDB;
4 create table : create table tablename(id int, name string, salary int)
row format delimited
fields terminated by ',';
5 Load data : load data local inpath (path of file) into table tablename;
or
insert into tablename(id,name,salary) values (1,name1,100000) , (1,name1,100000),
(1,name1,100000);
6 Array Datatype : create table temperature(sno int,place string,mytemp
array<double>)
> row format delimited
> fields terminated by '\t'
> collection items terminated by ',';
7 map Datatype :
create table tab(city string, gender string, collection map<int,int>)
> row format delimited
> fields terminated by '\t'
> collection items terminated by ','
> map keys terminated by ':';
8 structure datatype : create table struct(name string, city string, info
struct<place:string,temp:float>)
> row format delimited
> fields terminated by '\t'
> collection items terminated by ',';
9 Partitioning : first create table then apply on it
create table part(city string,pin bigint)
partitioned by(state string);
set hive.exec.dynamic.partition.mode=nonstrict;
insert overwrite table part partition(state)
select city,pin,state from states;
10 Bucketting : first create table then apply on it
set hive.enforce.bucketing=true;
create table buc1(id int,name string,sal float)
>clustered by(id) into 3 buckets
>row format delimited
>fields terminated by ',';
insert overwrite table buc1 select * from buctab;0.
******************************************************************************
Important Hbase command
***********************************************************************************
1 create tabele in hbase : create 'tableName', 'Colfam1','colfam2'
2 insert data : put 'tablename', 'mask', 'colfam1:newcolum', 'value'
3 show all data : scan 'tablename'
4 view individual colfam data : get 'tablename' ,'mask' ,{COLUMN =>
'colfam!:newcolum'
5 delete all cell : deleteall 'tablename' , 'mask'
6 delete specific colfam : delete 'tablename', 'mask' , 'colfam1:newcolum'
7 Count No Rows : count 'tablename'
8 List tables : list
9 Alter or version control : alter ‘test_table’, {NAME => ‘colfam1’, VERSIONS => 2}
10 Descripe the table : describe table;
