数据仓库的创建:
create database (if not exist)hivedwd;
创建时添加键值对信息:
create dabatase hivedwh with dbproperties(‘owner’=‘itcast’,‘data’=‘2021’);
数据仓库显示:
show databases;
显示仓库详细信息:
describe database extended hivedwh;
切换数据仓库:
use hivedwh;
数据仓库的修改:
alter database hivedwh set dbproperties(‘createtime’=‘20210112’);
数据仓库的删除:
drop database hivedwh;
数据仓库强制删除:
drop database (if exists)hivedwh cascade;
创建内部表:
create table table_1(id int,name string);
向表中插入数据:
insert into table_1 values (1,"张三");
创建内部表并指定字段之间的分隔符:
create table table_1(id int,name string) row format delimited fields terminated by '\t';
创建表并指定放入的路径:
create table if not exists table_1 row format delimited fields terminated by '\t' location '/user/stu2';
根据查询结果创建表:
create table if not exists table_1 as select * from stus
根据已经存在的表创建新的表:
create table table_1 like stu1;
查看表的详细信息:
desc formatted table_1;
删除表:
drop table table_1;
创建外部表:
create external table if not exists table_1 (id int,name string) row format delimited fields terminated by '\t';
加载数据:
load data local inpath "文件路径" into table table_1;
加载数据并覆盖已有数据:
load data local inpath "文件路径" overwrite into table table_1;
创建分区表:
create table if not exists table_1(id int , name string) partitioned by (month string) row format delimited fields terminated by'\t';
创建一个表带多个分区:
create table if not exists table_1(id int ,name string) partitioned by(month int,day string) row format delimited fields terminated by '\t';
多分区表联合查询:(union all)
select * from table_1 where month = '2021' union all select * from table_1 where month = '2020'
查看分区:
show partitions table_1;
添加一个分区:
alter table table_1 add partition(month='2021');
删除一个分区:
alter table table_1 drop partition(month='2021')
创建分桶表:
set hive.enforce.bucketing=true;
设置Reduce个数:
set mapreduce.job.reduce=3;
创建分桶表:
create table course (c_id string,c_name string,t_id string) clustered by(c_id) into 3 buckets row format delimited fields termainated by '\t';
数据加载时需要常见普通表,使用insert overwrite的方法进行加载数据