文章目录
新建数据表employees
create table employees(
name string,
salary float,
subordinates array<string>,
deductions map<string,float>,
address struct<street:string,city:string,state:string,zip:int>
)
partitioned by (country string,state string);
向表中装载数据
load data local inpath '/opt/datafiles/employees.txt' overwrite into table employees partition (country='US',state='CA');
partition子句分区表，用户必须为每个分区的键指定一个值。
数据将会存放到这个文件夹
/user/hive/warehouse/learnhive.db/employees/country=US/state=CA
select name,salary from employees;
+-------------------+-----------+
| name | salary |
+-------------------+-----------+
| John Doe | 100000.0 |
| Mary Smith | 80000.0 |
| Todd Jones | 70000.0 |
| Bill King | 60000.0 |
| Boss Man | 200000.0 |
| Fred Finance | 150000.0 |
| Stacy Accountant | 60000.0 |
+-------------------+-----------+
当用户选择的列是集合数据类型时，Hive会使用JSON语法应用于输出。subordinates列为一个数组，注意：集合的字符串元素是加上引号的，而基本数据类型string的列值是不加引号的。
select name,subordinates from employees;
deductions列是一个MAP
select name,deductions from employees;
address列是一个struct
select name,address from employees;
引用集合类型中的元素
引用数组（选择数组subordinates的第2个元素）
select name,subordinates[1] from employees;
引用一个不存在的元素将会返回NULL。同时提取出的string数据类型的值不再加引号
引用MAP元素
select name,deductions['Insurance'] from employees;
引用struct元素
select name,address.city from employees;
新建数据表stocks
create table stocks(
exchange_e string,
symbol string,
ymd string,
price_open float,
price_high float,
price_low float,
price_close float,
volume int,
price_adj_close float)
row format delimited fields terminated by ',';
装载数据
load data local inpath '/opt/datafiles/stocks.csv' overwrite into table stocks;
使用正则表达式来指定列
首先得执行这条语句
set hive.support.quoted.identifiers=none;
select symbol,`price.*` from stocks limit 5;
使用列值进行计算
select upper(name),salary,deductions["Federal Taxes"],round(salary*(1-deductions["Federal Taxes"])) from employees;
算术运算符
+,加
-,减
*,乘
/,除
%,求余
&,按位取与
|,按位取或
^,按位取亦或
~,按位取反
limit语句
select name,salary from employees limit 2;
select name,salary from employees limit 1,2;
查询从第1列开始，返回2列
列别名
select name as n,salary from employees;
DML数据操作
数据导入
load
load data [local] inpath '数据的path' [overwrite] into table student [partition (partcol1=val1,…)];
（1）load data:表示加载数据
（2）local:表示从本地加载数据到hive表；否则从HDFS加载数据到hive表
（3）inpath:表示加载数据的路径
（4）overwrite:表示覆盖表中已有数据，否则表示追加
（5）into table:表示加载到哪张表
（6）student:表示具体的表
（7）partition:表示上传到指定分区
insert
insert into或overwrite table student_par values(1,'wangwu'),(2,'zhaoliu');
insert into：以追加数据的方式插入到表或分区，原有数据不会删除
insert overwrite：会覆盖表中已存在的数据
insert overwrite table student_par select id, name from student ;
(根据单张表查询结果插入)
根据查询结果创建表
create table if not exists student3 as select id, name from student;
创建表时通过Location指定加载数据路径
create external table if not exists student5(
id int, name string
)
row format delimited fields terminated by '\t'
location '/student;
数据导出
Insert导出
1）将查询的结果导出到本地
insert overwrite local directory '/opt/outfiles' select * from employees;
2）将查询的结果格式化导出到本地
insert overwrite local directory '/opt/outfiles'
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
select * from employees;
3）将查询的结果导出到HDFS上(没有local)
insert overwrite directory '/opt/outfiles'
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
select * from employees;
Hadoop命令导出到本地
dfs -get /user/hive/warehouse/learnhive.db/test2/test.txt /opt/outfiles/out_test.txt;
Hive Shell 命令导出
[xwk@hadoop102 outfiles]$ cd /opt/software/hive/
[xwk@hadoop102 hive]$ ./bin/hive -e 'select * from learnhive.test2;' > /opt/outfiles/out_test01.txt;
Export导出到HDFS上
export和import主要用于两个Hadoop平台集群之间Hive表迁移。
export table learnhive.test2 to '/opt/outfiles';
Import数据到指定Hive表中
注意：先用export导出后，再将数据导入。
先删除数据
import table test2 from '/opt/outfiles';
清除表中数据（Truncate）
注意：Truncate只能删除管理表，不能删除外部表中数据
truncate table test2;
select * from test2;
+-------------+----------------+-----------------+----------------+
| test2.name | test2.friends | test2.children | test2.address |
+-------------+----------------+-----------------+----------------+
+-------------+----------------+-----------------+----------------+