Hive select查询语句

 

创建表

CREATE TABLE t_usa_covid19(
    count_date string,
    county string,
    state string,
    fips int,
    cases int,
    deaths int)
row format delimited fields terminated by ",";

--将数据load加载到t_usa_covid19表对应的路径下
load data local inpath '/root/hivedata/us-covid19-counties.dat' into table t_usa_covid19;

--查询所有字段或者指定字段
select *  from t_usa_covid19;

--查询某些字段
select county, cases, deaths from t_usa_covid19;

--查询常数返回 此时返回的结果和表中字段无关
select 1 from t_usa_covid19;

--查询当前数据库
select current_database(); --省去from关键字

去重查询走的是底层的MR，运行效率很低，所以，运行时间会很长，需要等待一下。

整体去重，两个字段都一样，才去重。

--2、ALL DISTINCT
--返回所有匹配的行
select state from t_usa_covid19;
--相当于
select all state from t_usa_covid19;

--返回所有匹配的行 去除重复的结果
select distinct state from t_usa_covid19;
--多个字段distinct 整体去重
select distinct county,state from t_usa_covid19;

--3、WHERE CAUSE
select * from t_usa_covid19 where 1 > 2;  -- 1 > 2 返回false
select * from t_usa_covid19 where 1 = 1;  -- 1 = 1 返回true

--找出来自于California州的疫情数据
select * from t_usa_covid19 where state = 'California';
--where条件中使用函数 找出州名字母长度超过10位的有哪些
select * from t_usa_covid19 where length(state) >10 ;

--注意：where条件中不能使用聚合函数
-- --报错 SemanticException:Not yet supported place for UDAF 'count'
--聚合函数要使用它的前提是结果集已经确定。
--而where子句还处于“确定”结果集的过程中，因而不能使用聚合函数。
select state,sum(deaths) from t_usa_covid19 where sum(deaths) >100 group by state;
--可以使用Having实现
select state,sum(deaths) from t_usa_covid19  group by state having sum(deaths) > 100;

第一个是错的 ，第二个才是对的

--4、聚合操作
--统计美国总共有多少个县county
select county as itcast from t_usa_covid19;
--学会使用as 给查询返回的结果起个别名
select count(county) as county_cnts from t_usa_covid19;
--去重distinct
select count(distinct county) as county_cnts from t_usa_covid19;

--统计美国加州有多少个县
select count(county) from t_usa_covid19 where state = "California";
--统计德州总死亡病例数
select sum(deaths) from t_usa_covid19 where state = "Texas";
--统计出美国最高确诊病例数是哪个县
select max(cases) from t_usa_covid19;

--5、GROUP BY

select *
from t_usa_covid19;

--根据state州进行分组 统计每个州有多少个县county
select count(county) from t_usa_covid19 where count_date = "2021-01-28" group by state;

--想看一下统计的结果是属于哪一个州的
select state,count(county) as county_nums from t_usa_covid19 where count_date = "2021-01-28" group by state;

--再想看一下每个县的死亡病例数，我们猜想很简单呀  把deaths字段加上返回  真实情况如何呢？
select state,count(county),sum(deaths) from t_usa_covid19 where count_date = "2021-01-28" group by state;
--很尴尬 sql报错了org.apache.hadoop.hive.ql.parse.SemanticException:Line 1:27 Expression not in GROUP BY key 'deaths'

--为什么会报错？？group by的语法限制
--结论：出现在GROUP BY中select_expr的字段：要么是GROUP BY分组的字段；要么是被聚合函数应用的字段。
--deaths不是分组字段 报错
--state是分组字段 可以直接出现在select_expr中

--被聚合函数应用
select state,count(county),sum(deaths) from t_usa_covid19 where count_date = "2021-01-28" group by state;

--6、having
--统计2021-01-28死亡病例数大于10000的州
select state,sum(deaths) from t_usa_covid19 where count_date = "2021-01-28" and sum(deaths) >10000 group by state;
--where语句中不能使用聚合函数 语法报错

--先where分组前过滤，再进行group by分组， 分组后每个分组结果集确定 再使用having过滤
select state,sum(deaths) from t_usa_covid19 where count_date = "2021-01-28" group by state having sum(deaths) > 10000;
--这样写更好 即在group by的时候聚合函数已经作用得出结果 having直接引用结果过滤 不需要再单独计算一次了
select state,sum(deaths) as cnts from t_usa_covid19 where count_date = "2021-01-28" group by state having cnts> 10000;

--7、order by
--根据确诊病例数升序排序 查询返回结果
select * from t_usa_covid19 ;
select * from t_usa_covid19 order by cases;
--不写排序规则 默认就是asc升序
select * from t_usa_covid19 order by cases asc;

--8、limit
--没有限制返回2021.1.28 加州的所有记录
select * from t_usa_covid19 where count_date = "2021-01-28" and state ="California";

--返回结果集的前5条
select * from t_usa_covid19 where count_date = "2021-01-28" and state ="California" limit 5;

--返回结果集从第1行开始 共3行
select * from t_usa_covid19 where count_date = "2021-01-28" and state ="California" limit 2,3;
--注意 第一个参数偏移量是从0开始的

--执行顺序
select state,sum(deaths) as cnts from t_usa_covid19
where count_date = "2021-01-28"
group by state
having cnts> 10000
limit 2;

--1、inner join
select e.id,e.name,e_a.city,e_a.street
from employee e inner join employee_address e_a
on e.id =e_a.id;

--等价于 inner join=join
select e.id,e.name,e_a.city,e_a.street
from employee e join employee_address e_a
on e.id =e_a.id;


--等价于 隐式连接表示法
select e.id,e.name,e_a.city,e_a.street
from employee e , employee_address e_a
where e.id =e_a.id;



--2、left join
select e.id,e.name,e_conn.phno,e_conn.email
from employee e left join employee_connection e_conn
on e.id =e_conn.id;

--等价于 left outer join
select e.id,e.name,e_conn.phno,e_conn.email
from employee e left outer join  employee_connection e_conn
on e.id =e_conn.id;