----sum+group by普通常规聚合操作------------
select sum(salary) as total from employee group by dept;
----sum+窗口函数聚合操作------------
select id,name,deg,salary,dept,sum(salary) over(partition by dept) as total from employee;

--其中Function(arg1,..., argn) 可以是下面分类中的任意一个
    --聚合函数：比如sum max avg等
    --排序函数：比如rank row_number等
    --分析函数：比如lead lag first_value等
--OVER [PARTITION BY <...>] 类似于group by 用于指定分组  每个分组你可以把它叫做窗口
--如果没有PARTITION BY 那么整张表的所有行就是一组
--[ORDER BY <....>]  用于指定每个分组内的数据排序规则 支持ASC、DESC
--[<window_expression>] 用于指定每个窗口中 操作的数据范围 默认是窗口中所有行

---建表并且加载数据
create table website_pv_info(
   cookieid string,
   createtime string,   --day
   pv int
) row format delimited
fields terminated by ',';
create table website_url_info (
    cookieid string,
    createtime string,  --访问时间
    url string       --访问页面
) row format delimited
fields terminated by ',';
load data local inpath '/root/hivedata/website_pv_info.txt' into table website_pv_info;
load data local inpath '/root/hivedata/website_url_info.txt' into table website_url_info;
select * from website_pv_info;
select * from website_url_info;

-----窗口聚合函数的使用-----------
--1、求出每个用户总pv数  sum+group by普通常规聚合操作
select cookieid,sum(pv) as total_pv from website_pv_info group by cookieid;
--2、sum+窗口函数 总共有四种用法 注意是整体聚合 还是累积聚合
--sum(...) over( )对表所有行求和
--sum(...) over( order by ... ) 连续累积求和
--sum(...) over( partition by... ) 同组内所有行求和
--sum(...) over( partition by... order by ... ) 在每个分组内，连续累积求和
--需求：求出网站总的pv数 所有用户所有访问加起来
--sum(...) over( )对表所有行求和
select cookieid,createtime,pv,
       sum(pv) over() as total_pv
from website_pv_info;
--需求：求出每个用户总pv数
--sum(...) over( partition by... )，同组内所行求和
select cookieid,createtime,pv,
       sum(pv) over(partition by cookieid) as total_pv
from website_pv_info;
--需求：求出每个用户截止到当天，累积的总pv数
--sum(...) over( partition by... order by ... )，在每个分组内，连续累积求和
select cookieid,createtime,pv,
       sum(pv) over(partition by cookieid order by createtime) as current_total_pv
from website_pv_info;

- preceding：往前
- following：往后
- current row：当前行
- unbounded：边界
- unbounded preceding 表示从前面的起点
- unbounded following：表示到后面的终点
---窗口表达式
--第一行到当前行
select cookieid,createtime,pv,
       sum(pv) over(partition by cookieid order by createtime rows between unbounded preceding and current row) as pv2
from website_pv_info;
--向前3行至当前行
select cookieid,createtime,pv,
       sum(pv) over(partition by cookieid order by createtime rows between 3 preceding and current row) as pv4
from website_pv_info;
--向前3行 向后1行
select cookieid,createtime,pv,
       sum(pv) over(partition by cookieid order by createtime rows between 3 preceding and 1 following) as pv5
from website_pv_info;
--当前行至最后一行
select cookieid,createtime,pv,
       sum(pv) over(partition by cookieid order by createtime rows between current row and unbounded following) as pv6
from website_pv_info;
--第一行到最后一行 也就是分组内的所有行
select cookieid,createtime,pv,
       sum(pv) over(partition by cookieid order by createtime rows between unbounded preceding  and unbounded following) as pv6
from website_pv_info;

-----窗口排序函数
SELECT
    cookieid,
    createtime,
    pv,
    RANK() OVER(PARTITION BY cookieid ORDER BY pv desc) AS rn1,
    DENSE_RANK() OVER(PARTITION BY cookieid ORDER BY pv desc) AS rn2,
    ROW_NUMBER() OVER(PARTITION BY cookieid ORDER BY pv DESC) AS rn3
FROM website_pv_info
WHERE cookieid = 'cookie1';

--需求：找出每个用户访问pv最多的Top3 重复并列的不考虑
SELECT * from
(SELECT
    cookieid,
    createtime,
    pv,
    ROW_NUMBER() OVER(PARTITION BY cookieid ORDER BY pv DESC) AS seq
FROM website_pv_info) tmp where tmp.seq <4;

--把每个分组内的数据分为3桶
SELECT
    cookieid,
    createtime,
    pv,
    NTILE(3) OVER(PARTITION BY cookieid ORDER BY createtime) AS rn2
FROM website_pv_info
ORDER BY cookieid,createtime;

--需求：统计每个用户pv数最多的前3分之1天。
--理解：将数据根据cookieid分 根据pv倒序排序 排序之后分为3个部分 取第一部分
SELECT * from
(SELECT
     cookieid,
     createtime,
     pv,
     NTILE(3) OVER(PARTITION BY cookieid ORDER BY pv DESC) AS rn
 FROM website_pv_info) tmp where rn =1;

-----------窗口分析函数----------
--LAG
SELECT cookieid,
       createtime,
       url,
       ROW_NUMBER() OVER(PARTITION BY cookieid ORDER BY createtime) AS rn,
       LAG(createtime,1,'1970-01-01 00:00:00') OVER(PARTITION BY cookieid ORDER BY createtime) AS last_1_time,
       LAG(createtime,2) OVER(PARTITION BY cookieid ORDER BY createtime) AS last_2_time
FROM website_url_info;
--LEAD
SELECT cookieid,
       createtime,
       url,
       ROW_NUMBER() OVER(PARTITION BY cookieid ORDER BY createtime) AS rn,
       LEAD(createtime,1,'1970-01-01 00:00:00') OVER(PARTITION BY cookieid ORDER BY createtime) AS next_1_time,
       LEAD(createtime,2) OVER(PARTITION BY cookieid ORDER BY createtime) AS next_2_time
FROM website_url_info;
--FIRST_VALUE
SELECT cookieid,
       createtime,
       url,
       ROW_NUMBER() OVER(PARTITION BY cookieid ORDER BY createtime) AS rn,
       FIRST_VALUE(url) OVER(PARTITION BY cookieid ORDER BY createtime) AS first1
FROM website_url_info;
--LAST_VALUE
SELECT cookieid,
       createtime,
       url,
       ROW_NUMBER() OVER(PARTITION BY cookieid ORDER BY createtime) AS rn,
       LAST_VALUE(url) OVER(PARTITION BY cookieid ORDER BY createtime) AS last1
FROM website_url_info;

--数据表
select * from student;
--需求：随机抽取2个学生的情况进行查看
SELECT * FROM student
DISTRIBUTE BY rand() SORT BY rand() LIMIT 2;
--使用order by+rand也可以实现同样的效果 但是效率不高
SELECT * FROM student
    ORDER BY rand() LIMIT 2;

---bucket table抽样
--根据整行数据进行抽样
SELECT * FROM t_usa_covid19_bucket TABLESAMPLE(BUCKET 1 OUT OF 2 ON rand());
--根据分桶字段进行抽样 效率更高
describe formatted t_usa_covid19_bucket;
SELECT * FROM t_usa_covid19_bucket TABLESAMPLE(BUCKET 1 OUT OF 2 ON state);