Hive基础增强-（窗口函数）

 jack,2017-01-01,10 tony,2017-01-02,15 jack,2017-02-03,23 tony,2017-01-04,29 jack,2017-01-05,46 jack,2017-04-06,42  - tony,2017-01-07,50 jack,2017-01-08,55 mart,2017-04-08,62  - mart,2017-04-09,68  - neil,2017-05-10,12 mart,2017-04-11,75  - neil,2017-06-12,80 mart,2017-04-13,94  -

select name,count(*)
from business
where month(orderdate)='4'
group by name;

+-------+------+--+
| name  | _c1  |
+-------+------+--+
| jack  | 1 |
| mart  | 4 |
+-------+------+--+

select name,count(*) over()
from business
where month(orderdate)='4'
group by name;

+-------+-----------------+--+
| name  | count_window_0  |
+-------+-----------------+--+
| jack  | 2 |
| mart  | 2 |
+-------+-----------------+--+

select name,count(*) over()
from business
where month(orderdate)='4';
+-------+-----------------+--+
| name  | count_window_0  |
+-------+-----------------+--+
| jack  | 5 |
| mart  | 5 |
| mart  | 5 |
| mart  | 5 |
| mart  | 5 |
+-------+-----------------+--+

select name,count(*) over(partition by name)
from business
where month(orderdate)='4'
group by name;

+-------+-----------------+--+
| name  | count_window_0  |
+-------+-----------------+--+
| jack  | 1 |
| mart  | 1 |
+-------+-----------------+--+


select name,count(*) over(partition by name)
from business
where month(orderdate)='4'

+-------+-----------------+--+
| name  | count_window_0  |
+-------+-----------------+--+
| jack  | 1 |
| mart  | 4 |
| mart  | 4 |
| mart  | 4 |
| mart  | 4 |
+-------+-----------------+--+

 name|orderdate|cost jack,2017-01-01,10 tony,2017-01-02,15 jack,2017-02-03,23 tony,2017-01-04,29 jack,2017-01-05,46 jack,2017-04-06,42 tony,2017-01-07,50 jack,2017-01-08,55 mart,2017-04-08,62 mart,2017-04-09,68 neil,2017-05-10,12 mart,2017-04-11,75 neil,2017-06-12,80 mart,2017-04-13,94
create table business(
name string,orderdate string,cost int)
row format delimited fields terminated by ','
load data local inpath "/opt/module/datas/business.txt"
into table business;

##按需求查询
1.查询在2017年4月购买过的顾客及总人数
select name,count(*) over()
from business
where subString(orderdate,1,7)='2017-04'
group by name;
2.查询顾客的购买明细及月购买总额
select name,sum(cost) over(partition by month(orderdate))
from business
3.上述的场景，将每个顾客的cost按照日期进行累加
select name,orderdate,cost,
sum(cost) over() as sample1, --将所有行相加
sum(cost) over(partition by name) as sample2,--按name分组，组内数据相加
sum(cost) over(partition by name order by orderdate) as sample3,--按name分组，组内数据累加 
sum(cost) over(partition by name order by orderdate rows between UNBOUNDED PRECEDING and current row) as sample4,--和sample3一样,由起点到当前行的聚合
sum(cost) over(partition by name order by orderdate rows between 1 PRECEDING AND current row) as sample5,--当前行和前面一行做聚合 
sum(cost) over(partition by name order by orderdate rows between 1 PRECEDING and 1 FOLLOWING) as simple6,--当前行和前边一行及后面一行 
sum(cost) over(partition by name order by orderdate rows between current row and UNBOUNDED FOLLOWING) as sample7 --当前行及后面所有行
from business

rows必须跟在Order by 子句之后，对排序的结果进行限制，使用固定的行数来限制分区中的数据行数量
4.查看顾客上次的购买时间(lag 往前n行)

select name,orderdate,cost,
lag(orderdate,1,'1970-01-01') over(partition by name order by orderdate ) as time1,
lag(orderdate,2) over(partition by name order by orderdate) as time2
from business;

结果：
name orderdate   cost time1   time2
jack 2017-01-01  10  1970-01-01  NULL
jack 2017-01-05  46  2017-01-01  NULL
jack 2017-01-08  55  2017-01-05  2017-01-01
jack 2017-02-03  23  2017-01-08  2017-01-05
jack 2017-04-06  42  2017-02-03  2017-01-08
mart 2017-04-08  62  1970-01-01  NULL
mart 2017-04-09  68  2017-04-08  NULL
mart 2017-04-11  75  2017-04-09  2017-04-08
mart 2017-04-13  94  2017-04-11  2017-04-09
neil 2017-05-10  12  1970-01-01  NULL
neil 2017-06-12  80  2017-05-10  NULL
tony 2017-01-02  15  1970-01-01  NULL
tony 2017-01-04  29  2017-01-02  NULL
tony 2017-01-07  50  2017-01-04  2017-01-02

NTILE(n)：把有序分区中的行分发到指定数据的组中，
各个组有编号，编号从1开始，对于每一行，NTILE返回此行所属的组的编号。
注意：n必须为int类型。

查询前20%时间的订单信息： select * from( select name,orderdate,cost,ntile(5) over(order by orderdate) sorted from business ) t where sorted = 1;

name subject score
孙悟空 语文  87
孙悟空 数学  95
孙悟空 英语  68
大海  语文  94
大海  数学  56
大海  英语  84
宋宋  语文  64
宋宋  数学  86
宋宋  英语  84
婷婷  语文  65
婷婷  数学  85
婷婷  英语  78

create table score(
name string,
subject string, 
score int) 
row format delimited fields terminated by "\t";
load data local inpath '/opt/module/datas/score.txt' into table score;

select name,subject,score,
rank() over(partition by subject order by score desc) rp,
dense_rank() over(partition by subject order by score desc) drp,
row_number() over(partition by subject order by score desc) rmp
from score;

name subject score   rp drp rmp
孙悟空  数学 95 1 1 1
宋宋 数学 86 2 2 2
婷婷 数学 85 3 3 3
大海 数学 56 4 4 4
宋宋 英语 84 1 1 1
大海 英语 84 1 1 2
婷婷 英语 78 3 2 3
孙悟空  英语 68 4 3 4
大海 语文 94 1 1 1
孙悟空  语文 87 2 2 2
婷婷 语文 65 3 3 3
宋宋 语文 64 4 4 4