over()
over() 函数在Hive中运用广泛,通常搭配row_number() ,min(),max(),sum()来使用,总结下over函数划定窗口的范围
idnamenum
1a12b33a54c95b3
over() 此时每一行的窗口都是所有的行
SELECT id
,name
,num
,
sum(num
) over() sum1
from aa
over(order by id) id=1的窗口只有一行,id=2的窗口包括id=1,id=2
SELECT id
,name
,num
,
sum(num
) over(order by id
) sum1
from aa
over(partition by name) 每一行根据 name来区分窗口
SELECT id
,name
,num
,
sum(num
) over(partition by name
) sum1
from aa
over(partition by name order by id) 每一行根据 name来区分窗口,再根据order by 取具体的范围
SELECT id
,name
,num
,
sum(num
) over(partition by name
order by id
) sum1
from aa
over( order by id range between 1 preceding and 1 following ) range 代表范围 preceding 向前 following 向后 窗口范围当前行前后一行
SELECT id
,name
,num
,
sum(num
) over( order by id range
between 1 preceding and 1 following ) sum1
from aa
over( order by id range between CURRENT ROW AND 1 following ) 窗口范围当前行和后面一行
SELECT id
,name
,num
,
sum(num
) over( order by id range
between CURRENT ROW AND 1 following ) sum1
from aa