求一个SQL聚合中去重复行的语句

[zbking]

表：
ID VAR1 VAR2 VAR3 NET
1 1001 X1001 M1001 1.1
2 1002 X1001 M1001 1.2
3 1003 X1002 M1001 1.3
4 1001 X1001 M1001 1.1

希望出现如下结果
X1001 2 2.3
X1002 1 1.3

简单来讲就是如果VAR1重复就排除。急1在线等待。谢谢

[longyi007]

select distinct VAR1 from biao

[dawugui]

select t.* from tb t where id = (select min(id) from tb where var2 = t.var2)
select t.* from tb t where not exists (select 1 from tb where var2 = t.var2 and id < t.id)

不知道你到底根据var1还是var2算,看结果应该是var2,如果不对,自己更改一下.

[longyi007]

还要sum么

[dawugui]

create table tb(ID int,VAR1 int,VAR2 varchar(10),VAR3 varchar(10),NET varchar(10))
insert into tb values(1 ,1001 ,'X1001', 'M1001', '1.1')
insert into tb values(2 ,1002 ,'X1001', 'M1001', '1.2')
insert into tb values(3 ,1003 ,'X1002', 'M1001', '1.3')
insert into tb values(4 ,1001 ,'X1001', 'M1001', '1.1')
go

select t.* from tb t where id = (select min(id) from tb where var2 = t.var2)
select t.* from tb t where not exists (select 1 from tb where var2 = t.var2 and id < t.id)


drop table tb

/*

ID          VAR1        VAR2       VAR3       NET        
----------- ----------- ---------- ---------- ---------- 
1           1001        X1001      M1001      1.1
3           1003        X1002      M1001      1.3

（所影响的行数为 2 行）
*/

相关内容给看我如下的小结:

--按某一字段分组取最大(小)值所在行的数据
--(爱新觉罗.毓华(十八年风雨,守得冰山雪莲花开) 2007-10-23于浙江杭州)
/*
数据如下：
name val memo
a    2   a2(a的第二个值)
a    1   a1--a的第一个值
a    3   a3:a的第三个值
b    1   b1--b的第一个值
b    3   b3:b的第三个值
b    2   b2b2b2b2
b    4   b4b4
b    5   b5b5b5b5b5
*/
--创建表并插入数据：
create table tb(name varchar(10),val int,memo varchar(20))
insert into tb values('a',    2,   'a2(a的第二个值)')
insert into tb values('a',    1,   'a1--a的第一个值')
insert into tb values('a',    3,   'a3:a的第三个值')
insert into tb values('b',    1,   'b1--b的第一个值')
insert into tb values('b',    3,   'b3:b的第三个值')
insert into tb values('b',    2,   'b2b2b2b2')
insert into tb values('b',    4,   'b4b4')
insert into tb values('b',    5,   'b5b5b5b5b5')
go

--一、按name分组取val最大的值所在行的数据。
--方法1：
select a.* from tb a where val = (select max(val) from tb where name = a.name) order by a.name
--方法2：
select a.* from tb a where not exists(select 1 from tb where name = a.name and val > a.val)
--方法3：
select a.* from tb a,(select name,max(val) val from tb group by name) b where a.name = b.name and a.val = b.val order by a.name
--方法4：
select a.* from tb a inner join (select name , max(val) val from tb group by name) b on a.name = b.name and a.val = b.val order by a.name
--方法5
select a.* from tb a where 1 > (select count(*) from tb where name = a.name and val > a.val ) order by a.name
/*
name       val         memo                 
---------- ----------- -------------------- 
a          3           a3:a的第三个值
b          5           b5b5b5b5b5
*/

--二、按name分组取val最小的值所在行的数据。
--方法1：
select a.* from tb a where val = (select min(val) from tb where name = a.name) order by a.name
--方法2：
select a.* from tb a where not exists(select 1 from tb where name = a.name and val < a.val)
--方法3：
select a.* from tb a,(select name,min(val) val from tb group by name) b where a.name = b.name and a.val = b.val order by a.name
--方法4：
select a.* from tb a inner join (select name , min(val) val from tb group by name) b on a.name = b.name and a.val = b.val order by a.name
--方法5
select a.* from tb a where 1 > (select count(*) from tb where name = a.name and val < a.val) order by a.name
/*
name       val         memo                 
---------- ----------- -------------------- 
a          1           a1--a的第一个值
b          1           b1--b的第一个值
*/

--三、按name分组取第一次出现的行所在的数据。
select a.* from tb a where val = (select top 1 val from tb where name = a.name) order by a.name
/*
name       val         memo                 
---------- ----------- -------------------- 
a          2           a2(a的第二个值)
b          1           b1--b的第一个值
*/

--四、按name分组随机取一条数据。
select a.* from tb a where val = (select top 1 val from tb where name = a.name order by newid()) order by a.name
/*
name       val         memo                 
---------- ----------- -------------------- 
a          1           a1--a的第一个值
b          5           b5b5b5b5b5
*/

--五、按name分组取最小的两个(N个)val
select a.* from tb a where 2 > (select count(*) from tb where name = a.name and val < a.val ) order by a.name,a.val
select a.* from tb a where val in (select top 2 val from tb where name=a.name order by val) order by a.name,a.val
select a.* from tb a where exists (select count(*) from tb where name = a.name and val < a.val having Count(*) < 2) order by a.name,a.val
/*
name       val         memo                 
---------- ----------- -------------------- 
a          1           a1--a的第一个值
a          2           a2(a的第二个值)
b          1           b1--b的第一个值
b          2           b2b2b2b2
*/

--六、按name分组取最大的两个(N个)val
select a.* from tb a where 2 > (select count(*) from tb where name = a.name and val > a.val ) order by a.name,a.val
select a.* from tb a where val in (select top 2 val from tb where name=a.name order by val desc) order by a.name,a.val
select a.* from tb a where exists (select count(*) from tb where name = a.name and val > a.val having Count(*) < 2) order by a.name , a.val
/*
name       val         memo                 
---------- ----------- -------------------- 
a          2           a2(a的第二个值)
a          3           a3:a的第三个值
b          4           b4b4
b          5           b5b5b5b5b5
*/
--七，如果整行数据有重复，所有的列都相同。
/*
数据如下：
name val memo
a    2   a2(a的第二个值)
a    1   a1--a的第一个值
a    1   a1--a的第一个值
a    3   a3:a的第三个值
a    3   a3:a的第三个值
b    1   b1--b的第一个值
b    3   b3:b的第三个值
b    2   b2b2b2b2
b    4   b4b4
b    5   b5b5b5b5b5
*/
--在sql server 2000中只能用一个临时表来解决，生成一个自增列，先对val取最大或最小，然后再通过自增列来取数据。
--创建表并插入数据：
create table tb(name varchar(10),val int,memo varchar(20))
insert into tb values('a',    2,   'a2(a的第二个值)')
insert into tb values('a',    1,   'a1--a的第一个值')
insert into tb values('a',    1,   'a1--a的第一个值')
insert into tb values('a',    3,   'a3:a的第三个值')
insert into tb values('a',    3,   'a3:a的第三个值')
insert into tb values('b',    1,   'b1--b的第一个值')
insert into tb values('b',    3,   'b3:b的第三个值')
insert into tb values('b',    2,   'b2b2b2b2')
insert into tb values('b',    4,   'b4b4')
insert into tb values('b',    5,   'b5b5b5b5b5')
go

select * , px = identity(int,1,1) into tmp from tb

select m.name,m.val,m.memo from
(
  select t.* from tmp t where val = (select min(val) from tmp where name = t.name)
) m where px = (select min(px) from
(
  select t.* from tmp t where val = (select min(val) from tmp where name = t.name)
) n where n.name = m.name)

drop table tb,tmp

/*
name       val         memo
---------- ----------- --------------------
a          1           a1--a的第一个值
b          1           b1--b的第一个值

(2 行受影响)
*/
--在sql server 2005中可以使用row_number函数，不需要使用临时表。
--创建表并插入数据：
create table tb(name varchar(10),val int,memo varchar(20))
insert into tb values('a',    2,   'a2(a的第二个值)')
insert into tb values('a',    1,   'a1--a的第一个值')
insert into tb values('a',    1,   'a1--a的第一个值')
insert into tb values('a',    3,   'a3:a的第三个值')
insert into tb values('a',    3,   'a3:a的第三个值')
insert into tb values('b',    1,   'b1--b的第一个值')
insert into tb values('b',    3,   'b3:b的第三个值')
insert into tb values('b',    2,   'b2b2b2b2')
insert into tb values('b',    4,   'b4b4')
insert into tb values('b',    5,   'b5b5b5b5b5')
go

select m.name,m.val,m.memo from
(
  select * , px = row_number() over(order by name , val) from tb
) m where px = (select min(px) from
(
  select * , px = row_number() over(order by name , val) from tb
) n where n.name = m.name)

drop table tb

/*
name       val         memo
---------- ----------- --------------------
a          1           a1--a的第一个值
b          1           b1--b的第一个值

(2 行受影响)
*/

[zbking]

[Quote=引用 2 楼 dawugui 的回复:]
select t.* from tb t where id = (select min(id) from tb where var2 = t.var2)
select t.* from tb t where not exists (select 1 from tb where var2 = t.var2 and id < t.id)

不知道你到底根据var1还是var2算,看结果应该是va……
[/Quote]
大哥我要由sum聚合啊

[中国风]

结果与数据不对

[zbking]

[Quote=引用 3 楼 longyi007 的回复:]
还要sum么
[/Quote]

要count 和 sum

[dawugui]

[Quote=引用 7 楼 zbking 的回复:]
引用 3 楼 longyi007 的回复:
还要sum么


要count 和 sum
[/Quote]

create table tb(ID int,VAR1 int,VAR2 varchar(10),VAR3 varchar(10),NET decimal(18,1))
insert into tb values(1 ,1001 ,'X1001', 'M1001', 1.1)
insert into tb values(2 ,1002 ,'X1001', 'M1001', 1.2)
insert into tb values(3 ,1003 ,'X1002', 'M1001', 1.3)
insert into tb values(4 ,1001 ,'X1001', 'M1001', 1.1)
go

select var2, count(1) cnt , sum(net) net from tb group by var2


drop table tb

/*

var2       cnt         net                                      
---------- ----------- ---------------------------------------- 
X1001      3           3.4
X1002      1           1.3

（所影响的行数为 2 行）
*/

[中国风]

--> --> (Roy)生成測試數據
 
if not object_id('Tempdb..#T') is null
	drop table #T
Go
Create table #T([ID] int,[VAR1] int,[VAR2] nvarchar(5),[VAR3] nvarchar(5),[NET] decimal(18,1))
Insert #T
select 1,1001,N'X1001',N'M1001',1.1 union all
select 2,1002,N'X1001',N'M1001',1.2 union all
select 3,1003,N'X1002',N'M1001',1.3 union all
select 4,1001,N'X1001',N'M1001',1.1
Go
Select [VAR2],COUNT([VAR1]) as [VAR1],SUM([NET]) as [NET] from #T as a 
where not exists(select 1 from #T where [VAR1]=a.[VAR1] and [VAR2]=a.[VAR2] and [NET]=a.[NET] and [ID]>a.[ID]) 
group by [VAR2]
/*
VAR2	VAR1	NET
X1001	2	2.3
X1002	1	1.3
*/

[中国风]

测测以上结果是否为你要的效果，先过滤重复再合计

[dawugui]

这样凑合出来的?

create table tb(ID int,VAR1 int,VAR2 varchar(10),VAR3 varchar(10),NET decimal(18,1))
insert into tb values(1 ,1001 ,'X1001', 'M1001', 1.1)
insert into tb values(2 ,1002 ,'X1001', 'M1001', 1.2)
insert into tb values(3 ,1003 ,'X1002', 'M1001', 1.3)
insert into tb values(4 ,1001 ,'X1001', 'M1001', 1.1)
go

select var2 , count(1) cnt , sum(net) net from
(
  select t.* from tb t where not exists (select 1 from tb where var1 = t.var1 and id < t.id)
) m
group by var2



drop table tb

/*

var2       cnt         net                                      
---------- ----------- ---------------------------------------- 
X1001      2           2.3
X1002      1           1.3

（所影响的行数为 2 行）
*/

[--小F--]

; with  f as
(
select * from tb t where id = (select min(id) from tb where var2 = t.var2)
)

select var2,count(1),sum(net) from f group by var2

[longyi007]

create table tbv(ID int,VAR1 int,VAR2 varchar(10),VAR3 varchar(10),NET decimal(18,1))
insert into tbv values(1 ,1001 ,'X1001', 'M1001', 1.1)
insert into tbv values(2 ,1002 ,'X1001', 'M1001', 1.2)
insert into tbv values(3 ,1003 ,'X1002', 'M1001', 1.3)
insert into tbv values(4 ,1001 ,'X1001', 'M1001', 1.1)
go

--来个简单的
select VAR2,
       count(distinct VAR1) as VAR1,
       sum(distinct NET) as NET
from tbv
group by VAR2 

--X1001	2	2.3
--X1002	1	1.3

[zbking]

[Quote=引用 11 楼 dawugui 的回复:]
这样凑合出来的?

SQL code
create table tb(ID int,VAR1 int,VAR2 varchar(10),VAR3 varchar(10),NET decimal(18,1))
insert into tb values(1 ,1001 ,'X1001', 'M1001', 1.1)
insert into tb values(2 ,1002 ,'X1001……
[/Quote]

谢谢，测试可以，如果没有ID列，改怎么写？

[中国风]

[Quote=引用 14 楼 zbking 的回复:]

引用 11 楼 dawugui 的回复:
这样凑合出来的?

SQL code
create table tb(ID int,VAR1 int,VAR2 varchar(10),VAR3 varchar(10),NET decimal(18,1))
insert into tb values(1 ,1001 ,'X1001', 'M1001', 1.1)
insert into tb……
[/Quote]

这样用

--> --> (Roy)生成測試數據
 
if not object_id('Tempdb..#T') is null
    drop table #T
Go
Create table #T([ID] int,[VAR1] int,[VAR2] nvarchar(5),[VAR3] nvarchar(5),[NET] decimal(18,1))
Insert #T
select 1,1001,N'X1001',N'M1001',1.1 union all
select 2,1002,N'X1001',N'M1001',1.2 union all
select 3,1003,N'X1002',N'M1001',1.3 union all
select 4,1001,N'X1001',N'M1001',1.1
Go
Select [VAR2],COUNT([VAR1]) as [VAR1],SUM([NET]) as [NET] 
from (select *,row=row_number()over(partition by [VAR2],[VAR1] order by [VAR1] asc )from #T as a )t
where row=1
group by [VAR2]

[bushy]

[Quote=引用 15 楼 roy_88 的回复:]
引用 14 楼 zbking 的回复:

引用 11 楼 dawugui 的回复:
这样凑合出来的?

SQL code
create table tb(ID int,VAR1 int,VAR2 varchar(10),VAR3 varchar(10),NET decimal(18,1))
insert into tb values(1 ,1001 ,'X1001', 'M1001'……
[/Quote]
支持