I have a table which is not sorted by any of column. Is there any way to select next/previous record if I know only Id of current? (I'm using mssql)
Id Label Date
---------------------
1 label1 2011-01-10
7 label2 2011-01-15 -- how to get previous?
5 label3 2011-01-12 -- I know id of this record
10 label10 2011-01-25 -- how to get next?
12 label8 2011-01-13
2 label5 2011-01-29
Thanks in advance!
try this:
VALUES (1, 'label1', '2011-01-10'), (7, 'label2', '2011-01-15'),
(5, 'label3', '2011-01-12'), (10, 'label10', '2011-01-25'),
(12, 'label8', '2011-01-13'), (2, 'label5', '2011-01-29')
select * from table007;
Declare #inptID int=12;
;WITH CTE
as
(
select *, ROW_NUMBER() over (order by (select 0)) as rn
from table007
)
select *
from CTE
where rn in( select rn-1 from CTE where id = #inptID)
union all
select * from CTE where rn in(select rn + 1 from CTE where id = #inptID);
SQL Fiddle Demo
DEMO
If it is not sorted by any column, there is no definitive next or previous record. Data in SQL Server has no order, other than that specified by an ORDER BY clause.
If you really want the previous from the list you enclosed, here is a way.
declare #t table(Id int, Label varchar(10), Date date, s int identity(1,1))
insert #t (id, label, date)
values(1,'label1','2011-01-10'),(7,'label2','2011-01-15'),
(5,'label3','2011-01-12'),(10,'label10','2011-01-25'),
(12,'label8','2011-01-13'),(2,'label5','2011-01-29')
--select the data with a self join
select t1.id as previous_id, t2.id, t2.Label, t2.Date, t3.id, t3.id as next_id
from #t t1
right join
#t t2 on t1.s + 1 = t2.s
left join
#t t3 on t2.s = t3.s - 1
Related
I've look at so many other questions and nothing quite fits my question or gets me the answer I need, maybe I'm just slow today :(
DECLARE #t TABLE (
[InstructionId] INT,
[InstructionDetailId] INT,
[Sequence] INT,
[Status] INT
)
INSERT INTO #t SELECT 222,111,1, 2
INSERT INTO #t SELECT 222,112,2,2
INSERT INTO #t SELECT 222,113,3,4
INSERT INTO #t SELECT 222,114,4,4
INSERT INTO #t SELECT 222,115,5,2
INSERT INTO #t SELECT 222,116,6,4
INSERT INTO #t SELECT 222,117,7,2
INSERT INTO #t SELECT 222,118,8,4
INSERT INTO #t SELECT 222,119,9,4
INSERT INTO #t SELECT 222,120,10,2
INSERT INTO #t SELECT 222,121,11,2
I need to find for which InstructionDetailId's there are consecutive failures (Status = 4) by using the [Sequence] field for checking the order to determine if they are consecutive. So for the above InstructionDetailId 113 and 114 would be consecutive failures as their [Sequence] is 3 & 4, same for InstructionDetailId 118 and 119 would be consecutive failures. I've tried so many row number variation and cte's and I can't quite crack it :( This is for SQL Server 2008 R2 by the way.
Expected output:
InstructionId InstructionDetailId Sequence Status
222 113 3 4
222 114 4 4
222 118 8 4
222 119 9 4
Thanx all!
Perhaps the simplest method is to use lag() and lead():
select t.*
from (select t.*,
lag(t.status) over (partition by t.InstructionId order by t.sequence) as prev_status,
lead(t.status) over (partition by t.InstructionId order by t.sequence) as next_status
from #t t
) t
where status = prev_status or status = next_status;
You can use APPLY :
select t.*
from #t t outer apply
( select top (1) t1.*
from #t t1
where t1.InstructionId = t.InstructionId and
t1.Sequence < t.Sequence
order by t1.Sequence desc
) t1 outer apply
( select top (1) t2.*
from #t t2
where t2.InstructionId = t.InstructionId and
t2.Sequence > t.Sequence
order by t2.Sequence
) t2
where t.status = 4 and (t.status = t1.status or t.status = t2.status);
Could you do something like...
select t1.InstructionID,
t1.InstructionDetailID,
t1.Sequence,
t1.Status,
from #t t1
inner join #t t2 on t1.InstructionID = t2.InstructionID
and t1.Sequence = (t2.Sequence - 1)
and t1.Status = t2.Status
and t1.Status = 4
Can anyone help me with the script which will select the latest date from the column dtUpdated_On if date is greater than last date and ID is less than last ID. I know the question is not clear but try to understand. In this example I want to delete ID 1003 (I know in this example we will say... Delete from tableName where ID=1003)
ID dtUpdated_On
-----------------------------------
1001 2009-12-11 20:08:16.857
1002 2012-03-31 02:35:16.650
1003 2012-09-01 00:00:00.000
1004 2012-03-31 02:35:16.650
Assuming that by "last" you mean the row with the highest id, then you can do:
select t.*
from t join
(select top 1 dtUpdated_On
from t
order by id desc
) last
on t.dtUpdated_On > last.dtUpdated_On;
You can also express this in the where clause, which is simpler for deletion (in my opinion):
delete t
where t.dtUpdated_On > (select top 1 t2.dtUpdated_On
from t
order by id desc
)
Try this,
DECLARE #MyTable TABLE(ID INT, dtUpdated_On DATETIME)
INSERT INTO #MyTable
VALUES (1001, '2009-12-11 20:08:16.857')
,(1002, '2012-03-31 02:35:16.650')
,(1003, '2012-09-01 00:00:00.000')
,(1004, '2012-03-31 02:35:16.650')
;WITH LatestDate AS
(
SELECT TOP 1 ID, dtUpdated_On
FROM #MyTable
ORDER BY dtUpdated_On DESC, ID DESC
),
LastestID AS
(
SELECT c.ID, c.dtUpdated_On, t.ID AS LatestID, t.dtUpdated_On AS LatestIDDate
FROM #MyTable t
INNER JOIN LatestDate c ON t.dtUpdated_On < c.dtUpdated_On
AND t.ID > c.ID
)
DELETE t
FROM #MyTable t
INNER JOIN LastestID c ON c.ID = t.ID
SELECT *
FROM #MyTable t
Class| Value
-------------
A | 1
A | 2
A | 3
A | 10
B | 1
I am not sure whether it is practical to achieve this using SQL.
If the difference of values are less than 5 (or x), then group the rows (of course with the same Class)
Expected result
Class| ValueMin | ValueMax
---------------------------
A | 1 | 3
A | 10 | 10
B | 1 | 1
For fixed intervals, we can easily use "GROUP BY". But now the grouping is based on nearby row's value. So if the values are consecutive or very close, they will be "chained together".
Thank you very much
Assuming MSSQL
You are trying to group things by gaps between values. The easiest way to do this is to use the lag() function to find the gaps:
select class, min(value) as minvalue, max(value) as maxvalue
from (select class, value,
sum(IsNewGroup) over (partition by class order by value) as GroupId
from (select class, value,
(case when lag(value) over (partition by class order by value) > value - 5
then 0 else 1
end) as IsNewGroup
from t
) t
) t
group by class, groupid;
Note that this assumes SQL Server 2012 for the use of lag() and cumulative sum.
Update:
*This answer is incorrect*
Assuming the table you gave is called sd_test, the following query will give you the output you are expecting
In short, we need a way to find what was the value on the previous row. This is determined using a join on row ids. Then create a group to see if the difference is less than 5. and then it is just regular 'Group By'.
If your version of SQL Server supports windowing functions with partitioning the code would be much more readable.
SELECT
A.CLASS
,MIN(A.VALUE) AS MIN_VALUE
,MAX(A.VALUE) AS MAX_VALUE
FROM
(SELECT
ROW_NUMBER()OVER(PARTITION BY CLASS ORDER BY VALUE) AS ROW_ID
,CLASS
,VALUE
FROM SD_TEST) AS A
LEFT JOIN
(SELECT
ROW_NUMBER()OVER(PARTITION BY CLASS ORDER BY VALUE) AS ROW_ID
,CLASS
,VALUE
FROM SD_TEST) AS B
ON A.CLASS = B.CLASS AND A.ROW_ID=B.ROW_ID+1
GROUP BY A.CLASS,CASE WHEN ABS(COALESCE(B.VALUE,0)-A.VALUE)<5 THEN 1 ELSE 0 END
ORDER BY A.CLASS,cASE WHEN ABS(COALESCE(B.VALUE,0)-A.VALUE)<5 THEN 1 ELSE 0 END DESC
ps: I think the above is ANSI compliant. So should run in most SQL variants. Someone can correct me if it is not.
These give the correct result, using the fact that you must have the same number of group starts as ends and that they will both be in ascending order.
if object_id('tempdb..#temp') is not null drop table #temp
create table #temp (class char(1),Value int);
insert into #temp values ('A',1);
insert into #temp values ('A',2);
insert into #temp values ('A',3);
insert into #temp values ('A',10);
insert into #temp values ('A',13);
insert into #temp values ('A',14);
insert into #temp values ('b',7);
insert into #temp values ('b',8);
insert into #temp values ('b',9);
insert into #temp values ('b',12);
insert into #temp values ('b',22);
insert into #temp values ('b',26);
insert into #temp values ('b',67);
Method 1 Using CTE and row offsets
with cte as
(select distinct class,value,ROW_NUMBER() over ( partition by class order by value ) as R from #temp),
cte2 as
(
select
c1.class
,c1.value
,c2.R as PreviousRec
,c3.r as NextRec
from
cte c1
left join cte c2 on (c1.class = c2.class and c1.R= c2.R+1 and c1.Value < c2.value + 5)
left join cte c3 on (c1.class = c3.class and c1.R= c3.R-1 and c1.Value > c3.value - 5)
)
select
Starts.Class
,Starts.Value as StartValue
,Ends.Value as EndValue
from
(
select
class
,value
,row_number() over ( partition by class order by value ) as GroupNumber
from cte2
where PreviousRec is null) as Starts join
(
select
class
,value
,row_number() over ( partition by class order by value ) as GroupNumber
from cte2
where NextRec is null) as Ends on starts.class=ends.class and starts.GroupNumber = ends.GroupNumber
** Method 2 Inline views using not exists **
select
Starts.Class
,Starts.Value as StartValue
,Ends.Value as EndValue
from
(
select class,Value ,row_number() over ( partition by class order by value ) as GroupNumber
from
(select distinct class,value from #temp) as T
where not exists (select 1 from #temp where class=t.class and Value < t.Value and Value > t.Value -5 )
) Starts join
(
select class,Value ,row_number() over ( partition by class order by value ) as GroupNumber
from
(select distinct class,value from #temp) as T
where not exists (select 1 from #temp where class=t.class and Value > t.Value and Value < t.Value +5 )
) ends on starts.class=ends.class and starts.GroupNumber = ends.GroupNumber
In both methods I use a select distinct to begin because if you have a dulpicate entry at a group start or end things go awry without it.
Here is one way of getting the information you are after:
SELECT Under5.Class,
(
SELECT MIN(m2.Value)
FROM MyTable AS m2
WHERE m2.Value < 5
AND m2.Class = Under5.Class
) AS ValueMin,
(
SELECT MAX(m3.Value)
FROM MyTable AS m3
WHERE m3.Value < 5
AND m3.Class = Under5.Class
) AS ValueMax
FROM
(
SELECT DISTINCT m1.Class
FROM MyTable AS m1
WHERE m1.Value < 5
) AS Under5
UNION
SELECT Over4.Class,
(
SELECT MIN(m4.Value)
FROM MyTable AS m4
WHERE m4.Value >= 5
AND m4.Class = Over4.Class
) AS ValueMin,
(
SELECT Max(m5.Value)
FROM MyTable AS m5
WHERE m5.Value >= 5
AND m5.Class = Over4.Class
) AS ValueMax
FROM
(
SELECT DISTINCT m6.Class
FROM MyTable AS m6
WHERE m6.Value >= 5
) AS Over4
I have a query with results like ID, Value. What I want is to get the values in order of their ids and also calculate the accumulated value in another column. take a look at my simplified code:
declare #TempTable Table
(
ID int,
Value int
)
insert into #TempTable values
(1, 10),
(2, -15),
(3, 12),
(4, 18),
(5, 5)
select t1.ID, t1.Value, SUM(t2.Value) AccValue from #TempTable t1
inner join #TempTable t2 on t1.ID >= t2.ID
group by t1.ID, t1.Value
order by t1.ID
Result:
ID Value AccValue
1 10 10
2 -15 -5
3 12 7
4 18 25
5 5 30
What I have come up with, is to use inner join between the result and itself for that purpose. But for huge amount of data, it's clearly a low performance issue.
Is there any other alternative to do that?
In 2012 version, you can use:
SELECT
id,
Value,
AccValue = SUM(Value) OVER (ORDER BY ID
ROWS BETWEEN UNBOUNDED PRECEDING
AND CURRENT ROW)
FROM
#TempTable ;
For previous versions of SQL-Server, see my answer in this similar question: Recursive SQL- How can I get this table with a running total?, with a cursor solution.
Even better, follow the link to the great article by #Aaron Bertrand, that has a thorough test of various methods to calculate a running total: Best approaches for running totals – updated for SQL Server 2012
You can use recursion:
;WITH x AS
(
SELECT
[ID],
[Value],
bal=[Value]
FROM Table1
WHERE [ID] = 1
UNION ALL
SELECT
y.[ID],
y.[Value],
x.bal+(y.[Value]) as bal
FROM x INNER JOIN Table1 AS y
ON y.[ID] = x.[ID] + 1
)
SELECT
[ID],
[Value],
AccValue= bal
FROM x
order by ID
OPTION (MAXRECURSION 10000);
SQL FIDDLE
The generic SQL way to do this is with a correlated subquery (at least, I think that is the cleanest way):
select t.*,
(select sum(t2.value)
from #TempTable t2
where t2.ID <= t.ID
) AccValue
from #TempTable t
SQL Server 2012 has a cumulative sum function:
select t.*,
sum(t.value) over (order by t.id) as AccValue
from #TempTable t
This question already has answers here:
Select top 10 records for each category
(14 answers)
Closed 5 years ago.
Assume we have a table which has two columns, one column contains the names of some people and the other column contains some values related to each person. One person can have more than one value. Each value has a numeric type. The question is we want to select the top 3 values for each person from the table. If one person has less than 3 values, we select all the values for that person.
The issue can be solved if there are no duplicates in the table by the query provided in this article Select top 3 values from each group in a table with SQL . But if there are duplicates, what is the solution?
For example, if for one name John, he has 5 values related to him. They are 20,7,7,7,4. I need to return the name/value pairs as below order by value descending for each name:
-----------+-------+
| name | value |
-----------+-------+
| John | 20 |
| John | 7 |
| John | 7 |
-----------+-------+
Only 3 rows should be returned for John even though there are three 7s for John.
In many modern DBMS (e.g. Postgres, Oracle, SQL-Server, DB2 and many others), the following will work just fine. It uses CTEs and ranking function ROW_NUMBER() which is part of the latest SQL standard:
WITH cte AS
( SELECT name, value,
ROW_NUMBER() OVER (PARTITION BY name
ORDER BY value DESC
)
AS rn
FROM t
)
SELECT name, value, rn
FROM cte
WHERE rn <= 3
ORDER BY name, rn ;
Without CTE, only ROW_NUMBER():
SELECT name, value, rn
FROM
( SELECT name, value,
ROW_NUMBER() OVER (PARTITION BY name
ORDER BY value DESC
)
AS rn
FROM t
) tmp
WHERE rn <= 3
ORDER BY name, rn ;
Tested in:
Postgres
Oracle
SQL-Server
In MySQL and other DBMS that do not have ranking functions, one has to use either derived tables, correlated subqueries or self-joins with GROUP BY.
The (tid) is assumed to be the primary key of the table:
SELECT t.tid, t.name, t.value, -- self join and GROUP BY
COUNT(*) AS rn
FROM t
JOIN t AS t2
ON t2.name = t.name
AND ( t2.value > t.value
OR t2.value = t.value
AND t2.tid <= t.tid
)
GROUP BY t.tid, t.name, t.value
HAVING COUNT(*) <= 3
ORDER BY name, rn ;
SELECT t.tid, t.name, t.value, rn
FROM
( SELECT t.tid, t.name, t.value,
( SELECT COUNT(*) -- inline, correlated subquery
FROM t AS t2
WHERE t2.name = t.name
AND ( t2.value > t.value
OR t2.value = t.value
AND t2.tid <= t.tid
)
) AS rn
FROM t
) AS t
WHERE rn <= 3
ORDER BY name, rn ;
Tested in MySQL
I was going to downvote the question. However, I realized that it might really be asking for a cross-database solution.
Assuming you are looking for a database independent way to do this, the only way I can think of uses correlated subqueries (or non-equijoins). Here is an example:
select distinct t.personid, val, rank
from (select t.*,
(select COUNT(distinct val) from t t2 where t2.personid = t.personid and t2.val >= t.val
) as rank
from t
) t
where rank in (1, 2, 3)
However, each database that you mention (and I note, Hadoop is not a database) has a better way of doing this. Unfortunately, none of them are standard SQL.
Here is an example of it working in SQL Server:
with t as (
select 1 as personid, 5 as val union all
select 1 as personid, 6 as val union all
select 1 as personid, 6 as val union all
select 1 as personid, 7 as val union all
select 1 as personid, 8 as val
)
select distinct t.personid, val, rank
from (select t.*,
(select COUNT(distinct val) from t t2 where t2.personid = t.personid and t2.val >= t.val
) as rank
from t
) t
where rank in (1, 2, 3);
Using GROUP_CONCAT and FIND_IN_SET you can do that.Check SQLFIDDLE.
SELECT *
FROM tbl t
WHERE FIND_IN_SET(t.value,(SELECT
SUBSTRING_INDEX(GROUP_CONCAT(t1.value ORDER BY VALUE DESC),',',3)
FROM tbl t1
WHERE t1.name = t.name
GROUP BY t1.name)) > 0
ORDER BY t.name,t.value desc
If your result set is not so heavy, you can write a stored procedure (or an anonymous PL/SQL-block) for that problem which iterates the result set and finds the bigges three by a simple comparing algorithm.
Try this -
CREATE TABLE #list ([name] [varchar](100) NOT NULL, [value] [int] NOT NULL)
INSERT INTO #list VALUES ('John', 20), ('John', 7), ('John', 7), ('John', 7), ('John', 4);
WITH cte
AS (
SELECT NAME
,value
,ROW_NUMBER() OVER (
PARTITION BY NAME ORDER BY (value) DESC
) RN
FROM #list
)
SELECT NAME
,value
FROM cte
WHERE RN < 4
ORDER BY value DESC
This works for MS SQL. Should be workable in any other SQL dialect that has the ability to assign row numbers in a group by or over clause (or equivelant)
if object_id('tempdb..#Data') is not null drop table #Data;
GO
create table #data (name varchar(25), value integer);
GO
set nocount on;
insert into #data values ('John', 20);
insert into #data values ('John', 7);
insert into #data values ('John', 7);
insert into #data values ('John', 7);
insert into #data values ('John', 5);
insert into #data values ('Jack', 5);
insert into #data values ('Jane', 30);
insert into #data values ('Jane', 21);
insert into #data values ('John', 5);
insert into #data values ('John', -1);
insert into #data values ('John', -1);
insert into #data values ('Jane', 18);
set nocount off;
GO
with D as (
SELECT
name
,Value
,row_number() over (partition by name order by value desc) rn
From
#Data
)
SELECT Name, Value
FROM D
WHERE RN <= 3
order by Name, Value Desc
Name Value
Jack 5
Jane 30
Jane 21
Jane 18
John 20
John 7
John 7