Related
I have one doubt in sql server
get records based on installments
Table :productdetails
CREATE TABLE [dbo].[productdetails](
[productid] [int] NULL,
[Productrstartdate] [date] NULL,
[Productenddate] [date] NULL,
[EMIInstallment] [int] NULL
) ON [PRIMARY]
GO
INSERT [dbo].[productdetails] ([productid], [Productrstartdate], [Productenddate], [EMIInstallment]) VALUES (1, CAST(N'2020-10-02' AS Date), CAST(N'2024-10-02' AS Date), 5)
GO
INSERT [dbo].[productdetails] ([productid], [Productrstartdate], [Productenddate], [EMIInstallment]) VALUES (2, CAST(N'2020-02-10' AS Date), CAST(N'2021-02-10' AS Date), 2)
GO
INSERT [dbo].[productdetails] ([productid], [Productrstartdate], [Productenddate], [EMIInstallment]) VALUES (3, CAST(N'2019-01-10' AS Date), CAST(N'2019-01-10' AS Date), 1)
GO
INSERT [dbo].[productdetails] ([productid], [Productrstartdate], [Productenddate], [EMIInstallment]) VALUES (4, CAST(N'2019-01-18' AS Date), CAST(N'2021-01-18' AS Date), 3)
GO
based on above data i want output like below
Productid |Installmentdate |noofinstallmentcount
1 |2020-10-02 |1
1 |2021-10-02 |2
1 |2022-10-02 |3
1 |2023-10-02 |4
1 |2024-10-02 |5
2 |2020-02-10 |1
2 |2021-02-10 |2
3 |2019-01-10 |1
4 |2019-01-18 |1
4 |2020-01-18 |2
4 |2021-01-18 |3
i tried like below :
DECLARE #MINDATE DATE='2019-01-18'
DECLARE #COUNT INT=10
dECLARE #MAXDATE DATE='2024-10-02'
;WITH ABC
AS
(
SELECT productid ,#MINDATE CalendarDate ,1 as id from [dbo].[productdetails]
UNION ALL
SELECT a.productid ,DATEADD(YEAR,1,a.Productrstartdate ), 1 FROM [dbo].[productdetails] a
join [dbo].[productdetails] b on a.productid=b.productid
WHERE #MINDATE <#MAXDATE )
SELECT * FROM ABC
above query not given expected output
could you please tell me how to write query to achive this task in sql server .
You want a tally here. If you're not going to have a value (much) higher than 10, then just a VALUES clause will work:
SELECT pd.productid,
DATEADD(YEAR, V.I, pd.Productrstartdate) AS Installmentdate,
V.I + 1 AS noofinstallmentcount
FROM dbo.productdetails pd
JOIN (VALUES(0),(1),(2),(3),(4),(5),(6),(7),(8),(9))V(I) ON pd.EMIInstallment > V.I;
If you need bigger numbers, just use a bigger tally:
WITH N AS(
SELECT N
FROM (VALUES(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL),(NULL))N(N)),
Tally AS(
SELECT ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) -1 AS I
FROM N N1, N N2, N N3) --1000 rows
SELECT pd.productid,
DATEADD(YEAR, T.I, pd.Productrstartdate) AS Installmentdate,
T.I + 1 AS noofinstallmentcount
FROM dbo.productdetails pd
JOIN Tally T ON pd.EMIInstallment > T.I;
You could create a temp table that mimics the actual productdetails table, then iterate through it, creating an output table that lists the product id with each installment date. Once you have that, you can use ROW_NUMBER() to count the installment numbers. Try this:
SELECT *
INTO #productdetails
FROM productdetails
CREATE TABLE #output (
productid int null
,installmentdate date null)
WHILE (SELECT COUNT(*) FROM #productdetails) > 0
BEGIN
DECLARE #yr int = 0
WHILE (SELECT TOP 1 DATEDIFF(year, DATEADD(year, #yr, Productrstartdate), productenddate) FROM #productdetails) >= 0
BEGIN
INSERT INTO #output (
productid
,installmentdate)
SELECT top 1
productid
,DATEADD(year, #yr, Productrstartdate) installmentdate
FROM #productdetails
SET #yr = #yr + 1
END
DELETE TOP (1) FROM #productdetails
END
SELECT *
,ROW_NUMBER() OVER (PARTITION BY ProductId ORDER BY InstallmentDate asc) NumberOfInstallmentCount
FROM #output
DROP TABLE #output, #productdetails
Say I have a column in a SQL Server table with the following entries:
+----+-----+
| ids| col1|
+----+-----+
|4 | a |
|4 | b |
|4 | a |
|4 | b |
|5 | a |
+----+-----+
I'd like to mask the ids column given that col1 = a. However, I'd also like to maintain the uniqueness of the ids masking, so the result would look as follows:
+----+-----+
| ids| col1|
+----+-----+
|XX | a |
|4 | b |
|XX | a |
|4 | b |
|YY | a |
+----+-----+
I have used a case...when with SHA2_256 algorithm to maintain uniqueness as in this post:
How do I mask/encrypt data in a view but maintain uniqueness of values?
,but then the resulting mask are 'Chinese-looking' characters that seem machine-unreadable. Is there a better way?
Would numbers be OK?
First, create and populate sample table (Please save us this step in your future questions)
DECLARE #T AS TABLE
(
ids int,
col1 char(1)
)
INSERT INTO #T VALUES
(4, 'a'),
(4, 'b'),
(4, 'a'),
(4, 'b'),
(5, 'a')
The query:
SELECT CASE WHEN col1 = 'a' THEN CHECKSUM(CAST(Ids as varchar(11))) ELSE ids END As ids,
col1
FROM #T
Results:
ids col1
136 a
4 b
136 a
4 b
137 a
Your suggested masked output values of XX and YY are perhaps misleading, because if you have millions of id values in your table, then two letters won't be able to uniquely/randomly cover all data. One option here might be to use NEWID() to generate a unique UUID for each id group:
WITH cte AS (
SELECT DISTINCT id, NEWID() AS mask
FROM yourTable
)
SELECT t2.mask, t1.col
FROM yourTable t1
INNER JOIN cte t2
ON t1.id = t2.id;
If you don't want to show the entire UUID, because it is too long, then you may instead show a substring of it, e.g. for just the first 5 characters:
SELECT LEFT(t2.mask, 5) AS mask, t1.col
FROM yourTable t1
INNER JOIN cte t2
ON t1.id = t2.id;
But keep in mind that the shorter you make the UUID being displayed, the greater the probability that two different id groups would be rendered with the same mask.
Try this query (Replace #test with your actual table name), In future case can come where you need to include other characters too in addition to just 'a'.
Below List table will help you with that.
create table #list
(
col1 varchar(1)
)
insert into #list values ('a')
select case when isnull(b.col1,'0')<>'0' then a.col1+cast ( Dense_rank() OVER(PARTITION BY a.col1 ORDER BY a.col1 ASC) as varchar(max)) else cast(a.ids as varchar(max)) end as ids,
a.col1 from #test a
left join #list b
on a.col1 =b.col1
Out Put
So this is what I ended up doing. Using the example provided by #Zohar Peled, but making the adjustment that the ids column is a varchar, we can make the table as follows:
DECLARE #T AS TABLE
(
ids varchar(150),
col1 char(1)
)
INSERT INTO #T VALUES
(4, 'a'),
(4, 'b'),
(4, 'a'),
(4, 'b'),
(5, 'a')
and then do the following:
SELECT CASE WHEN col1 = 'a' THEN CONVERT(VARCHAR(150),HashBytes('SHA2_256', ids),2) ELSE ids END As ids,
col1
FROM #T
This more closely resembles the initial solution in the link, I believe.
You can hide IDs also by integer numbers (don't know if it's secure enough in your case)
CREATE TABLE #t (ids int, col1 char(1));
INSERT INTO #t VALUES
(4, 'a'),
(4, 'b'),
(4, 'a'),
(4, 'b'),
(5, 'a');
Query
SELECT ISNULL(t2.num, t1.ids) AS ids, t1.col1
FROM
#t t1 LEFT JOIN
(
SELECT
ROW_NUMBER() OVER (ORDER BY ids, col1) + (SELECT MAX(ids) FROM #t) AS num,
ids, col1
FROM #t
WHERE col1 = 'a'
GROUP BY ids, col1) t2
ON t1.ids = t2.ids AND t1.col1 = t2.col1;
Result
ids col1
-------------------- ----
6 a
4 b
6 a
4 b
7 a
I have been reading the following Microsoft article on recursive queries using CTE and just can't seem to wrap my head around how to use it for group common items.
I have a table the contains the following columns:
ID
FirstName
LastName
DateOfBirth
BirthCountry
GroupID
What I need to do is start with the first person in the table and iterate through the table and find all the people that have the same (LastName and BirthCountry) or have the same (DateOfBirth and BirthCountry).
Now the tricky part is that I have to assign them the same GroupID and then for each person in that GroupID, I need to see if anyone else has the same information and then put the in the same GroupID.
I think I could do this with multiple cursors but it is getting tricky.
Here is sample data and output.
ID FirstName LastName DateOfBirth BirthCountry GroupID
----------- ---------- ---------- ----------- ------------ -----------
1 Jonh Doe 1983-01-01 Grand 100
2 Jack Stone 1976-06-08 Grand 100
3 Jane Doe 1982-02-08 Grand 100
4 Adam Wayne 1983-01-01 Grand 100
5 Kay Wayne 1976-06-08 Grand 100
6 Matt Knox 1983-01-01 Hay 101
John Doe and Jane Doe are in the same Group (100) because they have the same (LastName and BirthCountry).
Adam Wayne is in Group (100) because he has the same (BirthDate and BirthCountry) as John Doe.
Kay Wayne is in Group (100) because she has the same (LastName and BirthCountry) as Adam Wayne who is already in Group (100).
Matt Knox is in a new group (101) because he does not match anyone in previous groups.
Jack Stone is in a group (100) because he has the same (BirthDate and BirthCountry) as Kay Wayne who is already in Group (100).
Data scripts:
CREATE TABLE #Tbl(
ID INT,
FirstName VARCHAR(50),
LastName VARCHAR(50),
DateOfBirth DATE,
BirthCountry VARCHAR(50),
GroupID INT NULL
);
INSERT INTO #Tbl VALUES
(1, 'Jonh', 'Doe', '1983-01-01', 'Grand', NULL),
(2, 'Jack', 'Stone', '1976-06-08', 'Grand', NULL),
(3, 'Jane', 'Doe', '1982-02-08', 'Grand', NULL),
(4, 'Adam', 'Wayne', '1983-01-01', 'Grand', NULL),
(5, 'Kay', 'Wayne', '1976-06-08', 'Grand', NULL),
(6, 'Matt', 'Knox', '1983-01-01', 'Hay', NULL);
Here's what I came up with. I have rarely written recursive queries so it was some good practice for me. By the way Kay and Adam do not share a birth country in your sample data.
with data as (
select
LastName, DateOfBirth, BirthCountry,
row_number() over (order by LastName, DateOfBirth, BirthCountry) as grpNum
from T group by LastName, DateOfBirth, BirthCountry
), r as (
select
d.LastName, d.DateOfBirth, d.BirthCountry, d.grpNum,
cast('|' + cast(d.grpNum as varchar(8)) + '|' as varchar(1024)) as equ
from data as d
union all
select
d.LastName, d.DateOfBirth, d.BirthCountry, r.grpNum,
cast(r.equ + cast(d.grpNum as varchar(8)) + '|' as varchar(1024))
from r inner join data as d
on d.grpNum > r.grpNum
and charindex('|' + cast(d.grpNum as varchar(8)) + '|', r.equ) = 0
and (d.LastName = r.LastName or d.DateOfBirth = r.DateOfBirth)
and d.BirthCountry = r.BirthCountry
), g as (
select LastName, DateOfBirth, BirthCountry, min(grpNum) as grpNum
from r group by LastName, DateOfBirth, BirthCountry
)
select t.*, dense_rank() over (order by g.grpNum) + 100 as GroupID
from T as t
inner join g
on g.LastName = t.LastName
and g.DateOfBirth = t.DateOfBirth
and g.BirthCountry = t.BirthCountry
For the recursion to terminate it's necessary to keep track of the equivalences (via string concatenation) so that at each level it only needs to consider newly discovered equivalences (or connections, transitivities, etc.) Notice that I've avoided using the word group to avoid bleeding into the GROUP BY concept.
http://rextester.com/edit/TVRVZ10193
EDIT: I used an almost arbitrary numbering for the equivalences but if you wanted them to appear in a sequence based on the lowest ID with each block that's easy to do. Instead of using row_number() say min(ID) as grpNum presuming, of course, that IDs are unique.
I assume groupid is the output you want which start from 100.
Even if groupid come from another table,then it is no problem.
Firstly,sorry for my "No cursor comments".Cursor or RBAR operation is require for this task.In fact after a very long time i met such requirement which took so long and I use RBAR operation.
if tommorrow i am able to do using SET BASE METHOD,then I will come and edit it.
Most importantly using RBAR operation make the script more understanding and I think it wil work for other sample data too.
Also give feedback about the performance and how it work with other sample data.
Alsi in my script you note that id are not in serial,and it do not matter,i did this in order to test.
I use print for debuging purpose,you can remove it.
SET NOCOUNT ON
DECLARE #Tbl TABLE(
ID INT,
FirstName VARCHAR(50),
LastName VARCHAR(50),
DateOfBirth DATE,
BirthCountry VARCHAR(50),
GroupID INT NULL
);
INSERT INTO #Tbl VALUES
(1, 'Jonh', 'Doe', '1983-01-01', 'Grand', NULL) ,
(2, 'Jack', 'Stone', '1976-06-08', 'Grand', NULL),
(3, 'Jane', 'Doe', '1982-02-08', 'Grand', NULL),
(4, 'Adam', 'Wayne', '1983-01-01', 'Grand', NULL),
(5, 'Kay', 'Wayne', '1976-06-08', 'Grand', NULL),
(6, 'Matt', 'Knox', '1983-01-01', 'Hay', NULL),
(7, 'Jerry', 'Stone', '1976-06-08', 'Hay', NULL)
DECLARE #StartGroupid INT = 100
DECLARE #id INT
DECLARE #Groupid INT
DECLARE #Maxid INT
DECLARE #i INT = 1
DECLARE #MinGroupID int=#StartGroupid
DECLARE #MaxGroupID int=#StartGroupid
DECLARE #LastGroupID int
SELECT #maxid = max(id)
FROM #tbl
WHILE (#i <= #maxid)
BEGIN
SELECT #id = id
,#Groupid = Groupid
FROM #Tbl a
WHERE id = #i
if(#Groupid is not null and #Groupid<#MinGroupID)
set #MinGroupID=#Groupid
if(#Groupid is not null and #Groupid>#MaxGroupID)
set #MaxGroupID=#Groupid
if(#Groupid is not null)
set #LastGroupID=#Groupid
UPDATE A
SET groupid =case
when #id=1 and b.groupid is null then #StartGroupid
when #id>1 and b.groupid is null then #MaxGroupID+1--(Select max(groupid)+1 from #tbl where id<#id)
when #id>1 and b.groupid is not null then #MinGroupID --(Select min(groupid) from #tbl where id<#id)
end
FROM #Tbl A
INNER JOIN #tbl B ON b.id = #ID
WHERE (
(
a.BirthCountry = b.BirthCountry
and a.DateOfBirth = b.dateofbirth
)
or (a.LastName = b.LastName and a.BirthCountry = b.BirthCountry)
or (a.LastName = b.LastName and a.dateofbirth = b.dateofbirth)
)
--if(#id=7) --#id=2,#id=3 and so on (for debug
--break
SET #i = #i + 1
SET #ID = #I
END
SELECT *
FROM #Tbl
Alternate Method but still it return 56,000 rows without rownum=1.See if it work with other sample data or see if you can further optimize it.
;with CTE as
(
select a.ID,a.FirstName,a.LastName,a.DateOfBirth,a.BirthCountry
,#StartGroupid GroupID
,1 rn
FROM #Tbl A where a.id=1
UNION ALL
Select a.ID,a.FirstName,a.LastName,a.DateOfBirth,a.BirthCountry
,case when ((a.BirthCountry = b.BirthCountry and a.DateOfBirth = b.dateofbirth)
or (a.LastName = b.LastName and a.BirthCountry = b.BirthCountry)
or (a.LastName = b.LastName and a.dateofbirth = b.dateofbirth)
) then b.groupid else b.groupid+1 end
, b.rn+1
FROM #tbl A
inner join CTE B on a.id>1
where b.rn<#Maxid
)
,CTE1 as
(select * ,row_number()over(partition by id order by groupid )rownum
from CTE )
select * from cte1
where rownum=1
Maybe you can run it in this way
SELECT *
FROM table_name
GROUP BY
FirstName,
LastName,
GroupID
HAVING COUNT(GroupID) >= 2
ORDER BY GroupID
Using T-SQL (SQL Server 2008 R2), I'm trying to list only the rows with the second highest value in a particular column from a temp table and then place the results into a new temp table. The PK is the ID, which can have increasing version numbers and then unique codes.
Example:
ID | Name| Version | Code
------------------------
1 | A | 1 | 10
1 | A | 2 | 20
1 | A | 3 | NULL
2 | B | 1 | 40
2 | B | 2 | 50
2 | C | 1 | 60
The desired outcome of the query is
ID | Version | Code
------------------------
1 | 2 | 20
2 | 1 | 40
To achieve this I need the below query to be adapted to pull the second highest value as long as the result gives a version number greater than 1. These results come from a temp table and will then be placed into a final results temp table. EDIT: Please note this will be applied over 33000 rows of data so I would prefer something neater than INSERT VALUES. Thanks.
Current query:
SELECT
ID
,Version
,Code
INTO
#table2
FROM
#table1
SELECT *
FROM #table2
WHERE Version > 1
ORDER BY ID asc
DROP TABLE #table1
DROP TABLE #table2
I have tried running the where clause WHERE Version < (SELECT MAX(VERSION) FROM #TABLE 2) but this has no effect, presumably due to the unique code values and in any case wouldn't work where I have more than 3 Versions.
Ideas would be gratefully received.
Thanks in advance.
i HAVE TEST THE BELOW CODE AND IT IS GIVING OUTPUT AS PER The YOUR desired outcome of the query is
SELECT ID,Name,[Version],Code
FROM (
SELECT ROW_NUMBER() OVER (PARTITION BY NAME ORDER BY [Version] DESC) AS RNK,*
FROM
(
SELECT 1 ID, 'A' Name ,1 [Version] ,10 Code
UNION ALL
SELECT 1, 'A', 2 ,20
UNION ALL
SELECT 1, 'A', 3 ,30
UNION ALL
SELECT 1, 'A', 4 ,NULL
UNION ALL
SELECT 2, 'B', 1 ,40
UNION ALL
SELECT 2, 'B', 2 ,50
UNION ALL
SELECT 2, 'C', 1 ,60
)B
)BASE
WHERE RNK =2
If your primary key is only ID, you have duplicate rows. So I assume your primary key is something else, for example ID, Version, Name. You have two rows with the same ID and same Version, what kind of rule do you want to apply on this ? Lowest number ?
I made an example that does kind of what you want:
First declare the necessary tables:
declare #table1 table (
Id int,
Name nvarchar(20),
[Version] int,
Code int
)
insert into #table1 values (1,'A',1,10),(1,'A',2,20),(1,'A',3,30),(1,'A',4,NULL)
,(2,'B',1,40),(2,'B',2,50),(2,'C',1,60);
And then the query to get the results:
with HighestVersions (Id, MaxVersion) As
(
select Id, max(version) from #table1 group by Id
)
select
t1.Id,
t1.[Version],
min(t1.Code) as Code
from
#table1 t1
inner join
HighestVersions hv
on
hv.Id = t1.Id
and (hv.MaxVersion-1) = t1.[Version]
group by
t1.Id
,t1.[Version]
I had to do a little dirty trick with the outermost select, this is because of the duplicate 'Id' and 'Version'. Else you would have gotten two rows with ID = 2, Version = 1
If you want to remove the NULL value you can change the WITH part (according to your last edit):
with HighestVersions (Id, MaxVersion) As
(
select Id, max(version) from #table1 where Code is not null group by Id
)
Try this:
DECLARE #List TABLE (ID int, Name char(1), Version int, Code int NULL)
INSERT INTO #List
VALUES
(1, 'A', 1, 10),
(1, 'A', 2, 20),
(1, 'A', 3, 30),
(1, 'A', 4, NULL),
(2, 'B', 1, 40),
(2, 'B', 2, 50),
(2, 'C', 1, 60)
SELECT
ID, Name, Version, Code
FROM
(
SELECT
*,
ROW_NUMBER() OVER (PARTITION BY ID, Name ORDER BY Version DESC) Rn
FROM #List
) a
WHERE
a.Rn = 2
I am working with SQL Server 2008. I have a table which does not contain any unique columns; how to get alternate rows from it?
SQL Server table:
+-----+--------+
| id | name |
|-----+--------|
| 1 | abc |
| 2 | pqr |
| 2 | pqr |
| 3 | xyz |
| 4 | lmn |
| 5 | efg |
| 5 | efg |
+-----+--------+
As we've to come with at least one working suggestion with the question, I've tried below code; which is not so proper technique when fetching from a huge amount of data.
Trial:
create table #tmp
(
id int, name varchar(10), srNo int
)
insert into #tmp
select
id, name,
ROW_NUMBER() OVER (ORDER BY id) % 2 as srNo --,alternate rows
from
Employee
select *
from #tmp
where srNo = 1 --or srNo = 0
Above query gives out alternate rows i.e. 1st, 3rd, 5th OR 2nd, 4th, 6th etc.
Please help me out with proper way without #tmp to achieve the goal!
You can just use your select statement as an in-line view. You don't need the #tmp table.
select t.id, name
from (select id, name, ROW_NUMBER() over (order by id) as srNo from Employee) t
where (t.srNo % 2) = 1
SqlFiddle
--To fetch ALTERNATE records from a table (EVEN NUMBERED)
Select * from TableName where ColumnName % 2 = 0
For Eg : select * from HumanResources.Employee where BusinessEntityID % 2 = 0
--To fetch ALTERNATE records from a table (ODD NUMBERED)
Select * from TableName where ColumnName % 2 = 1
For Eg : select * from HumanResources.Employee where BusinessEntityID % 2 = 1
I'm taking student as a table name.
Here is my answer ->
For Even Row Number -
> SELECT id from (SELECT rowno, id from student) where mod(rowno,2)=0
For Odd Row Number -
> SELECT id from (SELECT rowno, id from student) where mod(rowno,2)=1
Same also can be achieved using having clause; but it adds group by task:
SELECT id, name
FROM (SELECT id, name, ROW_NUMBER()over(order by id) AS srNo FROM Employee) x
GROUP BY srNo, id, name
HAVING (srNo % 2) = 0
You can just use your select statement as an in-line view. You don't need the #tblCities table.
select tbl1.CityID,tbl1.CityName from (select ROW_NUMBER() over(order by CityID asc) as row_no,CityID,CityName from tblCities) as tbl1 where tbl1.row_no%2=1
declare #t table
(
id int,
name nvarchar(20)
)
insert into #t
Select 1, 'abc'
union all
Select 2, 'pqr'
union all
Select 2, 'pqr'
union all
Select 3, 'xyz'
union all
Select 4, 'lmn'
union all
Select 5, 'efg'
union all
Select 2, 'efg'
Select * from(
Select *, row_number() over(order by id) as rnum from #t ) t where rnum % 2 <> 0
create table t (id bigint NOT NULL, input_1 boolean not null, data_gps timestamp(0) not null);
insert into t (id, input_1,data_gps) values
(1, false , '2022-01-01 15:42:07'),
(2, true , '2022-01-02 15:42:07'),
(3, true , '2022-01-03 15:42:07'),
(4, false , '2022-01-04 15:42:07'),
(5, true , '2022-01-05 15:42:07'),
(6, true , '2022-01-06 15:42:07'),
(7, true , '2022-01-07 15:42:07'),
(8, true , '2022-01-08 15:42:07'),
(9, false , '2022-01-09 15:42:07'),
(10 ,true , '2022-01-10 15:42:07'),
(11, true , '2022-01-11 15:42:07'),
(12, true , '2022-01-12 15:42:07'),
(13, false , '2022-01-13 15:42:07'),
(14, true , '2022-01-14 15:42:07');
you will have
Here is the query that will group by value change
select input_1, min(data_gps) as mind, max(data_gps) as maxd
from (
select input_1, data_gps,
row_number() over (order by data_gps)
- row_number() over (partition by input_1 order by data_gps) as grp
from t
) as tmp
group by input_1, grp
order by min(data_gps);
The results
DEMO
https://dbfiddle.uk/6Ajy3H5O