Get top column base on maximum other column using group by? - sql-server

How to get top column base on maximum other column using group by?
My raw data:
DECLARE #TB TABLE (ID INT, APP VARCHAR(25), PRICE MONEY)
INSERT INTO #TB
VALUES
(1, 'Apple', 10),
(1, 'Banana', 30),
(1, 'Orange', 20),
(2, 'Apple', 20),
(2, 'Banana', 30),
(2, 'Orange', 40)
This what I want:
Explain:
TOP_APP = Banana because MAX(PRICE) GROUP BY ID,
TOTAL = 60 because SUM(PRICE) GROUP BY ID.

You can use ROW_NUMBER and aggregation to achieve your required output-
DEMO HERE
SELECT A.ID,A.App,A.SUM
FROM
(
select *,
SUM(Price) OVER(PARTITION BY ID) SUM,
ROW_NUMBER() OVER (PARTITION BY ID ORDER BY Price DESC) RN
from #tb
)A
WHERE RN = 1

Demo on db<>fiddle
;WITH cte_TempTable as
(
SELECT Id, app, price,
SUM(Price) OVER(PARTITION BY ID) Total,
ROW_NUMBER() OVER (PARTITION BY ID ORDER BY Price DESC) Row_Number
FROM #TB
)
SELECT Id, app as TOP_APP, Total
FROM cte_TempTable
WHERE Row_Number = 1
Output
Id TOP_APP Total
1 Banana 60.0000
2 Orange 90.0000

As my assumption you want the result is
SELECT identity (int,1,1) as ID,
APP AS TOP_APP
,SUM(PRICE) AS TOTAL INTO #T
FROM #TB
GROUP BY APP
order by SUM(PRICE)
select * from #t

Related

TSQL: Group by one column, count all rows and keep value on second column based on row_number

I have a query that returns an Id, a Name and the Row_Number() based on some rules.
The query looks like that
SELECT
tm.id AS Id,
pn.Name AS Name,
ROW_NUMBER() OVER(PARTITION BY tm.id ORDER BY tm.CreatedDate ASC) AS Row
FROM
#tempTable AS tm
LEFT JOIN
names pn WITH (NOLOCK) ON tm.nameId = pn.NameId
WHERE ....
The output of the above query looks like the table below with the dummy data
CREATE TABLE people
(
id int,
name varchar(55),
row int
);
INSERT INTO people
VALUES (1, 'John', 1), (1, 'John', 2), (2, 'Mary', 1),
(3, 'Jeff', 1), (4, 'Bill', 1), (4, 'Bill', 2),
(4, 'Bill', 3), (4, 'Billy', 4), (5, 'Bobby', 1),
(5, 'Bob', 2), (5, 'Bob' , 3), (5, 'Bob' , 4);
What I try to do, is group by the id field, count all rows, but for the name, use the one with row = 1
My attempt is like this, but, obviously, I get different rows since I include the x.name in the group by.
SELECT
x.id,
x.name,
COUNT(*) AS Value
FROM
(SELECT
tm.id AS Id,
pn.Name AS Name,
ROW_NUMBER() OVER(PARTITION BY tm.id ORDER BY tm.CreatedDate ASC) AS Row
FROM
#tempTable AS tm
LEFT JOIN
names pn WITH (NOLOCK) ON tm.nameId = pn.NameId
WHERE ....
) x
GROUP BY
x.id, x.name
ORDER BY
COUNT(*) DESC
The desired results from the dummy data are:
id name count
------------------
1 John 2
2 Mary 1
3 Jeff 1
4 Bill 4
5 Bobby 4
You can use FIRST_VALUE() window function to get the name of the row with row number = 1 and with the keyword DISTINCT there is no need to GROUP BY:
SELECT DISTINCT tm.id AS Id
, FIRST_VALUE(pn.Name) OVER (PARTITION BY tm.id ORDER BY tm.CreatedDate ASC) AS Name
, COUNT(*) OVER (PARTITION BY tm.id) AS counter
FROM #tempTable AS tm
LEFT JOIN names pn WITH (NOLOCK) ON tm.nameId = pn.NameId
WHERE ....
If you can't use FIRST_VALUE() then you can do it with conditional aggregation:
SELECT id,
MAX(CASE WHEN Row = 1 THEN Name END) AS NAME,
COUNT(*) AS Counter
FROM (
SELECT tm.id AS Id
, pn.Name AS Name
, ROW_NUMBER() OVER(PARTITION BY tm.id ORDER BY tm.CreatedDate ASC) AS Row
FROM #tempTable AS tm
LEFT JOIN names pn WITH (NOLOCK) ON tm.nameId = pn.NameId
WHERE ....
) t
GROUP BY id
This could be one solution to your problem: group on both id and the target name (case when p.row = 1 then p.name end) for the counting. Adding a with rollup to the grouping will "roll up" the count aggregations. Another aggregation on just id can then be use to merge the row values from the intermediate data set (visible in fiddle).
with cte as
(
select p.id,
case when p.row = 1 then p.name end as name,
count(1) as cnt
from people p
group by p.id, case when p.row = 1 then p.name end with rollup
having grouping(p.id) = 0
)
select cte.id,
max(cte.name) as name,
max(cte.cnt) as [count]
from cte
group by cte.id;
Fiddle
This would be another solution: do a regular count query with grouping on id and fetch the required name afterwards with a cross apply.
with cte as
(
select p.id,
count(1) as cnt
from people p
group by p.id
)
select cte.id,
n.name,
cte.cnt as [count]
from cte
cross apply ( select p.name
from people p
where p.id = cte.id
and p.row = 1 ) n;
Fiddle

Only show value of Max rows with partition by?

the title might be a bit off however i'm trying to remove the values of a row without removing the actual row.
This is my table:
SELECT ID,CustomerID,Weight FROM Orders
What am i trying to accomplish is this:
The MAX() value of ID Group By CustomerID that would give me null values in Weight where max and group by is not set
Is it possible to do this in one line? with a partiton by?
Something like:
SELECT MAX(ID) over (partition by CustomerID,Weight).... I know this is wrong but if possible to do without a join or CTE and only in one line in the select statement that would be great.
One possible approach is using ROW_NUMBER:
SELECT
ID,
CustomerID,
CASE
WHEN ROW_NUMBER() OVER (PARTITION BY CustomerId ORDER BY ID DESC) = 1 THEN [Weight]
ELSE Null
END AS [Weight]
FROM #Orders
ORDER BY ID
Input:
CREATE TABLE #Orders (
ID int,
CustomerID int,
[Weight] int
)
INSERT INTO #Orders
(ID, CustomerID, [Weight])
VALUES
(1, 11, 100),
(2, 11, 17),
(3, 11, 35),
(4, 22, 26),
(5, 22, 78),
(6, 22, 10030)
Output:
ID CustomerID Weight
1 11 NULL
2 11 NULL
3 11 35
4 22 NULL
5 22 NULL
6 22 10030
Try this
;WITH CTE
AS
(
SELECT
MAX_ID = MAX(ID) OVER(PARTITION BY CustomerId),
ID,
CustomerId,
Weight
FROM Orders
)
SELECT
ID,
CustomerId,
Weight = CASE WHEN ID = MAX_ID THEN Weight ELSE NULL END
FROM CTE
You can try this.
SELECT ID,CustomerId,CASE WHEN ID= MAX(ID) OVER(PARTITION BY CustomerId) THEN Weight ELSE NULL END AS Weight FROM Orders

Count and Row_Number

I want to get the top 5 Zipcodes for each Store with the highest Customers in them (zipcodes).
Please find below my query:
SELECT T.[Store], T.[ZipCode], Count(T.[Customer])
FROM ( SELECT T.[Store], T.[ZipCode],
Count(T.[Customer]) row_number() over (Partition By T.[StoreGitanjali] Order By Count (T.[Customer]) desc) as RN
FROM [Marketing].[dbo].[Poscus] as T
Group By T.[StoreGitanjali], T.[ZipCode]) as T
where T.RN <=5
Group By T.[StoreGitanjali], T.[ZipCode]
Please let me know how to use Count here in this scenario.
Thank you!
Example
CREATE TABLE #t
(
ID INT IDENTITY(1,1),
Customer NVARCHAR(3),
Store NVARCHAR(5),
ZIP INT
)
INSERT INTO #t VALUES('a', 'XYZ', 1234)
,('b', 'XYZ', 1234)
,('c', 'PQR', 1231)
,('d', 'PQR', 1231)
,('e', 'PQR', 1231)
,('f', 'XYZ', 1232)
,('g', 'XYZ', 1232)
,('h', 'XYZ', 1232)
,('i', 'PQR', 1236)
,('j', 'PQR', 1236)
,('k', 'LMN', 1237)
SELECT * FROM #t
The solution is, Set WHERE part < 2 according to your requirement.
SELECT TotalCustomer, Store, ZIP, Part FROM (
SELECT
COUNT(1) AS TotalCustomer,
Store,
ZIP,
ROW_NUMBER() OVER (PARTITION BY Store ORDER BY Store) AS Part
FROM #t
GROUP BY Store, ZIP
) t
WHERE Part < 2
ORDER BY Part
;WITH CTE
AS(
SELECT Store
,Zip
,COUNT(DISTINCT Customer) AS CustCount
FROM #t
GROUP BY Store,Zip
--ORDER BY Store,Zip
)
SELECT A.*
FROM(
SELECT *
--,DENSE_RANK() OVER(PARTITION BY Store ORDER BY CustCount DESC) AS DenRank
,ROW_NUMBER() OVER(PARTITION BY Store ORDER BY CustCount DESC) AS DenRank
FROM CTE
--ORDER BY Store,Zip
) AS A
WHERE A.DenRank <= 2

Maximum and Minimum Rows Alternatively in SQL Server

This is an Employee table,
Id Name Salary
1 A.J 7000
2 B.S 30000
3 C.K 2000
4 D.O 10000
5 E.L 500
Now i want to display 1st highest salary then minimum salary then 2nd maximum salary then 2nd minimum salaray and so on..up to nth row.
Expected Output,
Id Name Salary
2 B.S 30000
5 E.L 500
4 D.O 10000
3 C.K 2000
1 A.J 7000
One more variant without explicit COUNT. SQL Fiddle.
Try also to add this row to sample data (6, 'X.Y', 7000) in the fiddle. The query still returns correct results.
DECLARE #Employee TABLE (ID int, Name nvarchar(50), Salary money);
INSERT INTO #Employee (ID, Name, Salary) VALUES
(1, 'A.J', 7000),
(2, 'B.S', 30000),
(3, 'C.K', 2000),
(4, 'D.O', 10000),
(5, 'E.L', 500);
WITH
CTE
AS
(
SELECT *, NTILE(2) OVER (ORDER BY Salary, ID) AS n
FROM #Employee AS E
)
SELECT
*
,SIGN(n-1.5) AS s
,SIGN(n-1.5)*Salary AS ss
,ROW_NUMBER() OVER(PARTITION BY n ORDER BY SIGN(n-1.5)*Salary DESC) AS rn
FROM CTE
ORDER BY rn, ss DESC;
Result
ID Name Salary n s ss rn
2 B.S 30000.00 2 1.0 30000.00000 1
5 E.L 500.00 1 -1.0 -500.00000 1
4 D.O 10000.00 2 1.0 10000.00000 2
3 C.K 2000.00 1 -1.0 -2000.00000 2
1 A.J 7000.00 1 -1.0 -7000.00000 3
I left intermediary columns in the output to illustrate how it works.
Using Row_Number() and Count()
Fiddle Demo
declare #count int=(select count(1) from Employee);
with cte1 as
(
select ROW_NUMBER() over(order by salary desc) as rn,0 Sort,Id,Name,Salary, count(Id) over () cnt from Employee
union all
select ROW_NUMBER() over(order by salary) as rn,1 Sort,Id,Name,Salary, count(Id) over () cnt from Employee
)
select top (#count) Id,Name,Salary from cte1 where rn <= (floor(cnt/2) + cnt%2) order by rn,sort
Below is the solution:
--Create dummy employee table
CREATE TABLE tbl_Employee
(
Id INT,
Name VARCHAR(100),
Salary NUMERIC(9, 2)
)
GO
--Insert few dummy rows in the table
INSERT INTO #Employee
(Id, Name, Salary)
VALUES(100, 'John', 7000),
(101, 'Scott', 30000),
(102, 'Jeff', 2000),
(103, 'Jimy', 10000),
(104, 'Andrew', 500),
(105, 'Alister', 100)
GO
--Get data as required
DECLARE #Cnt INT = 0, #SeqLimit INT = 0
SELECT #Cnt = COUNT(1) FROM tbl_employee
SET #SeqLimit = CEILING(#Cnt / 2.0)
SELECT * FROM
(
SELECT ROW_NUMBER() OVER(ORDER BY Salary DESC) AS SEQ, Id, Name, Salary FROM tbl_employee
)DT1
WHERE SEQ <= #SeqLimit
UNION ALL
SELECT * FROM
(
SELECT ROW_NUMBER() OVER(ORDER BY Salary ASC) AS SEQ, Id, Name, Salary FROM tbl_employee
)DT2
WHERE SEQ <= #SeqLimit - (#Cnt % 2)
ORDER BY SEQ ASC, Salary DESC
The same can be achieved with different approaches and here you can find more on this:
http://www.sqlrelease.com/order-max-and-min-value-rows-alternatively-in-sql-server

Having trouble with grouping rows - MS SQL 2008

I have a product table which has some duplicate records.
I need to get primarykeys atfer grouped them according to names and types
DECLARE #Products TABLE
(
pkProductId INT,
productName NVARCHAR(500),
productType INT
)
INSERT INTO #Products (pkProductId, productName, productType)
VALUES
(1, 'iphone', 0),
(2, 'iphone', 0),
(3, 'iphone', 1),
(4, 'iphone', 1),
(5, 'iphone', 1)
After I run like tsql
SELECT pr.pkProductId FROM #Products pr
GROUP BY pr.productName, pr.productType
HAVING COUNT(pr.productName) > 1
I Want To Get These IDs
pkProductId
---------------
2
4
5
Thank You For Your Hepls :)
You could use row_number() to get the result:
select pkProductId
from
(
select pkProductId,
productName,
productType,
row_number() over(partition by productName, productType order by pkproductId) rn
from #Products
) d
where rn >1;
See SQL Fiddle with Demo

Resources