Select Max value For Each Entity - sql

Question

In Microsoft SQL Server, I have a table with columns EmployeeID, Category and Amount. How can I show just the Category with the highest Amount for each Employee?
Data Example:
EmployeeID Category Amount
11111 Vacation 4
11111 Personal 2
11111 Holiday 3
22222 Vacation 1
22222 Personal 3
22222 Holiday 2
33333 Personal 5
33333 Holiday 1
33333 Vacation 3
33333 Unspecified 3
Results:
EmployeeID Category Amount
11111 Vacation 4
22222 Personal 3
33333 Personal 5

Answer 1

Another option is the WITH TIES clause
Example
Select Top 1 with Ties *
From YourTable
Order By Row_Number() over (Partition By EmployeeID Order By Amount Desc)
Returns
Or using Row_Number() and a CTE
;with cte as (
Select *
,RN = Row_Number() over (Partition By EmployeeID Order By Amount Desc)
From YourTable
)
Select EmployeeID
,Category
,Amount
From cte where RN=1

Answer 2

Here are a few different options. Any of them can perform better than the other depending available indexes, so all three are worth testing in your environment.
SET NOCOUNT ON;
IF OBJECT_ID('tempdb..#TestData', 'U') IS NOT NULL
DROP TABLE #TestData;
CREATE TABLE #TestData (
EmployeeID INT NOT NULL,
Category VARCHAR(20) NOT NULL,
Amount MONEY NOT NULL
);
INSERT #TestData (EmployeeID, Category, Amount) VALUES
(11111, 'Vacation ', 4),
(11111, 'Personal ', 2),
(11111, 'Holiday ', 3),
(22222, 'Vacation ', 1),
(22222, 'Personal ', 3),
(22222, 'Holiday ', 2),
(33333, 'Personal ', 5),
(33333, 'Holiday ', 1),
(33333, 'Vacation ', 3),
(33333, 'Unspecified', 3);
-- add a covering index to improve performance of the various options
CREATE NONCLUSTERED INDEX ix_TestData ON #TestData (EmployeeID, Amount DESC) INCLUDE (Category);
------------------------------------------
IF OBJECT_ID('tempdb..#Employee', 'U') IS NOT NULL
DROP TABLE #Employee;
CREATE TABLE #Employee (
EmployeeID INT NOT NULL
);
INSERT #Employee (EmployeeID) VALUES
(11111), (22222), (33333);
-- SELECT * FROM #TestData td;
--============================================================
--============================================================
SELECT TOP 1 WITH TIES
td.EmployeeID, td.Category, td.Amount
FROM
#TestData td
ORDER BY
ROW_NUMBER() OVER (PARTITION BY td.EmployeeID ORDER BY td.Amount DESC);
--============================================================
SELECT
tdt.EmployeeID, tdt.Category, tdt.Amount
FROM
#Employee e
CROSS APPLY (
SELECT TOP 1
td.EmployeeID, td.Category, td.Amount
FROM
#TestData td
WHERE
e.EmployeeID = td.EmployeeID
ORDER BY
td.Amount DESC
) tdt;
--============================================================
WITH
cte_AddRN AS (
SELECT
td.EmployeeID, td.Category, td.Amount,
RN = ROW_NUMBER() OVER (PARTITION BY td.EmployeeID ORDER BY td.Amount DESC)
FROM
#TestData td
)
SELECT
ar.EmployeeID, ar.Category, ar.Amount
FROM
cte_AddRN ar
WHERE
ar.RN = 1;
All 3 produce the same results...
EmployeeID Category Amount
----------- -------------------- ---------------------
11111 Vacation 4.00
22222 Personal 3.00
33333 Personal 5.00
EmployeeID Category Amount
----------- -------------------- ---------------------
11111 Vacation 4.00
22222 Personal 3.00
33333 Personal 5.00
EmployeeID Category Amount
----------- -------------------- ---------------------
11111 Vacation 4.00
22222 Personal 3.00
33333 Personal 5.00

Answer 3

Use EXISTS/NOT EXISTS:
select *
from Employees
where not exists
(select * from Employees as E
where E.EmployeeID=Employees.EmployeeID -- join condition
and E.Amount>Employees.Amount) -- filter condition

Answer 4

SELECT EmployeeID, Category, Amount
FROM (select *, ROW_NUMBER() OVER (PARTITION BY EmployeeID
ORDER BY EmployeeID as rn ,Amount desc)
FROM getmaxdata) x WHERE x.rn =1