T-SQL INSERT - Increment value when other columns are duplicated - sql

I have the following table:
CREATE TABLE Budget (
Year Int,
Region varchar(50),
Amount float,
DraftNo int);
GO
INSERT INTO Budget
VALUES
(2018, 'Region1', 500000, 1),
(2018, 'Region2', 400000, 1),
(2018, 'Region3', 300000, 1);
End users will submit data for Year, Region, and Amount through an Excel form, which will use VBA to write INSERT statements against the table. DraftNo will be 1 by default, but if there is already a match in the table on the first two columns (Year and Region), I want to increment DraftNo by one each time.
For example, if the application tries to write:
INSERT INTO Budget VALUES (2018, 'Region1', 600000, 1)
It should be converted to:
INSERT INTO Budget VALUES (2018, 'Region1', 600000, 2)
Of course, the solution will also need to recognize the max draft number for the Year/Region combination and increment one more from there, rather than always using 2.

If you need to add new record with incremental DraftNo:
declare #y int = 2018, #r varchar(50) = 'Region6', #a float = 3
INSERT INTO Budget VALUES (#y, #r, #a, isnull((select max(DraftNo) from Budget where [Year] = #y and Region = #r), 0) + 1)
If you need update existing records and add DraftNo:
Using MERGE:
merge Budget as trg
using (select 2018, 'Region1', 600000) as src (y, r, a)
on trg.[Year] = src.y and trg.[Region] = src.r and trg.Amount = src.a
when matched then
update set DraftNo = DraftNo + 1
when not matched then
insert ([Year], Region, Amount, DraftNo)
values (y, r, a, 1);
Using Update + Insert:
declare #y int = 2018, #r varchar(50) = 'Region6', #a float = 3
update Budget
set DraftNo = DraftNo + 1
where [Year] = #y and [Region] = #r and Amount = #a
if ##ROWCOUNT = 0
insert Budget (Year, Region, Amount, DraftNo)
values (#y, #r, #a, 1)

Related

How can I delete trailing contiguous records in a partition with a particular value?

I'm using the latest version of SQL Server and have the following problem. Given the table below, the requirement, quite simply, is to delete "trailing" records in each _category partition that have _value = 0. Trailing in this context means, when the records are placed in _date order, any series or contiguous block of records with _value = 0 at the end of the list should be deleted. Records with _value = 0 that have subsequent records in the partition with some non-zero value should stay.
create table #x (_id int identity, _category int, _date date, _value int)
insert into #x values (1, '2022-10-01', 12)
insert into #x values (1, '2022-10-03', 0)
insert into #x values (1, '2022-10-04', 10)
insert into #x values (1, '2022-10-06', 11)
insert into #x values (1, '2022-10-07', 10)
insert into #x values (2, '2022-10-01', 1)
insert into #x values (2, '2022-10-02', 0)
insert into #x values (2, '2022-10-05', 19)
insert into #x values (2, '2022-10-10', 18)
insert into #x values (2, '2022-10-12', 0)
insert into #x values (2, '2022-10-13', 0)
insert into #x values (2, '2022-10-15', 0)
insert into #x values (3, '2022-10-02', 10)
insert into #x values (3, '2022-10-03', 0)
insert into #x values (3, '2022-10-05', 0)
insert into #x values (3, '2022-10-06', 12)
insert into #x values (3, '2022-10-08', 0)
I see a few ways to do it. The brute force way is to to run the records through a cursor in date order, and grab the ID of any record where _value = 0 and see if it holds until the category changes. I'm trying to avoid T-SQL though if I can do it in a query.
To that end, I thought I could apply some gaps and islands trickery and do something with window functions. I feel like there might be a way to leverage last_value() for this, but so far I only see it useful in identifying partitions that have the criteria, not so much in helping me get the ID's of the records to delete.
The desired result is the deletion of records 10, 11, 12 and 17.
Appreciate any help.
I'm not sure that your requirement requires a gaps and islands approach. Simple exists logic should work.
SELECT _id, _catrgory, _date, _value
FROM #x x1
WHERE _value <> 0 OR
EXISTS (
SELECT 1
FROM #x x2
WHERE x2._category = x1._category AND
x2._date > x1._date AND
x2._value <> 0
);
Assuming that all _values are greater than or equal to 0 you can use MAX() window function in an updatable CTE:
WITH cte AS (
SELECT *,
MAX(_value) OVER (
PARTITION BY _category
ORDER BY _date
ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING
) max
FROM #x
)
DELETE FROM cte
WHERE max = 0;
If there are negative _values use MAX(ABS(_value)) instead of MAX(_value).
See the demo.
Using common table expressions, you can use:
WITH CTE_NumberedRows AS (
SELECT *, rn = ROW_NUMBER() OVER(PARTITION BY _category ORDER BY _date)
FROM #x
),
CTE_Keepers AS (
SELECT _category, rnLastKeeper = MAX(rn)
FROM CTE_NumberedRows
WHERE _value <> 0
GROUP BY _category
)
DELETE NR
FROM CTE_NumberedRows NR
LEFT JOIN CTE_Keepers K
ON K._category = NR._category
WHERE NR.rn > ISNULL(K.rnLastKeeper, 0)
See this db<>fiddle for a working demo.
EDIT: My original post did not handle the all-zero's edge case. This has been corrected above, together with some naming tweaks. (The original can still be found here.
Tim Biegeleisen's post may be the simpler approach.

Calculate average rate in SQL Server

declare #table as table
(
LedgerId int,
Transaction_Type varchar(50),
Inward_qty decimal (18,3),
Inward_rate decimal (18,3)
)
insert into #table
values (1, 'Issue', 67.320, 473.66),
(2, 'Receipt', 201.290, 657.90),
(3, 'Receipt', 94.860, 473.66)
select * from #table
I want to calculate the average rate the formula is finding the receipt and subtract from issue remaining will be multiplied by the rate we will have the value than total value divided by total receipt qty and we will get an inward rate I have no clue how to do this
Formula
201.290 - 67.320 = 133.970 (receipt - issue)
133.970 * 657.900 = 88,138.863(remaining receipt qty * rate) will get value
94.860 * 473.660 = 44,931.3876(receipt * rate) will get value
88,138.863 + 44,931.3876 = 1,33,070.2506 (sum of total value)
133.970 + 94.860 = 228.83(sum of total qty )
1,33,070.2506 / 228.83 (sum of total value) / (sum of total qty )
= 581.5244967880086 thus 581.524 is average rate
output layout as per above calculation
declare #table1 as table
(
LedgerId int,
Transaction_Type varchar(50),
Inward_qty decimal (18,3),
Inward_rate decimal (18,3)
)
insert into #table1 values(1,'Issue',67.320,473.66),(2,'Receipt',133.970,657.90),(3,'Receipt',94.860,473.66)
select * , inward_Value = Inward_qty * Inward_rate into #temp from #table1
declare #Qty decimal (18,3)
declare #value decimal (18,3)
set #Qty= (select sum(Inward_qty) from #temp where Transaction_Type ='Receipt' )
set #value =(select sum(inward_Value) from #temp where Transaction_Type ='Receipt' )
declare #Rate decimal (18,3) = #Value/#Qty
select #Rate
drop table #temp

Insert grouped data

I am getting expected results from my query, I am using group by to group the data on the basis of different Ids.
The problem I am facing is that I have to insert this grouped data in the table called gstl_calculated_daily_fee, but when I pass the grouped result to variables called #total_mada_local_switch_high_value and #mada_range_id and insert them in the table then I get only the last result of the query in the table.
Sample result:
Fee range_id
1.23 1
1.22 2
2.33 3
I get only 2.33 and 1 after I insert but I have to insert the whole result in to the table.
Please suggest how can I insert the whole query result into the table. Below is the query:
DECLARE #total_mada_local_switch_high_value decimal(32,4) = 0.00;
DECLARE #mada_range_id int = 0;
select
#total_mada_local_switch_high_value = SUM(C.settlement_fees),
#mada_range_id = C.range_id
From
(
select
*
from
(
select
rowNumber = #previous_mada_switch_fee_volume_based_count + (ROW_NUMBER() OVER(PARTITION BY DATEPART(MONTH, x_datetime) ORDER BY x_datetime)),
tt.x_datetime
from gstl_trans_temp tt where (message_type_mapping = 0220) and card_type ='GEIDP1' and response_code IN(00,10,11) and tran_amount_req >= 5000
) A
CROSS APPLY
(
select
rtt.settlement_fees,
rtt.range_id
From gstl_mada_local_switch_fee_volume_based rtt
where A.rowNumber >= rtt.range_start
AND (A.rowNumber <= rtt.range_end OR rtt.range_end IS NULL)
) B
) C
group by CAST(C.x_datetime AS DATE),C.range_id
-- Insert Daily Volume
INSERT INTO
gstl_calculated_daily_fee(business_date,fee_type,fee_total,range_id)
VALUES
(#tlf_business_date,'MADA_SWITCH_FEE_LOCAL_CARD', #total_mada_local_switch_high_value, #mada_range_id)
I see no need for variables here. You can insert the aggregated results directly.
Sample data
create table Data
(
Range int,
Fee money
);
insert into Data (Range, Fee) values
(1, 1.00),
(1, 0.50),
(2, 3.00),
(3, 0.25),
(3, 0.50);
create table DataSum
(
Range int,
FeeSum money
);
Solution
insert into DataSum (Range, FeeSum)
select d.Range, sum(d.Fee)
from Data d
group by d.Range;
Fiddle to see things in action.

Replace cursors with queries

Let's say I have a booking covering 6 hours and 3 discounts covering 2 hours each. I want to split my booking into 3 parts so I can allocate 2 hours per discount.
It would return something like this:
BookingId 1 | DiscountId 1 | Qty 2
BookingId 1 | DiscountId 2 | Qty 2
BookingId 1 | DiscountId 3 | Qty 2
I would then insert those records this into another table.
I'm using an heavily optimized query to determine the number of hours available for each discount. However, I can't find a "good" way to allocate my booking to each discount without using a cursor.
(...)
WHILE ##FETCH_STATUS = 0
BEGIN
IF #RequiredQty = 0
RETURN
IF #RequiredQty <= #AvailableQty
BEGIN
INSERT INTO discount.Usage (DiscountId, BookingId, Quantity)
VALUES (#DiscountId, #BookingId, #RequiredQty)
SET #RequiredQty = 0
END
IF #RequiredQty > #AvailableQty
BEGIN
INSERT INTO discount.Usage (DiscountId, BookingId, Quantity)
VALUES (#DiscountId, #BookingId, #AvailableQty)
SET #RequiredQty -= #AvailableQty
END
FETCH NEXT FROM ecursor INTO #DiscountId, #AvailableQty
END
DEALLOCATE ecursor
I tried building the corresponding query but I can't select and assign variables at the same time. Using a cursor is not really a problem (besides some potential performance issues) but I was just curious to see if with the newest SQL Server we can convert our old cursors to something better?
Thanks,
Seb
You can useCTE RECURSIVE to make a Table.
like this.
DECLARE #BookingId INT = 1;
DECLARE #RequiredQty INT = 2;
DECLARE #Hours INT = 7;
CREATE TABLE #T
(
BookingId INT,
DiscountId INT,
Quantity INT
)
;WITH CTE([Count],[Quantity],Rk) AS
(
SELECT
CASE
WHEN [HOURS] - #RequiredQty > #RequiredQty THEN #RequiredQty
ELSE [HOURS] - #RequiredQty
END ,
T.HOURS,1
FROM
(
SELECT #Hours [HOURS]
) AS T
UNION ALL
SELECT CASE
WHEN CTE.[Quantity] - #RequiredQty > #RequiredQty THEN #RequiredQty
ELSE CTE.[Quantity] - #RequiredQty
END AS [Count],
CTE.[Quantity] - #RequiredQty,
RK + 1
FROM CTE
WHERE CTE.[Quantity] - #RequiredQty > 0
)
INSERT INTO #T(BookingId,DiscountId,Quantity)
SELECT #BookingId,Rk,[Count] FROM CTE
option (maxrecursion 0)
select * from #T
SQLDEMO
This is another approach, but don't know if this code has better performance than cursor.
DECLARE #DiscountStocks TABLE (Id INT IDENTITY(1,1), DiscountId INT, LastQty INT)
INSERT INTO #DiscountStocks (DiscountId, LastQty) VALUES (1, 5)
INSERT INTO #DiscountStocks (DiscountId, LastQty) VALUES (2, 2)
INSERT INTO #DiscountStocks (DiscountId, LastQty) VALUES (3, 1)
DECLARE #DiscountBookings TABLE (Id INT IDENTITY(1,1), DiscountId INT, BookingId INT, Qty INT)
DECLARE #BookingDiscount TABLE (Id INT IDENTITY(1,1), BookingId INT, DiscountId INT, Qty INT)
INSERT INTO #BookingDiscount (BookingId, DiscountId, Qty) VALUES (1, 1, 4)
INSERT INTO #BookingDiscount (BookingId, DiscountId, Qty) VALUES (1, 2, 2)
INSERT INTO #BookingDiscount (BookingId, DiscountId, Qty) VALUES (1, 3, 1)
INSERT INTO #BookingDiscount (BookingId, DiscountId, Qty) VALUES (2, 1, 1)
INSERT INTO #BookingDiscount (BookingId, DiscountId, Qty) VALUES (2, 2, 2)
SELECT BD.Id AS BDId, DS.Id AS DSId, DS.LastQty, BD.Qty
, DS.LastQty - (SELECT SUM(Qty) FROM #BookingDiscount WHERE Id <= BD.Id AND DiscountId = BD.DiscountId) AS QtyAfterSubstract
INTO #LastDiscountStock
FROM #DiscountStocks DS
INNER JOIN #BookingDiscount BD ON DS.DiscountId = BD.DiscountId
ORDER BY BD.Id, DS.Id
INSERT INTO #DiscountBookings (DiscountId, BookingId, Qty)
SELECT DSId, BDId, Qty
FROM #LastDiscountStock
WHERE QtyAfterSubstract >= 0
DROP TABLE #LastDiscountStock
SELECT * FROM #DiscountBookings

SQL Group By Modulo of Row Count

I have the following sample data:
Id Name Quantity
1 Red 1
2 Red 3
3 Blue 1
4 Red 1
5 Yellow 3
So for this example, there are a total of 5 Red, 1 Blue, and 3 Yellow. I am looking for a way to group them by Color, but with a maximum of 2 items per group (sorting is not important). Like so:
Name QuantityInPackage
Red 2
Red 2
Red 1
Blue 1
Yellow 2
Yellow 1
Any suggestions on how to accomplish this using T-SQL on MS-SQL 2005?
I would define a table containing sequential numbers, say 1 to 1000 and join that table (unless your database supports generating these numbers in the query like Oracle using CONNECT BY):
Table num
n
1
2
3
...
I tried the following query using Oracle (should work with TSQL too):
With summed_colors As (
Select name, Sum(quantity) quantity
From colors
Group By name
)
Select
name,
Case When n*2-1 = quantity Then 1 Else 2 End quantityInPackage
From summed_colors
Join nums On ( n*2-1 <= quantity )
Order By name, quantityInPackage Desc
and it returns
Blue 1
Red 2
Red 2
Red 1
Yellow 2
Yellow 1
You need to use a numbers table to unpivot your data to make multiple rows:
DECLARE #PackageSize AS int
SET #PackageSize = 2
DECLARE #numbers AS TABLE (Number int)
INSERT INTO #numbers
VALUES (1)
INSERT INTO #numbers
VALUES (2)
INSERT INTO #numbers
VALUES (3)
INSERT INTO #numbers
VALUES (4)
INSERT INTO #numbers
VALUES (5)
INSERT INTO #numbers
VALUES (6)
INSERT INTO #numbers
VALUES (7)
INSERT INTO #numbers
VALUES (8)
INSERT INTO #numbers
VALUES (9)
INSERT INTO #numbers
VALUES (10)
DECLARE #t AS TABLE
(
Id int
,Nm varchar(6)
,Qty int
)
INSERT INTO #t
VALUES (1, 'Red', 1)
INSERT INTO #t
VALUES (2, 'Red', 3)
INSERT INTO #t
VALUES (3, 'Blue', 1)
INSERT INTO #t
VALUES (4, 'Red', 1)
INSERT INTO #t
VALUES (5, 'Yellow', 3) ;
WITH Totals
AS (
SELECT Nm
,SUM(Qty) AS TotalQty
,SUM(Qty) / #PackageSize AS NumCompletePackages
,SUM(Qty) % #PackageSize AS PartialPackage
FROM #t
GROUP BY Nm
)
SELECT Totals.Nm
,#PackageSize AS QuantityInPackage
FROM Totals
INNER JOIN #numbers AS numbers
ON numbers.Number <= Totals.NumCompletePackages
UNION ALL
SELECT Totals.Nm
,PartialPackage AS QuantityInPackage
FROM Totals
WHERE PartialPackage <> 0
It's not grouping or modulo/division that's the hard part here, it's the fact that you need to do an aggregate (sum) and then explode the data again. There aren't actually any "Red 2" rows, you have to create them somehow.
For SQL Server 2005+, I would probably use a function do the "exploding":
CREATE FUNCTION dbo.CreateBuckets
(
#Num int,
#MaxPerGroup int
)
RETURNS TABLE
AS RETURN
WITH First_CTE AS
(
SELECT CASE
WHEN #MaxPerGroup < #Num THEN #MaxPerGroup
ELSE #Num
END AS Seed
),
Sequence_CTE AS
(
SELECT Seed AS [Current], Seed AS Total
FROM First_CTE
UNION ALL
SELECT
CASE
WHEN (Total + #MaxPerGroup) > #Num THEN (#Num - Total)
ELSE #MaxPerGroup
END,
Total + #MaxPerGroup
FROM Sequence_CTE
WHERE Total < #Num
)
SELECT [Current] AS Num
FROM Sequence_CTE
Then, in the main query, group (sum) the data first and then use the bucket function:
WITH Totals AS
(
SELECT Name, SUM(Quantity) AS Total
FROM Table
GROUP BY Name
)
SELECT Name, b.Num AS QuantityInPackage
FROM Totals
CROSS APPLY dbo.CreateBuckets(Total, 2) b
This should work for any bucket size, doesn't have to be 2 (just change the parameter).
This is very crude, but it works.
CREATE TABLE #Colors
(
Id int,
Name varchar(50),
Quantity int
)
INSERT INTO #Colors VALUES (1, 'Red', 1)
INSERT INTO #Colors VALUES (2, 'Red', 3)
INSERT INTO #Colors VALUES (3, 'Blue', 1)
INSERT INTO #Colors VALUES (4, 'Red', 1)
INSERT INTO #Colors VALUES (5, 'Yellow', 3)
INSERT INTO #Colors VALUES (6, 'Green', 2)
SELECT
Name,
SUM(Quantity) AS TotalQuantity
INTO #Summed
FROM
#Colors
GROUP BY
Name
SELECT
Name,
TotalQuantity / 2 AS RecordsWithQuantity2,
TotalQuantity % 2 AS RecordsWithQuantity1
INTO #SortOfPivot
FROM
#Summed
ORDER BY
Name
DECLARE #RowCount int
SET #RowCount = (SELECT COUNT(*) FROM #SortOfPivot)
DECLARE #Name varchar(50)
DECLARE #TwosInsertCount int
DECLARE #OnesInsertCount int
CREATE TABLE #Result (Name varchar(50), Quantity int)
WHILE #RowCount > 0
BEGIN
SET #Name = (SELECT TOP 1 Name FROM #SortOfPivot)
SET #TwosInsertCount = (SELECT TOP 1 RecordsWithQuantity2 FROM #SortOfPivot)
SET #OnesInsertCount = (SELECT TOP 1 RecordsWithQuantity1 FROM #SortOfPivot)
WHILE #TwosInsertCount > 0
BEGIN
INSERT INTO #Result (Name, Quantity) VALUES (#Name, 2)
SET #TwosInsertCount = #TwosInsertCount - 1
END
WHILE #OnesInsertCount > 0
BEGIN
INSERT INTO #Result (Name, Quantity) VALUES (#Name, 1)
SET #OnesInsertCount = #OnesInsertCount - 1
END
DELETE FROM #SortOfPivot WHERE Name = #Name
SET #RowCount = (SELECT COUNT(*) FROM #SortOfPivot)
END
SELECT * FROM #Result
DROP TABLE #Colors
DROP TABLE #Result
DROP TABLE #Summed
DROP TABLE #SortOfPivot