SELECT common entities only based on different corresponding entities - sql

3 Tables
Client -
CID Name
1 Ana
2 Bana
3 Cana
ClientProgram (Bridge Table) -
CID PID
1 4
1 5
1 8
2 10
Program -
PID Program
4 X
5 Y
8 Z
10 G
Desired Output:
Name Program
Ana X
Ana Y
I want to extract only those Clients which are common/exist in different Programs I choose (say X and Y in this case)
Query attempt:
SELECT
C.Name
,P.Program
FROM ClientProgram CP
INNER JOIN Client C
ON CP.CID=C.CID
INNER JOIN Program P
ON CP.PID=P.PID
INNER JOIN ClientProgram CP1
ON CP.CID=CP1.CID
WHERE P.Program = 'X' OR P.Program = 'Y'
AND CP.CID = CP1.CID
This however doesn't pulls in all clients and not only those which exist in multiple programs.

;WITH cte AS (
SELECT
c.Name
,p.Program
,COUNT(*) OVER (PARTITION BY c.CID) as ProgramCount
FROM
Program p
INNER JOIN ClientProgram cp
ON p.PID = cp.PID
INNER JOIN Client c
On cp.CID = c.CID
WHERE
p.Program IN ('X','Y')
)
SELECT Name, Program
FROM
cte
WHERE
ProgramCount > 1
The use of COUNT(*) over will be a problem if PID is not unique in Programs or if the combination of CID to PID in ClientProgram is not unique. However I would assume uniqueness based on what I see.
If not you can go a route like this:
;WITH cte AS (
SELECT
cp.CID
FROM
Program p
INNER JOIN ClientProgram cp
ON p.PID = cp.PID
WHERE
p.Program IN ('X','Y')
GROUP BY
cp.CID
HAVING
COUNT(DISTINCT p.PID) > 1
)
SELECT
c.Name
,p.Program
FROM
cte t
INNER JOIN Client c
ON t.CID = c.CID
INNER JOIN ClientProgram cp
ON t.CID = cp.CID
INNER JOIN Program p
ON cp.PID = p.PID
AND p.Program IN ('X','Y')

This is kind of a round about way of doing it. Probably a better way but this will do it. I through in scripts for temp table in case someone else wants to improve. Could do a temp table for example instead of CTE.
create table #client(cid int,name varchar(20))
create table #clientprogram (cid int, pid int)
create table #program( pid int, program varchar(20))
insert into #client
values(1,'Ana')
,(2,'Bana')
,(3,'Cana')
insert into #clientprogram
values (1,4)
,(1,5)
,(1,8)
,(2,10)
,(2,4)
insert into #program
values (4,'x')
,(5,'y')
,(8,'z')
,(10,'g')
WITH CHECKPLEASE AS(
Select c.Name,ISNULL(p.Program,p2.PRogram) Program
from #client c
inner join #clientprogram cp
on c.CID = cp.CID
left join #program p
on cp.PID = p.PID
and p.PRogram = 'X'
left join #program p2
on cp.PID = p2.PID
and p2.Program = 'Y'
where ISNULL(p.Program,p2.PRogram) is not null
)
Select *
From CHECKPLEASE
where Name in (
SELECT Name
From CHECKPLEASE
group by Name
having COUNT(*) > 1)

Related

SQL correct query or not

given these relationships, how could you query the following:
The tourists (name and email) that booked at least a pension whose rating is greater than 9, but didn't book any 3 star hotel with a rating less than 9.
Is the following correct?
SELECT Tourists.name, Tourists.email
FROM Tourists
WHERE EXISTS (
SELECT id FROM Bookings
INNER JOIN Tourists ON Bookings.touristId=Tourists.id
INNER JOIN AccomodationEstablishments ON Bookings.accEstId=AccomodationEstablishments.id
INNER JOIN AccomodationTypes ON AccomodationEstablishments.accType=AccomodationTypes.id
WHERE AccomodationTypes.name = 'Pension' AND
AccomodationEstablishments.rating > 9
) AND NOT EXISTS (
SELECT id FROM Bookings
INNER JOIN Tourists ON Bookings.touristId=Tourists.id
INNER JOIN AccomodationEstablishments ON Bookings.accEstId=AccomodationEstablishments.id
INNER JOIN AccomodationTypes ON AccomodationEstablishments.accType=AccomodationTypes.id
WHERE AccomodationTypes.name = 'Hotel' AND
AccomodationEstablishments.noOfStars = 3 AND
AccomodationEstablishments.rating < 9
)
I would do this using aggregation and having:
SELECT t.name, t.email
FROM Bookings b INNER JOIN
Tourists t
ON b.touristId = t.id INNER JOIN
AccomodationEstablishments ae
ON b.accEstId = ae.id INNER JOIN
AccomodationTypes a
ON ae.accType = a.id
GROUP BY t.name, t.email
HAVING SUM(CASE WHEN a.name = 'Pension' AND ae.rating > 9 THEN 1 ELSE 0 END) > 0 AND
SUM(a.name = 'Hotel' AND ae.noOfStars = 3 AND ae.rating < 9 THEN 1 ELSE 0 END)= 0;
Your method also works, but you probably need t.id in the subqueries.

SQL Filtering rows with no duplicate value

Hi so I'm new to SQL and I'm trying to find a way in which I can obtain only the rows that have values that are not duplicate to each other in a specific column of table.
For example the Table below is called T1 and contains:
ID|Branch ID
1 444
2 333
3 444
4 111
5 555
6 333
The result I want will be
ID|Branch ID
4 111
5 555
So only showing non duplicate rows
Edit: I want to apply this to a large relational code. Here is a snippet of where I want it to be added
FROM dbo.LogicalLine
INNER JOIN dbo.Page ON dbo.LogicalLine.page_id = dbo.Page.id
INNER JOIN dbo.Branch ON dbo.LogicalLine.branch_id = dbo.Branch.id
The table LogicalLine will have a column called branch_id containing duplicate id values. I wish to filter those out showing only the non-duplicate branch_id like above example then INNER JOIN the Branch table into the LogicalLine which I have done.
Added -Full Code here:
SELECT
(SELECT name
FROM ParentDevice
WHERE (Dev1.type NOT LIKE '%cable%') AND (id = Dev1.parent_device_id))T1_DeviceID,
(SELECT name
FROM Symbol
WHERE (id = CP1.symbol_id) AND (type NOT LIKE '%cable%'))T1_DeviceName,
(SELECT name
FROM Location
WHERE (id = Page.location_id))T1_Location,
(SELECT name
FROM Installation
WHERE (id = Page.installation_id))T1_Installation,
(SELECT name
FROM ParentDevice
WHERE (Dev2.type NOT LIKE '%cable%') AND (id = Dev2.parent_device_id))T2_DeviceID,
(SELECT name
FROM Symbol
WHERE ( id = CP2.symbol_id) AND (type NOT LIKE '%cable%'))T2_DeviceName,
(SELECT name
FROM Location
WHERE (id = PD2.location_id))T2_Location,
(SELECT name
FROM Installation
WHERE (id = Page.installation_id))T2_Installation,
(SELECT devicefamily
FROM Device
WHERE (type LIKE '%cable%') AND (id = SymCable.device_id))CablePartNumber,
(SELECT name
FROM ParentDevice
WHERE (id = DevCable.parent_device_id) AND (DevCable.type LIKE '%cable%'))CableTag
FROM dbo.LogicalLine
INNER JOIN dbo.Page ON dbo.LogicalLine.page_id = dbo.Page.id
INNER JOIN dbo.Branch ON dbo.LogicalLine.branch_id = dbo.Branch.id
LEFT OUTER JOIN dbo.Symbol AS SymCable ON dbo.LogicalLine.cable_id = SymCable.id
LEFT OUTER JOIN dbo.Device AS DevCable ON SymCable.device_id = DevCable.id
LEFT OUTER JOIN dbo.ParentDevice AS ParentCable ON DevCable.parent_device_id = ParentCable.id
INNER JOIN dbo.SymbolCP AS CP1 ON dbo.Branch.cp1_id = CP1.id
INNER JOIN dbo.SymbolCP AS CP2 ON dbo.Branch.cp2_id = CP2.id
INNER JOIN dbo.Symbol AS S1 ON CP1.symbol_id = S1.id
INNER JOIN dbo.Symbol AS S2 ON CP2.symbol_id = S2.id
INNER JOIN dbo.Device AS Dev1 ON S1.device_id = Dev1.id
INNER JOIN dbo.Device AS Dev2 ON S2.device_id = Dev2.id
INNER JOIN dbo.ParentDevice AS PD1 ON Dev1.parent_device_id = PD1.id
INNER JOIN dbo.ParentDevice AS PD2 ON Dev2.parent_device_id = PD2.id
INNER JOIN dbo.Location AS L1 ON PD1.location_id = L1.id
INNER JOIN dbo.Location AS L2 ON PD2.location_id = L2.id
INNER JOIN dbo.Installation AS I1 ON L1.installation_id = I1.id
INNER JOIN dbo.Installation AS I2 ON L2.installation_id = I2.id
WHERE
(PD1.project_id = #Projectid) AND (dbo.LogicalLine.drawingmode LIKE '%Single Line%');
Select Id, BranchId from table t
Where not exists
(Select * from table
where id != t.Id
and BranchId = t.BranchId)
or
Select Id, BranchId
From table
Group By BranchId
Having count(*) == 1
EDIT: to modify as requested, simply add to your complete SQL query a Where clause:
Select l.Id BranchId, [plus whatever else you have in your select clause]
FROM LogicalLine l
join Page p ON p.id = l.page_Id
join Branch b ON b.Id = l.branch_id
Group By l.branch_id, [Plus whatever else you have in Select clause]
Having count(*) == 1
or
Select l.Id BranchId, [plus whatever else you have in your select clause]
FROM LogicalLine l
join Page p on p.id = l.page_Id
join Branch b on b.Id = l.branch_id
Where not exists
(Select * from LogicalLine
where id != l.Id
and branch_id = l.branch_id)

Too many results in query

I'm fetching some data from our database in MSSQL. Out of this data I want to determine who created the client entry and who took the first payment from this client.
There can be many payment entries for a client on a single booking/enquiry and at the moment, my query shows results for each payment. How can I limit the output to only show the first payment entry?
My query:
SELECT
c.FirstName,
c.LastName,
c.PostalCode,
o.OriginOfEnquiry,
s.SuperOriginName,
c.DateOfCreation,
DATEDIFF(day, c.DateOfCreation, p.DateOfCreation) AS DaysToPayment,
pc.PackageName,
CONCAT(u.FirstName, ' ', u.LastName) AS CreateUser,
(SELECT CONCAT(u.FirstName, ' ', u.LastName)
WHERE u.UserID = p.UserID ) AS PaymentUser
FROM tblBookings b
INNER JOIN tblPayments p
ON b.BookingID = p.BookingID
INNER JOIN tblEnquiries e
ON e.EnquiryID = b.EnquiryID
INNER JOIN tblCustomers c
ON c.CustomerID = e.CustomerID
INNER JOIN tblOrigins o
ON o.OriginID = e.OriginID
INNER JOIN tblSuperOrigins s
ON s.SuperOriginID = o.SuperOriginID
INNER JOIN tblBookingPackages bp
ON bp.bookingID = p.BookingID
INNER JOIN tblPackages pc
ON pc.PackageID = bp.packageID
INNER JOIN tblUsers u
ON u.UserID = c.UserID
WHERE c.DateOfCreation >= '2016-06-01' AND c.DateOfCreation < '2016-06-30'
AND p.PaymentStatusID IN (1,2)
AND e.CustomerID = c.CustomerID
AND p.DeleteMark != 1
AND c.DeleteMark != 1
AND b.DeleteMark != 1
;
I tried adding a "TOP 1" to the nested select statement for PaymentUser, but it made no difference.
you can use cross apply with top 1:
FROM tblBookings b
cross apply
(select top 1 * from tblPayments p where b.BookingID = p.BookingID) as p
Instead of table tblPayments specify sub-query like this:
(SELECT TOP 1 BookingID, UserID, DateOfCreation
FROM tblPayments
WHERE DeleteMark != 1
AND PaymentStatusID IN (1,2)
ORDER BY DateOfCreation) as p
I'm assuming that tblPayments has a primary key column ID. If it is true, you can use this statment:
FROM tblBookings b
INNER JOIN tblPayments p ON p.ID = (
SELECT TOP 1 ID
FROM tblPayments
WHERE BookingID = b.BookingID
AND DeleteMark != 1
AND PaymentStatusID IN (1,2)
ORDER BY DateOfCreation)

Select qry to using 2 databases

I have the below query:
SELECT
--a.DateEntered,
--a.InventoryId,
a.SKU, a.QtyOnHand,
b.Dateentered AS VDateEntered,
b.GoLive, b.DateOnSite, b.CostPrice,
--a.CurrentPrice,
m.name AS Status,
hrf.category, hrf.department, hrf.BrandedOB, hrf.Division,
hrf.Fascia,
(a.QtyOnHand * b.CostPrice) AS Cost_Value,
NULL AS Item_Quantity, NULL AS Item,
NULL AS Season, hrf.Company,
(a.QtyOnHand * b.CurrentPrice) AS Sellilng_Value,
b.merchandisingseason, b.CostPrice AS Costprice_RP,
b.CurrentPrice, b.InventoryID,
-- a.AverageUnitCost,
-- a.AverageUnitCost AS RP_Stk_AverageUnitCost,
-- a.CurrentPrice AS RP_Stk_Current_Price,
-- a.Statusid,
-- a.Quantity_Sign,
(a.QtyOnHand * b.CostPrice) AS Cost_Value_RP,
(a.QtyOnHand * b.AverageUnitCost) AS AWC_Value
-- a.StockReconciliationId,
-- a.AverageUnitCost,
FROM
[dbo].[FC03QTY] a
JOIN
dbo.inventory b ON a.SKU = b.SKU
LEFT JOIN
(------Hierarchy-------
SELECT
ih.InventoryId, hry.category, hry.department,
hry.BrandedOB, hry.Division, hry.Fascia, hry.Company
FROM
(SELECT
ihn.HierarchyNodeId, ihn.InventoryId
FROM bm.InventoryHierarchyNode IHN
GROUP BY ihn.HierarchyNodeId, ihn.InventoryId) IH
JOIN
(SELECT
g.categoryid, g.category, h.department, i.BrandedOB,
j.Division, K.Fascia, L.company
FROM
Category g (NOLOCK)
JOIN
Department H ON g.departmentid = h.departmentID
JOIN
BrandedOB I (NOLOCK) ON h.BrandedOBID = i.BrandedOBID
JOIN
Division j (NOLOCK) ON i.divisionid = j.divisionid
JOIN
Fascia k (NOLOCK) ON j.fasciaid = k.fasciaID
JOIN
company l (NOLOCK) ON k.companyid = l.companyid
GROUP BY
g.categoryid, g.category, h.department,
i.BrandedOB, j.Division, K.Fascia, L.company) HRY ON ih.HierarchyNodeId = hry.CategoryId
GROUP BY
ih.InventoryId, hry.category, hry.department,
hry.BrandedOB, hry.Division, hry.Fascia, hry.Company) HRF ON b.inventoryid = hrf.inventoryid
JOIN
inventorystatus m (NOLOCK) ON b.statusid = m.statusid
It is using 2 tables -
[dbo].[FC03QTY] a
and
dbo.inventory b
that are joined at the SKU level.
[dbo].[FC03QTY] is on the scratch database and dbo.inventory is on the reports database.
How can I get my query to use these tables if they are on 2 different db?
Any advice greatly received.
In sql server the syntaxis for tables is [database name].[schema name].[table name]
So you need something like this:
SELECT A.*, B.*
FROM
Database1.dbo.Table1 as A,
Database2.dbo.Table2 as B

selecting the max values based on a count

How can i retrieve the max of each ValueCount based on the firmid. I need the data to be output like so.
My code is below
SELECT
F.FirmID,
F.Name,
DL.ValueId,
DL.ValueName,
count(DL.ValueName) AS ValueCount
FROM
dbo.Jobs AS J
INNER JOIN DimensionValues AS DV ON
DV.CrossRef = J.JobId
INNER JOIN dbo.DimensionLists AS DL ON
DV.ValueId = DL.ValueId
INNER JOIN Firms AS F ON
F.FirmId = J.ClientFirmId
WHERE
DL.DimensionId = 4
GROUP BY
F.FirmID,
F.Name,
DL.ValueName,
DL.ValueId
this produces something like
firmid | value | count
1 1 5
1 2 10
2 3 1
2 1 6
i need to return back the records with 10 and 6.
EDIT : SQL 2005 answer deleted.
Then you could push your results into a temporary table (or table variable) and do something like this...
SELECT
*
FROM
TempTable
WHERE
ValueCount = (SELECT MAX(ValueCount) FROM TempTable AS Lookup WHERE FirmID = TempTable.FirmID)
Or...
SELECT
*
FROM
TempTable
INNER JOIN
(SELECT FirmID, MAX(ValueCount) AS ValueCount FROM TempTable GROUP BY FirmID) AS lookup
ON lookup.FirmID = TempTable.FirmID
AND lookup.ValueCount = TempTable.ValueCount
These will give multiple records if any ValueCount is tied with another for the same FirmID. As such, you could try this...
SELECT
*
FROM
TempTable
WHERE
value = (
SELECT TOP 1
value
FROM
TempTable as lookup
WHERE
FirmID = TempTable.FirmID
ORDER BY
ValueCount DESC
)
For this problem you need to produce the result set of the query in order to determine the Max ValueCount, then you need to do the query again to pull just the records with Max ValueCount. You can do this many way, like repeating the main query as subqueries, and in SQL Server 2005/2008 by using a CTE. I think using the subqueries gets a little messy and would prefer the CTE, but for SQL Server 2000 you don't have that as an option. So, I've used a temp table instead of a CTE. I run it once to get the MaxValueCount and save that into a temp table, then run the query again and join against the temp table to get just the record with MaxValueCount.
create table #tempMax
(
FirmID int,
MaxValueCount int
)
insert #tempMax
SELECT t.FirmID, MAX(t.ValueCount) AS MaxValueCount
FROM (
SELECT F.FirmID, F.Name, DL.ValueId, DL.ValueName
, count(DL.ValueName) AS ValueCount
FROM dbo.Jobs AS J
INNER JOIN DimensionValues AS DV ON DV.CrossRef = J.JobId
INNER JOIN dbo.DimensionLists AS DL ON DV.ValueId = DL.ValueId
INNER JOIN Firms AS F ON F.FirmId = J.ClientFirmId
WHERE DL.DimensionId = 4
GROUP BY F.FirmID, F.Name, DL.ValueName, DL.ValueId) t
SELECT t.FirmID, t.Name, t.ValueID, t.ValueName, t.ValueCount
FROM (
SELECT F.FirmID, F.Name, DL.ValueId, DL.ValueName
, count(DL.ValueName) AS ValueCount
FROM dbo.Jobs AS J
INNER JOIN DimensionValues AS DV ON DV.CrossRef = J.JobId
INNER JOIN dbo.DimensionLists AS DL ON DV.ValueId = DL.ValueId
INNER JOIN Firms AS F ON F.FirmId = J.ClientFirmId
WHERE DL.DimensionId = 4
GROUP BY F.FirmID, F.Name, DL.ValueName, DL.ValueId) t
INNER JOIN #tempMax m ON t.FirmID = m.FirmID and t.ValueCount = m.MaxValueCount
DROP TABLE #tempMax
You should be able to use a derived table for this:
SELECT F.FirmID,
F.Name,
DL.ValueId,
DL.ValueName,
T.ValueCount
FROM Jobs J
INNER JOIN DimensionValues DV
ON DV.Crossref = J.JobID
INNER JOIN DimensionList DL
ON DV.ValueID = DL.ValueID
INNER JOIN Firms F
ON F.FirmID = J.ClientFirmID
--derived table
INNER JOIN (SELECT FirmID, MAX(ValueName) ValueCount FROM DimensionList GROUP BY FirmID) T
ON T.FirmID = F.FirmID
WHERE DL.DimensionId = 4
TBL1 and TBL2 is your query:
SELECT *
FROM TBL1
WHERE
TBL1.ValueCount = (SELECT MAX(TBL2.ValueCount) FROM TBL2 WHERE TBL2.FIRMID = TBL1.FIRMID)