In this query I cant understand what would be the proper syntax to PIVOT it by month and also display just top 10 records based on SUM(NetWrittenPremium).
;with cte_TopClasses
AS (
select
b.YearNum,
b.MonthNum,
REPLACE(ClassCode,'+','') + ' - '+ QLL.Description as Description,
SUM( Premium) as NetWrittenPremium
FROM tblCalendar b
LEFT JOIN ProductionReportMetrics prm ON b.MonthNum=Month(prm.EffectiveDate) AND b.YearNum = YEAR(EffectiveDate)
AND prm.EffectiveDate >=DateAdd(yy, -1, DATEADD(d, 1, EOMONTH(GETDATE()))) AND prm.EffectiveDate <= EOMONTH(GETDATE()) AND CompanyLine = 'Ironshore Insurance Company'
LEFT JOIN NetRate_Quote_Insur_Quote Q ON prm.NetRate_QuoteID = Q.QuoteID
LEFT JOIN NetRate_Quote_Insur_Quote_Locat QL ON Q.QuoteID = QL.QuoteID
LEFT JOIN (SELECT * FROM NetRate_Quote_Insur_Quote_Locat_Liabi nqI
JOIN ( SELECT LocationID as LocID, MAX(ClassCode) as ClCode
FROM NetRate_Quote_Insur_Quote_Locat_Liabi GROUP BY LocationID ) nqA
ON nqA.LocID = nqI.LocationID AND nqA.ClCode = nqI.ClassCode ) QLL
ON QLL.LocationID = QL.LocationID
WHERE ( b.YearNum = YEAR(GETDATE())-1 and b.MonthNum >= MONTH(GETDATE())+1 ) OR
( b.YearNum = YEAR(GETDATE()) and b.MonthNum <= MONTH(GETDATE()) )
GROUP BY b.YearNum,b.MonthNum,ClassCode, QLL.Description
)
SELECT
--TOP 10
RANK() OVER (ORDER BY NetWrittenPremium DESC) AS Rank, *
FROM cte_TopClasses
WHERE Description IS NOT NULL
ORDER BY NetWrittenPremium DESC,YearNum,MonthNum
The result should look something like that:
If I use the query below and then using matrics in SSRS to PIVOT it - then after grouping by Description it only displays me 2 Description.
;with cte_TopClasses
AS (
select
b.YearNum,
b.MonthNum,
REPLACE(ClassCode,'+','') + ' - '+ QLL.Description as Description,
SUM( Premium) as NetWrittenPremium
FROM tblCalendar b
LEFT JOIN ProductionReportMetrics prm ON b.MonthNum=Month(prm.EffectiveDate) AND b.YearNum = YEAR(EffectiveDate)
AND prm.EffectiveDate >=DateAdd(yy, -1, DATEADD(d, 1, EOMONTH(GETDATE()))) AND prm.EffectiveDate <= EOMONTH(GETDATE()) AND CompanyLine = 'Ironshore Insurance Company'
LEFT JOIN NetRate_Quote_Insur_Quote Q ON prm.NetRate_QuoteID = Q.QuoteID
LEFT JOIN NetRate_Quote_Insur_Quote_Locat QL ON Q.QuoteID = QL.QuoteID
LEFT JOIN (SELECT * FROM NetRate_Quote_Insur_Quote_Locat_Liabi nqI
JOIN ( SELECT LocationID as LocID, MAX(ClassCode) as ClCode
FROM NetRate_Quote_Insur_Quote_Locat_Liabi GROUP BY LocationID ) nqA
ON nqA.LocID = nqI.LocationID AND nqA.ClCode = nqI.ClassCode ) QLL
ON QLL.LocationID = QL.LocationID
WHERE ( b.YearNum = YEAR(GETDATE())-1 and b.MonthNum >= MONTH(GETDATE())+1 ) OR
( b.YearNum = YEAR(GETDATE()) and b.MonthNum <= MONTH(GETDATE()) )
GROUP BY b.YearNum,b.MonthNum,ClassCode, QLL.Description
)
SELECT *
FROM (SELECT RANK() OVER (ORDER BY NetWrittenPremium DESC) AS Rank, *
FROM cte_TopClasses
WHERE Description IS NOT NULL) AA
WHERE AA.Rank <= 10
ORDER BY AA.NetWrittenPremium DESC, AA.YearNum, AA.MonthNum
And the result of it in SSRS matrics :
You could try something like this at the end of the query, rather than what is there now:
SELECT *
FROM (SELECT RANK() OVER (ORDER BY [Description] DESC) AS Rank, *
FROM cte_TopClasses
WHERE Description IN (SELECT [Description]
FROM (SELECT RANK() OVER (ORDER BY SUM(NetWrittenPremium) DESC) AS [Rank], [Description], SUM(NetWrittenPremium) AS total
FROM cte_TopClasses
WHERE [Description] IS NOT NULL
GROUP BY [Description]) BB
WHERE [Rank] <= 10)) AA
ORDER BY YearNum, MonthNum
This wraps the query in a SELECT, and filters the ranked results to the 10 you want.
Then use a matrix in the report to pivot the results.
Related
I want to recreate this query in spark sql
SELECT
[Id],
[Group],
[Name],
min([Date]) as MinDate,
max([Date]) as MaxDate
FROM recordTable
GROUP BY [Id],[Group],[Name]
)
SELECT
t.Id,
t.[Group],
t.[Name],
c.[Date],
(SELECT top 1 ScoreCount
from recordTable x
where x.[Date] <= c.[Days]
and x.[Group] = t.[Group]
and x.[Name] = t.[Name]
order by x.[Date] desc
) ScoreCount
FROM t
LEFT JOIN calendar c ON c.[Days] BETWEEN t.MinDate AND t.MaxDate
so I have
df = spark.sql("""
WITH t as (
SELECT
Id,
Group,
Name,
min(Date) as MinDate,
max(Date) as MaxDate
FROM recordTable
GROUP BY Id,Group,Name
)
SELECT
t.Id,
t.Group,
t.Name,
c.Date,
(SELECT ScoreCount
from recordTable x
where x.Date <= c.Days
and x.Group = t.Group
and x.Name = t.Name
order by x.Date desc LIMIT 1
) ScoreCount
FROM t
LEFT JOIN calendar c ON c.Days BETWEEN t.MinDate AND t.MaxDate
""")
But I'm getting an error when trying to limit 1 and using an order by clause. Any alternatives?
"Expressions referencing the outer query are not supported outside of where/having clauses"
PostgreSQL 11
How to pass o.create_date value into INNER JOIN? I need Max ID before o.create_date
SELECT o.id,
o.create_date date,
sum(oi.quantity) qty,
sum(oi.quantity * sp.price) total
FROM ax_order o
LEFT JOIN ax_order_invenotry oi on o.id = oi.order_id
LEFT JOIN ax_inventory i on i.id = oi.inventory_id
LEFT JOIN ax_suppliers s on s.id = o.supplier_id
INNER JOIN ax_supplier_price sp ON (sp.inventory_id = oi.inventory_id and sp.supplier_id = o.supplier_id)
INNER JOIN
(
SELECT inventory_id,
max(id) id
FROM ax_supplier_price
WHERE create_date <= o.create_date
GROUP BY inventory_id
) lsp ON (sp.id = lsp.id)
WHERE o.store_id = 13
AND o.supplier_id = 35
GROUP BY o.id, o.create_date
ORDER BY o.id
You could use the LATERAL join mechanism to make it work:
WITH ax_order AS (
SELECT *
FROM (VALUES (1, '2000-1-1'::date, 1, 1)) as x(id, create_date, store_id, supplier_id)
), ax_order_inventory AS (
SELECT *
FROM (VALUES (1, 2, 4)) as x(order_id, inventory_id, quantity)
), ax_supplier_price AS (
SELECT *
FROM (VALUES (1, 2, 1, 10, '1999-12-31'::date)) as x(id, inventory_id, supplier_id, price, create_date)
)
SELECT o.id,
o.create_date date,
sum(oi.quantity) qty,
sum(oi.quantity * sp.price) total
FROM ax_order o
LEFT JOIN ax_order_inventory oi on o.id = oi.order_id
INNER JOIN ax_supplier_price sp ON (sp.inventory_id = oi.inventory_id and sp.supplier_id = o.supplier_id)
INNER JOIN LATERAL
(
SELECT inventory_id,
max(lsp.id) id
FROM ax_supplier_price lsp
WHERE sp.create_date <= o.create_date
GROUP BY inventory_id
) lsp ON sp.id = lsp.id
GROUP BY o.id, o.create_date
ORDER BY o.id
I deleted some JOINs that were not strictly necessary and mocked your data as well as I could see. Note, however, that you could also use a WHERE clause to find it - which should be more efficient:
WITH ax_order AS (
SELECT *
FROM (VALUES (1, '2000-1-1'::date, 1, 1)) as x(id, create_date, store_id, supplier_id)
),
ax_order_inventory AS (
SELECT *
FROM (VALUES (1, 2, 4)) as x(order_id, inventory_id, quantity)
),
ax_supplier_price AS (
SELECT *
FROM (VALUES (1, 2, 1, 10, '1999-12-31'::date)) as x(id, inventory_id, supplier_id, price, create_date)
)
SELECT o.id,
o.create_date date,
sum(oi.quantity) qty,
sum(oi.quantity * sp.price) total
FROM ax_order o
LEFT JOIN ax_order_inventory oi on o.id = oi.order_id
INNER JOIN ax_supplier_price sp
ON (sp.inventory_id = oi.inventory_id and sp.supplier_id = o.supplier_id)
WHERE sp.id =
(
-- NOTE: no GROUP BY necessary!
SELECT max(lsp.id) id
FROM ax_supplier_price lsp
WHERE sp.create_date <= o.create_date
AND lsp.inventory_id = sp.inventory_id
)
GROUP BY o.id, o.create_date
ORDER BY o.id
Table1:
Shop
Manager
Date
Table2:
Shop
Date
Sales
I need to get Table2 with Manager field from Table1. I did the following trick:
select
t1.[Shop]
,t1.[Date]
,t1.[Sum]
,t2.[Manager]
from t1
left join t2
on t1.[Shop] = t2.[Shop]
and t2.[Date] = (select max(t2.[Date]) from t2
where t2.[Shop] = t1.[Shop]
and t2.[Date] < t1.[Date])
It works, but subquerying is very slow, so I wonder if there is more elegant and fast way to do so?
Some sample data to play around: http://pastebin.com/uLN6x5JE
may seem like a round about way but join on a single condition is typically faster
select t12.[Shop], t12.[Date], t12.[Sum]
, t12.[Manager]
from
( select t1.[Shop], t1.[Date], t1.[Sum]
, t2.[Manager]
, row_number() over (partition by t2.[Shop] order by t2.[Date] desc) as rn
from t1
join t2
on t2.[Shop] = t1.[Shop]
and t1.[Date] < t1.[Date]
) as t12
where t12.rn = 1
union
select t1.[Shop], t1.[Date], t1.[Sum]
, null as [Manager]
from t1
left join t2
on t2.[Shop] = t1.[Shop]
and t1.[Date] < t1.[Date]
group by t1.[Shop], t1.[Date], t1.[Sum]
having count(*) = 1
You may get much better performance by adding a covering index on t2 if you don't already have one:
create index T2ShopDate on t2 ([Shop], [Date]) include ([Manager])
Here is a version that uses a CTE to find all maximum manager dates first and then join back to t2 to get the manager:
;with MaxDates ([Shop], [Date], [Sum], [MaxMgrDate]) as
(
select
t1.[Shop]
,t1.[Date]
,t1.[Sum]
,max(t2.[Date])
from t1
left join t2
on t2.[Shop] = t1.[Shop]
and t2.[Date] < t1.[Date]
group by
t1.[Shop]
,t1.[Date]
,t1.[Sum]
)
select
MaxDates.[Shop]
,MaxDates.[Date]
,MaxDates.[Sum]
,t2.[Manager]
from MaxDates
inner join t2
on t2.[Date] = MaxDates.[MaxMgrDate]
You might be able to remove the second join back to t2 by using row_number():
;with MaxDates ([Shop], [Date], [Sum], [Manager], [RowNum]) as
(
select
t1.[Shop]
,t1.[Date]
,t1.[Sum]
,t2.[Manager]
,row_number() over (partition by (t1.[Shop]) order by t2.[Date] desc)
from t1
left join t2
on t2.[Shop] = t1.[Shop]
and t2.[Date] < t1.[Date]
)
select *
from MaxDates
where RowNum = 1
I have a stored procedure that does paging for the front end and is working fine. I now need to modify that procedure to group by four columns of the 20 returned and then only return the row within each group that contains the lowest priority. So when resort_id, bedrooms, kitchen and checkin (date) all match then only return the row that has the min priority. I have to still maintain the paging functionality. The #startIndex and #upperbound are parms passed into the procedure from the front end for paging. I’m thinking that RANK OVER (PARTITION BY) is the answer I just can’t quite figure out how to put it all together.
SELECT I.id,
I.resort_id,
I.[bedrooms],
I.[kitchen],
I.[checkin],
I.[priority],
I.col_1,
I.col_2 /* ..... (more cols) */
FROM (
SELECT ROW_NUMBER() OVER(ORDER by checkin) AS rowNumber,
*
FROM Inventory
) AS I
WHERE rowNumber >= #startIndex
AND rowNumber < #upperBound
ORDER BY rowNumber
Example 2 after fix:
SELECT I.resort_id,
I.[bedrooms],
I.[kitchen],
I.[checkin],
I.[priority],
I.col_1,
I.col_2 /* ..... (more cols) */
FROM Inventory i
JOIN
(
SELECT ROW_NUMBER() OVER(ORDER BY h.checkin) as rowNumber, MIN(h.id) as id
FROM Inventory h
JOIN (
SELECT resort_id, bedrooms, kitchen, checkin, id, MIN(priority) as priority
FROM Inventory
GROUP BY resort_id, bedrooms, kitchen, checkin, id
) h2 on h.resort_id = h2.resort_id and
h.bedrooms = h2.bedrooms and
h.kitchen = h2.kitchen and
h.checkin = h2.checkin and
h.priority = h2.priority
GROUP BY h.resort_id, h.bedrooms, h.kitchen, h.checkin, h.priority
) AS I2
on i.id = i2.id
WHERE rowNumber >= #startIndex
AND rowNumber < #upperBound
ORDER BY rowNumber
I would accompish it this way.
SELECT I.resort_id,
I.[bedrooms],
I.[kitchen],
I.[checkin],
I.[priority],
I.col_1,
I.col_2 /* ..... (more cols) */
FROM Inventory i
JOIN
(
SELECT ROW_NUMBER(ORDER BY Checkin) as rowNumber, MIN(id) id
FROM Inventory h
JOIN (
SELECT resort_id, bedrooms, kitchen, checkin id, MIN(priority) as priority
FROM Inventory
GROUP BY resort_id, bedrooms, kitchen, checkin
) h2 on h.resort_id = h2.resort and
h.bedrooms = h2.bedrooms and
h.kitchen = h2.kitchen and
h.checkin = h2.checkin and
h.priority = h2.priority
GROUP BY h.resort_id, h.bedrooms, h.kitchen, h.checkin, h.priority
) AS I2
on i.id = i2.id
WHERE rowNumber >= #startIndex
AND rowNumber < #upperBound
ORDER BY rowNumber
Can someone help me with this query?
SELECT p.OwnerName, SUM(ru.MonthlyRent) AS PotentinalRent, SUM(
(SELECT COUNT(t.ID) * ru.MonthlyRent FROM tblTenant t
WHERE t.UnitID = ru.ID)
) AS ExpectedRent
FROM tblRentalUnit ru
LEFT JOIN tblProperty p ON p.ID = ru.PropertyID
GROUP BY p.OwnerName
I'm having problems with the second sum, it won't let me do it. Evidently SUM won't work on subqueries, but I need to calculate the expected rent (MonthlyRent if there is a tenant assigned to the RentalUnit's id, 0 of they're not). How can I make this work?
SELECT p.OwnerName, SUM(ru.MonthlyRent) AS PotentialRent, SUM(cnt) AS ExpectedRent
FROM tblRentalUnit ru
LEFT JOIN
tblProperty p
ON p.ID = ru.PropertyID
OUTER APPLY
(
SELECT COUNT(t.id) * ru.MonthlyRent AS cnt
FROM tblTenant t
WHERE t.UnitID = ru.ID
) td
GROUP BY p.OwnerName
Here's a test script to check:
WITH tblRentalUnit AS
(
SELECT 1 AS id, 100 AS MonthlyRent, 1 AS PropertyID
UNION ALL
SELECT 2 AS id, 300 AS MonthlyRent, 2 AS PropertyID
),
tblProperty AS
(
SELECT 1 AS id, 'Owner 1' AS OwnerName
UNION ALL
SELECT 2 AS id, 'Owner 2' AS OwnerName
),
tblTenant AS
(
SELECT 1 AS id, 1 AS UnitID
UNION ALL
SELECT 2 AS id, 1 AS UnitID
)
SELECT p.OwnerName, SUM(ru.MonthlyRent) AS PotentialRent, SUM(cnt) AS ExpectedRent
FROM tblRentalUnit ru
LEFT JOIN
tblProperty p
ON p.ID = ru.PropertyID
OUTER APPLY
(
SELECT COUNT(t.id) * ru.MonthlyRent AS cnt
FROM tblTenant t
WHERE t.UnitID = ru.ID
) td
GROUP BY p.OwnerName
What is the meaning of the sum of the unitMonthlyRent times the number of tenants, for some partiicular rental unit (COUNT(t.ID) * ru.MonthlyRent )?
Is it the case that all you are trying to do is see the difference between the total potential rent from all untis versus the expected rent (From only occcupied units) ? If so, then try this
Select p.OwnerName,
Sum(r.MonthlyRent) AS PotentinalRent,
Sum(Case t.Id When Null Then 0
Else r.MonthlyRent End) ExpectedRent
From tblRentalUnit r
Left Join tblTenant t
On t.UnitID = r.ID
left Join tblProperty p
On p.ID = r.PropertyID)
Group By p.OwnerName