Related
Here is my code:
arrival_cluster_raw as (
SELECT
routes.uc_id ,
cg.cluster_id ,
cg.cluster_centroid ,
routes.imei ,
routes.time_created::date as campaign_date,
min(routes.time_created) as m_per_imei_cluster
FROM cluster_groups as cg
group by 1,2,3,4,5
)
,
arrival_cluster_final as
(
select uc_id, campaign_date, cluster_id, cluster_centroid , date_trunc('second', AVG(m_per_imei_cluster::TIME)) as avg_arrival_time,
count(case when m_per_imei_cluster::TIME < (select AVG(m_per_imei_cluster::TIME) from arrival_cluster_raw) then 1 else null END) as "num_of_arrival_teams_before_avg_time"
,count(case when m_per_imei_cluster::TIME > (select AVG(m_per_imei_cluster::TIME) from arrival_cluster_raw) then 1 else null END) as "num_of_arrival_teams_after_avg_time"
FROM arrival_cluster_raw
group by uc_id,cluster_id, cluster_centroid ,campaign_date
)
The problem is that in the "arrival_cluster_final", the average value of the entire cluster
is being compared whereas I want to compare the average value for the combination of uc_id,cluster_id, cluster_centroid ,campaign_date
--can you try this one.
WITH arrival_cluster_raw AS (
SELECT
routes.uc_id,
cg.cluster_id,
cg.cluster_centroid,
routes.imei,
routes.time_created::date AS campaign_date,
min(routes.time_created) AS m_per_imei_cluster
FROM
cluster_groups AS cg
JOIN routes ON routes.uc_id = cg.id --assume the way you want join.
GROUP BY
1,2,3,4,5
),
arrival_cluster_final AS (
SELECT
uc_id,
cluster_id,
cluster_centroid,
imei,
campaign_date,
date_trunc('second', (avg(m_per_imei_cluster) OVER w))
,count( CASE WHEN (avg(m_per_imei_cluster) OVER w) < m_per_imei_cluster THEN
1
ELSE
NULL
END) AS num_of_arrival_teams_before_avg_time
,count(
CASE WHEN (avg(m_per_imei_cluster) OVER w) > m_per_imei_cluster THEN
1
ELSE
NULL
END) AS num_of_arrival_teams_after_avg_time
FROM
arrival_cluster_raw
WINDOW w AS (PARTITION BY uc_id,
cluster_id,
cluster_centroid,
campaign_date))
SELECT * FROM arrival_cluster_final ORDER BY 1;
I have a large table that has a structure something like the following:
Create Table public.example
(
id character varying(7) ,
type character varying(1) ,
amount decimal ,
date1 date ,
plan character varying(2) ,
date2 date );
Insert into public.example
( Id,Type,Amount,Date1,Plan,Date2)
values
( '1343657' , 'e',235.26 ,'2021-01-03', 'HS', '2021-07-03'),
( '1343657' , 's',6234.25,'2021-01-15', 'RT', '2021-05-09'),
( '1343657' , 's',235.26 ,'2021-01-05', 'HS', '2021-05-03'),
( '1343657' , '3',235.26 ,'2021-01-05', 'HS', '2021-05-17'),
( '1343657' , 's',235.26 ,'2021-01-05', 'HS', '2021-03-19'),
( '5364324' , 'e',1245.90,'2021-01-17', 'MM', '2021-04-23'),
( '5364324' , '1',5285.88,'2021-01-14', 'MM', '2021-02-28'),
( '5364324' , 'e',1245.10,'2021-01-08', 'VI', '2021-06-30'),
( '5364324' , 'e',7452.05,'2021-01-10', 'DT', '2021-03-07') ;
I need to list the "amount" field across the report in different buckets based on the value of the “Plan” field. I also need to summarize the amount by Id and Type. My method doesn’t work because it adds another required Group BY and I don’t get a summarized amount by Id and Type.
Select id,type,
case When a.plan ='HS' then sum(amount) else 0 end as "HS",
case When a.plan ='RT' then sum(amount) else 0 end as "RT",
case When a.plan ='MM' then sum(amount) else 0 end as "MM",
case When a.plan ='VI' then sum(amount) else 0 end as "VI",
case When a.plan ='DT' then sum(amount) else 0 end as "DT"
from public.example a
where date2>='2021-01-01' and date2<='2021-12-31'
group by 1,2,a.plan
The perfect solution would allow me to add date1 to the Select output as well.
Select OUTPUT
Thx
I'm using SQL Server 2000 (80). So, it's not possible to use the LAG function.
I have a code a data set with four columns:
Purchase_Date
Facility_no
Seller_id
Sale_id
I need to identify missing Sale_ids. So every sale_id is a 100% sequential, so the should not be any gaps in order.
This code works for a specific date and store if specified. But i need to work on entire data set looping looping through every facility_id and every seller_id for ever purchase_date
declare #MAXCOUNT int
set #MAXCOUNT =
(
select MAX(Sale_Id)
from #table
where
Facility_no in (124) and
Purchase_date = '2/7/2020'
and Seller_id = 1
)
;WITH TRX_COUNT AS
(
SELECT 1 AS Number
union all
select Number + 1 from TRX_COUNT
where Number < #MAXCOUNT
)
select * from TRX_COUNT
where
Number NOT IN
(
select Sale_Id
from #table
where
Facility_no in (124)
and Purchase_Date = '2/7/2020'
and seller_id = 1
)
order by Number
OPTION (maxrecursion 0)
My Dataset
This column:
case when
Sale_Id=0 or 1=Sale_Id-LAG(Sale_Id) over (partition by Facility_no, Purchase_Date, Seller_id)
then 'OK' else 'Previous Missing' end
will tell you which Seller_Ids have some sale missing. If you want to go a step further and have exactly your desired output, then filter out and distinct the 'Previous Missing' ones, and join with a tally table on not exists.
Edit: OP mentions in comments they can't use LAG(). My suggestion, then, would be:
Make a temp table that that has the max(sale_id) group by facility/seller_id
Then you can get your missing results by this pseudocode query:
Select ...
from temptable t
inner join tally N on t.maxsale <=N.num
where not exists( select ... from sourcetable s where s.facility=t.facility and s.seller=t.seller and s.sale=N.num)
> because the only way to "construct" nonexisting combinations is to construct them all and just remove the existing ones.
This one worked out
; WITH cte_Rn AS (
SELECT *, ROW_NUMBER() OVER(PARTITION BY Facility_no, Purchase_Date, Seller_id ORDER BY Purchase_Date) AS [Rn_Num]
FROM (
SELECT
Facility_no,
Purchase_Date,
Seller_id,
Sale_id
FROM MyTable WITH (NOLOCK)
) a
)
, cte_Rn_0 as (
SELECT
Facility_no,
Purchase_Date,
Seller_id,
Sale_id,
-- [Rn_Num] AS 'Skipped Sale'
-- , case when Sale_id = 0 Then [Rn_Num] - 1 Else [Rn_Num] End AS 'Skipped Sale for 0'
, [Rn_Num] - 1 AS 'Skipped Sale for 0'
FROM cte_Rn a
)
SELECT
Facility_no,
Purchase_Date,
Seller_id,
Sale_id,
-- [Skipped Sale],
[Skipped Sale for 0]
FROM cte_Rn_0 a
WHERE NOT EXISTS
(
select * from cte_Rn_0 b
where b.Sale_id = a.[Skipped Sale for 0]
and a.Facility_no = b.Facility_no
and a.Purchase_Date = b.Purchase_Date
and a.Seller_id = b.Seller_id
)
--ORDER BY Purchase_Date ASC
I need to select 10 or less rows with the SUM(FileSize) < 1000000. Results need to be ordered by AttachmentId. Let's say that if a single FileSize exceeds the limit it's okay just for that row (and no other) to be selected.
Ideally I'd like it to be just a select query with no more statements.
The table is:
CREATE TABLE [Attachment](
[AttachmentId] [int] NOT NULL,
[FileSize] [int] NOT NULL
)
Please help.
Updated. Sorry to hear that the requirements are unclear for most of the readers. There is no requirement to do any grouping. All I need to get is just plain first 10 rows or less. It will be less than 10 if their total on FileSize exceeds 1000000. It will be only 1 row if its FileSize equals 1000000 or more. The server is SQL 2008.
Updated. Many thanks to Nikola. We are getting there, but I'm still not sure how to implement the case when the first row exceeds FileSize of 1000000.
SELECT TOP 10 a.AttachmentId, rt.runningTotal
FROM Attachment a
CROSS APPLY (SELECT SUM(aa.FileSize) AS runningTotal
FROM Attachment aa
WHERE aa.AttachmentId <= a.AttachmentId
) AS rt
GROUP BY a.AttachmentId, rt.runningTotal
HAVING rt.runningTotal < 1000000
ORDER BY a.AttachmentId
Solution. This is the code (slightly modified) from Stuart which I accept as answer. Many thanks to Stuart!:
WITH CTE
AS ( SELECT TOP 10 AttachmentId, FileSize
, RunningID = ROW_NUMBER() OVER (ORDER BY AttachmentId)
FROM Attachment
)
SELECT AttachmentId, FileSize
FROM CTE AS a
WHERE (SELECT SUM(FileSize)
FROM CTE
WHERE RunningID <= a.RunningID
) <= 10000000
OR a.RunningID = 1
Maybe this will get you started:
BEGIN TRAN
CREATE TABLE [Attachment]
(
[AttachmentId] [int] NOT NULL
, [FileSize] [int] NOT NULL
)
INSERT INTO Attachment
SELECT 1
, 10
UNION
SELECT 2
, 20
UNION
SELECT 3
, 30
--values to exceed
DECLARE #p INT = 50
--row count to restrict to
DECLARE #r INT = 10
;
WITH CTE
AS ( SELECT AttachmentID
, FileSize
, RunningID = ROW_NUMBER() OVER ( ORDER BY FileSize DESC )
FROM Attachment
)
SELECT TOP ( #r )
AttachmentID
, FileSize
FROM CTE AS A
WHERE ( SELECT SUM(FileSize)
FROM CTE
WHERE RunningID <= A.RunningID
) <= #p
OR A.RunningID = 1
ROLLBACK
SELECT TOP 10 AttachmentId
FROM Attachment
GROUP BY AttachmentId
HAVING SUM(FileSize) < 1000000
ORDER BY AttachmentId
Just a brief of business scenario is table has been created for a good receipt. So here we have good expected line with PurchaseOrder(PO) in first few line. And then we receive each expected line physically and that time these quantity may be different, due to business case like quantity may damage and short quantity like that. So we maintain a status for that eg: OK, Damage, also we have to calculate short quantity based on total of expected quantity of each item and total of received line.
if object_id('DEV..Temp','U') is not null
drop table Temp
CREATE TABLE Temp
(
ID INT IDENTITY(1,1) PRIMARY KEY CLUSTERED,
Item VARCHAR(32),
PO VARCHAR(32) NULL,
ExpectedQty INT NULL,
ReceivedQty INT NULL,
[STATUS] VARCHAR(32) NULL,
BoxName VARCHAR(32) NULL
)
Please see first few line with PO data will be the expected lines,
and then rest line will be received line
INSERT INTO TEMP (Item,PO,ExpectedQty,ReceivedQty,[STATUS],BoxName)
SELECT 'ITEM01','PO-01','30',NULL,NULL,NULL UNION ALL
SELECT 'ITEM01','PO-02','20',NULL,NULL,NULL UNION ALL
SELECT 'ITEM02','PO-01','40',NULL,NULL,NULL UNION ALL
SELECT 'ITEM03','PO-01','50',NULL,NULL,NULL UNION ALL
SELECT 'ITEM03','PO-02','30',NULL,NULL,NULL UNION ALL
SELECT 'ITEM03','PO-03','20',NULL,NULL,NULL UNION ALL
SELECT 'ITEM04','PO-01','30',NULL,NULL,NULL UNION ALL
SELECT 'ITEM01',NULL,NULL,'20','OK','box01' UNION ALL
SELECT 'ITEM01',NULL,NULL,'25','OK','box02' UNION ALL
SELECT 'ITEM01',NULL,NULL,'5','DAMAGE','box03' UNION ALL
SELECT 'ITEM02',NULL,NULL,'38','OK','box04' UNION ALL
SELECT 'ITEM02',NULL,NULL,'2','DAMAGE','box05' UNION ALL
SELECT 'ITEM03',NULL,NULL,'30','OK','box06' UNION ALL
SELECT 'ITEM03',NULL,NULL,'30','OK','box07' UNION ALL
SELECT 'ITEM03',NULL,NULL,'30','OK','box08' UNION ALL
SELECT 'ITEM03',NULL,NULL,'10','DAMAGE','box09' UNION ALL
SELECT 'ITEM04',NULL,NULL,'25','OK','box10'
Below Table is my expected result based on above data.
I need to show those data following way.
So I appreciate if you can give me an appropriate query for it.
Note: first row is blank and it is actually my table header. :)
SELECT '' as 'ITEM', '' as 'PO#', '' as 'ExpectedQty',
'' as 'ReceivedQty','' as 'DamageQty' ,'' as 'ShortQty' UNION ALL
SELECT 'ITEM01','PO-01','30','30','0' ,'0' UNION ALL
SELECT 'ITEM01','PO-02','20','15','5' ,'0' UNION ALL
SELECT 'ITEM02','PO-01','40','38','2' ,'0' UNION ALL
SELECT 'ITEM03','PO-01','50','50','0' ,'0' UNION ALL
SELECT 'ITEM03','PO-02','30','30','0' ,'0' UNION ALL
SELECT 'ITEM03','PO-03','20','10','10','0' UNION ALL
SELECT 'ITEM04','PO-01','30','25','0' ,'5'
Note : we don't received more than expected.
solution should be based on SQL 2000
You should reconsider how you store this data. Separate Expected and Received+Damaged in different tables (you have many unused (null) cells). This way any query should become more readable.
I think what you try to do can be achieved more easily with a stored procedure.
Anyway, try this query:
SELECT Item, PO, ExpectedQty,
CASE WHEN [rec-consumed] > 0 THEN ExpectedQty
ELSE CASE WHEN [rec-consumed] + ExpectedQty > 0
THEN [rec-consumed] + ExpectedQty
ELSE 0
END
END ReceivedQty,
CASE WHEN [rec-consumed] < 0
THEN CASE WHEN DamageQty >= -1*[rec-consumed]
THEN -1*[rec-consumed]
ELSE DamageQty
END
ELSE 0
END DamageQty,
CASE WHEN [rec_damage-consumed] < 0
THEN DamageQty - [rec-consumed]
ELSE 0
END ShortQty
FROM (
select t1.Item,
t1.PO,
t1.ExpectedQty,
st.sum_ReceivedQty_OK
- (sum(COALESCE(t2.ExpectedQty,0))
+t1.ExpectedQty)
[rec-consumed],
st.sum_ReceivedQty_OK + st.sum_ReceivedQty_DAMAGE
- (sum(COALESCE(t2.ExpectedQty,0))
+t1.ExpectedQty)
[rec_damage-consumed],
st.sum_ReceivedQty_DAMAGE DamageQty
from #tt t1
left join #tt t2 on t1.Item = t2.Item
and t1.PO > t2.PO
and t2.PO is not null
join (select Item
, sum(CASE WHEN status = 'OK' THEN ReceivedQty ELSE 0 END)
sum_ReceivedQty_OK
, sum(CASE WHEN status != 'OK' THEN ReceivedQty ELSE 0 END)
sum_ReceivedQty_DAMAGE
from #tt where PO is null
group by Item) st on t1.Item = st.Item
where t1.PO is not null
group by t1.Item, t1.PO, t1.ExpectedQty,
st.sum_ReceivedQty_OK,
st.sum_ReceivedQty_DAMAGE
) a
order by Item, PO