T-SQL Pivot query - tsql

I have a table that contains a laserform name and a date e.g.
My table is called myBWB_LaserForms
laserform editwhen
LRAP1.lpw 2009-09-03 16:06:00.000
CON29R.lpw 2009-10-29 12:35:00.000
UN1.lpw 2010-03-02 11:38:00.000
UN244.lpw 2012-04-19 12:14:00.000
LT3.lpw 2013-01-02 11:00:00.000
LRAP1.lpw 2007-12-10 15:34:00.000
What I am trying to produce is a report which has the name of the laserform down the left and years across the top e.g. 2004, 2005, 2006 and then each intersecting cell would have a count of the number of records for that form name for that particular year.
Normally I would do something like
select l.laserform,
(select count(*) from mybwb_laserforms l1 where l1.laserform=l.laserform and year(editwhen)=2004) AS [2004],
(select count(*) from mybwb_laserforms l2 where l2.laserform=l.laserform and year(editwhen)=2005) AS [2005],
(select count(*) from mybwb_laserforms l3 where l3.laserform=l.laserform and year(editwhen)=2006) AS [2006],
(select count(*) from mybwb_laserforms l4 where l4.laserform=l.laserform and year(editwhen)=2007) AS [2007]
from mybwb_laserforms l
group by l.laserform
order by l.laserform
However I realise that this is pretty horrible SQL and I should be much more intelligent about it.
I've been trying to learn how to use the pivot function but am struggling to get my head around it.
Also most examples I have found seem to have the columns of the query hard coded - it would be good if the pivot could be dynamic and get the unique year(editwhen) values so I don't have to modify the query next year and the year after that.

Just sum it up.
select laserform,
sum(case when year(editwhen)=2004 then 1 else 0 end) AS [2004],
sum(case when year(editwhen)=2005 then 1 else 0 end) AS [2005],
sum(case when year(editwhen)=2006 then 1 else 0 end) AS [2006],
sum(case when year(editwhen)=2007 then 1 else 0 end) AS [2007]
from mybwb_laserforms
where year(editwhen) between 2004 and 2007
group by laserform
order by laserform
Or dynamic
declare #Year int = year(GetDate());
declare #Years TABLE ([year] varchar(4));
insert into #Years values (#Year-12),(#Year-11),(#Year-10),(#Year-9);
declare #SQLSums varchar(max) = '';
select #SQLSums = #SQLSums +char(13)+', sum(case when year(editwhen)='+[year]+' then 1 else 0 end) AS ['+[year]+']'
from #Years;
DECLARE #SQL nvarchar(max) = 'select laserform'+ #SQLSums +'
from mybwb_laserforms
group by laserform
where year(editwhen) between '+cast(#Year-12 as varchar)+' and '+cast(#Year-9 as varchar)+'
order by laserform';
--select #SQL;
exec (#SQL);

Related

SQL Server - Select with Group By together Raw_Number

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

Cumulative sum with group by and join

I'm a little struggled with finding a clean way to do this. Assume that I have the following records in my table named Records:
|Name| |InsertDate| |Size|
john 30.06.2015 1
john 10.01.2016 10
john 12.01.2016 100
john 05.03.2016 1000
doe 01.01.2016 1
How do I get the records for year of 2016 and month is equal to or less than 3 grouped by month(even that month does not exists e.g. month 2 in this case) with cumulative sum of Size including that month? I want to get the result as the following:
|Name| |Month| |Size|
john 1 111
john 2 111
john 3 1111
doe 1 1
As other commenters have already stated, you simply need a table with dates in that you can join from to give you the dates that your source table does not have records for:
-- Build the source data table.
declare #t table(Name nvarchar(10)
,InsertDate date
,Size int
);
insert into #t values
('john','20150630',1 )
,('john','20160110',10 )
,('john','20160112',100 )
,('john','20160305',1000)
,('doe' ,'20160101',1 );
-- Specify the year you want to search for by storing the first day here.
declare #year date = '20160101';
-- This derived table builds a set of dates that you can join from.
-- LEFT JOINing from here is what gives you rows for months without records in your source data.
with Dates
as
(
select #year as MonthStart
,dateadd(day,-1,dateadd(month,1,#year)) as MonthEnd
union all
select dateadd(month,1,MonthStart)
,dateadd(day,-1,dateadd(month,2,MonthStart))
from Dates
where dateadd(month,1,MonthStart) < dateadd(yyyy,1,#year)
)
select t.Name
,d.MonthStart
,sum(t.Size) as Size
from Dates d
left join #t t
on(t.InsertDate <= d.MonthEnd)
where d.MonthStart <= '20160301' -- Without knowing what your logic is for specifying values only up to March, I have left this part for you to automate.
group by t.Name
,d.MonthStart
order by t.Name
,d.MonthStart;
If you have a static date reference table in your database, you don't need to do the derived table creation and can just do:
select d.DateValue
,<Other columns>
from DatesReferenceTable d
left join <Other Tables> o
on(d.DateValue = o.AnyDateColumn)
etc
Here's another approach that utilizes a tally table (aka numbers table) to create the date table. Note my comments.
-- Build the source data table.
declare #t table(Name nvarchar(10), InsertDate date, Size int);
insert into #t values
('john','20150630',1 )
,('john','20160110',10 )
,('john','20160112',100 )
,('john','20160305',1000)
,('doe' ,'20160101',1 );
-- A year is fine, don't need a date data type
declare #year smallint = 2016;
WITH -- dummy rows for a tally table:
E AS (SELECT E FROM (VALUES (1),(1),(1),(1),(1),(1),(1),(1),(1),(1)) t(e)),
dateRange(totalDays, mn, mx) AS -- Get the range and number of months to create
(
SELECT DATEDIFF(MONTH, MIN(InsertDate), MAX(InsertDate)), MIN(InsertDate), MAX(InsertDate)
FROM #t
),
iTally(N) AS -- Tally Oh! Create an inline Tally (aka numbers) table starting with 0
(
SELECT ROW_NUMBER() OVER (ORDER BY (SELECT 1))-1
FROM E a CROSS JOIN E b CROSS JOIN E c CROSS JOIN E d
),
RunningTotal AS -- perform a running total by year/month for each person (Name)
(
SELECT
yr = YEAR(DATEADD(MONTH, n, mn)),
mo = MONTH(DATEADD(MONTH, n, mn)),
Name,
Size = SUM(Size) OVER
(PARTITION BY Name ORDER BY YEAR(DATEADD(MONTH, n, mn)), MONTH(DATEADD(MONTH, n, mn)))
FROM iTally
CROSS JOIN dateRange
LEFT JOIN #t ON MONTH(InsertDate) = MONTH(DATEADD(MONTH, n, mn))
WHERE N <= totalDays
) -- Final output will only return rows where the year matches #year:
SELECT
name = ISNULL(name, LAG(Name, 1) OVER (ORDER BY yr, mo)),
yr, mo,
size = ISNULL(Size, LAG(Size, 1) OVER (ORDER BY yr, mo))
FROM RunningTotal
WHERE yr = #year
GROUP BY yr, mo, name, size;
Results:
name yr mo size
---------- ----------- ----------- -----------
doe 2016 1 1
john 2016 1 111
john 2016 2 111
john 2016 3 1111

TSQL - Control a number sequence

Im a new in TSQL.
I have a table with a field called ODOMETER of a vehicle. I have to get the quantity of km in a period of time from 1st of the month to the end.
SELECT MAX(Odometer) - MIN(Odometer) as TotalKm FROM Table
This will work in ideal test scenary, but the Odomometer can be reset to 0 in anytime.
Someone can help to solve my problem, thank you.
I'm working with MS SQL 2012
EXAMPLE of records:
Date Odometer value
datetime var, 37210
datetime var, 37340
datetime var, 0
datetime var, 220
Try something like this using the LAG. There are other ways, but this should be easy.
EDIT: Changing the sample data to include records outside of the desired month range. Also simplifying that Reading for easy hand calc. Will shows a second option as siggested by OP.
DECLARE #tbl TABLE (stamp DATETIME, Reading INT)
INSERT INTO #tbl VALUES
('02/28/2014',0)
,('03/01/2014',10)
,('03/10/2014',20)
,('03/22/2014',0)
,('03/30/2014',10)
,('03/31/2014',20)
,('04/01/2014',30)
--Original solution with WHERE on the "outer" SELECT.
--This give a result of 40 as it include the change of 10 between 2/28 and 3/31.
;WITH cte AS (
SELECT Reading
,LAG(Reading,1,Reading) OVER (ORDER BY stamp ASC) LastReading
,Reading - LAG(Reading,1,Reading) OVER (ORDER BY stamp ASC) ChangeSinceLastReading
,CONVERT(date, stamp) stamp
FROM #tbl
)
SELECT SUM(CASE WHEN Reading = 0 THEN 0 ELSE ChangeSinceLastReading END)
FROM cte
WHERE stamp BETWEEN '03/01/2014' AND '03/31/2014'
--Second option with WHERE on the "inner" SELECT (within the CTE)
--This give a result of 30 as it include the change of 10 between 2/28 and 3/31 is by the filtered lag.
;WITH cte AS (
SELECT Reading
,LAG(Reading,1,Reading) OVER (ORDER BY stamp ASC) LastReading
,Reading - LAG(Reading,1,Reading) OVER (ORDER BY stamp ASC) ChangeSinceLastReading
,CONVERT(date, stamp) stamp
FROM #tbl
WHERE stamp BETWEEN '03/01/2014' AND '03/31/2014'
)
SELECT SUM(CASE WHEN Reading = 0 THEN 0 ELSE ChangeSinceLastReading END)
FROM cte
I think Karl solution using LAG is better than mine, but anyway:
;WITH [Rows] AS
(
SELECT o1.[Date], o1.[Value] as CurrentValue,
(SELECT TOP 1 o2.[Value]
FROM #tbl o2 WHERE o1.[Date] < o2.[Date]) as NextValue
FROM #tbl o1
)
SELECT SUM (CASE WHEN [NextValue] IS NULL OR [NextValue] < [CurrentValue] THEN 0 ELSE [NextValue] - [CurrentValue] END )
FROM [Rows]

Help with difficult 'group by' clause

need some your help with a query.
I have a table Managers (ManagerId, ManagerName)
I have a table Statuses (StatusId, StatusName)
(There's about 10 statuses in that table)
I have a table Clients (ClientId, ClientName, ManagerId, StatusId, WhenAdded)
(WhenAdded is a datetime type)
It's obvious that field 'ManagerId' refers to a table 'Managers' and field 'StatusId' refers to a table 'Statuses'.
User wants to get some statistics about Managers over a period of time (from startDate to endDate using field 'WhenAdded') in the following table.
Columns:
ManagerName, NumberOfClients, NumberOfClientsWithStatus1, NumberOfClientsWithStatus2, NumberOfClientsWithStatus3 and so on.
Number of columns with name NumberOfClientsWithStatusI where i is a number of statuses equal to number of rows in table 'Statuses'.
How can I do that?
t-sql, sql server 2008 r2 express edition.
SELECT
ManagerName,
COUNT(*) AS NumberOfClients,
COUNT(CASE WHEN S.StatusId = 1 THEN 1 ELSE NULL END) AS NumberOfClientsWithStatus1,
COUNT(CASE WHEN S.StatusId = 2 THEN 1 ELSE NULL END) AS NumberOfClientsWithStatus2,
COUNT(CASE WHEN S.StatusId = 3 THEN 1 ELSE NULL END) AS NumberOfClientsWithStatus3,
...
FROM
Clients C
JOIN
Managers M ON C.ManagerId = M.ManagerId
JOIN
Statuses S ON C.StatusId = S.StatusId
WHERE
M.WhenAdded BETWEEN #startDate AND #endDate
GROUP BY
M.ManagerName
Note: there is no clean way to add arbritrary numbers of status columns in SQL (not just SQL Server) because its a fixed column output. You'd have to change the query for status, unless you deal with this in the client
Edit, after comment
SELECT
ManagerName,
COUNT(*) AS NumberOfClients,
COUNT(CASE WHEN S.StatusId = 1 THEN 1 ELSE NULL END) AS NumberOfClientsWithStatus1,
COUNT(CASE WHEN S.StatusId = 2 THEN 1 ELSE NULL END) AS NumberOfClientsWithStatus2,
COUNT(CASE WHEN S.StatusId = 3 THEN 1 ELSE NULL END) AS NumberOfClientsWithStatus3,
...
FROM
Managers M ON C.ManagerId = M.ManagerId
LEFT JOIN
Clients C
LEFT JOIN
Statuses S ON C.StatusId = S.StatusId
WHERE
M.WhenAdded BETWEEN #startDate AND #endDate
GROUP BY
M.ManagerName
If you know that statuses table will always contain a limited number of statuses, you can do this:
SELECT M.ManagerName,
COUNT(C.ClientId) NumberOfClients,
SUM(CASE WHEN S.StatusId= 1 THEN 1 ELSE 0 END) NumberOfClientsWithStatus1,
SUM(CASE WHEN S.StatusId= 2 THEN 1 ELSE 0 END) NumberOfClientsWithStatus2,
...
FROM Clients C
JOIN Managers M on M.ManagerId = C.ManagerId
JOIN Statuses S on S.StatusId = C.StatusId
WHERE C.WhenAdded BETWEEN startDate AND endDate
GROUP BY ManagerName

SQL Server 2000: how do i get a list of tables and the row counts? [duplicate]

This question already has answers here:
Query to list number of records in each table in a database
(23 answers)
Closed 8 years ago.
I know that I can get a list of tables with
SELECT TABLE_NAME FROM information_schema.tables
WHERE NOT TABLE_NAME='sysdiagrams'
AND TABLE_SCHEMA = 'dbo'
AND TABLE_TYPE= 'BASE TABLE'
But I'm not sure how to modify that to get a 2nd column with the current count of rows for the tables. I though of something like this:
DECLARE #tbl VARCHAR(200)
(SELECT #tbl = TABLE_NAME, TABLE_NAME,
(SELECT COUNT(ID) AS Cnt FROM #tbl)
FROM information_schema.tables
WHERE NOT TABLE_NAME='sysdiagrams'
AND TABLE_SCHEMA = 'dbo'
AND TABLE_TYPE= 'BASE TABLE')
I know the above is not valid T-SQL but I think it gets the point of what I would like the have done. This is for SQL Server 2000. I would prefer not to use store procedures if at all possible.
A quick and dirty way (includes uncommitted changes and possibly forwarding pointers on heaps)
select o.name, rows
from sysindexes i join sysobjects o on o.id=i.id
where indid < 2 and type='U'
exec sp_MSforeachtable 'select count(*) as nr_of_rows, ''?'' as table_name from ?'
You can go whole hog on this one. The problem with using sysIndexes to get rowcounts is that they're not always up to date. There is a way to make them all up to date, though. The following code will give you row counts for each table and a whole bunch more.
/**********************************************************************************************************************
Purpose:
Returns a single result set similar to sp_Space used for all user tables at once.
Notes:
1. May be used as a view, stored procedure, or table-valued function.
2. Must comment out 1 "Schema" in the SELECT list below prior to use. See the adjacent comments for more info.
Revision History:
Rev 00 - 22 Jan 2007 - Jeff Moden
- Initital creation for SQL Server 2000
Rev 01 - 11 Mar 2007 - Jeff Moden
- Add automatic page size determination for future compliance
Rev 02 - 05 Jan 2008 - Jeff Moden
- Change "Owner" to "Schema" in output. Add optional code per Note 2 to find correct schema name
**********************************************************************************************************************/
--===== Ensure that all row counts, etc is up to snuff
-- Obviously, this will not work in a view or UDF and should be removed if in a view or UDF. External code should
-- execute the command below prior to retrieving from the view or UDF.
DBCC UPDATEUSAGE(0) WITH COUNT_ROWS, NO_INFOMSGS
--===== Return the single result set similar to what sp_SpaceUsed returns for a table, but more
SELECT DBName = DB_NAME(),
--SchemaName = SCHEMA_NAME(so.UID), --Comment out if for SQL Server 2000
SchemaName = USER_NAME(so.UID), --Comment out if for SQL Server 2005
TableName = so.Name,
TableID = so.ID,
MinRowSize = MIN(si.MinLen),
MaxRowSize = MAX(si.XMaxLen),
ReservedKB = SUM(CASE WHEN si.IndID IN (0,1,255) THEN si.Reserved ELSE 0 END) * pkb.PageKB,
DataKB = SUM(CASE WHEN si.IndID IN (0,1 ) THEN si.DPages ELSE 0 END) * pkb.PageKB
+ SUM(CASE WHEN si.IndID IN ( 255) THEN ISNULL(si.Used,0) ELSE 0 END) * pkb.PageKB,
IndexKB = SUM(CASE WHEN si.IndID IN (0,1,255) THEN si.Used ELSE 0 END) * pkb.PageKB
- SUM(CASE WHEN si.IndID IN (0,1 ) THEN si.DPages ELSE 0 END) * pkb.PageKB
- SUM(CASE WHEN si.IndID IN ( 255) THEN ISNULL(si.Used,0) ELSE 0 END) * pkb.PageKB,
UnusedKB = SUM(CASE WHEN si.IndID IN (0,1,255) THEN si.Reserved ELSE 0 END) * pkb.PageKB
- SUM(CASE WHEN si.IndID IN (0,1,255) THEN si.Used ELSE 0 END) * pkb.PageKB,
Rows = SUM(CASE WHEN si.IndID IN (0,1 ) THEN si.Rows ELSE 0 END),
RowModCtr = MIN(si.RowModCtr),
HasTextImage = MAX(CASE WHEN si.IndID IN ( 255) THEN 1 ELSE 0 END),
HasClustered = MAX(CASE WHEN si.IndID IN ( 1 ) THEN 1 ELSE 0 END)
FROM dbo.SysObjects so,
dbo.SysIndexes si,
(--Derived table finds page size in KB according to system type
SELECT Low/1024 AS PageKB --1024 is a binary Kilo-byte
FROM Master.dbo.spt_Values
WHERE Number = 1 --Identifies the primary row for the given type
AND Type = 'E' --Identifies row for system type
) pkb
WHERE si.ID = so.ID
AND si.IndID IN (0, --Table w/o Text or Image Data
1, --Table with clustered index
255) --Table w/ Text or Image Data
AND so.XType = 'U' --User Tables
AND PERMISSIONS(so.ID) <> 0
GROUP BY so.Name,
so.UID,
so.ID,
pkb.PageKB
ORDER BY ReservedKB DESC
how about "dtproperties" and "sysdiagrams" ?
these tables will show up as user table incorrectly