T-SQL list of years and months between two dates - tsql

I have a table with a list of individuals that have a effective date and a termination date.
example Person 1, 20171201, 20180601
For each record, I need to output a list of years and months they were "active" between the two dates.
So the output would look like
Data Output
This is in SQL Server 2016
Any help would be appreciated!

Just because I did not see it offered. Here is yet another approach which uses an ad-hoc calendar table
Note the base date of 2000-01-01 and 10,000 days ... expand or contract if needed
Example
Declare #YourTable table (Person int,startdate date, enddate date)
Insert Into #YourTable values
(1,'20171201','20180601')
Select Distinct
A.Person
,ActiveYear = year(D)
,ActiveMonth = month(D)
From #YourTable A
Join (
Select Top 10000 D=DateAdd(DAY,-1+Row_Number() Over (Order By (Select Null)),'2000-01-01')
From master..spt_values n1,master..spt_values n2
) B on D between startdate and enddate
Returns
Person ActiveYear ActiveMonth
1 2017 12
1 2018 1
1 2018 2
1 2018 3
1 2018 4
1 2018 5
1 2018 6

Based on info you've provided, I did a little guessing. Perhaps a recursive CTE will help:
DECLARE #tab TABLE (Person INT, EffectiveDate DATE, TerminationDate DATE)
INSERT #tab VALUES
(1, '2017-12-01', '2018-05-31'),
(2, '2017-10-01', '2018-01-01'),
(3, '2018-02-01', '2018-12-01')
;WITH t AS (
SELECT Person, EffectiveDate AS Dt
FROM #tab
UNION ALL
SELECT Person, DATEADD(mm,1,Dt)
FROM t
WHERE t.Dt < (SELECT DATEADD(mm,-1,TerminationDate) FROM #tab tt WHERE tt.Person = t.Person)
)
SELECT *
FROM t
ORDER BY Dt
Then take the DATEPART()
SELECT t.Person
, t.Dt
, DATEPART(yyyy, t.Dt) ActiveYear
, DATEPART(mm, t.Dt) ActiveMonth
FROM t
ORDER BY Dt

Welcome to stackoverflow! For better help it's good to include DDL easily consumable sample data that we can use to quickly re-create what you are doing and provide a solution. Note this sample data:
DECLARE #yourtable TABLE(person VARCHAR(20), date1 DATE, date2 DATE)
INSERT #yourtable (person, date1, date2)
VALUES ('Person1','20171201', '20180601'), ('Person2','20171001', '20180101'),
('Person3','20180101', '20180301');
SELECT t.* FROM #yourtable AS t;
Returns:
person date1 date2
-------------------- ---------- ----------
Person1 2017-12-01 2018-06-01
Person2 2017-10-01 2018-01-01
Person3 2018-01-01 2018-03-01
(I added a couple rows). Here's my solution:
DECLARE #yourtable TABLE(person VARCHAR(20), date1 DATE, date2 DATE)
INSERT #yourtable (person, date1, date2)
VALUES ('Person1','20171201', '20180601'), ('Person2','20171001', '20180101'),
('Person3','20180101', '20180301');
SELECT
Person = t.person,
ActiveYear = YEAR(st.DT),
ActiveMonth = MONTH(st.Dt)
FROM #yourtable AS t
CROSS APPLY
(
SELECT TOP (DATEDIFF(MONTH,t.date1,t.date2)) ROW_NUMBER() OVER (ORDER BY (SELECT NULL))
FROM (VALUES(1),(1),(1),(1),(1),(1),(1),(1),(1),(1)) AS a(x)
CROSS JOIN (VALUES(1),(1),(1),(1),(1),(1),(1),(1),(1),(1)) AS b(x)
) AS iTally(N)
CROSS APPLY (VALUES(DATEADD(MONTH, iTally.N-1, t.date1))) AS st(Dt);
Which returns:
Person ActiveYear ActiveMonth
-------------------- ----------- -----------
Person1 2017 12
Person1 2018 1
Person1 2018 2
Person1 2018 3
Person1 2018 4
Person1 2018 5
Person2 2017 10
Person2 2017 11
Person2 2017 12
Person3 2018 1
Person3 2018 2
Let me know if you have questions.

Related

SQL Group by Month

I have a table of Sales data with each line as a sale date mm/dd/yy.
I'm trying to create a query so I can see total sales for each month I have.
Would I have to create a column separate that dictates only the month? Or is there a way that it can take the month from that date format?
The short answer is: You don't need a separate column. You can group by the result of a function call.
The details of what that function might depend on your database, how you want results formatted, and performance considerations.
The following both work in Oracle:
SELECT extract(YEAR FROM ae.saledate), extract(MONTH FROM ae.saledate), count(*)
FROM mytable ae
GROUP BY extract(YEAR FROM ae.saledate), extract(MONTH FROM ae.saledate);
SELECT TO_CHAR(ae.saledate, 'YYYY-MM'), count(*)
FROM mytable ae
GROUP BY TO_CHAR(ae.saledate, 'YYYY-MM');
Edited to add versions that ignore year and only look at month (since I was making an assumption above that wasn't actually in the question):
SELECT extract(MONTH FROM ae.saledate), count(*)
FROM mytable ae
GROUP BY extract(MONTH FROM ae.saledate);
SELECT TO_CHAR(ae.saledate, 'MM'), count(*)
FROM mytable ae
GROUP BY TO_CHAR(ae.saledate, 'MM');
The following Query will helpful.
CREATE TABLE #TEMP
(SalesDate DATETime,
Amount float
)
INSERT INTO #TEMP
SELECT '2016-01-12', 12
UNION
SELECT '2016-01-13', 12
UNION
SELECT '2016-02-12', 12
UNION
SELECT '2016-03-12', 12
SELECT CONVERT(VARCHAR(7), SalesDate, 120) AS 'YYYY-MM',
SUM(Amount) as 'Amount'
FROM #Temp
GROUP BY CONVERT(VARCHAR(7), SalesDate, 120)
OUTPUT :
YYYY-MM Amount
------- ----------------------
2016-01 24
2016-02 12
2016-03 12
(3 row(s) affected)
For only Month Wise
SELECT RIGHT(CONVERT(VARCHAR(7), SalesDate, 120), 2) AS 'MM',
sum(Amount) as 'Amount'
from #Temp
group by RIGHT(CONVERT(VARCHAR(7), SalesDate, 120), 2)
Output:
MM Amount
---- ----------------------
01 24
02 12
03 12
(3 row(s) affected)

Capture first character of last group of 1s in a binary series

I have a series something like this:
Month J F M A M J J A S O N D
Status 1 0 0 1 0 1 0 0 1 1 1 1
Using t-SQL, I am trying to capture the month corresponding to the first 1 in the last group of 1s, i.e., September in this example.
Here is the code I'm using:
IF OBJECT_ID('tempdb..#Temp1') IS NOT NULL DROP TABLE #Temp1
;WITH PARTITIONED1 AS
(SELECT , t0.ID
, t0.Year_Month
, t0.Status
, LAST_VALUE(t0.Year_Month) OVER (PARTITION BY t0.ID ORDER BY t0.Year_Month) AS D_YM
, ROW_NUMBER() OVER (PARTITION BY t0.ID ORDER BY t0.Year_Month) AS rn1
FROM #Temp0 t0
However, this just returns the first occurence of a 1; January here.
I really can't figure this one out, so any help would be very much appreciated.
Carefull with
although the ordering is performed in a previous stage
The previous sorting does not guarantee the later processing!
Try something like this. It is a very simple approach where you rely on gapless IDs:
DECLARE #tbl TABLE(ID INT IDENTITY,Mnth VARCHAR(100),[Status] TINYINT);
INSERT INTO #tbl VALUES
('J',1)
,('F',0)
,('M',0)
,('A',1)
,('M',0)
,('J',1)
,('J',0)
,('A',0)
,('S',1)
,('O',1)
,('N',1)
,('D',1);
SELECT a.*
FROM #tbl AS a
WHERE a.ID=(SELECT MAX(b.ID)+1 FROM #tbl AS b WHERE b.[Status]=0)
this can also be used :
select top 1 Month from table t where Status=1
and not exists
(select id from table t1 where stat=0 and t1.id>t.id)
order by t.id
I might have overcomplicated this but not knowing the table structure I put the below together:
IF OBJECT_ID('tempdb..#Temp1') IS NOT NULL DROP TABLE #Temp1
CREATE TABLE #Temp1
(
Jan int,
Feb int,
Mar int,
Apr int,
May int,
June int,
July int ,
Aug int,
Sep int,
Oct int,
Nov int,
Dec int
)
insert into #temp1
select
1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 1
IF OBJECT_ID('tempdb..#monthTranslate') IS NOT NULL DROP TABLE #monthTranslate
create table #monthTranslate
(
MonthValue varchar(50),
MonthInt int
)
insert into #monthTranslate
select 'Jan',1
union all select 'Feb',2
union all select 'Mar',3
union all select 'Apr',4
union all select 'May',5
union all select 'June',6
union all select 'July',7
union all select 'Aug',8
union all select 'Sep',9
union all select 'OCt',10
union all select 'Nov',11
union all select 'Dec',12
--find the max month w\ 0 and add 1... becareful on null, it might return January incorrectly. I'd check for that in a a case statement
select max(b.MonthInt)+1
from
(
select
MonthPassVal, months , t.MonthInt
from
(
select Jan, Feb, Mar, Apr, May, June, July, Aug, Sep, Oct, Nov, Dec
from #temp1
) as r
Unpivot
(
MonthPassVal for Months
in (Jan, Feb, Mar, Apr, May, June, July, Aug, Sep, Oct, Nov, Dec)
) as u
inner join #monthTranslate t
on t.MonthValue = months
) as b
where
MonthPassVal=0

Insert subquery date according to day

I would like to insert subquery a date based on it day. Plus, each date can only be used four times. Once it reached fourth times, the fifth value will use another date of same day. In other word, use date of Monday of next week. Example, Monday with 6 JUNE 2016 to Monday with 13 JUNE 2016 (you may check the calendar).
I have a query of getting a list of date based on presentationdatestart and presentationdateend from presentation table:
select a.presentationid,
a.presentationday,
to_char (a.presentationdatestart + delta, 'DD-MM-YYYY', 'NLS_CALENDAR=GREGORIAN') list_date
from presentation a,
(select level - 1 as delta
from dual
connect by level - 1 <= (select max (presentationdateend - presentationdatestart)
from presentation))
where a.presentationdatestart + delta <= a.presentationdateend
and a.presentationday = to_char(a.presentationdatestart + delta, 'fmDay')
order by a.presentationdatestart + delta,
a.presentationid; --IMPORTANT!!!--
For example,
presentationday presentationdatestart presentationdateend
Monday 01-05-2016 04-06-2016
Tuesday 01-05-2016 04-06-2016
Wednesday 01-05-2016 04-06-2016
Thursday 01-05-2016 04-06-2016
The query result will list all possible dates between 01-05-2016 until 04-06-2016:
Monday 02-05-2016
Tuesday 03-05-2016
Wednesday 04-05-2016
Thursday 05-05-2016
....
Monday 30-05-2016
Tuesday 31-05-2016
Wednesday 01-06-2016
Thursday 02-06-2016 (20 rows)
This is my INSERT query :
insert into CSP600_SCHEDULE (studentID,
studentName,
projectTitle,
supervisorID,
supervisorName,
examinerID,
examinerName,
exavailableID,
availableday,
availablestart,
availableend,
availabledate)
select '2013816591',
'mong',
'abc',
'1004',
'Sue',
'1002',
'hazlifah',
2,
'Monday', //BASED ON THIS DAY
'12:00:00',
'2:00:00',
to_char (a.presentationdatestart + delta, 'DD-MM-YYYY', 'NLS_CALENDAR=GREGORIAN') list_date //FOR AVAILABLEDATE
from presentation a,
(select level - 1 as delta
from dual
connect by level - 1 <= (select max (presentationdateend - presentationdatestart)
from presentation))
where a.presentationdatestart + delta <= a.presentationdateend
and a.presentationday = to_char(a.presentationdatestart + delta, 'fmDay')
order by a.presentationdatestart + delta,
a.presentationid;
This query successfully added 20 rows because all possible dates were 20 rows. I would like modify the query to be able to insert based on availableDay and each date can only be used four times for each different studentID.
Possible outcome in CSP600_SCHEDULE (I am removing unrelated columns to ease readability):
StudentID StudentName availableDay availableDate
2013 abc Monday 01-05-2016
2014 def Monday 01-05-2016
2015 ghi Monday 01-05-2016
2016 klm Monday 01-05-2016
2010 nop Tuesday 02-05-2016
2017 qrs Tuesday 02-05-2016
2018 tuv Tuesday 02-05-2016
2019 wxy Tuesday 02-05-2016
.....
2039 rrr Monday 09-05-2016
.....
You may check the calendar :)
I think what you're asking for is to list your students and then batch them up in groups of 4 - each batch is then allocated to a date. Is that right?
In which case something like this should work (I'm using a list of tables as the student names just so I don't need to insert any data into a custom table) :
WITH students AS
(SELECT table_name
FROM all_tables
WHERE rownum < 100
)
SELECT
table_name
,SYSDATE + (CEIL(rownum/4) -1)
FROM
students
;
I hope that helps you
...okay, following your comments, I think this might be a better solution :
WITH students AS
(SELECT table_name student_name
FROM all_tables
WHERE rownum < 100
)
, dates AS
(SELECT TRUNC(sysdate) appointment_date from dual UNION
SELECT TRUNC(sysdate+2) from dual UNION
SELECT TRUNC(sysdate+4) from dual UNION
SELECT TRUNC(sysdate+6) from dual UNION
SELECT TRUNC(sysdate+8) from dual UNION
SELECT TRUNC(sysdate+10) from dual UNION
SELECT TRUNC(sysdate+12) from dual UNION
SELECT TRUNC(sysdate+14) from dual
)
SELECT
s.student_name
,d.appointment_date
FROM
--get a list of students each with a sequential row number, ordered by student name
(SELECT
student_name
,ROW_NUMBER() OVER (ORDER BY student_name) rn
FROM students
) s
--get a list of available dates with a sequential row number, ordered by date
,(SELECT
appointment_date
,ROW_NUMBER() OVER (ORDER BY appointment_date) rn
FROM dates
) d
WHERE 1=1
--allocate the first four students to date rownumber1, next four students to date rownumber 2...
AND CEIL(s.rn/4) = d.rn
;

T-SQL - Data Islands and Gaps - How do I summarise transactional data by month?

I'm trying to query some transactional data to establish the CurrentProductionHours value for each Report at the end of each month.
Providing there has been a transaction for each report in each month, that's pretty straight-forward... I can use something along the lines of the code below to partition transactions by month and then pick out the rows where TransactionByMonth = 1 (effectively, the last transaction for each report each month).
SELECT
ReportId,
TransactionId,
CurrentProductionHours,
ROW_NUMBER() OVER (PARTITION BY [ReportId], [CalendarYear], [MonthOfYear]
ORDER BY TransactionTimestamp desc
) AS TransactionByMonth
FROM
tblSource
The problem that I have is that there will not necessarily be a transaction for every report every month... When that's the case, I need to carry forward the last known CurrentProductionHours value to the month which has no transaction as this indicates that there has been no change. Potentially, this value may need to be carried forward multiple times.
Source Data:
ReportId TransactionTimestamp CurrentProductionHours
1 2014-01-05 13:37:00 14.50
1 2014-01-20 09:15:00 15.00
1 2014-01-21 10:20:00 10.00
2 2014-01-22 09:43:00 22.00
1 2014-02-02 08:50:00 12.00
Target Results:
ReportId Month Year ProductionHours
1 1 2014 10.00
2 1 2014 22.00
1 2 2014 12.00
2 2 2014 22.00
I should also mention that I have a date table available, which can be referenced if required.
** UPDATE 05/03/2014 **
I now have query which is genertating results as shown in the example below but I'm left with islands of data (where a transaction existed in that month) and gaps in between... My question is still similar but in some ways a little more generic - What is the best way to fill gaps between data islands if you have the dataset below as a starting point?
ReportId Month Year ProductionHours
1 1 2014 10.00
1 2 2014 12.00
1 3 2014 NULL
2 1 2014 22.00
2 2 2014 NULL
2 3 2014 NULL
Any advice about how to tackle this would be greatly appreciated!
Try this:
;with a as
(
select dateadd(m, datediff(m, 0, min(TransactionTimestamp))+1,0) minTransactionTimestamp,
max(TransactionTimestamp) maxTransactionTimestamp from tblSource
), b as
(
select minTransactionTimestamp TT, maxTransactionTimestamp
from a
union all
select dateadd(m, 1, TT), maxTransactionTimestamp
from b
where tt < maxTransactionTimestamp
), c as
(
select distinct t.ReportId, b.TT from tblSource t
cross apply b
)
select c.ReportId,
month(dateadd(m, -1, c.TT)) Month,
year(dateadd(m, -1, c.TT)) Year,
x.CurrentProductionHours
from c
cross apply
(select top 1 CurrentProductionHours from tblSource
where TransactionTimestamp < c.TT
and ReportId = c.ReportId
order by TransactionTimestamp desc) x
A similar approach but using a cartesian to obtain all the combinations of report ids/months.
in the first step.
A second step adds to that cartesian the maximum timestamp from the source table where the month is less or equal to the month in the current row.
Finally it joins the source table to the temp table by report id/timestamp to obtain the latest source table row for every report id/month.
;
WITH allcombinations -- Cartesian (reportid X yearmonth)
AS ( SELECT reportid ,
yearmonth
FROM ( SELECT DISTINCT
reportid
FROM tblSource
) a
JOIN ( SELECT DISTINCT
DATEPART(yy, transactionTimestamp)
* 100 + DATEPART(MM,
transactionTimestamp) yearmonth
FROM tblSource
) b ON 1 = 1
),
maxdates --add correlated max timestamp where the month is less or equal to the month in current record
AS ( SELECT a.* ,
( SELECT MAX(transactionTimestamp)
FROM tblSource t
WHERE t.reportid = a.reportid
AND DATEPART(yy, t.transactionTimestamp)
* 100 + DATEPART(MM,
t.transactionTimestamp) <= a.yearmonth
) maxtstamp
FROM allcombinations a
)
-- join previous data to the source table by reportid and timestamp
SELECT distinct m.reportid ,
m.yearmonth ,
t.CurrentProductionHours
FROM maxdates m
JOIN tblSource t ON t.transactionTimestamp = m.maxtstamp and t.reportid=m.reportid
ORDER BY m.reportid ,
m.yearmonth

T-SQL get months from ranges of date

I have a Table with id and start date and end date. i want insert into another table, end of each month between the start data and end date and the ID, e.g.
ID Start Date End Date
1 2012-01-01 2012-03-31
2 2012-10-01 2012-12-31
Results
ID MONTH END
1 2012-01-31
1 2012-02-29
1 2012-03-31
2 2012-10-31
2 2012-11-30
2 2012-12-31
This answer makes some assumptions - no end-dates greater than start-dates, but you should see how it works. It creates a recursive union CTE and uses that to figure out the end dates
CREATE TABLE #Dates
(
ID INT IDENTITY PRIMARY KEY,
START_DATE DATETIME2(0) NOT NULL,
END_DATE DATETIME2(0) NOT NULL
)
INSERT INTO #Dates VALUES ('2012-01-01', '2012-03-31'), ('2012-10-01','2012-12-31')
WITH MONTHS ([ID],[Month],[Date], [End])
AS
(
SELECT ID, DATEPART(m,START_DATE) AS [Month], START_DATE AS [Date], DATEADD(s,-1,DATEADD(m,DATEDIFF(m,0,START_DATE)+1,0)) as [End]
FROM #Dates
UNION ALL
SELECT D.ID, DATEPART(m,DATEADD(m,1,[Date])),DATEADD(m,1,[Date]), DATEADD(s,-1,DATEADD(m,DATEDIFF(m,0,DATEADD(m,1,[Date]))+1,0)) as [End]
FROM #Dates D
INNER JOIN MONTHS M
ON D.ID = M.ID
WHERE DATEADD(m,1,[Date]) < [END_DATE]
)
SELECT *
FROM MONTHS ORDER BY ID, Date
DROP TABLE #Dates