Get dates with in consecutive 50 days of given date - tsql

Activity table:
create table #activity(id int, begin_date datetime, end_date datetime)
insert into #activity values(1, '1/1/2017', '1/31/2017')
insert into #activity values(1, '9/1/2017', '9/15/2017')
insert into #activity values(1, '4/1/2017', '4/15/2017')
insert into #activity values(1, '2/5/2017', '2/15/2017')
insert into #activity values(1, '8/1/2017', '8/31/2017')
Insert into #activity values(2, '11/1/2016', '11/15/2016')
Now input date is 12/1/2016 and id, would like to get all activities within 50 days after 12/1/2016. Query should return activities with begin dates 1/1/2017, 2/5/2017 (because this is within 50 days of 1/31/2017), and 4/1/17.
8/1/2017 and 9/1/2017 of id 1 shouldn't be selected 8/1 is not with in 50 days of 4/15 and 50 day cycle was broken.
TIA

The OP says:
would like to get all activities within 50 days after 12/1/2016
one possible query to achieve that result would be
-- get all activities with a begin_date within 50 days of input_date
select *
from #activity as a
where #input_date <= a.begin_date and a.begin_date < dateadd(day, 50, #input_date)
However, the OP then says:
Query should return activities with begin dates 1/1/2017, 2/5/2017 (because this is within 50 days of 1/31/2017), and 4/1/17. 8/1/2017 and 9/1/2017 of id 1 shouldn't be selected 8/1 is not with in 50 days of 4/15 and 50 day cycle was broken.
This would indicate that you want to find all sequential activities starting after 12/1/2016 where the gap between sequential activities is less than 50 days.
One possible approach for this is to use the lag function. An example of how to use the lag function on this problem is:
select
a.*
, lag(a.end_date, 1, #input_date) over (order by a.end_date) as previous_end
, datediff(day, lag(a.end_date, 1, #input_date) over (order by a.end_date), a.begin_date) as previous_end_to_this_begin
from #activity as a
where #input_date <= a.begin_date
order by a.begin_date
Simplifying that slightly would produce this:
-- get all activities in a row where the gap between activities is less than 50
select * from #activity as a where #input_date <= a.begin_date and a.begin_date < (
select
min(a.begin_date) as first_begin_to_not_include
from
(
select
a.begin_date
, datediff(day, lag(a.end_date, 1, #input_date) over (order by a.end_date), a.begin_date) as previous_end_to_this_begin
from #activity as a
where #input_date <= a.begin_date
) as a
where a.previous_end_to_this_begin > 50
)
order by a.begin_date

Related

Calculate past 3 month average for every past 3rd month

I am using SQL Server 2014. I have a table like this
create table revenue (id varchar(2), trasdate date, revenue int);
insert into revenue(id, trasdate, revenue)
values ('aa', '2018/09/01', 1234.5),
('aa' , '2018/08/04', 450),
('aa', '2018/07/03',500),
('aa', '2018/06/04',600),
('ab', '2018/09/01', 1234.5),
('ab' , '2018/08/04', 450),
('ab', '2018/07/03',500),
('ab', '2018/06/04',600),
('ab', '2018/05/03', 200),
('ab', '2018/04/02', 150),
('ab', '2018/03/01', 350),
('ab', '2018/02/05', 700),
('aa', '2018/01/07', 400)
;
I am preparing a SQL query to create a SSRS report. I want to calculate a past 3 month average for current and every past 3rd month with result like below. As we are in month of September right now. The result should show something like this:
**id Period Revenue_3Mon**
aa March-May 233
aa June-Aug 516
ab March-May 233
ab June-Aug 516
Though I can figure out about the Period column. I was mainly focussing on getting the Revenue_3Mon. So I initially tried with the below query after some googling. But this query throws an error as incorrect syntax near 'rows' and if I remove rows from the query then it throws an error as Incorrect syntax near the keyword 'between'. And incorrect syntax near i.
select i.id,i.mon,
avg([i.mon_revenue]) over (partition by i.id, i.mon order by [i.id],
[i.mon] rows between 3 preceding and 1 preceding row) as revenue_3mon --
-- using 3 preceding and 1 preceding row you exclude the current row
from (select a.id, month(a.trasdate) as mon,
sum(a.revenue) as mon_revenue
from revenue a
group by a.id, month(a.trasdate)) i
group by i.id, i.mon
order by i.id,i.mon;
After few efforts, I gave up on this query and came up with new solution which was a bit close to my expectation (after lots of trial and errors).
Declare #count as int;
declare #max as int;
set #count = 4
declare #temp as table (id varchar(2), monthoftrasdate int, revenue int,
[3monavg] int);
SET #MAX = (SELECT distinct MAX(a.ROWNUM) FROM (SELECT id, month(trasdate)
as mon, SUM(revenue) TotalRevenue,
-- sum(revenue) as mon_revenue,
ROW_NUMBER() OVER(PARTITION BY ID ORDER BY MONTH(TRASDATE)) AS ROWNUM
FROM revenue
GROUP BY ID, MONTH(TRASDATE)
) A GROUP BY A.ID);
while (#count <= #max )
begin
WITH CTE AS (
SELECT id, month(trasdate) as mon, SUM(revenue) TotalRevenue,
-- sum(revenue) as mon_revenue,
ROW_NUMBER() OVER(PARTITION BY ID ORDER BY MONTH(TRASDATE)) AS
ROWNUM
FROM revenue
GROUP BY ID, MONTH(TRASDATE)
)
insert into #temp
SELECT A.ID,A.MON, a.TotalRevenue
,( SELECT avg(b.TotalRevenue) as avgrev
FROM CTE B
WHERE B.ROWNUM BETWEEN A.ROWNUM-3 AND A.ROWNUM-1
AND A.ID = B.ID --AND A.mon = B.mon
--and b.ROWNUM < a.ROWNUM
and (a.mon > 3 and a.ROWNUM > 3)
GROUP BY B.id
) AS REVENUE_3MON
FROM CTE A
set #count = #count + 1
end
select distinct a.* from #temp a
The reason I had to use 'distinct' is because the query was showing duplicate records for every id and every month. So far the result shows like below
id MonthofTrasdate Revenue 3MonAvg
aa 1 400 NULL
aa 2 700 NULL
aa 3 350 NULL
aa 4 150 483
aa 5 200 400
aa 6 600 233
aa 7 500 316
aa 8 450 433
aa 9 1234 516
ab 1 400 NULL
ab 2 700 NULL
ab 3 350 NULL
ab 4 150 483
ab 5 200 400
ab 6 600 233
ab 7 500 316
ab 8 450 433
ab 9 1234 516
This pulls out past 3 month average for every month. But i will just manipulate the rest on SSRS the way i want it.
As currently my table has no data for previous year. This works for me showing the appropriate result for next couple of months for now. But my concern is when I have to show my boss for next year Jan, Feb and March then it should be able to pull also for these months as well like Oct-Dec (Previous year), Nov-Jan and Dec - Feb. I am struggling to figure out the proper way to put this in my query.
Can you please help me out with this query? And also let me know what is wrong with my former query.
Problems with your first attempt:
You enclosed some of the aliases and column names in square brackets like [i.mon_revenue]. There is no need for square brackets, but if you want to use them, you have to break them up at the dot: [i].[mon_revenue].
In your window function expression, there is one row too many (in the end).
Window functions are applied at the very end (after the rest of the respective query), so you also have to include i.mon_revenue in your GROUP BY clause of the outer query.
Knowing that the inner query will produce one row per id and mon, there will never be preceding rows in an id-mon partition. Therefore, you must not partition by both, but only by id.
To simplify the query after resolving the issues: ordering by a partition column generally makes no sense, and since - as already mentioned - the inner query returns unique id-mon combinations, you don't have to group by these in the outer query. Looking at that query, we see that the outer query just directly selects and uses the values from the inner query, which makes a separation in two queries unneccessary. So, in fact, you wanted to perform the following query, which will produce the rolling 3-month average (I added the monthly TotalRevenue as well):
SELECT id, MONTH(trasdate) AS mon, SUM(revenue) AS TotalRevenue,
AVG(SUM(revenue)) OVER (PARTITION BY id ORDER BY MONTH(trasdate) ROWS BETWEEN 3 PRECEDING AND 1 PRECEDING) AS revenue_3mon
FROM revenue
GROUP BY id, MONTH(trasdate)
ORDER BY id, MONTH(trasdate);
Suggestions on your second attempt:
When calculating the #MAX value, you rely on the fact that each id has revenues for the same number of months. Are you sure?
The code inside the WHILE loop does not depend on #count, so it will add the same data into the #temp table multiple times, which is probably the reason why you thought you needed a DISTINCT. Therfore: No need for the variables, no need for a loop and a #temp, no need for DISTINCT.
The conditions A.mon > 3 and A.rownum > 3 are redundant with your current data. In general, I guess, you don't want to explicitly excluse the months from January to March, so A.mon > 3 should be removed. A.rownum > 3 could be removed, too, unless you really don't want to see a 3-month average when there are only 2 preceding months or less.
As the subquery for the average is restricted to only one id, there's no need for a GROUP BY.
Since the ROW_NUMBER function doesn't care about gaps in the months, I suggest to use a different numbering function, for example DATEDIFF(month, MAX(trasdate), GETDATE()) AS mnum. Of course, the comparison in the WHERE clause of the subquery then has to be changed to B.mnum BETWEEN A.mnum+1 AND A.mnum+3.
So, your second attempt can be reduced to this, which will produce the same result as the above, at least with your sample data, where no gaps in the months exist:
WITH CTE AS (
SELECT id, MONTH(trasdate) AS mon, SUM(revenue) AS TotalRevenue,
DATEDIFF(month, MAX(trasdate), GETDATE()) AS mnum
FROM revenue
GROUP BY id, MONTH(trasdate)
)
SELECT id, mon, TotalRevenue
, (SELECT AVG(B.TotalRevenue)
FROM CTE B
WHERE B.mnum BETWEEN A.mnum+1 AND A.mnum+3
AND A.id = B.id
) AS revenue_3mon
FROM CTE A
ORDER BY id, mnum DESC;
Now, guess what, an expression like my mnum using DATEDIFF increases by one every month as we move to the past, regardless of a change of years, so this might be useful for grouping as well, whether you want to (or can?) use Window functions or not:
With OVER()
SELECT id, MONTH(MIN(trasdate)) AS mon, YEAR(MIN(trasdate)) AS yr, SUM(revenue) AS TotalRevenue,
AVG(SUM(revenue)) OVER (PARTITION BY id ORDER BY MIN(trasdate) ROWS BETWEEN 3 PRECEDING AND 1 PRECEDING) AS revenue_3mon
FROM revenue
GROUP BY id, DATEDIFF(month, trasdate, GETDATE())
ORDER BY id, DATEDIFF(month, trasdate, GETDATE()) DESC;
Without OVER()
WITH CTE AS (
SELECT id, MIN(trasdate) AS min_dt, SUM(revenue) AS TotalRevenue,
DATEDIFF(month, trasdate, GETDATE()) AS mnum
FROM revenue
GROUP BY id, DATEDIFF(month, trasdate, GETDATE())
)
SELECT id, MONTH(min_dt) AS mon, YEAR(min_dt) AS yr, TotalRevenue
, (SELECT AVG(B.TotalRevenue)
FROM CTE B
WHERE B.mnum BETWEEN A.mnum+1 AND A.mnum+3
AND A.id = B.id
) AS revenue_3mon
FROM CTE A
ORDER BY id, mnum DESC;
Both queries allow for retrieving the minimum and maximum date for each period (including month and year).
If you instead wanted what you originally posted under The result should show something like this (just grouping by previous 3-months intervals), you just would have to group your original revenue table by id and (DATEDIFF(month, trasdate, GETDATE())-1)/3 (filtering WHERE DATEDIFF(month, trasdate, GETDATE()) > 0). If so, this kind of grouping and aggregation could, of course, be done also by the Report Server.
I think this should do what you want:
select r.*,
avg(r.mon_revenue) over (partition by r.id
order by r.mon_min
rows between 3 preceding and 1 preceding row
) as revenue_3mon
-- using 3 preceding and 1 preceding row you exclude the current row
from (select r.id, month(r.trasdate) as mon,
min(r.trasdate) as mon_min,
sum(r.revenue) as mon_revenue
from revenue r
group by r.id, year(r.trasdate), month(r.trasdate)
) 4
order by r.id, r.mon, r.mon_min;
Notes:
I fixed the code so it recognizes years as well as dates.
The expression [i.mon_revenue] is not a valid column reference (in your case). You have no column with the name "i.mon_revenue" (with the . in the name).
I changed the column alias to r to match the table.
I added a date column for each month to make it easier to express the ordering.
The outer group by is not necessary.
There are several syntax errors in your code. This should give you what you need. The inner query is the important bit but hopefully this will be enough to get you on your way.
I switch our the temp table for variable and changed the revenue column to not be INT as you have decimal values in there but other than that your original sample table is unchanged
DECLARE #revenue table (id varchar(2), trasdate date, revenue float)
insert into #revenue(id, trasdate, revenue)
values ('aa', '2018/09/01', 1234.5),
('aa' , '2018/08/04', 450),
('aa', '2018/07/03',500),
('aa', '2018/06/04',600),
('ab', '2018/09/01', 1234.5),
('ab' , '2018/08/04', 450),
('ab', '2018/07/03',500),
('ab', '2018/06/04',600),
('ab', '2018/05/03', 200),
('ab', '2018/04/02', 150),
('ab', '2018/03/01', 350),
('ab', '2018/02/05', 700),
('aa', '2018/01/07', 400)
SELECT
*
FROM
(
SELECT
*
, MONTH(trasdate) as MonthNumber
, AVG(revenue) OVER (PARTITION BY id
ORDER BY
id
, MONTH(trasdate) ROWS BETWEEN 3 PRECEDING AND 1 PRECEDING) as ThreeMonthAvg
FROM #revenue
) a
WHERE MONTH(GETDATE()) - MonthNumber IN (0, 3, 6, 9)
This gives the following results
aa 2018-06-04 600 6 400
aa 2018-09-01 1234.5 9 516.666666666667
ab 2018-03-01 350 3 700
ab 2018-06-04 600 6 233.333333333333
ab 2018-09-01 1234.5 9 516.666666666667

How to find the First, Second, Third and Fourth Saturday in month?

How do I find the first, second, third and fourth saturday of the month?
Ex.: I want to end up with this format...
Blockquote
YYYY, MM, Week#1
Blockquote
YYYY, MM, Week#2
Blockquote
Thanks,
This solution does not depend on Datefirst setting.
declare #d datetime = getdate();
select
dateadd(dd, n, firstSaturday)
from (
select
firstSaturday = dateadd(day, 7-(##datefirst+datepart(weekday, dateadd(day,-1, convert(char(6),#d,112)+'01')))%7, dateadd(day,-1, convert(char(6),#d,112)+'01'))
) t
cross apply (values (0), (7), (14), (21)) q(n)
Here is one way to do it, using a stacked cte to create an inline tally table, with another cte on top of that to generate the months calendar.
Please note that you can change the GETDATE() in the first row code to any date you want (even if it's in the middle of the month) and the code will produce all the Saturdays in that month.
-- Get the current month's start date
DECLARE #MonthStart datetime = DATEADD(MONTH, (DATEDIFF(MONTH, 0, GETDATE())), 0)
;WITH lv0 AS (SELECT 0 g UNION ALL SELECT 0)
,lv1 AS (SELECT 0 g FROM lv0 a CROSS JOIN lv0 b) -- 4
,lv2 AS (SELECT 0 g FROM lv1 a CROSS JOIN lv1 b) -- 16
,lv3 AS (SELECT 0 g FROM lv2 a CROSS JOIN lv2 b) -- 256
,Tally (n) AS (SELECT ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) FROM lv3)
-- gets all the dates in the current month
,CurrentMonth AS (SELECT TOP (32) dateadd(day, n-1, #MonthStart) As TheDate
FROM Tally
WHERE MONTH(dateadd(day, n-1, #MonthStart)) = MONTH(#MonthStart)
ORDER BY n)
-- gets all the Saturday dates of the current month
SELECT TheDate, DATENAME(WEEKDAY, TheDate)
FROM CurrentMonth
WHERE DATEPART(WEEKDAY, TheDate) = 7 -- Depending on server settings!
If you already have a numbers table, you can use it instead of the stacked cte. If you don't know what is a numbers table and why you should have one, read The "Numbers" or "Tally" Table: What it is and how it replaces a loop by Jeff Moden
You can try this.
SET DATEFIRST 1
DECLARE #MonthId INT = 5
DECLARE #FirstDayOfTheMonth DATE = CONCAT(YEAR(GETDATE()), RIGHT(CONCAT('00', #MonthId),2), '01')
DECLARE #SaturdayId INT = 6
SELECT
DATEADD(DAY, #SaturdayId + WK.ID - DATEPART(WEEKDAY, #FirstDayOfTheMonth), #FirstDayOfTheMonth)
FROM ( VALUES(0),(7),(14),(21),(28)) AS WK(ID)
WHERE
MONTH(DATEADD(DAY, #SaturdayId + WK.ID- DATEPART(WEEKDAY, #FirstDayOfTheMonth),#FirstDayOfTheMonth)) = #MonthId

Last Working Day is showing null while on weekend

Here is my code but its showing null while today is friday. But I would like to get last working day.
-- Insert statements for procedure here
--Below is the param you would pass
DECLARE #dateToEvaluate date=GETDATE();
--Routine
DECLARE #startDate date=CAST('1/1/'+CAST(YEAR(#dateToEvaluate) AS char(4)) AS date); -- let's get the first of the year
WITH
tally(n) AS (SELECT ROW_NUMBER() OVER (ORDER BY (SELECT NULL))-1 FROM sys.all_columns),
dates AS (
SELECT ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) AS dt_id,
DATEADD(DAY,n,#startDate) AS dt,
DATENAME(WEEKDAY,DATEADD(DAY,n,#startdate)) AS dt_name
FROM tally
WHERE n<366 --arbitrary
AND DATEPART(WEEKDAY,DATEADD(DAY,n,#startDate)) NOT IN (6)
AND DATEADD(DAY,n,#startDate) NOT IN (SELECT CAST(HolidayDate AS date) FROM Holiday)),
curr_id(id) AS (SELECT dt_id FROM dates WHERE dt=#dateToEvaluate)
SELECT d.dt
FROM dates AS d
CROSS JOIN
curr_id c
WHERE d.dt_id+1=c.id
The code below will take any date and "walk backward" to find the previous week day (M-F) which is not in the #holidays table.
declare #currentdate datetime = '2015-03-22'
declare #holidays table (holiday datetime)
insert #holidays values ('2015-03-20')
;with cte as (
select
#currentdate k
union all
select
dateadd(day, -1, k)
from cte
where
k = #currentdate
or ((datepart(dw, k) + ##DATEFIRST - 1 - 1) % 7) + 1 > 5 --determine day of week independent of culture
or k in (select holiday from #holidays)
)
select min(k) from cte
The dates table doesn't have any FRIDAY dates in it. Change the NOT IN (6) to NOT IN (1, 7). This will remove Saturday and Sundays from the dates table.

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

Calculation of total duration of events for a day

We have a table called Events, with columns Id(int), EventDate(DateTime), EventStart(datetime) and EventEnd(datetime).
All events start and end on a single day (i.e. no events end the next day), however events in a given date may overlap between them (including one of them could cover another entirely).
Any number of events may occur for a given date.
I would like to, for a single day calculate the total duration during which at least one event was running in T-SQL. I can select the events on a given date, and have even written a function returning true if two events are overlapping and false if not.
I am stuck however in how to take the records in pairs and run them through my function, adding the durations appropriately until I run out of events.
Can you help?
Chris
Try this:
--test table
declare #t table(fromt datetime, tot datetime)
--test data
insert #t values('2011-01-01 10:00', '2011-01-01 11:00')
insert #t values('2011-01-01 10:00', '2011-01-01 10:05')
insert #t values('2011-01-01 10:30', '2011-01-01 11:30')
insert #t values('2011-01-01 12:00', '2011-01-01 12:30')
insert #t values('2011-01-02 12:00', '2011-01-02 12:30')
--query
;with f as
(
select distinct fromt from #t t
where not exists(select 1 from #t where t.fromt > fromt and t.fromt < tot)
), t as
(
select distinct tot from #t t
where not exists(select 1 from #t where t.tot >= fromt and t.tot < tot)
), s as
(
select datediff(day, 0, fromt) d, datediff(second, fromt, (select min(tot)
from t where f.fromt < tot and datediff(day, f.fromt, tot) = 0)) sec
from f
)
select dateadd(day, 0, d) day, sum(sec)/60 [minutes]
from s
group by d
order by d
Result:
day minutes
----------------------- -------
2011-01-01 00:00:00.000 120
2011-01-02 00:00:00.000 30