SQL fill next date (month) with loop - sql

I have input table, and need to add missing dates, but not to max, but up to next available month.
so I need to use loop.
SET #mindate = '2021.01'
SET #maxdate = CAST( GETDATE() AS Date ) --date today as max date
while
begin
if #mindate => #maxdate
begin
break
end
set #mindate = #mindate + 1
end
then i can get 1+.. but it does not stop to 7 month
so i totally got stuck with writing loop.
Data table :
could anybody help on code? as most examples are with joins, to data tables, or to one max value.

Paul, I'm assuming that you forgot to specify the month in your mock data.
I hope the code below may help you understand how non-trivial is what you are trying to accomplish :-) Kudos for your will to get rid of loops.
To make it better, I propose a denormalization (CAUTION!):
create another column price_valid_until
the latest prices records will have price_valid_until = '21000101' (aka, far away in the future)
when registering a new price, update the previous with new price_valid_from - 1 day
Here's the solution, with a pretty complex, but efficient query (http://sqlfiddle.com/#!18/4ab23/4)
create table price_history(
SKU varchar(255),
price_valid_from date,
price decimal(16, 2)
)
insert into price_history
values
('a', '20210101', 10),
('a', '20210107', 12),
('b', '20210102', 4),
('b', '20210110', 2),
('b', '20210214', 5);
-- This fiddler won't let me initialize and reference:
--
-- declare
-- #from_date date,
-- #to_date date;
--
-- select
-- #from_date = min(date_from),
-- #to_date = max(date_from)
-- from price_history
with
date_range as(
select
min(price_valid_from) as from_date,
--
eomonth(
max(price_valid_from)
) as to_date
from price_history
),
--
all_dates as(
select from_date as date_in_range
from date_range
-- ----------
union all
-- ----------
select dateadd(day, 1, date_in_range)
from all_dates
where
date_in_range < (
select to_date
from date_range
)
),
--
price_history_boundaries as(
select
ph.SKU,
ph.price,
--
ph.price_valid_from,
-- The latest price, so far, is valid until 01/01/2100
coalesce(
dateadd(
day,
-1,
min(ph_next.price_valid_from)
),
'21000101'
) as price_valid_until
from
price_history ph
left outer join price_history ph_next
on(
ph_next.SKU = ph.SKU
and ph_next.price_valid_from > ph.price_valid_from
)
group by ph.SKU, ph.price_valid_from, ph.price
)
select
phb.SKU,
ad.date_in_range,
phb.price
from
all_dates ad
inner join price_history_boundaries phb
on(
phb.price_valid_from <= ad.date_in_range
and phb.price_valid_until >= ad.date_in_range
)
order by phb.SKU, ad.date_in_range

You can easily achieve your desired result by creating list of dates from which to join to. Here I've used a recursive CTE to create a range of dates, adding 1 month per iteration up to the current date.
It's then a simple matter of joining to your source data, here lead() is handy for limiting the joined rows. Also, assuming SQL Server from the usage of Getdate:
declare #start date=(select Min([date]) from sourcetable);
with m as (
select 1 num, #start [Date]
union all
select num+1 , DateAdd(month,1,m.[date])
from m
where DateAdd(month,1,m.[date]) <= GetDate()
), t as (
select *, Lead([date],1,GetDate()) over (order by [date]) NextDate
from sourcetable
)
select m.[Date], t.sku, t.price
from m
join t on m.[date] >= t.[date] and m.[date] < t.nextdate
See Working Fiddle

Related

SQL Cross Join getting all dates between date range

I have a table with the following structure:
ID: StartDate: EndDate
I want to show all dates in the date range for each ID.
Eg
ID = 1: StartDate = 01/01/2018: EndDate = 03/01/2018
ID: 1 01/01/2018
ID: 1 02/01/2018
ID: 1 03/01/2018
I think i need to use a cross join but im unsure how to create this for multiple rows?
Here is the CTE for SQL Server, the syntax is somewhat different:
declare #startdate date = '2018-01-01';
declare #enddate date = '2018-03-18';
with
dates as (
select #startdate as [date]
union all
select dateadd(dd, 1, [date]) from dates where [date] < #enddate
)
select [date] from dates
So i ended up using a date table and just cross referencing that
select *
from Date d
inner join WorkingTable w
on d.Date >= w.StartDate
and d.date < w.EndDate
In standard SQL you can use a recursive CTE:
with recursive dates as (
select date '2018-01-01' as dte
union all
select dte + interval '1 day'
from dates
where dte < date '2018-01-03'
)
select dte
from dates;
The exact syntax (whether recursive is needed and date functions) differ among databases. Not all databases support this standard functionality.
Now got this for only one id..,
create table #dateTable(id int, col1 date, col2 date)
insert into #dateTable values(1,'05-May-2018','08-May-2018') ,(2,'05-May-2018','05-May-2018')
select *from #dateTable
with cte(start, ends) as(
select start = (select top 1 col1 from #dateTable), ends = (select top 1 col2 from #dateTable)
union all
select DATEADD(dd,1,start),ends from cte where start <> ends
)select start from cte option (maxrecursion 10)
I'm still working... I update soon...!

SELECT DateTime not in SQL

I have the following table:
oDateTime pvalue
2017-06-01 00:00:00 70
2017-06-01 01:00:00 65
2017-06-01 02:00:00 90
ff.
2017-08-01 08:00:00 98
The oDateTime field is an hourly data which is impossible to have a duplicate value.
My question is, how can I know if the oDateTime data is correct? I meant, I need to make sure the data is not jump? It should be always 'hourly' base.
Am I missing the date? Am I missing the time?
Please advice. Thank you.
Based on this answer, you can get the missing times form your table MyLogTable it like this:
DECLARE #StartDate DATETIME = '20170601', #EndDate DATETIME = '20170801'
SELECT DATEADD(hour, nbr - 1, #StartDate)
FROM ( SELECT ROW_NUMBER() OVER ( ORDER BY c.object_id ) AS Nbr
FROM sys.columns c
) nbrs
WHERE nbr - 1 <= DATEDIFF(hour, #StartDate, #EndDate) AND
NOT EXISTS (SELECT 1 FROM MyLogTable WHERE DATEADD(hour, nbr - 1, #StartDate)= oDateTime )
If you need to check longer period, you can just add CROSS JOIN like this
FROM sys.columns c
CROSS JOIN sys.columns c1
It enables you to check much more than cca thousand records (rowcount of sys.columns table) in one query.
Since your table is not having any unique id number, use a row_number() to get the row number in the cte , then perform an self inner join with the row id and next id ,take the difference of oDateTime accordingly, this will show exactly which row do not have time difference of one hour
;with cte(oDateTime,pValue,Rid)
As
(
select *,row_number() over(order by oDateTime) from [YourTableName] t1
)
select *,datediff(HH,c1.oDateTime,c2.oDateTime) as HourDiff from cte c1
inner join cte c2
on c1.Rid=c2.Rid-1 where datediff(HH,c1.oDateTime,c2.oDateTime) >1
You could use DENSE_RANK() for numbering the hours in a day from 1 to 24. Then all you have to do is to check whether the max rank is 24 or not for a day. if there is at least one entry for each hour, then dense ranking will have max value of 24.
Use the following query to find the date when you have a oDateTime missing.
SELECT [date]
FROM
(
SELECT *
, CAST(oDateTime AS DATE) AS [date]
, DENSE_RANK() OVER(PARTITION BY CAST(oDateTime AS DATE) ORDER BY DATEPART(HOUR, oDateTime)) AS rank_num
FROM Test
) AS t
GROUP BY [date]
HAVING(MAX(rank_num) != 24);
If you need validation for each row of oDateTime, you could do self join based on rank and get the missing hour for each oDateTime.
Perhaps you are looking for this? This will return dates having count < 24 - which indicates a "jump"
;WITH datecount
AS ( SELECT CAST(oDateTime AS DATE) AS [date] ,
COUNT(CAST(oDateTime AS DATE)) AS [count]
FROM #temp
GROUP BY ( CAST(oDateTime AS DATE) )
)
SELECT *
FROM datecount
WHERE [count] < 24;
EDIT: Since you changed the requirement from "How to know if there is missing" to "What is the missing", here's an updated query.
DECLARE #calendar AS TABLE ( oDateTime DATETIME )
DECLARE #min DATETIME = (SELECT MIN([oDateTime]) FROM #yourTable)
DECLARE #max DATETIME = (SELECT MAX([oDateTime]) FROM #yourTable)
WHILE ( #min <= #max )
BEGIN
INSERT INTO #calendar
VALUES ( #min );
SET #min = DATEADD(hh, 1, #min);
END;
SELECT t1.[oDateTime]
FROM #calendar t1
LEFT JOIN #yourTable t2 ON t1.[oDateTime] = t2.[oDateTime]
GROUP BY t1.[oDateTime]
HAVING COUNT(t2.[oDateTime]) = 0;
I first created a hourly calendar based on your MAX and MIN Datetime, then compared your actual table to the calendar to find out if there is a "jump".

Find missing date as compare to calendar

I am explain problem in short.
select distinct DATE from #Table where DATE >='2016-01-01'
Output :
Date
2016-11-23
2016-11-22
2016-11-21
2016-11-19
2016-11-18
Now i need to find out missing date a compare to our calender dates from year '2016'
i.e. Here date '2016-11-20' is missing.
I want list of missing dates.
Thanks for reading this. Have nice day.
You need to generate dates and you have to find missing ones. Below with recursive cte i have done it
;WITH CTE AS
(
SELECT CONVERT(DATE,'2016-01-01') AS DATE1
UNION ALL
SELECT DATEADD(DD,1,DATE1) FROM CTE WHERE DATE1<'2016-12-31'
)
SELECT DATE1 MISSING_ONE FROM CTE
EXCEPT
SELECT * FROM #TABLE1
option(maxrecursion 0)
Using CTE and get all dates in CTE table then compare with your table.
CREATE TABLE #yourTable(_Values DATE)
INSERT INTO #yourTable(_Values)
SELECT '2016-11-23' UNION ALL
SELECT '2016-11-22' UNION ALL
SELECT '2016-11-21' UNION ALL
SELECT '2016-11-19' UNION ALL
SELECT '2016-11-18'
DECLARE #DATE DATE = '2016-11-01'
;WITH CTEYear (_Date) AS
(
SELECT #DATE
UNION ALL
SELECT DATEADD(DAY,1,_Date)
FROM CTEYear
WHERE _Date < EOMONTH(#DATE,0)
)
SELECT * FROM CTEYear
WHERE NOT EXISTS(SELECT 1 FROM #yourTable WHERE _Date = _Values)
OPTION(maxrecursion 0)
You need to generate the dates and then find the missing ones. A recursive CTE is one way to generate a handful of dates. Another way is to use master..spt_values as a list of numbers:
with n as (
select row_number() over (order by (select null)) - 1 as n
from master..spt_values
),
d as (
select dateadd(day, n.n, cast('2016-01-01' as date)) as dte
from n
where n <= 365
)
select d.date
from d left join
#table t
on d.dte = t.date
where t.date is null;
If you are happy enough with ranges of missing dates, you don't need a list of dates at all:
select date, (datediff(day, date, next_date) - 1) as num_missing
from (select t.*, lead(t.date) over (order by t.date) as next_date
from #table t
where t.date >= '2016-01-01'
) t
where next_date <> dateadd(day, 1, date);

How can I sum values per day and then plot them on calendar from start date to last date

I have a table, part of which is given below. It contain multiple values (durations) per day. I need two things 1) addition of durations per day. 2) plotting them on calendar in such a way that startdate is first_date from the table and last_date is Last_update from the table. I want to mention 0 for which date there is no duration. I think it will something like below but need help.
;WITH AllDates AS(
SELECT #Fromdate As TheDate
UNION ALL
SELECT TheDate + 1
FROM AllDates
WHERE TheDate + 1 <= #ToDate
)SELECT UserId,
TheDate,
COALESCE(
SUM(
-- When the game starts and ends in the same date
CASE WHEN DATEDIFF(DAY, GameStartTime, GameEndTime) = 0
Here is what I am looking for
Another way to generate the date range you are after would be something like .....
;WITH DateLimits AS
(
SELECT MIN(First_Date) FirstDate
,MAX(Last_Update) LastDate
FROM TableName
),
DateRange AS
(
SELECT TOP (SELECT DATEDIFF(DAY,FirstDate,LastDate ) FROM DateLimits)
DATEADD(DAY
,ROW_NUMBER() OVER (ORDER BY (SELECT NULL))
, (SELECT FirstDate FROM DateLimits)
) AS Dates
FROM master..spt_values a cross join master..spt_values b
)
SELECT * FROM DateRange --<-- you have the desired date range here
-- other query whatever you need.

Sql to select row from each day of a month

I have a table which store records of all dates of a month. I want to retrieve some data from it. The table is so large that I should only selecting a fews of them. If the records have a column "ric_date" which is a date, how can I select records from each of the dates in a month, while selecting only a fews from each date?
The table is so large that the records for 1 date can have 100000 records.
WITH T AS (
SELECT ric_date
FROM yourTable
WHERE rice_date BETWEEN #start_date AND #end_date -- thanks Aaron Bertrand
GROUP BY ric_date
)
SELECT CA.*
FROM T
CROSS APPLY (
SELECT TOP 500 * -- 'a fews'
FROM yourTable AS YT
WHERE YT.ric_date = T.ric_date
ORDER BY someAttribute -- not required, but useful
) AS CA
Rough idea. This will get the first three rows per day for the current month (or as many that exist for any given day - there may be days with no rows represented).
DECLARE
#manys INT = 3,
#month DATE = DATEADD(DAY, 1-DAY(GETDATE()), DATEDIFF(DAY, 0, GETDATE()));
;WITH x AS
(
SELECT some_column, ric_date, rn = ROW_NUMBER() OVER
(PARTITION BY ric_date ORDER BY ric_date)
FROM dbo.data
WHERE ric_date >= #month
AND ric_date < DATEADD(MONTH, 1, #month)
)
SELECT some_column, ric_date FROM x
WHERE rn <= #manys;
If you don't have supporting indexes (most importantly on ric_date), this won't necessarily scale well at the high end.