I am using SQL Server 2014 and I have the following T-SQL query:
Use MyDatabase
;WITH Query_CTE AS
(
SELECT
ResID, Name,
ArrivalDate, Status,
ProfileID,
ROW_NUMBER() OVER(PARTITION BY [ResID] ORDER BY [StayDate]) AS xy
FROM
(SELECT *
FROM View1) xx
)
SELECT *
FROM Query_CTE
WHERE Query_CTE.[xy] = 1
I need to modify the above query so that it outputs all the records whose ArrivalDate is between '2018-04-01'and '2018-12-31' which are also present in the list of records having their ArrivalDate less than '2018-04-01' based on ProfileID.
How can I do this?
First you need to a where clause to your CTE, to get only the records where arrival date is between 2018-04-01 and 2018-12-31.
Then you need to add EXISTS to check if the same profile id also exists in records before 2018-04-01:
;WITH Query_CTE AS
(
SELECT
ResID
,Name
,ArrivalDate
,Status
,ProfileID
,ROW_NUMBER() OVER(PARTITION BY [ResID] ORDER BY [StayDate]) AS xy
FROM View1 v1
WHERE ArrivalDate >= '2018-04-01'
AND ArrivalDate <= '2018-12-31'
AND EXISTS
(
SELECT 1
FROM View1 v2
WHERE v2.ProfileID = v1.ProfileID
AND v2.ArrivalDate < '2018-04-01'
)
)
SELECT * FROM Query_CTE
WHERE Query_CTE.[xy] = 1
Side note: The derived table in the cte is completely redundant, so I've removed it.
Related
How would I filter this SQL server database so only the green records are left aka the last recorded date every year for each Customer ID field.
If you want to get the rows, not only the date values, using ROW_NUMBER() is an option (you only need to use the appropriate PARTITON BY and ORDER BY clauses):
SELECT *
FROM (
SELECT
CustomerId,
[Date],
ROW_NUMBER() OVER (PARTITION BY CustomerId, YEAR[Date] ORDER BY [Date] DESC) AS Rn
FROM YourTable
) t
WHERE Rn = 1
To check the maximum date in the year, you can write a query to get for each year the date where not exists another (in the same year), as follow:
SELECT *
FROM yourtable t1
WHERE NOT EXISTS
(SELECT 1
FROM yourtable t2
WHERE t1.customerID = t2.customerID
AND t1.date > t2.date
AND DATEPART(YEAR, t1) = DATEPART(YEAR, t2))
If you have only two columns, then you can just use aggregation:
select customer_id, max(date)
from t
group by customer_id, year(date);
I have to query in sql server where I have to find for each id it's volume such that we have last 1 year date for each id with it's volume.
for example below is my data ,
for each id I need to query the last 1 year transaction from when we have the entry for that id as you can see from the snippet for id 1 we have the latest date as 7/31/2020 so I need the last 1 year entry from that date for that id, The highlighted one is exclude because that date is more than 1 year from the latest date for that id
Similarly for Id 3 we have all the date range in one year from the latest date for that particular id
I tried using the below query and I can get the latest date for each id but I am not sure how to extract all the dates for each id from the latest date to one year, I would appreciate if some one could help me.
I am using Microsoft sql server would need the query which executes in sql server, Table name is emp and have millions of id
Select *
From emp as t
inner join (
Select tm.id, max(tm.date_tran) as MaxDate
From emp tm
Group by tm.id
) tm on t.id = tm.id and t.date_tran = tm.MaxDate
To exclude transactions where the date difference between the tran_date and the maximum tran_date for each id is greater than 1 year, something like this:
;with max_cte(id, max_date) as (
Select id, max(date_tran)
From emp tm
Group by id )
Select *
From emp e
join max_cte mc on e.id=mc.id
and datediff(d, e.date_tran, mc.max_date)<=365;
Update: per comments, added volume. Thnx GMB :)
;with max_cte(id, date_tran, volume, max_date) as (
Select *, dateadd(year, -1, max(date_tran) over(partition by id)) max_date
From #emp tm)
Select id, sum(volume) sum_volume
From max_cte mc
where mc.date_tran>max_date
group by id;
You can do this with window functions:
select id, sum(volume) total_volume
from (
select t.*, max(date_tran) over(partition by id) max_date_tran
from mytable t
) t
where date_tran > dateadd(year, -1, max_date_tran)
group by id
Alternatively, you can use a correlated subquery for filtering:
select id, sum(volume) total_volume
from mytable t
where t.date_tran > (
select dateadd(year, -1, max(t1.date_tran))
from mytable t1
where t1.id = t.id
)
The second query would take advantage of an index on (id, date_tran).
this should do the trick for you:
SELECT
*
FROM
emp
JOIN
(
SELECT
MAX(date_tran) max_date_tran
, Id
FROM
emp
GROUP BY
id
) emp2
ON emp2.Id = emp.Id
AND DATEADD(YEAR, -1, emp2.max_date_tran) <= emp.date_tran;
Your code is good. Just add the date difference function to get the particular time in between the transaction, like the following:
Select *
From emp as t
inner join ( Select id as id, max(date_tran) as maxdate
From emp tm
Group by id
) tm on t.id = tm.id and datediff(d, e.date_tran, mc.maxdate)<=365;
This is a sample data file
Data Contains unique IDs with different latitudes and longitudes on multiple timestamps.I would like to select the rows of latest 30 days of coordinates for each unique ID.Please help me on how to run the query .This date is in Hive table
Regards,
Akshay
According to your example above (where no current year dates for id=2,3), you can numbering date for each id (order by date descending) using window function ROW_NUMBER(). Then just get latest 30 values:
--get all values for each id where num<=30 (get last 30 days for each day)
select * from
(
--numbering each date for each id order by descending
select *, row_number()over(partition by ID order by DATE desc)num from Table
)X
where num<=30
If you need to get only unique dates (without consider time) for each id, then can try this query:
select * from
(
--numbering date for each id
select *, row_number()over(partition by ID order by new_date desc)num
from
(
-- move duplicate using distinct
select distinct ID,cast(DATE as date)new_date from Table
)X
)Y
where num<=30
In Oracle this will be:
SELECT * FROM TEST_DATE1
WHERE DATEUPDT > SYSDATE - 30;
select * from MyTable
where
[Date]>=dateadd(d, -30, getdate());
To group by ID and perform aggregation, something like this
select ID,
count(*) row_count,
max(Latitude) max_lat,
max(Longitude) max_long
from MyTable
where
[Date]>=dateadd(d, -30, getdate())
group by ID;
In need of some help :)
So I have a table of records with the following columns:
Key (PK, FK, int) DT (smalldatetime) Value (real)
The DT is a datetime for every half hour of the day with an associated value
E.g.
Key DT VALUE
1000 2010-01-01 08:00:00 80
1000 2010-01-01 08:30:00 75
1000 2010-01-01 09:00:00 100
I have a Query that finds the max value every 24 hour period and its associated time however, on one day the max value occurs twice and hence duplicates the date which is causing processing issues. I have tried using rownumber() which works but I can't use a calculated column in my where clause?
Currently I have:
SELECT cast(T1.DT as date) as 'Date',Cast(T1.DT as time(0)) as 'HH', ROW_NUMBER() over (PARTITION BY cast(DT as date) ORDER BY DT) AS 'RowNumber'
FROM TABLE_1 AS T1
INNER JOIN (
SELECT CAST([DT] as date) as 'DATE'
, MAX([VALUE]) as 'MAX_HH'
FROM TABLE_1
WHERE DT > '6-nov-2016' and [KEY] = '1000'
GROUP BY CAST([DT] as date)
) AS MAX_DT
ON MAX_DT.[DATE] = CAST(T1.[DT] as date)
AND T1.VALUE = MAX_DT.MAX_HH
WHERE DT > '6-nov-2016' and [KEY] = '1000'
ORDER BY DT
This results in
Key DT VALUE HH
1000 2010-01-01 80 07:00:00
1000 2010-02-01 100 17:30:00
1000 2010-02-01 100 18:00:00
I need to remove the duplicate date (I Have no preference which HH it takes)
I think I've explained that terribly, let me know if it makes no sense and i'll try and re write
Any ideas?
Can you try this the new code is in ** **:
SELECT cast(T1.DT as date) as 'Date', ** MIN(Cast(T1.DT as time(0))) as 'HH' **
FROM TABLE_1 AS T1
INNER JOIN (
SELECT CAST([DT] as date) as 'DATE'
, MAX([VALUE]) as 'MAX_HH'
FROM TABLE_1
WHERE DT > '6-nov-2016' and [KEY] = '1000'
GROUP BY CAST([DT] as date)
) AS MAX_DT
ON MAX_DT.[DATE] = CAST(T1.[DT] as date)
AND T1.VALUE = MAX_DT.MAX_HH
WHERE DT > '6-nov-2016' and [KEY] = '1000'
here put the group by
GROUP BY cast(T1.DT as date)
ORDER BY DT
i would do something like this
i didnt try it but i think it s correct.
SELECT cast(T1.DT as date) as 'Date',Cast(T1.DT as time(0)) as 'HH', VALUE
FROM TABLE_1 T1
WHERE [DT] IN (
--select the max date from Table_1 for each day
SELECT MAX([DT]) max_date FROM TABLE_1
WHERE (CAST([DT] as date) ,value) IN
(
SELECT CAST([DT] as date) as 'CAST_DATE'
,MAX([VALUE]) as 'MAX_HH'
FROM TABLE_1
WHERE DT > '6-nov-2016' and [KEY] = '1000'
GROUP BY CAST([DT] as date
)group by [DT]
)
WHERE DT > '6-nov-2016' and [KEY] = '1000'
Change the JOIN to an APPLY.
The APPLY operation will allow you to limit the connected relation to just one result for each source relation.
SELECT v.[Key], cast(v.DT As Date) as "Date", v.[Value], cast(v.DT as Time(0)) as "HH"
FROM
( -- First a projection to get just the exact dates you want
SELECT DISTINCT [Key], CAST(DT as DATE) as DT
FROM Table_1
WHERE [Key] = '1000' AMD DT > '20161106'
) dates
CROSS APPLY (
-- Then use APPLY rather than JOIN to find just the exact one record you need for each date
SELECT TOP 1 *
FROM Table_1
WHERE [Key] = dates.[Key] AND cast(DT as DATE) = dates.DT ORDER BY [Value] DESC
) v
A final note: Both this query and your sample query in the question will include values from Nov 6, 2016. The query says > 2016-11-05 with an exlusive inequality, but the original was still comparing using full DateTime values, meaning there is a implied 0 as a time component. So 12:01 AM on Nov 6 is still greater than 12:00:00.001 AM on Nov 6. If you want to exclude all Nov 6 dates from the query, you either need to change this to use a time value at the end of the date, or cast to date before making that > comparison.
With SQL you can use SELECT DISTINCT,
The SELECT DISTINCT statement is used to return only distinct (different) values.
Inside a table, a column often contains many duplicate values; and sometimes you only want to list the different (distinct) values.
The SELECT DISTINCT statement is used to return only distinct (different) values.
I am loading data into a table. I don't have any info on how frequent or when the source data is loaded, all I know is I need data from the source to run my script.
Here's the issue, if I run max(date) I get the latest date from the source, but I don't know if the data is still loading. I've ran into cases where I've only gotten a percentage of the data. Thus, I need the next business day after max date.
I want to know is there a way to get the second latest date in the system. I know I can get max(date) - 1, but that give me literally the day after. I don't need the literal day after.
Example, if I run the script on Tuesday, max(date) will be Monday, but since weekend are not in the source system, I need to get Friday instead of Monday.
DATE
---------
2017-04-29
2017-04-25
2017-04-21
2017-04-19
2017-04-18
2017-04-15
2017-04-10
max(date) = 2017-04-29
how do I get 2017-04-25?
Depending on your version of SQL Server, you can use a windowing function like row_number:
select [Date]
from
(
select [Date],
rn = row_number() over(order by [Date] desc)
from #yourtable
) d
where rn = 2
Here is a demo.
Should you have multiple of the same date, you can perform a distinct first:
;with cte as
(
select distinct [date]
from #yourtable
)
select [date]
from
(
select [date],
rn = row_number() over(order by [date] desc)
from cte
) x
where rn = 2;
You can use row_number and get second as below
select * from ( select *, Rown= row_number() over (order by date desc) from yourtable ) a
where a.RowN = 2
More recent SQL Server versions support FETCH FIRST:
select date
from tablename
order by date desc
offset 1 fetch first 1 row only
OFFSET 1 means skip one row. (The 2017-04-29 row.)
;With cte([DATE])
AS
(
SELECT '2017-04-29' union all
SELECT '2017-04-25' union all
SELECT '2017-04-21' union all
SELECT '2017-04-19' union all
SELECT '2017-04-18' union all
SELECT '2017-04-15' union all
SELECT '2017-04-10'
)
SELECT [DATE] FROM
(
SELECT *,ROW_NUMBER()OVER(ORDER BY Seq)-1 As Rno FROM
(
SELECT *,MAX([DATE])OVER(ORDER BY (SELECT NULL))Seq FROM cte
)dt
)Final
WHERE Final.Rno=1
OutPut
DATE
-----
2017-04-25
You can also use FIRST_VALUE with a dynamic date something like DATEADD(DD, -1, GETDATE()). The example below has the date hard coded.
SELECT DISTINCT
FIRST_VALUE([date]) OVER(ORDER BY [date] DESC) AS FirstDate
FROM CTE
WHERE [date] < '2017-04-25'
Another way
DECLARE #T TABLE ([DATE] DATE)
INSERT INTO #T VALUES
('2017-04-29'),
('2017-04-25'),
('2017-04-21'),
('2017-04-19'),
('2017-04-18'),
('2017-04-15'),
('2017-04-10');
SELECT
MAX([DATE]) AS [DATE]
FROM #T
WHERE DATENAME(DW,[DATE]) NOT IN ('Saturday','Sunday')
Another way of doing it, just for example sake...
SELECT MIN(A.date)
FROM
(
SELECT TOP 2 DISTINCT date
FROM YourTable AS C
ORDER BY date DESC
) AS A