Let say that I have this table "contract" which have duplicated records in the "END" column for the same ID.
ID
Begin
End
20
2016-01-01
9999-12-31
20
2020-01-01
9999-12-31
30
2018-01-01
2019-02-28
30
2019-03-01
9999-12-31
30
2020-02-01
9999-12-31
10
2019-01-01
2019-06-30
10
2019-07-01
2020-02-29
10
2020-03-01
9999-12-31
I want to get the oldest date in the "Begin" column for all the ID's that have duplicated records in the "END" column with the date "9999-12-31". So for this example I expect to get:
ID
Begin
20
2016-01-01
30
2019-03-01
I made an SQL script, but there should be a better way.
select ID, MIN(Begin) from
(
select * from contract m where exists
(
select 1 from contract v where END = '9999-12-31' and v.ID = m.ID
having count(ID)=2
)
and END = '9999-12-31'
)a
group by FUN_ID
If it is a big table, you really want to use EXISTS for finding duplicates because it will short circuit. Here's two ways to use EXISTS that might help with what you are trying to do.
DROP TABLE IF EXISTS #Test;
CREATE TABLE #Test
(
ID INT NOT NULL
,[Begin] DATE NOT NULL
,[End] DATE NOT NULL
)
;
INSERT INTO #Test
VALUES
(20,'2016-01-01','9999-12-31')
,(20,'2020-01-01','9999-12-31')
,(30,'2018-01-01','2019-02-28')
,(30,'2019-03-01','9999-12-31')
,(30,'2020-02-01','9999-12-31')
,(10,'2019-01-01','2019-06-30')
,(10,'2019-07-01','2020-02-29')
,(10,'2020-03-01','9999-12-31')
;
--See all duplicates with OldestBegin for context
SELECT
TST.ID
,TST.[Begin]
,TST.[End]
,OldestBegin = MIN([Begin]) OVER (PARTITION BY TST.ID,TST.[End])
FROM #Test AS TST
WHERE EXISTS
(
SELECT 1
FROM #Test AS _TST
WHERE TST.ID = _TST.ID
AND TST.[End] = _TST.[End]
AND TST.[Begin] <> _TST.[Begin]
)
;
--Get only oldest duplicate
SELECT
TST.ID
,TST.[End]
,[Begin] = MIN([Begin])
FROM #Test AS TST
WHERE EXISTS
(
SELECT 1
FROM #Test AS _TST
WHERE TST.ID = _TST.ID
AND TST.[End] = _TST.[End]
AND TST.[Begin] <> _TST.[Begin]
)
GROUP BY
TST.ID
,TST.[End]
;
Perhaps this will help:
DECLARE #Tab TABLE(ID INT,[Begin] DATE,[End] DATE)
INSERT #Tab
VALUES
(20,'2016-01-01','9999-12-31')
,(20,'2020-01-01','9999-12-31')
,(30,'2018-01-01','2019-02-28')
,(30,'2019-03-01','9999-12-31')
,(30,'2020-02-01','9999-12-31')
,(10,'2019-01-01','2019-06-30')
,(10,'2019-07-01','2020-02-29')
,(10,'2020-03-01','9999-12-31')
;WITH cte AS(
SELECT *
FROM #Tab
WHERE [End] = '9999-12-31'
)
SELECT ID, MIN([Begin]) AS [Begin]
FROM cte
GROUP BY ID
HAVING COUNT(*) > 1
Try this:
WITH test as (SELECT
count(*), min(begin) as Begin, ID from contract
where end = '9999-12-31' group by ID having count(*) > 1) select ID, Begin from test
Related
Based on feedback, I am restructuring my question.
I am working with SQL on a Presto database.
My objective is to report on employees that take consecutive days of PTO or Sick Time since the beginning of 2018. My desired output would have the individual islands of time taken by employee with the start and end dates, along the lines of:
The main table I am using is d_employee_time_off
There are only two time_off_type_name: PTO and Sick Leave.
The ds is a datestamp and I use the latest ds (usually the current date)
I have access to a date table named d_date
I can join the tables on d_employee_time_off.time_off_date = d_date.full_date
I hope that I have structured this question in a fashion that is understandable.
I believe the need here is to join the day off material to a calendar table.
In the example solution below I am generating this "on the fly" but I think you do have your own solution for this. Also in my example I have used the string 'Monday' and moved backward from that (or, you could use 'Friday' and move forward). I'm, not keen on language dependent solutions but as I'm not a Presto user wasn't able to test anything on Presto. So the example below uses some of your own logic, but using SQL Server syntax which I trust you can translate to Presto:
Query:
;WITH
Digits AS (
SELECT 0 AS digit UNION ALL
SELECT 1 UNION ALL SELECT 2 UNION ALL SELECT 3 UNION ALL SELECT 4 UNION ALL
SELECT 5 UNION ALL SELECT 6 UNION ALL SELECT 7 UNION ALL SELECT 8 UNION ALL
SELECT 9
)
, cal AS (
SELECT
ca.number
, dateadd(day,ca.number,'20180101') as cal_date
, datename(weekday,dateadd(day,ca.number,'20180101')) weekday
FROM Digits [1s]
CROSS JOIN Digits [10s]
CROSS JOIN Digits [100s] /* add more like this as needed */
cross apply (
SELECT
[1s].digit
+ [10s].digit * 10
+ [100s].digit * 100 /* add more like this as needed */
AS number
) ca
)
, time_off AS (
select
*
from cal
inner join mytable t on (cal.cal_date = t.time_off_date and cal.weekday <> 'Monday')
or (cal.cal_date between dateadd(day,-2,t.time_off_date)
and t.time_off_date and datename(weekday,t.time_off_date) = 'Monday')
)
, starting_points AS (
SELECT
employee_id,
cal_date,
dense_rank() OVER(partition by employee_id
ORDER BY
time_off_date
) AS rownum
FROM
time_off A
WHERE
NOT EXISTS (
SELECT
*
FROM
time_off B
WHERE
B.employee_id = A.employee_id
AND B.cal_date = DATEADD(day, -1, A.cal_date)
)
)
, ending_points AS (
SELECT
employee_id,
cal_date,
dense_rank() OVER(partition by employee_id
ORDER BY
time_off_date
) AS rownum
FROM
time_off A
WHERE
NOT EXISTS (
SELECT
*
FROM
time_off B
WHERE
B.employee_id = A.employee_id
AND B.cal_date = DATEADD(day, 1, A.cal_date)
)
)
SELECT
S.employee_id,
S.cal_date AS start_range,
E.cal_date AS end_range
FROM
starting_points S
JOIN
ending_points E
ON E.employee_id = S.employee_id
AND E.rownum = S.rownum
order by employee_id
, start_range
Result:
employee_id start_range end_range
1 200035 02.01.2018 02.01.2018
2 200035 20.04.2018 27.04.2018
3 200037 27.01.2018 29.01.2018
4 200037 31.03.2018 02.04.2018
see: http://rextester.com/MISZ50793
CREATE TABLE mytable(
ID INT NOT NULL
,employee_id INTEGER NOT NULL
,type VARCHAR(3) NOT NULL
,time_off_date DATE NOT NULL
,time_off_in_days INT NOT NULL
);
INSERT INTO mytable(id,employee_id,type,time_off_date,time_off_in_days) VALUES (1,200035,'PTO','2018-01-02',1);
INSERT INTO mytable(id,employee_id,type,time_off_date,time_off_in_days) VALUES (2,200035,'PTO','2018-04-20',1);
INSERT INTO mytable(id,employee_id,type,time_off_date,time_off_in_days) VALUES (3,200035,'PTO','2018-04-23',1);
INSERT INTO mytable(id,employee_id,type,time_off_date,time_off_in_days) VALUES (4,200035,'PTO','2018-04-24',1);
INSERT INTO mytable(id,employee_id,type,time_off_date,time_off_in_days) VALUES (5,200035,'PTO','2018-04-25',1);
INSERT INTO mytable(id,employee_id,type,time_off_date,time_off_in_days) VALUES (6,200035,'PTO','2018-04-26',1);
INSERT INTO mytable(id,employee_id,type,time_off_date,time_off_in_days) VALUES (7,200035,'PTO','2018-04-27',1);
INSERT INTO mytable(id,employee_id,type,time_off_date,time_off_in_days) VALUES (8,200037,'PTO','2018-01-29',1);
INSERT INTO mytable(id,employee_id,type,time_off_date,time_off_in_days) VALUES (9,200037,'PTO','2018-04-02',1);
I have 2 tables, one is working pattern, another is absences.
1) Work pattern
ID | Shift Start | Shift End
123| 01-03-2017 | 02-03-2017
2) Absences
ID| Absence Start | Absence End
123| 01-03-2017 | 04-03-2017
What would be the best way, when selecting rows from work pattern, to exclude any that have a date marked as an absence in the absence table?
For example, I have a report that uses the work pattern table to count how may days a week an employee has worked, however I don't want it to include the days that have been marked as an absence on the absence table if that makes sense? Also don't want it to include any days that fall between the absence start and absence end date?
If the span of the absence should always encompass the shift to be excluded you can use not exists():
select *
from WorkPatterns w
where not exists (
select 1
from Absences a
where a.Id = w.Id
and a.AbsenceStart <= w.ShiftStart
and a.AbsenceEnd >= w.ShiftEnd
)
rextester demo: http://rextester.com/DCODC76816
returns:
+-----+------------+------------+
| id | ShiftStart | ShiftEnd |
+-----+------------+------------+
| 123 | 2017-02-27 | 2017-02-28 |
| 123 | 2017-03-05 | 2017-03-06 |
+-----+------------+------------+
given this test setup:
create table WorkPatterns ([id] int, [ShiftStart] datetime, [ShiftEnd] datetime) ;
insert into WorkPatterns ([id], [ShiftStart], [ShiftEnd]) values
(123, '20170227', '20170228')
,(123, '20170301', '20170302')
,(123, '20170303', '20170304')
,(123, '20170305', '20170306')
;
create table Absences ([id] int, [AbsenceStart] datetime, [AbsenceEnd] datetime) ;
insert into Absences ([id], [AbsenceStart], [AbsenceEnd]) values
(123, '20170301', '20170304');
What would be the best way, when selecting rows from work pattern
If you dealing only whit dates (no time) and have control over db schema,
One approach will be to create calendar table ,
Where you going to put all dates since company started and some years in future
Fill that table once.
After it is easy to join other tables whit dates and do math.
If you have trouble whit constructing TSQL query please edit question whit more details about columns and values of tables, relations and needed results.
How about this:
SELECT WP_START.[id], WP_START.[shift_start], WP_START.[shift_end]
FROM work_pattern AS WP_START
INNER JOIN absences AS A ON WP_START.id = A.id
WHERE WP_START.[shift_start] NOT BETWEEN A.[absence_start] AND A.[absence_end]
UNION
SELECT WP_END.[id], WP_END.[shift_start], WP_END.[shift_end]
FROM work_pattern AS WP_END
INNER JOIN absences AS A ON WP_END.id = A.id
WHERE WP_END.[shift_end] NOT BETWEEN A.[absence_start] AND A.[absence_end]
See it on SQL Fiddle: http://sqlfiddle.com/#!6/49ae6/6
Here is my example that includes a Date Dimension table. If your DBAs won't add it, you can create #dateDim as a temp table, like I've done with SQLFiddle (didn't know I could do that). A typical date dimension would have a lot more details you need about the days, but if the table can't be added, just use what you need. You'll have to populate the other Holidays you need. The DateDim I use often is at https://github.com/shawnoden/SQL_Stuff/blob/master/sql_CreateDateDimension.sql
SQL Fiddle
MS SQL Server 2014 Schema Setup:
/* Tables for your test data. */
CREATE TABLE WorkPatterns ( id int, ShiftStart date, ShiftEnd date ) ;
INSERT INTO WorkPatterns ( id, ShiftStart, ShiftEnd )
VALUES
(123, '20170101', '20171031')
, (124, '20170601', '20170831')
;
CREATE TABLE Absences ( id int, AbsenceStart date, AbsenceEnd date ) ;
INSERT INTO Absences ( id, AbsenceStart, AbsenceEnd )
VALUES
( 123, '20170123', '20170127' )
, ( 123, '20170710', '20170831' )
, ( 124, '20170801', '20170820' )
;
/* ******** MAKE SIMPLE CALENDAR TABLE ******** */
CREATE TABLE dateDim (
theDate DATE NOT NULL
, IsWeekend BIT DEFAULT 0
, IsHoliday BIT DEFAULT 0
, IsWorkDay BIT DEFAULT 0
);
/* Populate basic details of dates. */
INSERT dateDim(theDate, IsWeekend, IsHoliday)
SELECT d
, CONVERT(BIT, CASE WHEN DATEPART(dw,d) IN (1,7) THEN 1 ELSE 0 END)
, CONVERT(BIT, CASE WHEN d = '20170704' THEN 1 ELSE 0 END) /* 4th of July. */
FROM (
SELECT d = DATEADD(DAY, rn - 1, '20170101')
FROM
(
SELECT TOP (DATEDIFF(DAY, '20170101', '20171231'))
rn = ROW_NUMBER() OVER (ORDER BY s1.[object_id])
FROM sys.all_objects AS s1
CROSS JOIN sys.all_objects AS s2
ORDER BY s1.[object_id]
) AS x
) AS y ;
/* If not a weekend or holiday, it's a WorkDay. */
UPDATE dateDim
SET IsWorkDay = CASE WHEN IsWeekend = 0 AND IsHoliday = 0 THEN 1 ELSE 0 END
;
Query For Calculation:
SELECT wp.ID, COUNT(d.theDate) AS workDayCount
FROM WorkPatterns wp
INNER JOIN dateDim d ON d.theDate BETWEEN wp.ShiftStart AND wp.ShiftEnd
AND d.IsWorkDay = 1
LEFT OUTER JOIN Absences a ON d.theDate BETWEEN a.AbsenceStart AND a.AbsenceEnd
AND wp.ID = a.ID
WHERE a.ID IS NULL
GROUP BY wp.ID
ORDER BY wp.ID
Results:
| ID | workDayCount |
|-----|--------------|
| 123 | 172 | << 216 total days, 44 non-working
| 124 | 51 | << 65 total days, 14 non-working
I have a column of QualityCheckTimes. I also have a different table with the StartTimes and EndTimes of ProductionSkids.
I need a query that returns for each QualityCheckTime, the minimum SkidID and maximum SkidID based on their StartTimes and EndTimes.
Sample Data
QCCheckTimes
12:00 AM
1:00 AM
2:00 AM
SkidID SkidStartTime SkidEndTime
1 12:05 AM 12:20 AM
2 12:21 AM 12:40 AM
3 12:41 AM 12:50 AM
4 12:51 AM 1:06 AM
Expected Output:
QCCheckTimes MinSkidID MaxSkidID
12:00 AM Skid1 Skid3
1:00 AM Skid4 ...
2:00 AM ...
I've tried a few things, but the crux of it is that I need to find a way to get all the matching Skid Times between two QualityCheck times, with those QualityTimes being on separate rows.
SELECT...
WHERE [SkidStartDateTime] >= [QualitySamples_tbl].[SampleDateTime]
AND [SkidEndDateTime] < NEXT?? [QualitySamples_tbl].[SampleDateTime]);
I don't use access but in SQL Server you have two functions to achieve this query LAG and LEAD, previous and next row, you can see a tutorial here http://www.c-sharpcorner.com/UploadFile/f82e9a/lag-and-lead-functions-in-sql-server/
so in SQL you can do something like this (this example is using integers not time)
----------------your single table-----------------
declare #a table(id int)
insert into #a
select 1 union
select 5 union
select 10 union
select 14 union
select 17 union
select 20
----------------table with ranges-----------------
declare #b table (start int, finish int)
insert into #b
select 1,4 union
select 2,5 union
select 5,8 union
select 10,15
----------------Aux Table--------------------------
declare #a_PlusNext table (id int, idNext int)
insert into #a_PlusNext
SELECT id,LEAD(id) OVER(ORDER BY id) nextId from #A
----------------------Final Query------------------
SELECT
*
FROM #a_PlusNext
INNER JOIN #b on start >= id and finish <= idNext
You can use subqueries and Hour() function to achieve this.
Try this:
table1 contains: QCCheckTimes
table2 Contains: SkidID,SkidStartTime,SkidEndTime
Code:
SELECT table1.qcchecktimes,
Iif([minofid] IS NULL, "...", "skid" & [minofid]) AS MinSkidID,
Iif([c].[maxofid] = [b].[minofid], "...",
Iif([maxofid] IS NULL, "...", "skid" & [maxofid])) AS MaxSkidID
FROM (table1
LEFT JOIN (SELECT table1.qcchecktimes,
Min(table2.skidid) AS MinOfID
FROM table1,
table2
WHERE (( ( Hour([skidendtime]) ) = Hour([qcchecktimes]) ))
GROUP BY table1.qcchecktimes) AS b
ON table1.qcchecktimes = b.qcchecktimes)
LEFT JOIN (SELECT table1.qcchecktimes,
Max(table2.skidid) AS MaxOfid
FROM table1,
table2
WHERE (( ( Hour([skidendtime]) ) = Hour([qcchecktimes]) ))
GROUP BY table1.qcchecktimes) AS c
ON table1.qcchecktimes = c.qcchecktimes
GROUP BY table1.qcchecktimes,
Iif([minofid] IS NULL, "...", "skid" & [minofid]),
Iif([c].[maxofid] = [b].[minofid], "...",
Iif([maxofid] IS NULL, "...", "skid" & [maxofid]));
I have table with dates:
select id,date date_ranges where range_id = 1;
1 2016-04-12
2 2016-04-13
3 2016-04-14
also i have an array:
example:
array('2016-04-11','2016-04-12','2016-04-13','2016-04-14','2016-04-15')
or
array('2016-04-13','2016-04-14','2016-04-15')
How can i insert new values from array to my table without changing existing table values?
And if i have second array, how can i delete value 2016-04-12 from table?
Help plz, I need one query)
WITH current_values AS (
SELECT generate_series('2016-04-13'::DATE, '2016-04-17'::DATE, '1 day')::DATE AS date
),
deleted_values AS (
DELETE FROM date_ranges WHERE date NOT IN (SELECT * FROM current_values) RETURNING id
)
INSERT INTO date_ranges ("date", range_id)
WITH new_values AS (
SELECT new."date"
FROM current_values AS new
LEFT JOIN date_ranges AS old
ON old."date" = new."date"
WHERE old.id IS NULL
)
SELECT date, 1 FROM new_values;
I am using SQL Server 2008 and need to create a query that shows rows that fall within a date range.
My table is as follows:
ADM_ID WH_PID WH_IN_DATETIME WH_OUT_DATETIME
My rules are:
If the WH_OUT_DATETIME is on or within 24 hours of the WH_IN_DATETIME of another ADM_ID with the same WH_P_ID
I would like another column added to the results which identify the grouped value if possible as EP_ID.
e.g.
ADM_ID WH_PID WH_IN_DATETIME WH_OUT_DATETIME
------ ------ -------------- ---------------
1 9 2014-10-12 00:00:00 2014-10-13 15:00:00
2 9 2014-10-14 14:00:00 2014-10-15 15:00:00
3 9 2014-10-16 14:00:00 2014-10-17 15:00:00
4 9 2014-11-20 00:00:00 2014-11-21 00:00:00
5 5 2014-10-17 00:00:00 2014-10-18 00:00:00
Would return rows with:
ADM_ID WH_PID EP_ID EP_IN_DATETIME EP_OUT_DATETIME WH_IN_DATETIME WH_OUT_DATETIME
------ ------ ----- ------------------- ------------------- ------------------- -------------------
1 9 1 2014-10-12 00:00:00 2014-10-17 15:00:00 2014-10-12 00:00:00 2014-10-13 15:00:00
2 9 1 2014-10-12 00:00:00 2014-10-17 15:00:00 2014-10-14 14:00:00 2014-10-15 15:00:00
3 9 1 2014-10-12 00:00:00 2014-10-17 15:00:00 2014-10-16 14:00:00 2014-10-17 15:00:00
4 9 2 2014-11-20 00:00:00 2014-11-20 00:00:00 2014-10-16 14:00:00 2014-11-21 00:00:00
5 5 1 2014-10-17 00:00:00 2014-10-18 00:00:00 2014-10-17 00:00:00 2014-10-18 00:00:00
The EP_OUT_DATETIME will always be the latest date in the group. Hope this clarifies a bit.
This way, I can group by the EP_ID and find the EP_OUT_DATETIME and start time for any ADM_ID/PID that fall within.
Each should roll into the next, meaning that if another row has an WH_IN_DATETIME which follows on the WH_OUT_DATETIME of another for the same WH_PID, than that row's WH_OUT_DATETIME becomes the EP_OUT_DATETIME for all of the WH_PID's within that EP_ID.
I hope this makes some sense.
Thanks,
MR
Since the question does not specify that the solution be a "single" query ;-), here is another approach: using the "quirky update" feature dealy, which is updating a variable at the same time you update a column. Breaking down the complexity of this operation, I create a scratch table to hold the piece that is the hardest to calculate: the EP_ID. Once that is done, it gets joined into a simple query and provides the window with which to calculate the EP_IN_DATETIME and EP_OUT_DATETIME fields.
The steps are:
Create the scratch table
Seed the scratch table with all of the ADM_ID values -- this lets us do an UPDATE as all of the rows already exist.
Update the scratch table
Do the final, simple select joining the scratch table to the main table
The Test Setup
SET ANSI_NULLS ON;
SET NOCOUNT ON;
CREATE TABLE #Table
(
ADM_ID INT NOT NULL PRIMARY KEY,
WH_PID INT NOT NULL,
WH_IN_DATETIME DATETIME NOT NULL,
WH_OUT_DATETIME DATETIME NOT NULL
);
INSERT INTO #Table VALUES (1, 9, '2014-10-12 00:00:00', '2014-10-13 15:00:00');
INSERT INTO #Table VALUES (2, 9, '2014-10-14 14:00:00', '2014-10-15 15:00:00');
INSERT INTO #Table VALUES (3, 9, '2014-10-16 14:00:00', '2014-10-17 15:00:00');
INSERT INTO #Table VALUES (4, 9, '2014-11-20 00:00:00', '2014-11-21 00:00:00');
INSERT INTO #Table VALUES (5, 5, '2014-10-17 00:00:00', '2014-10-18 00:00:00');
Step 1: Create and Populate the Scratch Table
CREATE TABLE #Scratch
(
ADM_ID INT NOT NULL PRIMARY KEY,
EP_ID INT NOT NULL
-- Might need WH_PID and WH_IN_DATETIME fields to guarantee proper UPDATE ordering
);
INSERT INTO #Scratch (ADM_ID, EP_ID)
SELECT ADM_ID, 0
FROM #Table;
Alternate scratch table structure to ensure proper update order (since "quirky update" uses the order of the Clustered Index, as noted at the bottom of this answer):
CREATE TABLE #Scratch
(
WH_PID INT NOT NULL,
WH_IN_DATETIME DATETIME NOT NULL,
ADM_ID INT NOT NULL,
EP_ID INT NOT NULL
);
INSERT INTO #Scratch (WH_PID, WH_IN_DATETIME, ADM_ID, EP_ID)
SELECT WH_PID, WH_IN_DATETIME, ADM_ID, 0
FROM #Table;
CREATE UNIQUE CLUSTERED INDEX [CIX_Scratch]
ON #Scratch (WH_PID, WH_IN_DATETIME, ADM_ID);
Step 2: Update the Scratch Table using a local variable to keep track of the prior value
DECLARE #EP_ID INT; -- this is used in the UPDATE
;WITH cte AS
(
SELECT TOP (100) PERCENT
t1.*,
t2.WH_OUT_DATETIME AS [PriorOut],
t2.ADM_ID AS [PriorID],
ROW_NUMBER() OVER (PARTITION BY t1.WH_PID ORDER BY t1.WH_IN_DATETIME)
AS [RowNum]
FROM #Table t1
LEFT JOIN #Table t2
ON t2.WH_PID = t1.WH_PID
AND t2.ADM_ID <> t1.ADM_ID
AND t2.WH_OUT_DATETIME >= (t1.WH_IN_DATETIME - 1)
AND t2.WH_OUT_DATETIME < t1.WH_IN_DATETIME
ORDER BY t1.WH_PID, t1.WH_IN_DATETIME
)
UPDATE sc
SET #EP_ID = sc.EP_ID = CASE
WHEN cte.RowNum = 1 THEN 1
WHEN cte.[PriorOut] IS NULL THEN (#EP_ID + 1)
ELSE #EP_ID
END
FROM #Scratch sc
INNER JOIN cte
ON cte.ADM_ID = sc.ADM_ID
Step 3: Select Joining the Scratch Table
SELECT tab.ADM_ID,
tab.WH_PID,
sc.EP_ID,
MIN(tab.WH_IN_DATETIME) OVER (PARTITION BY tab.WH_PID, sc.EP_ID)
AS [EP_IN_DATETIME],
MAX(tab.WH_OUT_DATETIME) OVER (PARTITION BY tab.WH_PID, sc.EP_ID)
AS [EP_OUT_DATETIME],
tab.WH_IN_DATETIME,
tab.WH_OUT_DATETIME
FROM #Table tab
INNER JOIN #Scratch sc
ON sc.ADM_ID = tab.ADM_ID
ORDER BY tab.ADM_ID;
Resources
MSDN page for UPDATE
look for "#variable = column = expression"
Performance Analysis of doing Running Totals (not exactly the same thing as here, but not too far off)
This blog post does mention:
PRO: this method is generally pretty fast
CON: "The order of the UPDATE is controlled by the order of the clustered index". This behavior might rule out using this method depending on circumstances. But in this particular case, if the WH_PID values are not at least grouped together naturally via the ordering of the clustered index and ordered by WH_IN_DATETIME, then those two fields just get added to the scratch table and the PK (with implied clustered index) on the scratch table becomes (WH_PID, WH_IN_DATETIME, ADM_ID).
I would do this using exists in a correlated subquery:
select t.*,
(case when exists (select 1
from table t2
where t2.WH_P_ID = t.WH_P_ID and
t2.ADM_ID = t.ADM_ID and
t.WH_OUT_DATETIME between t2.WH_IN_DATETIME and dateadd(day, 1, t2.WH_OUT_DATETIME)
)
then 1 else 0
end) as TimeFrameFlag
from table t;
Try this query :
;WITH cte
AS (SELECT t1.ADM_ID AS EP_ID,*
FROM #yourtable t1
WHERE NOT EXISTS (SELECT 1
FROM #yourtable t2
WHERE t1.WH_PID = t2.WH_PID
AND t1.ADM_ID <> t2.ADM_ID
AND Abs(Datediff(HH, t1.WH_OUT_DATETIME, t2.WH_IN_DATETIME)) <= 24)
UNION ALL
SELECT t2.EP_ID,t1.ADM_ID,t1.WH_PID,t1.WH_IN_DATETIME,t1.WH_OUT_DATETIME
FROM #yourtable t1
JOIN cte t2
ON t1.WH_PID = t2.WH_PID
AND t1.ADM_ID <> t2.ADM_ID
AND Abs(( Datediff(HH, t2.WH_IN_DATETIME, t1.WH_OUT_DATETIME) )) <= 24),
cte_result
AS (SELECT t1.*,Dense_rank() OVER ( partition BY wh_pid ORDER BY t1.WH_PID, ISNULL(t2.EP_ID, t1.ADM_ID)) AS EP_ID
FROM #yourtable t1
LEFT OUTER JOIN (SELECT DISTINCT ADM_ID,
EP_ID
FROM cte) t2
ON t1.ADM_ID = t2.ADM_ID)
SELECT ADM_ID,WH_PID,EP_ID,Min(WH_IN_DATETIME)OVER(partition BY wh_pid, ep_id) AS [EP_IN_DATETIME],Max(WH_OUT_DATETIME)OVER(partition BY wh_pid, ep_id) AS [EP_OUT_DATETIME],
WH_IN_DATETIME,
WH_OUT_DATETIME
FROM cte_result
ORDER BY ADM_ID
I assumed these things :
Those rows which follow your rule, are a group.
min(WH_IN_DATETIME) of the group will be shown in EP_IN_DATETIME column for all rows belong to that group. Similarly, max(WH_OUT_DATETIME) of the group will be shown in EP_IN_DATETIME column for all rows belong to that group.
EP_ID will be assigned to groups of each WH_PID separately.
One thing which is not justified by your question that how EP_OUT_DATETIME and WH_IN_DATETIME of 4th row become 2014-11-20 00:00:00 and 2014-10-16 14:00:00 respectively. Assuming that it is a typo and it should be 2014-11-21 00:00:00.000 and 2014-11-20 00:00:00.000.
Explaination :
First CTE cte will return the possible groups based on your rule. Second CTE cte_result will assign EP_ID to groups. In the last, you can select min(WH_IN_DATETIME) and Max(WH_OUT_DATETIME) in partitions of wh_pid, ep_id.
sqlfiddle
Here's yet another alternative... which may miss your results still.
I agree with #NoDisplayName that there appears to be an error in your ADM_ID 5 output, the 2 OUT dates should match - at least that seems logical to me. I can't understand why you would want an out date to ever be showing an in date value, but of course there could be a good reason. :)
Also, the wording of your question makes it sound like this is just a part of the problem and that you may take this output to then further. I'm not sure what you are really aiming for, but I've broken the query below up into 2 CTEs and you may find your final information in the 2nd CTE (as it sounds like you want to group the data back together).
Here's the complete structure & query on SQL Fiddle
-- The Cross Join ensures we always have a pair of first and last time pairs
-- The left join matches all overlapping combinations,
-- allowing the where clause to restrict to just the first and last
-- These first/last pairs are then grouped in the first CTE
-- Data is restricted in the second CTE
-- The final select is then quite simple
With GroupedData AS (
SELECT
(Row_Number() OVER (ORDER BY t1.WH_PID, t1.WH_IN_DATETIME) - 1) / 2 Grp,
t1.WH_IN_DATETIME, t1.WH_OUT_DATETIME, t1.WH_PID
FROM yourtable t1
CROSS JOIN (SELECT 0 AS [First] UNION SELECT 1) SetOrder
LEFT OUTER JOIN yourtable t2
ON t1.WH_PID = t2.WH_PID
AND ((DATEADD(d,1,t1.WH_OUT_DATETIME) BETWEEN t2.WH_IN_DATETIME AND t2.WH_OUT_DATETIME AND [First] = 0)
OR (DATEADD(d,1,t2.WH_OUT_DATETIME) BETWEEN t1.WH_IN_DATETIME AND t1.WH_OUT_DATETIME AND [First] = 1))
WHERE t2.WH_PID IS NULL
), RestrictedData AS (
SELECT WH_PID, MIN(WH_IN_DATETIME) AS WH_IN_DATETIME, MAX(WH_OUT_DATETIME) AS WH_OUT_DATETIME
FROM GroupedData
GROUP BY Grp, WH_PID
)
SELECT yourtable.ADM_ID, yourtable.WH_PID, RestrictedData.WH_IN_DATETIME AS EP_IN_DATETIME, RestrictedData.WH_OUT_DATETIME AS EP_OUT_DATETIME, yourtable.WH_IN_DATETIME, yourtable.WH_OUT_DATETIME
FROM RestrictedData
INNER JOIN yourtable
ON RestrictedData.WH_PID = yourtable.WH_PID
AND yourtable.WH_IN_DATETIME BETWEEN RestrictedData.WH_IN_DATETIME AND RestrictedData.WH_OUT_DATETIME
ORDER BY yourtable.ADM_ID
A Left Outer Join and DateDiff Function should help you to filter the records. Finally Use Window Function to create GroupID's
create table #test
(ADM_ID int,WH_PID int,WH_IN_DATETIME DATETIME,WH_OUT_DATETIME DATETIME)
INSERT #test
VALUES ( 1,9,'2014-10-12 00:00:00','2014-10-13 15:00:00'),
(2,9,'2014-10-14 14:00:00','2014-10-15 15:00:00'),
(3,9,'2014-10-16 14:00:00','2014-10-17 15:00:00'),
(1,10,'2014-10-16 14:00:00','2014-10-17 15:00:00'),
(2,10,'2014-10-18 14:00:00','2014-10-19 15:00:00')
SELECT Row_number()OVER(partition by a.WH_PID ORDER BY a.WH_IN_DATETIME) Group_Id,
a.WH_PID,
a.WH_IN_DATETIME,
b.WH_OUT_DATETIME
FROM #test a
LEFT JOIN #test b
ON a.WH_PID = b.WH_PID
AND a.ADM_ID <> b.ADM_ID
where Datediff(hh, a.WH_OUT_DATETIME, b.WH_IN_DATETIME)BETWEEN 0 AND 24
OUTPUT :
Group_Id WH_PID WH_IN_DATETIME WH_OUT_DATETIME
-------- ------ ----------------------- -----------------------
1 9 2014-10-12 00:00:00.000 2014-10-15 15:00:00.000
2 9 2014-10-14 14:00:00.000 2014-10-17 15:00:00.000
1 10 2014-10-16 14:00:00.000 2014-10-19 15:00:00.000