SQL Server : query for DENSE_RANK() grouped by 2 column? - sql-server

Need help in construct SQL, over an orders table, that holds the Date, SalesID, ItemID and other misc. columns.
Table looks like:
Date SalesID ItemID
13-9-15 6:15:00 56 6
13-9-15 6:00:00 56 6
13-9-15 6:26:00 56 4
13-9-15 6:38:00 34 4
13-9-15 7:05:00 34 2
13-9-15 6:42:00 12 2
13-9-15 7:20:00 12 5
13-9-15 7:34:00 78 5
13-9-15 7:41:00 78 6
What I'd like to have as an additional column is, one counter which is increments each time when new SalesID begins order by date.And the counter column will count until max no is 3.I'm using DENSE_RANK()for the increment column.
Finally what I need:
Date SalesID ItemID Counter
13-9-15 6:00:00 56 6 1
13-9-15 6:15:00 56 6 1
13-9-15 6:26:00 56 4 1
13-9-15 6:38:00 34 4 2
13-9-15 6:42:00 34 2 2
13-9-15 7:05:00 12 2 3
13-9-15 7:20:00 12 5 3
13-9-15 7:34:00 78 5 1
13-9-15 7:41:00 78 6 1

This solution works for sqlserver 2012+. I had to correct invalid data in your example in order to get the correct output
DECLARE #t table(Date datetime, SalesID int, ItemID int)
INSERT #t values
('2015-09-13 6:15:00',56,6),
('2015-09-13 6:00:00',56,6),
('2015-09-13 6:26:00',56,4),
('2015-09-13 6:38:00',34,4),
('2015-09-13 6:42:00',34,2),
('2015-09-13 7:05:00',12,2),
('2015-09-13 7:10:00',12,5),
('2015-09-13 7:34:00',78,5),
('2015-09-13 7:41:00',78,6)
;WITH CTE as
(
SELECT
[Date], [SalesID], [ItemID],
CASE WHEN lag(SalesID) over (order by Date) = SalesID
THEN 0 ELSE 1 END x
FROM #t
)
SELECT
[Date], [SalesID], [ItemID],
(sum(x) over (ORDER BY Date) - 1) % 3 + 1 [Counter]
FROM CTE
Result:
Date SalesID ItemID Counter
2015-09-13 06:00 56 6 1
2015-09-13 06:15 56 6 1
2015-09-13 06:26 56 4 1
2015-09-13 06:38 34 4 2
2015-09-13 06:42 34 2 2
2015-09-13 07:05 12 2 3
2015-09-13 07:10 12 5 3
2015-09-13 07:34 78 5 1
2015-09-13 07:41 78 6 1
This will work for sqlserver 2008:
;WITH CTE as
(
SELECT
[Date],
SalesID,
ItemID,
row_number() over (order by Date)-
row_number() over (partition by SalesID order by Date) x
FROM #t
)
SELECT
[Date],
SalesID,
ItemID,
(dense_rank() over (order by x) - 1) % 3 + 1 [Counter]
FROM CTE

Related

SQL - Select non repeating columns

I have a table like
id name R_id mgr_id
----------------------------
61 a 22 1
62 a 22 2
62 b 23 1
63 c 24 4
63 b 22 3
64 c 25 3
and I would like to get the following result set
R_id mgr_id
--------------
22 1
23 1
24 4
25 3
I would like select repeating R_ids only once
I tried using this query but with not much success, can anyone help me.
SELECT DISTINCT R_id, mgr_id from DT
Perhaps something like this... WITH TIES clause in concert with Row_NUmber()
Example
Select Top 1 with ties
R_ID
,mgr_id
From #YourTable
Order By Row_Number() over (Partition By R_ID order by Mgr_id)
Returns
R_ID mgr_id
22 1
23 1
24 4
25 3

How to count number of months in T-SQL

I've got a problem in SQL Server.
"Whate'er is well conceived is clearly said, And the words to say it flow with ease", Nicolas Boileau-Despreaux
Well, I don't think I'll be able to make it clear but I'll try ! And I'd like to apologize for my bad english !
I've got this table :
id ind lvl result date
1 1 a 3 2017-01-31
2 1 a 3 2017-02-28
3 1 a 1 2017-03-31
4 1 a 1 2017-04-30
5 1 a 1 2017-05-31
6 1 b 1 2017-01-31
7 1 b 3 2017-02-28
8 1 b 3 2017-03-31
9 1 b 1 2017-04-30
10 1 b 1 2017-05-31
11 2 a 3 2017-01-31
12 2 a 1 2017-02-28
13 2 a 3 2017-03-31
14 2 a 1 2017-04-30
15 2 a 3 2017-05-31
I'd like to count the number of month the combo {ind, lvl} remain in the result 1 before re-initializing the number of month to 0 if the result is not 1.
Clearly, I need to get something like that :
id ind lvl result date BadResultRemainsFor%Months
1 1 a 3 2017-01-31 0
2 1 a 3 2017-02-28 0
3 1 a 1 2017-03-31 1
4 1 a 1 2017-04-30 2
5 1 a 1 2017-05-31 3
6 1 b 1 2017-01-31 1
7 1 b 3 2017-02-28 0
8 1 b 3 2017-03-31 0
9 1 b 1 2017-04-30 1
10 1 b 1 2017-05-31 2
11 2 a 3 2017-01-31 0
12 2 a 1 2017-02-28 1
13 2 a 3 2017-03-31 0
14 2 a 1 2017-04-30 1
15 2 a 3 2017-05-31 0
So that if I was looking for the number of months the result was 1 for the date 2017-05-31 with the id 1 and the lvl a, I know it's been 3 months.
Assume all the date the the end day of month:
;WITH tb(id,ind,lvl,result,date) AS(
select 1,1,'a',3,'2017-01-31' UNION
select 2,1,'a',3,'2017-02-28' UNION
select 3,1,'a',1,'2017-03-31' UNION
select 4,1,'a',1,'2017-04-30' UNION
select 5,1,'a',1,'2017-05-31' UNION
select 6,1,'b',1,'2017-01-31' UNION
select 7,1,'b',3,'2017-02-28' UNION
select 8,1,'b',3,'2017-03-31' UNION
select 9,1,'b',1,'2017-04-30' UNION
select 10,1,'b',1,'2017-05-31' UNION
select 11,2,'a',3,'2017-01-31' UNION
select 12,2,'a',1,'2017-02-28' UNION
select 13,2,'a',3,'2017-03-31' UNION
select 14,2,'a',1,'2017-04-30' UNION
select 15,2,'a',3,'2017-05-31'
)
SELECT t.id,t.ind,t.lvl,t.result,t.date
,CASE WHEN t.isMatched=1 THEN ROW_NUMBER()OVER(PARTITION BY t.ind,t.lvl,t.id-t.rn ORDER BY t.id) ELSE 0 END
FROM (
SELECT t1.*,c.MonthDiff,CASE WHEN c.MonthDiff=t1.result THEN 1 ELSE 0 END AS isMatched
,CASE WHEN c.MonthDiff=t1.result THEN ROW_NUMBER()OVER(PARTITION BY t1.ind,t1.lvl,CASE WHEN c.MonthDiff=t1.result THEN 1 ELSE 0 END ORDER BY t1.id) ELSE null END AS rn
FROM tb AS t1
LEFT JOIN tb AS t2 ON t1.ind=t2.ind AND t1.lvl=t2.lvl AND t2.id=t1.id-1
CROSS APPLY(VALUES(ISNULL(DATEDIFF(MONTH,t2.date,t1.date),1))) c(MonthDiff)
) AS t
ORDER BY t.id
id ind lvl result date
----------- ----------- ---- ----------- ---------- --------------------
1 1 a 3 2017-01-31 0
2 1 a 3 2017-02-28 0
3 1 a 1 2017-03-31 1
4 1 a 1 2017-04-30 2
5 1 a 1 2017-05-31 3
6 1 b 1 2017-01-31 1
7 1 b 3 2017-02-28 0
8 1 b 3 2017-03-31 0
9 1 b 1 2017-04-30 1
10 1 b 1 2017-05-31 2
11 2 a 3 2017-01-31 0
12 2 a 1 2017-02-28 1
13 2 a 3 2017-03-31 0
14 2 a 1 2017-04-30 1
15 2 a 3 2017-05-31 0
By slightly tweaking your input data and slightly tweaking how we define the requirement, it becomes quite simple to produce the expected results.
First, we tweak your date values so that the only thing that varies is the month and year - the days are all the same. I've chosen to do that my adding 1 day to each value1. The fact that this produces results which are one month advanced doesn't matter here, since all values are similarly transformed, and so the monthly relationships stay the same.
Then, we introduce a numbers table - here, I've assumed a small fixed table is adequate. If it doesn't fit your needs, you can easily locate examples online for creating a large fixed numbers table that you can use for this query.
And, finally, we recast the problem statement. Instead of trying to count months, we instead ask "what's the smallest number of months, greater of equal to zero, that I need to go back from the current row, to locate a row with a non-1 result?". And so, we produce this query:
declare #t table (id int not null,ind int not null,lvl varchar(13) not null,
result int not null,date date not null)
insert into #t(id,ind,lvl,result,date) values
(1 ,1,'a',3,'20170131'), (2 ,1,'a',3,'20170228'), (3 ,1,'a',1,'20170331'),
(4 ,1,'a',1,'20170430'), (5 ,1,'a',1,'20170531'), (6 ,1,'b',1,'20170131'),
(7 ,1,'b',3,'20170228'), (8 ,1,'b',3,'20170331'), (9 ,1,'b',1,'20170430'),
(10,1,'b',1,'20170531'), (11,2,'a',3,'20170131'), (12,2,'a',1,'20170228'),
(13,2,'a',3,'20170331'), (14,2,'a',1,'20170430'), (15,2,'a',3,'20170531')
;With Tweaked as (
select
*,
DATEADD(day,1,date) as dp1d
from
#t
), Numbers(n) as (
select 0 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
)
select
id, ind, lvl, result, date,
COALESCE(
(select MIN(n) from Numbers n1
inner join Tweaked t2
on
t2.ind = t1.ind and
t2.lvl = t1.lvl and
t2.dp1d = DATEADD(month,-n,t1.dp1d)
where
t2.result != 1
),
1) as [BadResultRemainsFor%Months]
from
Tweaked t1
The COALESCE is just there to deal with the edge case, such as for your 1,b data, where there is no previous row with a non-1 result.
Results:
id ind lvl result date BadResultRemainsFor%Months
----------- ----------- ------------- ----------- ---------- --------------------------
1 1 a 3 2017-01-31 0
2 1 a 3 2017-02-28 0
3 1 a 1 2017-03-31 1
4 1 a 1 2017-04-30 2
5 1 a 1 2017-05-31 3
6 1 b 1 2017-01-31 1
7 1 b 3 2017-02-28 0
8 1 b 3 2017-03-31 0
9 1 b 1 2017-04-30 1
10 1 b 1 2017-05-31 2
11 2 a 3 2017-01-31 0
12 2 a 1 2017-02-28 1
13 2 a 3 2017-03-31 0
14 2 a 1 2017-04-30 1
15 2 a 3 2017-05-31 0
1An alternative way to perform the adjustment is to use a DATEADD/DATEDIFF pair to perform a "floor" operation against the dates:
DATEADD(month,DATEDIFF(month,0,date),0) as dp1d
Which resets all of the date values to be the first of their own month rather than the following month. This may fell more "natural" to you, or you may already have such values available in your original data.
Assuming the dates are continously increasing in month, you can use window function like so:
select
t.id, ind, lvl, result, dat,
case when result = 1 then row_number() over (partition by grp order by id) else 0 end x
from (
select t.*,
dense_rank() over (order by e, result) grp
from (
select
t.*,
row_number() over (order by id) - row_number() over (partition by ind, lvl, result order by id) e
from your_table t
order by id) t ) t;

Sqlserver predict top5 records but various group - mathematical logic

I have table like below,
user_id Task_name Score
__________________________________
1 101 10
1 102 9
1 103 8
2 104 10
2 105 9
3 106 9
4 107 9
4 108 8
5 109 8
5 110 7
5 111 6
6 112 10
6 113 9
6 114 8
7 115 9
7 116 8
I want to take top 5 score or max 5 Tasks.
Condition:
1) At least try to get one Tasks from one user.
Output:
User_Id Task_Name Score
____________________________________
1 101 10
2 104 10
6 112 10
3 106 9
4 107 9
I think this is what you need:
SELECT TOP 5 User_id, Task_name, Score
FROM
(
SELECT *, ROW_NUMBER() OVER (PARTITION BY user_id ORDER BY Score DESC) R
FROM Src
) T
ORDER BY R, Score DESC, user_id
It yields:
User_Id Task_Name Score
____________________________________
1 101 10
2 104 10
6 112 10
3 106 9
4 107 9
If you need top 5 ordered, wrap results with another SELECT..ORDER clauses:
SELECT * FROM
(
SELECT TOP 5 user_id, Task_name, Score
FROM
(
SELECT *, RANK() OVER (PARTITION BY user_id ORDER BY Score DESC) R
FROM Src
) T
ORDER BY R, Score DESC, user_id
) E
ORDER BY Score DESC, user_id
I think this is what you want:
select top 5 t.*
from (select t.*,
row_number() over (partition by user_id order by score desc) as seqnum
from t
) t
where seqnum = 1
order by score desc;
The row_number() is used to select the best row for each user. The outer query then chooses the top 5 users with the tasks.

SQL Server 2008 R2: Recursive query

This is the follow up question of : Prepare a recursive query
I have the table with the two columns namely cola and colb as shown below:
Table : Test
create table Test
(
cola int,
colb int
);
Records I have entered are:
Cola Colb
------------
1 2
1 3
1 4
2 5
2 6
2 3
3 2
3 4
3 7
3 10
10 11
11 12
11 13
11 14
12 15
13 16
14 99
15 88
16 77
Note: Now I want to show the only records who are connected with value I have pass. For example If I pass the value as 1 then it should display me the connected number to it and form connect like a tree.
For the above requirement I have got the script from Dark Knight as shown below which works fine.
;WITH CTE AS
(
SELECT COLA,COLB,','+CAST(COLA AS VARCHAR(MAX))+',' AS CHCK FROM test WHERE COLA=1
UNION ALL
SELECT C1.COLA,C1.COLB,C.CHCK+CAST(C1.cola AS VARCHAR(MAX))+','
FROM CTE C INNER JOIN test C1 ON C.colb = C1.cola
WHERE CHARINDEX(','+CAST(C.colb AS VARCHAR(MAX))+',',C.CHCK)=0
),
OUTERCTE AS
(
SELECT DISTINCT COLA,COLB,ROW_NUMBER() OVER(PARTITION BY Colb ORDER BY Cola) rn FROM CTE --ORDER BY COLA
)
SELECT Cola,Colb FROM OUTERCTE
WHERE rn<=1
ORDER BY CASE WHEN Cola = 1 THEN 1 ELSE 2 END;
Which gives me this:
----------------
Cola Colb
----------------
1 2
1 3
1 4
2 5
2 6
3 7
3 10
10 11
11 12
11 13
11 14
12 15
13 16
16 77
15 88
14 99
Requirement: Now I want to show the levels of records.
Expected Result:
------------------------------
Cola Colb Level
------------------------------
1 2 1
1 3 1
1 4 1
2 5 2
2 6 2
3 7 2
3 10 2
10 11 3
11 12 4
11 13 4
11 14 4
12 15 5
13 16 5
16 77 6
15 88 6
14 99 5
;WITH CTE AS
(
SELECT COLA,COLB
,','+CAST(COLA AS VARCHAR(MAX))+',' AS CHCK
, 1 as lvl FROM #Test WHERE COLA=1
UNION ALL
SELECT C1.COLA,C1.COLB ,C.CHCK+CAST(C1.cola AS VARCHAR(MAX))+','
, c.lvl+1
FROM CTE C INNER JOIN #Test C1 ON C.colb = C1.cola
WHERE CHARINDEX(','+CAST(C.colb AS VARCHAR(MAX))+',',C.CHCK)=0
),
cte2 as (
select * , ROW_NUMBER() over (partition by colb order by lvl)as rn From CTE
)
select cola,colb,lvl from cte2 where rn = 1

Reset a sum in a query when a date field changes month

I am currently executing the following query:
Select *, Balance = SUM(DailyReAdmits)
OVER (ORDER BY Date_Total ROWS UNBOUNDED PRECEDING)
From #AllReadmits
Which returns these results:
Date_Total DailyReAdmits Balance
2015-08-25 4 4
2015-08-26 8 12
2015-08-27 9 21
2015-08-28 3 24
2015-08-29 1 25
2015-08-30 4 29
2015-08-31 3 32
2015-09-01 5 37
However, when a new month starts, I would like the balance to start over again and look like this:
Date_Total DailyReAdmits Balance
2015-08-25 4 4
2015-08-26 8 12
2015-08-27 9 21
2015-08-28 3 24
2015-08-29 1 25
2015-08-30 4 29
2015-08-31 3 32
2015-09-01 5 5
How can I achieve this?
I supposed that you want partition by month, so try this:
SELECT *, Balance = SUM(DailyReAdmits)
OVER (PARTITION BY DATEPART(MM,Date_Total) ORDER BY Date_Total ROWS UNBOUNDED PRECEDING)
FROM #AllReadmits

Resources