Can somebody help me in finding the sum of 4 consecutive values i.e rolling sum of last 4 values.
Like:
VALUE SUM
1 NULL
2 NULL
3 NULL
4 10
5 14
6 18
7 22
8 26
9 30
10 34
11 38
12 42
13 46
14 50
15 54
16 58
17 62
18 66
19 70
20 74
21 78
22 82
23 86
24 90
25 94
26 98
27 102
28 106
29 110
30 114
31 118
32 122
33 126
34 130
35 134
36 138
37 142
38 146
Thanks,
select sum(select top 4 Value from [table] order by Value Desc)
or, perhaps
select sum(value)
from [Table]
where Value >= (Max(Value) - 4)
I haven't actually tried either of those- and can't at the moment, but they should get you pretty close.
Quick attempt, which gets the results you've posted in your question (except the 1st 3 rows are not NULL). Assumes that VALUE field is unique and in ascending order:
-- Create test TABLE with 38 values in
DECLARE #T TABLE (Value INTEGER)
DECLARE #Counter INTEGER
SET #Counter = 1
WHILE (#Counter <= 38)
BEGIN
INSERT #T VALUES(#Counter)
SET #Counter = #Counter + 1
END
-- This gives the results
SELECT t1.VALUE, x.Val
FROM #T t1
OUTER APPLY(SELECT SUM(VALUE) FROM (SELECT TOP 4 VALUE FROM #T t2 WHERE t2.VALUE <= t1.VALUE ORDER BY t2.VALUE DESC) x) AS x(Val)
ORDER BY VALUE
At the very least, you should see the kind of direction I was heading in.
Assuming ID can give you the last 4 rows.
SELECT SUM([SUM])
FROM
(
SELECT TOP 4 [SUM] FROM myTable ORDER BY ID DESC
) foo
Each time you query it, it will read the last 4 rows.
If this is wrong (e.g. you want the sum of each consecutive 4 rows), then please give sample output
Following would work if your Value column is sequential
;WITH q (Value) AS (
SELECT 1
UNION ALL
SELECT q.Value + 1
FROM q
WHERE q.Value < 38
)
SELECT q.Value
, CASE WHEN q.Value >= 4 THEN q.Value * 4 - 6 ELSE NULL END
FROM q
otherwise you might use something like this
;WITH q (Value) AS (
SELECT 1
UNION ALL
SELECT q.Value + 1
FROM q
WHERE q.Value < 38
)
, Sequential (ID, Value) AS (
SELECT ID = ROW_NUMBER() OVER (ORDER BY Value)
, Value
FROM q
)
SELECT s1.Value
, [SUM] = s1.Value + s2.Value + s3.Value + s4.Value
FROM Sequential s1
LEFT OUTER JOIN Sequential s2 ON s2.ID = s1.ID - 1
LEFT OUTER JOIN Sequential s3 ON s3.ID = s2.ID - 1
LEFT OUTER JOIN Sequential s4 ON s4.ID = s3.ID - 1
Note that the table qin the examples is a stub for your actual table. The actual statement then becomes
;WITH Sequential (ID, Value) AS (
SELECT ID = ROW_NUMBER() OVER (ORDER BY Value)
, Value
FROM YourTable
)
SELECT s1.Value
, [SUM] = s1.Value + s2.Value + s3.Value + s4.Value
FROM Sequential s1
LEFT OUTER JOIN Sequential s2 ON s2.ID = s1.ID - 1
LEFT OUTER JOIN Sequential s3 ON s3.ID = s2.ID - 1
LEFT OUTER JOIN Sequential s4 ON s4.ID = s3.ID - 1
Related
I am trying to break up a running (ordered) sum into groups of a max value. When I implement the following example logic...
IF OBJECT_ID(N'tempdb..#t') IS NOT NULL DROP TABLE #t
SELECT TOP (ABS(CHECKSUM(NewId())) % 1000) ROW_NUMBER() OVER (ORDER BY name) AS ID,
LEFT(CAST(NEWID() AS NVARCHAR(100)),ABS(CHECKSUM(NewId())) % 30) AS Description
INTO #t
FROM sys.objects
DECLARE #maxGroupSize INT
SET #maxGroupSize = 100
;WITH t AS (
SELECT
*,
LEN(Description) AS DescriptionLength,
SUM(LEN(Description)) OVER (/*PARTITION BY N/A */ ORDER BY ID) AS [RunningLength],
SUM(LEN(Description)) OVER (/*PARTITION BY N/A */ ORDER BY ID)/#maxGroupSize AS GroupID
FROM #t
)
SELECT *, SUM(DescriptionLength) OVER (PARTITION BY GroupID) AS SumOfGroup
FROM t
ORDER BY GroupID, ID
I am getting groups that are larger than the maximum group size (length) of 100.
A recusive common table expression (rcte) would be one way to resolve this.
Sample data
Limited set of fixed sample data.
create table data
(
id int,
description nvarchar(20)
);
insert into data (id, description) values
( 1, 'qmlsdkjfqmsldk'),
( 2, 'mldskjf'),
( 3, 'qmsdlfkqjsdm'),
( 4, 'fmqlsdkfq'),
( 5, 'qdsfqsdfqq'),
( 6, 'mds'),
( 7, 'qmsldfkqsjdmfqlkj'),
( 8, 'qdmsl'),
( 9, 'mqlskfjqmlkd'),
(10, 'qsdqfdddffd');
Solution
For every recursion step evaluate (r.group_running_length + len(d.description) <= #group_max_length) if the previous group must be extended or a new group must be started in a case expression.
Set group target size to 40 to better fit the sample data.
declare #group_max_length int = 40;
with rcte as
(
select d.id,
d.description,
len(d.description) as description_length,
len(d.description) as running_length,
1 as group_id,
len(d.description) as group_running_length
from data d
where d.id = 1
union all
select d.id,
d.description,
len(d.description),
r.running_length + len(d.description),
case
when r.group_running_length + len(d.description) <= #group_max_length
then r.group_id
else r.group_id + 1
end,
case
when r.group_running_length + len(d.description) <= #group_max_length
then r.group_running_length + len(d.description)
else len(d.description)
end
from rcte r
join data d
on d.id = r.id + 1
)
select r.id,
r.description,
r.description_length,
r.running_length,
r.group_id,
r.group_running_length,
gs.group_sum
from rcte r
cross apply ( select max(r2.group_running_length) as group_sum
from rcte r2
where r2.group_id = r.group_id ) gs -- group sum
order by r.id;
Result
Contains both the running group length as well as the group sum for every row.
id description description_length running_length group_id group_running_length group_sum
-- ---------------- ------------------ -------------- -------- -------------------- ---------
1 qmlsdkjfqmsldk 14 14 1 14 33
2 mldskjf 7 21 1 21 33
3 qmsdlfkqjsdm 12 33 1 33 33
4 fmqlsdkfq 9 42 2 9 39
5 qdsfqsdfqq 10 52 2 19 39
6 mds 3 55 2 22 39
7 qmsldfkqsjdmfqlkj 17 72 2 39 39
8 qdmsl 5 77 3 5 28
9 mqlskfjqmlkd 12 89 3 17 28
10 qsdqfdddffd 11 100 3 28 28
Fiddle to see things in action (includes random data version).
I am attempting to remove transactions that have been reversed from a table. the table has Account, Date, Amount and Row. If a transaction has been reversed Account will match and Amount will be inverse of each other.
Example Table
Account Date Amount Row
12 1/1/18 45 72 -- Case 1
12 1/2/18 50 73
12 1/2/18 -50 74
12 1/3/18 52 75
15 1/1/18 51 76 -- Case 2
15 1/2/18 51 77
15 1/2/18 -51 78
15 1/2/18 51 79
18 1/2/18 50 80 -- Case 3
18 1/2/18 50 81
18 1/2/18 -50 82
18 1/2/18 -50 83
18 1/3/18 50 84
18 1/3/18 50 85
20 1/1/18 57 88 -- Case 4
20 1/2/18 57 89
20 1/4/18 -57 90
20 1/5/18 57 91
Desired Results Table
Account Date Amount Row
12 1/1/18 45 72 -- Case 1
12 1/3/18 52 75
15 1/1/18 51 76 -- Case 2
15 1/2/18 51 79
18 1/3/18 50 84 -- Case 3
18 1/3/18 50 85
20 1/1/18 57 88 -- Case 4
20 1/5/18 57 91
Removing all instances of inverse transactions does not work when there are multiple transactions when all other columns are the same. My attempt was to count all duplicate transactions, count of all inverse duplicate transactions, subtracting those to get the number of rows I needed from each transactions group. I was going to pull the first X rows but found in most cases I want the last X rows of each group, or even a mix (the first and last in Case 2).
I either need a method of removing pairs from the original table, or working from what I have so far, a method of distinguishing which transactions to pull.
Code so far:
--adding row Numbers
with a as (
select
account a,
date d,
amount f,
row_number() over(order by account, date) r
from table),
--counting Duplicates
b as (
select a.a, a.f, Dups
from a join (
select a, f, count(*) Dups
from a
group by a.a, a.f
having count(*)>1
) b
on a.a=b.a and
b.f=a.f
where a.f>0
),
--counting inverse duplicates
c as (
select a.a, a.f, InvDups
from a join (
select a, f, count(*) InvDups
from a
group by a.a, a.f
having count(*)>1
) b
on a.a=b.a and
-b.f=a.f
where a.f>0
),
--combining c and d to get desired number of rows of each transaction group
d as (
select
b.a, b.f, dups, InvDups, Dups-InvDups TotalDups
from b join c
on b.a=c.a and
b.f=c.f
),
--getting the number of rows from the beginning of each transaction group
select d.a, d.d, d.f
from
(select
a, d, f, row_number() over (group by a, d, f) r2
from a) e
join d
on e.a=d.a and
TotalDups<=r2
You can try this.
SELECT T_P.* FROM
( SELECT *, ROW_NUMBER() OVER(PARTITION BY Account, Amount ORDER BY [Row] ) RN from #MyTable WHere Amount > 0 ) T_P
LEFT JOIN
( SELECT *, ROW_NUMBER() OVER(PARTITION BY Account, Amount ORDER BY [Row] ) RN from #MyTable WHere Amount < 0 ) T_N
ON T_P.Account = T_N.Account
AND T_P.Amount = ABS(T_N.Amount)
AND T_P.RN = T_N.RN
WHERE
T_N.Account IS NULL
The following handles your three cases:
with t as (
select t.*,
row_number() over (partition by account, date, amount order by row) as seqnum
from table t
)
select t.*
from t
where not exists (select 1
from t t2
where t2.account = t.account and t2.date = t.date and
t2.amount = -t.amount and t2.seqnum = t.seqnum
);
Use This
;WITH CTE
AS
(
SELECT
[Row]
FROM YourTable YT
WHERE Amount > 0
AND EXISTS
(
SELECT 1 FROM YourTable WHERE Account = YT.Account
AND [Date] = YT.[Date]
AND (Amount+YT.Amount)=0
)
UNION ALL
SELECT
[Row]
FROM YourTable YT
WHERE Amount < 0
AND EXISTS
(
SELECT 1 FROM YourTable WHERE Account = YT.Account
AND [Date] = YT.[Date]
AND (Amount+YT.Amount)>0
)
)
SELECT * FROM YourTable
WHERE EXISTS
(
SELECT 1 FROM CTE WHERE [Row] = YourTable.[Row]
)
Raw data with 2 columns:
0 33
2 null
0 44
2 null
2 null
2 null
0 55
2 null
2 null
.....
Results I want:
2 33
2 44
2 44
2 44
2 55
2 55
....
Can I use a SQL statement to accomplish this? (return the rows with 2 only but fill with values come from the previous row that is 0), there could be many '2 null' between 0.
This way
with s as (
select *
from
(values
(1,0,33 ),
(2,2,null),
(3,0,44 ),
(4,2,null),
(5,2,null),
(6,2,null),
(7,0,55 ),
(8,2,null),
(9,2,null)
) T(id,a,b)
)
select s1.a, t.b
from s s1
cross apply (
select top(1) s2.b
from s s2
where s2.id < s1.id and s2.b is not null and s2.a = 0
order by s2.id desc ) t
where s1.a = 2
order by s1.id;
I use CROSS APPLY so the query may be easily extended to get other columns from the relevant '0' row.
First of all, select value for every row with null:
SELECT col2 FROM (SELECT MAX(ID) FROM your_tbl t WHERE t.ID < ID AND col2 IS NOT NULL);
Then write a condition for your table with that subquery:
SELECT col1, (
SELECT col2 FROM your_tbl where id = (SELECT MAX(ID) FROM your_tbl t
WHERE t.ID < tbl.ID AND col2 IS NOT NULL))
FROM your_tbl tbl WHERE col1 <> 0;
I'm struggling coming up with a way to solve this answer. I want to start at a specific value and keep increasing it by 1 every time a new line.
For example, if I have a table like so.
90
93
110
87
130
Etc..
I want to select the number 87 and then keep incrementing up from there but also read if the incremented number is there and skip it.
I am just struggling with trying to put the right logic together in my head. I know I need a while loop to keep reading through the table but I can't think of the proper way to go about it. Just looking for some suggestions to push me in the right direction.
Edit: I am using T-SQL for MSFT SQL Server 2012.
Here is an example of what the output should look like
90
93
110
87
130
88
89
91
92
94
It would skip over adding 90 and 93 because they already exist in the table.
I hope that makes sense to you guys.
I do it all in one recursive CTE and I make it so you can use order by and guarantee your results are returned in the correct order.
For the recursion, you can either choose and start and end number or #desiredNumberOfNewValues(keep in mind, it doesn't account for repeats). Let me know if you have any questions or need anything else.
DECLARE #yourTable TABLE (nums INT);
INSERT INTO #yourTable
VALUES (90),(93),(110),(87),(130);
DECLARE #Specific_Number INT = 87;
DECLARE #Last_Number INT = 94;
DECLARE #DesiredNumberOfNewValues INT = 7;
WITH CTE_Numbers
AS
(
SELECT 1 AS order_id,nums, 1 AS cnt
FROM #yourTable
UNION ALL
SELECT 2,
CASE
WHEN #Specific_Number + cnt NOT IN (SELECT * FROM #yourTable) --if it's not already in the table, return it
THEN #Specific_Number + cnt
ELSE NULL -- if it is in the table, return NULL
END,
cnt + 1
FROM CTE_Numbers
WHERE nums = #Specific_Number
--OR (cnt > 1 AND #Specific_Number + cnt < #Last_Number) --beginning and end(option 1)
OR (cnt > 1 AND cnt <= #DesiredNumberOfNewValues) --number of new values(option 2)
)
SELECT order_id,nums
FROM CTE_Numbers
WHERE nums IS NOT NULL
ORDER BY order_id,nums
Results:
order_id nums
----------- -----------
1 87
1 90
1 93
1 110
1 130
2 88
2 89
2 91
2 92
2 94
You might be able to do this with some modifications by using Numbers table. In SQL Server, you could do the following. Assuming Test has the data. To create Numbers table, please refer to the following link.
http://dataeducation.com/you-require-a-numbers-table/
SELECT n.Number,t.ColB
FROM Numbers n
LEFT JOIN Test t
ON n.Number = t.ColA
Where n.Number < (SELECT MAX(COLA) FROM Test t)
WITH Numbers_CTE (Number)
AS
(
SELECT 1 AS Number
UNION ALL
SELECT Number+1 FROM Numbers_CTE
)
SELECT top 10 *
FROM Numbers_CTE n
LEFT JOIN <TABLE> t ON t.ID=n.Number
WHERE t.ID IS NULL
AND n.Number BETWEEN 5 AND 100
There is a system table you can use for numbers called master..spt_values.
DECLARE sample TABLE
DECLARE #tbl TABLE(Id INT)
INSERT statement
INSERT INTO #tbl VALUES (90)
,(93)
,(110)
,(87)
,(130)
You can easily make a UNION to remove duplicates value you have in your table and ORDER it within a CTE
DECLARE #number INT = 87
;WITH C AS(
SELECT Id, Row_Id, ROW_NUMBER() OVER(PARTITION BY Id ORDER BY Id) AS Rn FROM (
SELECT 1 AS Row_Id, Id FROM #tbl
UNION
SELECT 2 AS Row_Id, number
FROM master..spt_values
WHERE [type] = 'P'
AND number >= #number
) t
)
SELECT Id FROM C
WHERE Rn = 1
ORDER BY Row_Id, Id
Output
Id
----
87
90
93
110
130
88
89
91
92
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
111
112
113
114
.
.
.
SQLFiddle
I'm trying to get the top N records for each unique row of data in a table (I'm grouping on columns b,c and d, column a is the unique identifier and column e is the score of which i want the top 1 in this case).
a b c d e
2 38 NULL NULL 141
1 38 NULL NULL 10
1 38 1 NULL 10
2 38 1 NULL 1
1 38 1 8 10
2 38 1 8 1
2 38 16 NULL 140
2 38 16 12 140
e.g. from this data i would like to find the following rows:
a b c d e
2 38 NULL NULL 141
1 38 1 NULL 10
1 38 1 8 10
2 38 16 NULL 140
2 38 16 12 140
can someone please point me in the right direction to solve this?
Your example doesn't show, and you don't explain how you determine which row is the "top" one, so I've put ?????? in the query where you need to provide a ranking column, such as
a desc
for example. In any case, this is exactly what the analytic functions in SQL Server 2005 and later are for.
declare #howmany int = 3;
with TRanked (a,b,c,d,e,rk) as (
select
a,b,c,d,e,
rank() over (
partition by b,c,d
order by ???????
)
from T
)
select a,b,c,d,e
from TRanked
where rk <= #howmany;
The nulls are a pain, but something like this:
select * from table1 t1
where a in (
select top 1 a from table1 t2
where (t1.b = t2.b or (t1.b is null and t2.b is null))
and (t1.c = t2.c or (t1.c is null and t2.c is null))
and (t1.d = t2.d or (t1.d is null and t2.d is null))
order by e desc
)
or better yet:
select * from (
select *, seqno = row_number() over (partition by b, c, d order by e desc)
from table1
) a
where seqno = 1
I believe this will do what you said (extending the idea from here):
select b,c,d,e,
rank() over
(partition by b,c,d order by e desc) "rank"
from t1 where rank < 5
Cheers.