SQL group by, sum, total query - tsql

Can someone help with the query?
I have a table here:
CREATE TABLE [dbo].[aas](
[id] [int] IDENTITY(1,1) NOT NULL,
[Status] [nchar](10) NULL,
[price] [int] NOT NULL
) ON [PRIMARY]
GO
insert into [dbo].[aas] ([Status], [price])
values ('a', 23)
insert into [dbo].[aas] ([Status], [price])
values ('a', 23)
insert into [dbo].[aas] ([Status], [price])
values ('a', 23)
insert into [dbo].[aas] ([Status], [price])
values ('b', 4)
insert into [dbo].[aas] ([Status], [price])
values ('b', 4)
insert into [dbo].[aas] ([Status], [price])
values ('b', 4)
insert into [dbo].[aas] ([Status], [price])
values ('b', 4)
insert into [dbo].[aas] ([Status], [price])
values ('c', 8)
insert into [dbo].[aas] ([Status], [price])
values ('c', 8)
insert into [dbo].[aas] ([Status], [price])
values ('c', 8)
insert into [dbo].[aas] ([Status], [price])
values ('c', 8)
insert into [dbo].[aas] ([Status], [price])
values ('c', 8)
insert into [dbo].[aas] ([Status], [price])
values ('y', 2)
insert into [dbo].[aas] ([Status], [price])
values ('y', 2)
insert into [dbo].[aas] ([Status], [price])
values ('y', 2)
insert into [dbo].[aas] ([Status], [price])
values ('y', 2)
insert into [dbo].[aas] ([Status], [price])
values ('y', 2)
insert into [dbo].[aas] ([Status], [price])
values ('y', 2)
insert into [dbo].[aas] ([Status], [price])
values ('y', 2)
insert into [dbo].[aas] ([Status], [price])
values ('y', 2)
insert into [dbo].[aas] ([Status], [price])
values ('y', 2)
insert into [dbo].[aas] ([Status], [price])
values ('y', 2)
insert into [dbo].[aas] ([Status], [price])
values ('y', 2)
insert into [dbo].[aas] ([Status], [price])
values ('y', 2)
I am expecting an output like this:
TotalA TotalPriceA TotalB TotalPriceB TotalC TotalPriceC TotalY TotalPriceY
3 69 4 16 5 40 12 24
But this query returns redundant data:
select
COUNT(CASE WHEN [status] = 'a' THEN 1 ELSE 0 END) as [TotalA],
case when [status] = 'a' then
sum(price)
else 0
END as [TotalpriceA],
COUNT(CASE WHEN [status] = 'b' THEN 1 ELSE 0 END) as [TotalB],
case when [status] = 'b' then
sum(price)
else 0
END as [TotalpriceB],
COUNT(CASE WHEN [status] = 'c' THEN 1 ELSE 0 END) as [TotalC],
case when [status] = 'c' then
sum(price)
else 0
END as [TotalpriceC],
COUNT(CASE WHEN [status] = 'y' THEN 1 ELSE 0 END) as [TotalY],
case when [status] = 'y' then
sum(price)
else 0
END as [TotalpriceY]
from [dbo].[aas]
group by [status]
Any suggestions?

Group By is going to return one row per 'Status', that's why you are getting 4 rows.
This is the query you want. Though you may want to pivot the data.
SELECT [status], count(*) as 'Total', sum(price) as 'TotalPrice'
from aas
group by [status]

Related

Group Rows by Date

I have been asked to group transactions that have occurred within two minutes of one another into separate "date groups". I'm having a tough time wrapping my head around how to split the data by minutes.
I wrote a test table below along with expected "date groups"
CREATE TABLE #tmpData
(ID int,actionDt datetime)
INSERT INTO #tmpData
(ID,actionDt)
VALUES
(1, '7/22/2021 9:51'),
(1, '7/22/2021 9:52'),
(1, '7/22/2021 9:55'),
(1, '7/22/2021 9:56'),
(1, '7/22/2021 9:57'),
(1, '7/22/2021 9:58'),
(1, '7/22/2021 10:00'),
(1, '7/22/2021 10:10'),
(2, '7/22/2021 8:38'),
(2, '7/22/2021 8:39'),
(2, '7/22/2021 8:40'),
(2, '7/22/2021 12:05')
the expected "date groups" should be
id
DtGroup
1
7/22/2021 9:51
1
7/22/2021 9:55
1
7/22/2021 9:58
1
7/22/2021 10:10
2
7/22/2021 8:38
2
7/22/2021 12:05
I wrote the below which gets close but the timestamps 9:58 and 10:00 for ID 1 should be their own date group.
;with resultSet AS
(
SELECT a.id, a.actiondt, a.diff FROM
(
SELECT
id,
actiondt,
diff = datediff(mi,lag(actiondt) OVER (PARTITION BY id ORDER BY actiondt),actiondt)
FROM #tmpdata
) AS a
WHERE diff IS NULL OR diff > 2
)
SELECT
t.id,
t.actiondt AS currDt,
resultset.actiondt AS DtGrp
from #tmpdata t
left JOIN resultset
on t.id = resultset.id
and t.actiondt between dateadd(mi,-2,resultset.actiondt) and dateadd(mi,2,resultset.actiondt)
Is the logic 2 minutes or greater between actionDt? If so should the expected results be the following? Otherwise, I don't understand your expected results to try to help.
(1, '7/22/2021 9:51'),
(1, '7/22/2021 9:55'),
(1, '7/22/2021 9:57'),
(1, '7/22/2021 10:00'),
(1, '7/22/2021 10:10'),
(2, '7/22/2021 8:38'),
(2, '7/22/2021 8:40'),
(2, '7/22/2021 12:05')
This will give you the above results.
declare #Count int, 
#LoopCount int,
#PrevMinutes int,
#CurrentMinutes int,
#NextMinutes int,
#PrevFlag int,
#Flag int
;with dID as (
select distinct id,
actiondt
from #tmpData
)
select
identity(int,1,1) RowNo,
d.id as Grp,
d.actiondt,
lag(DATEPART(mi, d.actiondt), 1,0) over (order by d.actiondt) as PrevMinutes,
DATEPART(mi, d.actiondt) as CurrentMinutes,
lead(DATEPART(mi, d.actiondt), 1,0) over (order by d.actiondt) as NextMinutes,
0 as flag
into #Temp
from #tmpData d
full outer join dID on d.id = dID.id
and d.actiondt = dID.actiondt
order by d.id, actiondt
select #Count = ##RowCount 
set #LoopCount = 1 
while #LoopCount <= #Count 
begin 
set #PrevMinutes = (select PrevMinutes from #Temp where RowNo = #LoopCount)
set #CurrentMinutes = (select CurrentMinutes from #Temp where RowNo = #LoopCount)
set #NextMinutes = (select NextMinutes from #Temp where RowNo = #LoopCount)
set #Flag = (select flag from #Temp where RowNo = #LoopCount)
set #PrevFlag = (select flag from #Temp where RowNo = #LoopCount - 1)
if (#LoopCount = 1)
begin
update #Temp
set flag = 1
where RowNo = 1
end
else if (abs(#PrevMinutes - #CurrentMinutes) >= 2)
begin
update #Temp
set flag = 1
where RowNo = #LoopCount
end
else if (#PrevFlag = 0 and #Flag = 0)
begin
update #Temp
set flag = 1
where RowNo = #LoopCount
end
    set #LoopCount=#LoopCount + 1 
end 
select Grp as id,
actiondt
from #Temp
where flag = 1

Unexpected ROW_NUMBER behaviour when OUTPUT through DELETE

I would expect [version] to be larger than 1 in #X below, but it rather seems as if ROW_NUMBER is reevaluated on its way into #X. Is this the intended behavior and is there any way to prevent it?
DROP TABLE IF EXISTS #T;
CREATE TABLE #T (id INT, v CHAR(1));
INSERT INTO #T VALUES (1, 'a'), (1, 'b'), (2, 'a'), (2, 'b'), (2, 'c');
DROP TABLE IF EXISTS #X;
SELECT TOP 0 *, 1 AS [version] INTO #X FROM #T;
DELETE t OUTPUT deleted.* INTO #X FROM (
SELECT *, ROW_NUMBER() OVER (PARTITION BY id ORDER BY v) AS [version] FROM #T
) t WHERE t.[version] > 1;
SELECT * FROM #X;

Order rows in a sequence and fill gaps for missing rows

I got a problem regarding missing rows in a table that is giving me a headache.
As base data, I have the following table:
declare #table table
(
id1 int,
id2 int,
ch char(1) not null,
val int
)
insert into #table values (1112, 121, 'A', 12)
insert into #table values (1351, 121, 'A', 13)
insert into #table values (1411, 121, 'B', 81)
insert into #table values (1312, 7, 'C', 107)
insert into #table values (1401, 2, 'A', 107)
insert into #table values (1454, 2, 'D', 107)
insert into #table values (1257, 6, 'A', 1)
insert into #table values (1269, 6, 'B', 12)
insert into #table values (1335, 6, 'C', 12)
insert into #table values (1341, 6, 'D', 5)
insert into #table values (1380, 6, 'A', 3)
The output should be ordered by id2 and follow a fixed sequence of ch, which should repeat until next id2 begins.
Sequence:
'A'
'B'
'C'
'D'
If the sequence or the pattern is interrupted, it should fill the missing rows with null, so that i get this result table:
id1 id2 ch val
----------------------------
1112 121 'A' 12
NULL 121 'B' NULL
NULL 121 'C' NULL
NULL 121 'D' NULL
1351 121 'A' 13
1411 121 'B' 81
NULL 121 'C' NULL
NULL 121 'D' NULL
NULL 7 'A' NULL
NULL 7 'B' NULL
1312 7 'C' 107
NULL 7 'D' NULL
1401 2 'A' 107
NULL 2 'B' NULL
NULL 2 'C' NULL
1454 2 'D' 107
and so on...
What I'm looking for is a way to do this without iterations.
I hope someone can help!
Thanks in advance!
A solution might be this:
declare #table table ( id1 int, id2 int, ch char(1) not null, val int )
insert into #table values (1112, 121, 'A', 12)
,(1351, 121, 'A', 13),(1411, 121, 'B', 81),(1312, 7, 'C', 107),(1401, 2, 'A', 107)
,(1454, 2, 'D', 107),(1257, 6, 'A', 1),(1269, 6, 'B', 12),(1335, 6, 'C', 12)
,(1341, 6, 'D', 5),(1380, 6, 'A', 3)
;with foo as
(select
*
,row_number() over (partition by id2 order by id1) rwn
,ascii(isnull(lag(ch,1) over (partition by id2 order by id1),'A'))-ascii('A') prev
,count(*) over (partition by id2,ch) nr
,ascii(ch)-ascii('A') cur
from #table
)
,bar as
(
select
*,case when cur<=prev and rwn>1 then 4 else 0 end + cur-prev step
from foo
)
,foobar as
(
select *,sum(step) over (partition by id2 order by id1 rows unbounded preceding) rownum
from bar
)
,iterations as
(
select id2,max(nr) nr from foo
group by id2
)
,blanks as
(
select
id2,ch chnr,char(ch+ascii('A') )ch,ROW_NUMBER() over (partition by id2 order by c.nr,ch)-1 rownum,c.nr
from iterations a
inner join (values (1),(2),(3),(4),(5),(6),(7),(8),(9),(10)) c(nr)
on c.nr<=a.nr
cross join (values (0),(1),(2),(3)) b(ch)
)
select
b.id1,a.id2,a.ch,b.val
from blanks a
left join foobar b
on a.id2=b.id2 and a.rownum=b.rownum
order by a.id2,a.rownum
I first make the query "foo" which looks at the row number and gets the previous value for ch for each id2.
"bar" then finds how many missing values there are between the rows. For instance If the previous was an A and the current is a c then there are 2. If the previous was an A and the current is an A, then there are 4!
"foobar" then adds the steps, thus numbering the original rows, where they should be in the final output.
"iterations" counts the number of times the "ABCD" rows should appear.
"BLANKS" then is all the final rows, that is for each id2, it outputs all the "ABCD" rows that should be in the final output, and numbers them in rownum
Finally I left join "foobar" with "BLANKS" on id2 and rownum. Thus we get the correct number of rows, and the places where there are values in the original is output.
If you can manage to add an extra column in your table, that defines which [id2] are part from the same sequence you can try this:
declare #table table
(
id1 int,
id2 int,
ch char(1) not null,
val int,
category int -- extra column
)
insert into #table values (1112, 121, 'A', 12, 1)
insert into #table values (1351, 121, 'A', 13, 2)
insert into #table values (1411, 121, 'B', 81, 2)
insert into #table values (1312, 7, 'C', 107, 3)
insert into #table values (1401, 2, 'A', 107, 4)
insert into #table values (1454, 2, 'D', 107, 4)
insert into #table values (1257, 6, 'A', 1, 5)
insert into #table values (1269, 6, 'B', 12, 5)
insert into #table values (1335, 6, 'C', 12, 5)
insert into #table values (1341, 6, 'D', 5, 5)
insert into #table values (1380, 6, 'A', 3, 5)
DECLARE #sequence table (seq varchar(1))
INSERT INTO #sequence values ('A'), ('B'), ('C'), ('D')
SELECT b.id1, a.id2, a.seq, b.val, a.category
INTO #T1
FROM (
SELECT *
FROM #table
CROSS JOIN #sequence
) A
LEFT JOIN (
SELECT * FROM #table
) B
ON 1=1
AND a.id1 = b.id1
AND a.id2 = b.id2
AND a.seq = b.ch
AND a.val = b.val
;WITH rem_duplicates AS (
SELECT *, dup = ROW_NUMBER() OVER (PARTITION by id2, seq, category ORDER BY id1 DESC)
FROM #T1
) DELETE FROM rem_duplicates WHERE dup > 1
SELECT * FROM #T1 ORDER BY id2 DESC, category ASC, seq ASC
DROP TABLE #T1
I'm little confused by your output, try this:
Update
DECLARE #table TABLE
(
row INT IDENTITY(1, 1) ,
id1 INT ,
id2 INT ,
ch CHAR(1) NOT NULL ,
val INT
);
DECLARE #Sequence TABLE ( ch3 CHAR(1) NOT NULL );
INSERT INTO #Sequence
VALUES ( 'A' );
INSERT INTO #Sequence
VALUES ( 'B' );
INSERT INTO #Sequence
VALUES ( 'C' );
INSERT INTO #Sequence
VALUES ( 'D' );
INSERT INTO #table
VALUES ( 1112, 121, 'A', 12 );
INSERT INTO #table
VALUES ( 1351, 121, 'A', 13 );
INSERT INTO #table
VALUES ( 1411, 121, 'B', 81 );
INSERT INTO #table
VALUES ( 1312, 7, 'C', 107 );
INSERT INTO #table
VALUES ( 1401, 2, 'A', 107 );
INSERT INTO #table
VALUES ( 1454, 2, 'D', 107 );
INSERT INTO #table
VALUES ( 1257, 6, 'A', 1 );
INSERT INTO #table
VALUES ( 1269, 6, 'B', 12 );
INSERT INTO #table
VALUES ( 1335, 6, 'C', 12 );
INSERT INTO #table
VALUES ( 1341, 6, 'D', 5 );
INSERT INTO #table
VALUES ( 1380, 6, 'A', 3 );
SELECT r.id1 ,
fin.id2 ,
ch3 ,
r.val
FROM ( SELECT *
FROM ( SELECT CASE WHEN r.chd - l.chd = 1 THEN 0
ELSE 1
END [gap in sq] ,
l.*
FROM ( SELECT id2 ,
ASCII(ch) chd ,
ch ,
val ,
id1 ,
row
FROM #table
) AS l
LEFT JOIN ( SELECT id2 ,
ASCII(ch) chd ,
row
FROM #table
) AS r ON l.row = r.row - 1
) AS temp ,
#Sequence s
WHERE temp.[gap in sq] = 1
OR ( temp.[gap in sq] = 0
AND s.ch3 = temp.ch
)
) AS fin
LEFT JOIN #table r ON r.id2 = fin.id2
AND r.id1 = fin.id1
AND r.ch = fin.ch3

Need help with a SELECT statement

I express the relationship between records and searchtags that can be attached to records like so:
TABLE RECORDS
id
name
TABLE SEARCHTAGS
id
recordid
name
I want to be able to SELECT records based on the searchtags that they have. For example, I want to be able to SELECT all records that have searchtags:
(1 OR 2 OR 5) AND (6 OR 7) AND (10)
Using the above data structure, I am uncertain how to structure the SQL to accomplish this.
Any suggestions?
Thanks!
You may want to try the following:
SELECT r.id, r.name
FROM records r
WHERE EXISTS (SELECT NULL FROM searchtags WHERE recordid = r.id AND id IN (1, 2, 5)) AND
EXISTS (SELECT NULL FROM searchtags WHERE recordid = r.id AND id IN (6, 7)) AND
EXISTS (SELECT NULL FROM searchtags WHERE recordid = r.id AND id IN (10));
Test case: Note that only records 1 and 4 will satisfy the query criteria.
CREATE TABLE records (id int, name varchar(10));
CREATE TABLE searchtags (id int, recordid int);
INSERT INTO records VALUES (1, 'a');
INSERT INTO records VALUES (2, 'b');
INSERT INTO records VALUES (3, 'c');
INSERT INTO records VALUES (4, 'd');
INSERT INTO searchtags VALUES (1, 1);
INSERT INTO searchtags VALUES (2, 1);
INSERT INTO searchtags VALUES (6, 1);
INSERT INTO searchtags VALUES (10, 1);
INSERT INTO searchtags VALUES (1, 2);
INSERT INTO searchtags VALUES (2, 2);
INSERT INTO searchtags VALUES (3, 2);
INSERT INTO searchtags VALUES (1, 3);
INSERT INTO searchtags VALUES (10, 3);
INSERT INTO searchtags VALUES (5, 4);
INSERT INTO searchtags VALUES (7, 4);
INSERT INTO searchtags VALUES (10, 4);
Result:
+------+------+
| id | name |
+------+------+
| 1 | a |
| 4 | d |
+------+------+
2 rows in set (0.01 sec)
SELECT
id, name
FROM
records
WHERE
EXISTS (
SELECT 1 FROM searchtags WHERE recordid = records.id AND id IN (1, 2, 5)
)
AND EXISTS (
SELECT 1 FROM searchtags WHERE recordid = records.id AND id IN (6, 7)
)
AND EXISTS (
SELECT 1 FROM searchtags WHERE recordid = records.id AND id IN (10)
)
not sure how to do it in mysql, but in t-sql, you could do something like:
SELECT id, name FROM RECORDS where id in (SELECT recordid from SEARCHTAGS where id in (1,2,5,6,7,10))
I may not be understanding your question entirely... but I gave it my best.
Try:
SELECT R.*
FROM RECORDS R, SEARCHTAGS S
WHERE R.id == S.recordid
AND S.name in (1,2,5,6,7,10);
Don't know if you need S.name or S.id, but this is an example.
select RECORDS.name
from RECORDS join SEARCHTAGS
on RECORDS.id = SEARCHTAGS.recordid
where RECORDS.id in (1,2,...)
I misread the question first time around, and thought it was asking for
(1 AND 2 AND 5) OR (6 AND 7) OR (10)
instead of the correct
(1 OR 2 OR 5) AND (6 OR 7) AND (10)
All the answers so far have concentrated on answering the specific example, rather than addressing the more general question "and suppose I want a different set of criteria next time".
Actual question
I can't do much better than the selected answer for the actual question (Query 1):
SELECT r.id, r.name
FROM Records AS r
WHERE EXISTS(SELECT * FROM SearchTags AS s
WHERE r.id = s.recordid AND s.id IN (1, 2, 5))
AND EXISTS(SELECT * FROM SearchTags AS s
WHERE r.id = s.recordid AND s.id IN (6, 7))
AND EXISTS(SELECT * FROM SearchTags AS s
WHERE r.id = s.recordid AND s.id IN (10));
This could be written as a join to 3 aliases for the SearchTags table.
Alternative question
There are several ways to answer the alternative - I think this is the most nearly neat and extensible. Clearly, the one item (10) is easy (Query 2):
SELECT r.id, r.name
FROM records AS r JOIN searchtags AS t ON r.id = t.recordid
WHERE t.id IN (10) -- or '= 10' but IN is consistent with what follows
The two items (6 or 7) can be done with (Query 3):
SELECT r.id, r.name
FROM records AS r JOIN searchtags AS t ON r.id = t.recordid
WHERE t.id IN (6, 7)
GROUP BY r.id, r.name
HAVING COUNT(*) = 2
The three items (1, 2, 5) can be done with (Query 4):
SELECT r.id, r.name
FROM records AS r JOIN searchtags AS t ON r.id = t.recordid
WHERE t.id IN (1, 2, 5)
GROUP BY r.id, r.name
HAVING COUNT(*) = 3
And the whole collection can be a UNION of the three terms.
Generalizing the solutions
The downside of this solution is that the SQL must be manually crafted for each set of items.
If you want to automate the 'SQL generation', you need the control data - the sets of interesting search tags - in a table:
CREATE TABLE InterestingTags(GroupID INTEGER, TagID INTEGER);
INSERT INTO InterestingTags(1, 1);
INSERT INTO InterestingTags(1, 2);
INSERT INTO InterestingTags(1, 5);
INSERT INTO InterestingTags(2, 6);
INSERT INTO InterestingTags(2, 7);
INSERT INTO InterestingTags(3, 10);
For the query asking for '(1 OR 2 OR 5) AND (...)' (conjunctive normal form), you can write (Query 5):
SELECT r.id, r.name
FROM records AS r JOIN
searchtags AS s ON r.id = s.recordID JOIN
interestingtags AS t ON s.id = t.tagID
GROUP BY r.id, r.name
HAVING COUNT(DISTINCT t.GroupID) = (SELECT COUNT(DISTINCT GroupID)
FROM InterestingTags);
This checks that the number of distinct 'interesting groups of tags' for a given record is equal to the total number of 'interesting groups of tags'.
For the query asking for '(1 AND 2 AND 5) OR (...)' (disjunctive normal form), you can write a join with InterestingTags and check that the Record has as many entries as the group of tags (Query 6):
SELECT i.id, i.name
FROM (SELECT q.id, q.name, c.GroupSize,
COUNT(DISTINCT t.GroupID) AS GroupCount
FROM records AS q JOIN
searchtags AS s ON q.id = s.recordID JOIN
interestingtags AS t ON s.id = t.tagID JOIN
(SELECT GroupID, COUNT(*) AS GroupSize
FROM InterestingTags
GROUP BY GroupID) AS c ON c.GroupID = t.GroupID
GROUP BY q.id, q.name, c.GroupSize
) AS i
WHERE i.GroupCount = i.GroupSize;
Test Data
I took the test data from Daniel Vassalo's answer and augmented it with some extra values:
CREATE TABLE records (id int, name varchar(10));
CREATE TABLE searchtags (id int, recordid int);
INSERT INTO records VALUES (1, 'a');
INSERT INTO records VALUES (2, 'b');
INSERT INTO records VALUES (3, 'c');
INSERT INTO records VALUES (4, 'd');
INSERT INTO records VALUES (11, 'A11');
INSERT INTO records VALUES (21, 'B12');
INSERT INTO records VALUES (31, 'C13');
INSERT INTO records VALUES (41, 'D14');
INSERT INTO records VALUES (51, 'E15');
INSERT INTO records VALUES (61, 'F16');
INSERT INTO searchtags VALUES (1, 1);
INSERT INTO searchtags VALUES (2, 1);
INSERT INTO searchtags VALUES (6, 1);
INSERT INTO searchtags VALUES (10, 1);
INSERT INTO searchtags VALUES (1, 2);
INSERT INTO searchtags VALUES (2, 2);
INSERT INTO searchtags VALUES (3, 2);
INSERT INTO searchtags VALUES (1, 3);
INSERT INTO searchtags VALUES (10, 3);
INSERT INTO searchtags VALUES (5, 4);
INSERT INTO searchtags VALUES (7, 4);
INSERT INTO searchtags VALUES (10, 4);
INSERT INTO searchtags VALUES (1, 11);
INSERT INTO searchtags VALUES (2, 11);
INSERT INTO searchtags VALUES (5, 11);
INSERT INTO searchtags VALUES (6, 21);
INSERT INTO searchtags VALUES (7, 21);
INSERT INTO searchtags VALUES (10, 31);
INSERT INTO searchtags VALUES (1, 41);
INSERT INTO searchtags VALUES (6, 41);
INSERT INTO searchtags VALUES (10, 41);
INSERT INTO searchtags VALUES (2, 51);
INSERT INTO searchtags VALUES (5, 51);
INSERT INTO searchtags VALUES (10, 51);
INSERT INTO searchtags VALUES (7, 61);
INSERT INTO searchtags VALUES (2, 61);
INSERT INTO searchtags VALUES (1, 61);
CREATE TABLE InterestingTags(GroupID INTEGER, TagID INTEGER);
INSERT INTO InterestingTags VALUES(1, 1);
INSERT INTO InterestingTags VALUES(1, 2);
INSERT INTO InterestingTags VALUES(1, 5);
INSERT INTO InterestingTags VALUES(2, 6);
INSERT INTO InterestingTags VALUES(2, 7);
INSERT INTO InterestingTags VALUES(3, 10);
Test results
The outputs that I got were:
Query 1
1 a
4 d
41 D14
Query 2
1 a
3 c
4 d
31 C13
41 D14
51 E15
Query 3
21 B12
Query 4
11 A11
Query 5
1 a
41 D14
4 d
Query 6
4 d
31 C13
3 c
1 a
41 D14
51 E15
Clearly, if I wanted the output in a specific order, I would add an ORDER BY clause to the queries.

SQL Server Conditional Comparing

I have two tables:
CREATE TABLE #HOURS
(DAY INTEGER,
HOUR INTEGER)
CREATE TABLE #PERSONS
(DAY INTEGER, HOUR INTEGER,
Name NVARCHAR(50))
GO
INSERT #HOURS VALUES (1, 5)
INSERT #HOURS VALUES (1, 6)
INSERT #HOURS VALUES (1, 8)
INSERT #HOURS VALUES (1, 10)
INSERT #HOURS VALUES (1, 14)
INSERT #HOURS VALUES (1, 15)
INSERT #HOURS VALUES (1, 16)
INSERT #HOURS VALUES (1, 17)
INSERT #HOURS VALUES (1, 18)
INSERT #PERSONS VALUES (1, 5, 'Steve')
INSERT #PERSONS VALUES (1, 6, 'Steve')
INSERT #PERSONS VALUES (1, 7, 'Steve')
INSERT #PERSONS VALUES (1, 8, 'Steve')
INSERT #PERSONS VALUES (1, 10, 'Steve')
INSERT #PERSONS VALUES (1, 14, 'Steve')
INSERT #PERSONS VALUES (1, 15, 'Steve')
INSERT #PERSONS VALUES (1, 16, 'Steve')
INSERT #PERSONS VALUES (1, 17, 'Steve')
INSERT #PERSONS VALUES (1, 10, 'Jim')
INSERT #PERSONS VALUES (1, 11, 'Jim')
INSERT #PERSONS VALUES (1, 12, 'Jim')
INSERT #PERSONS VALUES (1, 13, 'Jim')
GO
Hours shows the work hours and #Persons shows the persons that entered the system on hourly base.
I'd like to find the persons whose work hours matches the hours table. But he or she can skip two work hours.
I've tried this:
select t.Day, sum(t.Nulls)
from
(select h.Hour, h.Day
, Case
WHEN p.Hour is null Then 1 ELSE 0 END Nulls
from #HOURS h
left join #PERSONS P on h.Hour = p.Hour AND h.Day = p.Day) t
group by t.Day
HAVING sum(t.Nulls) < 2
But this only works when there is not different persons on the same day ;)
Any suggestions?
What I think you mean is that for each combination of day and person, you want to return it if the number of valid hours that that person worked on that day is within 2 hours of the number of valid hours that exist for that day. If so, this should do the trick:
SELECT
Day
, Name
, HoursWorked
, HoursInDay
FROM (
SELECT
p.Day
, p.Name
, COUNT(*) HoursWorked
, (SELECT COUNT(*) FROM #Hours H2 WHERE H2.Day = P.Day) HoursInDay
FROM
#Persons P INNER JOIN #Hours H
ON P.Day = H.Day And P.Hour = H.Hour
GROUP BY
p.Day, p.Name
) Data
WHERE
HoursWorked + 2 >= HoursInDay
I think you still need to clarify a bit further what you'd expect as a result. In the mean time, would this get you started?
SELECT p.DAY, p.Name, WORKED = COUNT(*), WORKHOURS = AVG(hc.WORKHOURS)
FROM #PERSONS p
INNER JOIN #HOURS h ON h.DAY = p.DAY AND h.HOUR = p.HOUR
LEFT OUTER JOIN (
SELECT DAY, WORKHOURS = COUNT(*)
FROM #HOURS
GROUP BY DAY
) hc ON hc.DAY = p.DAY
GROUP BY p.DAY, p.Name