I have sample data:
RowId TypeId Value
1 1 34
2 1 53
3 1 34
4 2 43
5 2 65
6 16 54
7 16 34
8 1 45
9 6 43
10 6 34
11 16 64
12 16 63
I want to count row for each type (The Value does not matter to me), but only for... neighbor TypeId
TypeId Count
1 3
2 2
16 2
1 1
6 2
16 2
How to achieve this result?
This should give you COUNT of rows within a group of unchanged values:
SELECT TypeId, grp, COUNT(*) FROM (
SELECT RowId, TypeId , Value, gap, SUM(gap) over (ORDER BY RowId ) grp
FROM (SELECT RowId, TypeId , Value,
CASE WHEN TypeId = lag(TypeId) over (ORDER BY RowId )
THEN 0
ELSE 1
END gap
FROM dummy
) t
) tt
GROUP BY TypeId, grp;
If you prefer WITH over endless sub-query inclusions:
WITH dummy_with_groups AS (
SELECT RowId, TypeId , Value, SUM(gap) OVER (ORDER BY RowId) grp
FROM (SELECT RowId, TypeId , Value,
CASE WHEN TypeId = lag(TypeId) OVER (ORDER BY RowId)
THEN 0 ELSE 1 END gap
FROM dummy) t
)
SELECT TypeId, COUNT(*) as Result
FROM dummy_with_groups
GROUP BY TypeId, grp;
http://www.sqlfiddle.com/#!6/f16e9/34
Check this fiddle demo. I have renamed your columns a little.
WITH myCTE AS
(SELECT row_id,
type_id,
ROW_NUMBER () OVER (PARTITION BY type_id ORDER BY row_id)
AS cnt,
CASE LEAD (type_id) OVER (ORDER BY row_id)
WHEN type_id THEN 0
ELSE 1
END
AS show
FROM dummy),
innerQuery AS
(SELECT row_id, type_id, cnt
FROM myCTE
WHERE show = 1)
SELECT iq1.type_id, iq1.cnt - ISNULL (iq2.cnt, 0) CNT
FROM innerQuery iq1
LEFT OUTER JOIN innerQuery iq2
ON iq1.type_id = iq2.type_id
AND EXISTS
(SELECT 1
FROM innerQuery iq3
WHERE iq3.type_id = iq1.type_id
AND iq3.row_id < iq1.row_id
HAVING MAX (iq3.row_id) = iq2.row_id)
The output is exactly as expected.
Related
I wrote these 2 queries, the first one is keeping duplicates and the second one is dropping them
Does anyone know a more efficient way to achieve this?
Queries are for MSSQL, returning the top 3 values
1-
SELECT TMP.entity_id, TMP.value
FROM(
SELECT TAB.entity_id, LEAD(TAB.entity_id, 3, 0) OVER(ORDER BY TAB.entity_id, TAB.value) AS next_id, TAB.value
FROM mytable TAB
) TMP
WHERE TMP.entity_id <> TMP.next_id
2-
SELECT TMP.entity_id, TMP.value
FROM(
SELECT TMX.entity_id, LEAD(TMX.entity_id, 3, 0) OVER(ORDER BY TMX.entity_id, TMX.value) AS next_id, TMX.value
FROM(
SELECT TAB.entity_id, LEAD(TAB.entity_id, 1, 0) OVER(ORDER BY TAB.entity_id, TAB.value) AS next_id, TAB.value, LEAD(TAB.value, 1, 0) OVER(ORDER BY TAB.entity_id, TAB.value) AS next_value
FROM mytable TAB
) TMX
WHERE TMP.entity_id <> TMP.next_id OR TMX.value <> TMX.next_value
) TMP
WHERE TMP.entity_id <> TMP.next_id
Example:
Table:
entity_id value
--------- -----
1 9
1 11
1 12
1 3
2 25
2 25
2 5
2 37
3 24
3 9
3 2
3 15
Result Query 1 (25 appears twice for entity_id 2):
entity_id value
--------- -----
1 9
1 11
1 12
2 25
2 25
2 37
3 9
3 15
3 24
Result Query 2 (25 appears only once for entity_id 2):
entity_id value
--------- -----
1 9
1 11
1 12
2 5
2 25
2 37
3 9
3 15
3 24
You can use the ROW_NUMBER which will allow duplicates as follows:
select entity_id, value from
(select t.*, row_number() over (partition by entity_id order by value desc) as rn
from your_Table) where rn <= 3
You can use the rank to remove the duplicate as follows:
select distinct entity_id, value from
(select t.*, rank() over (partition by entity_id order by value desc) as rn
from your_Table) where rn <= 3
What we have
I have table like this
id PlayerId Amount
----------- ----------- -----------
1 1 10
2 1 20
3 1 30
4 1 40
5 1 40
11 1 20
13 1 20
15 1 40
14 2 19
12 2 10
6 2 1
7 2 5
8 2 10
9 2 20
10 2 30
I have to select only rows where amount greater than previous row amount (per player).
So here is a query
SELECT a.id,
a.PlayerId,
a.Amount,
a.PreVval,
a.NextVal
FROM (SELECT id,
PlayerId,
Amount,
LAG(Amount) OVER (PARTITION BY PlayerId ORDER BY id) PreVval,
lead(Amount) OVER (PARTITION BY PlayerId ORDER BY id) NextVal
FROM dbo.Bets ) a
WHERE a.Amount > a.PreVval OR a.Amount < a.NextVal OR (a.PreVval IS NULL AND a.Amount < a.NextVal)
ORDER BY a.PlayerId, a.id
id PlayerId Amount PreVval NextVal
----------- ----------- ----------- ----------- -----------
1 1 10 NULL 20
2 1 20 10 30
3 1 30 20 40
4 1 40 30 40
13 1 20 20 40
15 1 40 20 NULL
6 2 1 NULL 5
7 2 5 1 10
8 2 10 5 20
9 2 20 10 30
10 2 30 20 10
12 2 10 30 19
14 2 19 10 NULL
Question
So now i need to select sets where increase step count > 4 , i mean 1,2,3,4 for player 1 and 6,7,8,9,10 for player 2
Query should run over 15m rows
The following query is an example where you can set the "step_count".
WITH Bets(id,PlayerId,Amount)
AS
(
SELECT 1,1,10 UNION ALL
SELECT 2,1,20 UNION ALL
SELECT 3,1,30 UNION ALL
SELECT 4,1,40 UNION ALL
SELECT 5,1,40 UNION ALL
SELECT 11,1,20 UNION ALL
SELECT 13,1,20 UNION ALL
SELECT 15,1,40 UNION ALL
SELECT 14,2,19 UNION ALL
SELECT 12,2,10 UNION ALL
SELECT 6,2,1 UNION ALL
SELECT 7,2,5 UNION ALL
SELECT 8,2,10 UNION ALL
SELECT 9,2,20 UNION ALL
SELECT 10,2,30
)
,split_ranges
as(
select *,case when lag(amount) over(partition by playerid order by id) > amount
or lag(amount) over(partition by playerid order by id) is null
then row_number() over(partition by playerid order by id)
end as rnk_val
from bets
)
,groups_data
as(
select *
,max(rnk_val) over(partition by playerid order by id) as fill_ranges
from split_ranges
)
select * from (
select *,count(*) over(partition by playerid,fill_ranges) as cnt
from groups_data
)x
where x.cnt>=4
https://dbfiddle.uk/?rdbms=sqlserver_2019&fiddle=6bd815da2cbfa8f65bc999e5736f2041
The following logic is bit tricky, but you can check this out-
DEMO HERE
WITH CTE
AS
(
SELECT * FROM
(
SELECT id,
PlayerId,
Amount,
LAG(Amount) OVER (PARTITION BY PlayerId ORDER BY id) PreVval,
lead(Amount) OVER (PARTITION BY PlayerId ORDER BY id) NextVal,
ISNULL(LAG(ID,3) OVER (PARTITION BY PlayerId ORDER BY id),0) LAG3,
ISNULL(LAG(ID,2) OVER (PARTITION BY PlayerId ORDER BY id),0) LAG2,
ISNULL(LAG(ID,1) OVER (PARTITION BY PlayerId ORDER BY id),0) LAG1,
ISNULL(LEAD(ID,1) OVER (PARTITION BY PlayerId ORDER BY id),0) LEAD1,
ISNULL(LEAD(ID,2) OVER (PARTITION BY PlayerId ORDER BY id),0) LEAD2,
ISNULL(LEAD(ID,3) OVER (PARTITION BY PlayerId ORDER BY id),0) LEAD3
FROM Bets
) a
WHERE a.Amount > a.PreVval
OR a.Amount < a.NextVal
OR (a.PreVval IS NULL AND a.Amount < a.NextVal)
)
SELECT id,PlayerId,Amount,PreVval,NextVal
FROM CTE A
WHERE ID-LAG3 = 3
OR LEAD1 - LAG2 = 3
OR LEAD2 - LAG1 = 3
OR LEAD3 - ID = 3
In DB2 is there a way to assign a column value based on the first x%, then y% and remaining z% of rows?
I've tried using row_number() function but no luck!
Example below
Assuming that the below example count(id) is already arranged in descending order
Input:
ID count(id)
5 10
3 8
1 5
4 3
2 1
Output:
First 30% rows of the above input should be assigned code H, last 30% of the rows will have code L and remaining will have code M. If 30% of rows evaluates to decimal then round up-to 0 decimal place.
ID code
5 H
3 H
1 M
4 L
2 L
You can use window functions:
select t.id,
(case ntile(3) over (order by count(id) desc)
when 1 then 'H'
when 2 then 'M'
when 3 then 'L'
end) as grp
from t
group by t.id;
This puts them into equal sized groups.
For 30-40-30% split with your conditions, you have to be more careful:
select t.id,
(case when (seqnum - 1.0) < 0.3 * cnt then 'H'
when (seqnum + 1.0) > 0.7 * cnt then 'L'
else 'M'
end) as grp
from (select t.id,
count(*) as cnt,
count(*) over () as num_ids,
row_number() over (order by count(*) desc) as seqnum
from t
group by t.id
) t
Try this:
with t(ID, count_id) as (values
(5, 10)
, (3, 8)
, (1, 5)
, (4, 3)
, (2, 1)
)
select t.*
, case
when pst <=30 then 'H'
when pst <=70 then 'M'
else 'L'
end as code
from
(
select t.*
, rownumber() over (order by count_id desc) as rn
, 100*rownumber() over (order by count_id desc)/nullif(count(1) over(), 0) as pst
from t
) t;
The result is:
ID COUNT_ID RN PST CODE
-- -------- -- --- ----
5 10 1 20 H
3 8 2 40 M
1 5 3 60 M
4 3 4 80 L
2 1 5 100 L
I have a table like so
ID OrdID Value
1 1 0
2 2 0
3 1 1
4 2 1
5 1 1
6 2 0
7 1 0
8 2 0
9 2 1
10 1 0
11 2 0
I want to get the count of consecutive value where the value is 0. Using the example above the result will be 3 (Rows 6, 7 and 8). I am using sql server 2008 r2.
I am going to presume that id is unique and increasing. You can get counts of consecutive values by using the different of row numbers. The following counts all sequences:
select grp, value, min(id), max(id), count(*) as cnt
from (select t.*,
(row_number() over (order by id) - row_number() over (partition by value order by id)
) as grp
from table t
) t
group by grp, value;
If you want the longest sequence of 0s:
select top 1 grp, value, min(id), max(id), count(*) as cnt
from (select t.*,
(row_number() over (order by id) - row_number() over (partition by value order by id)
) as grp
from table t
) t
group by grp, value
having value = 0
order by count(*) desc
A query using not exists to find consecutive 0s
select top 1 min(t2.id), max(t2.id), count(*)
from mytable t
join mytable t2 on t2.id <= t.id
where not exists (
select 1 from mytable t3
where t3.id between t2.id and t.id
and t3.value <> 0
)
group by t.id
order by count(*) desc
http://sqlfiddle.com/#!3/52989/3
I have a table that has values and group ids (simplified example). I need to get the average for each group of the middle 3 values. So, if there are 1, 2, or 3 values it's just the average. But if there are 4 values, it would exclude the highest, 5 values the highest and lowest, etc. I was thinking some sort of window function, but I'm not sure if it's possible.
http://www.sqlfiddle.com/#!11/af5e0/1
For this data:
TEST_ID TEST_VALUE GROUP_ID
1 5 1
2 10 1
3 15 1
4 25 2
5 35 2
6 5 2
7 15 2
8 25 3
9 45 3
10 55 3
11 15 3
12 5 3
13 25 3
14 45 4
I'd like
GROUP_ID AVG
1 10
2 15
3 21.6
4 45
Another option using analytic functions;
SELECT group_id,
avg( test_value )
FROM (
select t.*,
row_number() over (partition by group_id order by test_value ) rn,
count(*) over (partition by group_id ) cnt
from test t
) alias
where
cnt <= 3
or
rn between floor( cnt / 2 )-1 and ceil( cnt/ 2 ) +1
group by group_id
;
Demo --> http://www.sqlfiddle.com/#!11/af5e0/59
I'm not familiar with the Postgres syntax on windowed functions, but I was able to solve your problem in SQL Server with this SQL Fiddle. Maybe you'll be able to easily migrate this into Postgres-compatible code. Hope it helps!
A quick primer on how I worked it.
Order the test scores for each group
Get a count of items in each group
Use that as a subquery and select only the middle 3 items (that's the where clause in the outer query)
Get the average for each group
--
select
group_id,
avg(test_value)
from (
select
t.group_id,
convert(decimal,t.test_value) as test_value,
row_number() over (
partition by t.group_id
order by t.test_value
) as ord,
g.gc
from
test t
inner join (
select group_id, count(*) as gc
from test
group by group_id
) g
on t.group_id = g.group_id
) a
where
ord >= case when gc <= 3 then 1 when gc % 2 = 1 then gc / 2 else (gc - 1) / 2 end
and ord <= case when gc <= 3 then 3 when gc % 2 = 1 then (gc / 2) + 2 else ((gc - 1) / 2) + 2 end
group by
group_id
with cte as (
select
*,
row_number() over(partition by group_id order by test_value) as rn,
count(*) over(partition by group_id) as cnt
from test
)
select
group_id, avg(test_value)
from cte
where
cnt <= 3 or
(rn >= cnt / 2 - 1 and rn <= cnt / 2 + 1)
group by group_id
order by group_id
sql fiddle demo
in the cte, we need to get count of elements over each group_id by window function + calculate row_number inside each group_id. Then, if this count > 3 then we need to get middle of the group by dividing count by 2 and then get +1 and -1 element. If count <= 3, then we should just take all elements.
This works:
SELECT A.group_id, avg(A.test_value) AS avg_mid3 FROM
(SELECT group_id,
test_value,
row_number() OVER (PARTITION BY group_id ORDER BY test_value) AS position
FROM test) A
JOIN
(SELECT group_id,
CASE
WHEN count(*) < 4 THEN 1
WHEN count(*) % 2 = 0 THEN (count(*)/2 - 1)
ELSE (count(*) / 2)
END AS position_start,
CASE
WHEN count(*) < 4 THEN count(*)
WHEN count(*) % 2 = 0 THEN (count(*)/2 + 1)
ELSE (count(*) / 2 + 2)
END AS position_end
FROM test GROUP BY group_id) B
ON A.group_id=B.group_id
AND A.position >= B.position_start
AND A.position <= B.position_end
GROUP BY A.group_id
Fiddle link: http://www.sqlfiddle.com/#!11/af5e0/56
If you need to calculate the average values for groups then you can do this:
SELECT CASE WHEN NUMBER_FIRST_GROUP <> 0
THEN SUM_FIRST_GROUP / NUMBER_FIRST_GROUP
ELSE NULL
END AS AVG_FIRST_GROUP,
CASE WHEN NUMBER_SECOND_GROUP <> 0
THEN SUM_SECOND_GROUP / NUMBER_SECOND_GROUP
ELSE NULL
END AS AVG_SECOND_GROUP,
CASE WHEN NUMBER_THIRD_GROUP <> 0
THEN SUM_THIRD_GROUP / NUMBER_THIRD_GROUP
ELSE NULL
END AS AVG_THIRD_GROUP,
CASE WHEN NUMBER_FOURTH_GROUP <> 0
THEN SUM_FOURTH_GROUP / NUMBER_FOURTH_GROUP
ELSE NULL
END AS AVG_FOURTH_GROUP
FROM (
SELECT
SUM(CASE WHEN GROUP_ID = 1 THEN 1 ELSE 0 END) AS NUMBER_FIRST_GROUP,
SUM(CASE WHEN GROUP_ID = 1 THEN TEST_VALUE ELSE 0 END) AS SUM_FIRST_GROUP,
SUM(CASE WHEN GROUP_ID = 2 THEN 1 ELSE 0 END) AS NUMBER_SECOND_GROUP,
SUM(CASE WHEN GROUP_ID = 2 THEN TEST_VALUE ELSE 0 END) AS SUM_SECOND_GROUP,
SUM(CASE WHEN GROUP_ID = 3 THEN 1 ELSE 0 END) AS NUMBER_THIRD_GROUP,
SUM(CASE WHEN GROUP_ID = 3 THEN TEST_VALUE ELSE 0 END) AS SUM_THIRD_GROUP,
SUM(CASE WHEN GROUP_ID = 4 THEN 1 ELSE 0 END) AS NUMBER_FOURTH_GROUP,
SUM(CASE WHEN GROUP_ID = 4 THEN TEST_VALUE ELSE 0 END) AS SUM_FOURTH_GROUP
FROM TEST
) AS FOO