How to Group based on Distinct value of other column - sql-server

Question

I have this input table
+--------+-----------+------------+----------+
| TaskId | OwnerName | WorkerName | Category |
+--------+-----------+------------+----------+
| 1 | Sara | Sara | 1 |
| 1 | Sara | Maya | 1 |
| 1 | Sara | Sara | 1 |
| 2 | Sara | Sara | 0 |
| 2 | Sara | Sara | 0 |
| 3 | Sam | Sam | 1 |
| 3 | Sam | Sam | 1 |
| 3 | Sam | Sam | 1 |
| 4 | Ella | Ella | 1 |
| 4 | Ella | Ella | 1 |
| 5 | Ella | Ella | 1 |
| 6 | Ella | Ella | 0 |
+--------+-----------+------------+----------+
I want to calculate how many times the owner name has in category column high (1) or low (0).
The tasks should be counted as Distinct , also if a task has owner name != worker name... the entire task will be dropped.
For example, TaskId 1 will be dropped.
Expected Output:
+-----------+------------------+-----------------+-------+------+
| OwnerName | #UniqueHighTasks | #UniqueLowTasks | %High | %Low |
+-----------+------------------+-----------------+-------+------+
| Sara | 0 | 1 | 0 | 100 |
| Sam | 1 | 0 | 100 | 0 |
| Ella | 2 | 1 | 66% | 33% |
+-----------+------------------+-----------------+-------+------+
My Attempt isn't taking into consideration that the distinct ids and that task 1 will be dropped, how to accomplish that?
Attempt:
SELECT
[OwnerName],
(100 * COALESCE(COUNT(CASE
WHEN [Category] = 1 THEN 1
END), 0) /
(COALESCE(COUNT(CASE
WHEN [Category] = 1 THEN 1
END), 0) + COALESCE(COUNT(CASE
WHEN [Category] = 0 THEN 1
END), 0))) AS %High,
(100 * COALESCE(COUNT(CASE
WHEN [Category] = 0 THEN 1
END), 0) /
(COALESCE(COUNT(CASE
WHEN [Category] = 0 THEN 1
END), 0) + COALESCE(COUNT(CASE
WHEN [Category] = 1 THEN 1
END), 0))) AS %Low,
SUM(case [Category] when 1 then 1 else 0 end) AS '#UniqueHighTasks',
SUM(case [Category] when 0 then 1 else 0 end) AS '#UniqueLowTasks'
FROM [dbo].[mytable]
Group by [OwnerName]

Answer 1

Try this query:
declare #t table (TaskId int, OwnerName varchar(10), WorkerName varchar(10), Category int)
insert into #t
values
(1, 'Sara','Sara', 1), (1, 'Sara','Maya', 1)
, (1, 'Sara','Sara', 1), (2, 'Sara','Sara', 0)
, (2, 'Sara','Sara', 0), (3, 'Sam','Sam', 1)
, (3, 'Sam','Sam', 1), (3, 'Sam','Sam', 1)
, (4, 'Ella','Ella', 1), (4, 'Ella','Ella', 1)
, (5, 'Ella','Ella', 1), (6, 'Ella','Ella', 0)
select
OwnerName, UniqueHighTasks, UniqueLowTasks
, [%High] = UniqueHighTasks * 100.0 / (UniqueHighTasks + UniqueLowTasks)
, [%Low] = UniqueLowTasks * 100.0 / (UniqueHighTasks + UniqueLowTasks)
from (
select
OwnerName, UniqueHighTasks = count(distinct case when Category = 1 then TaskId end)
, UniqueLowTasks = count(distinct case when Category = 0 then TaskId end)
from
#t
where
TaskId not in (select TaskId from #t where OwnerName <> WorkerName)
group by OwnerName
) t

Answer 2

I think this will do it
declare #T table (TaskId int, OwnerName varchar(20), WorkerName varchar(20), Category int);
insert into #T values
(1, 'Sara', 'Sara', 1 )
, (1, 'Sara', 'Maya', 1 )
, (1, 'Sara', 'Sara', 1 )
, (2, 'Sara', 'Sara', 0 )
, (2, 'Sara', 'Sara', 0 )
, (3, 'Sam', 'Sam', 1 )
, (3, 'Sam', 'Sam', 1 )
, (3, 'Sam', 'Sam', 1 )
, (4, 'Ella', 'Ella', 1 )
, (4, 'Ella', 'Ella', 1 )
, (5, 'Ella', 'Ella', 1 )
, (6, 'Ella', 'Ella', 0 );
with cte as
( select distinct t.TaskId, t.OwnerName, t.Category
from #T t
where TaskID not in (select TaskId from #T where OwnerName <> WorkerName)
)
select cte.OwnerName
, count(*) taskCount
, sum(category) as highCount
, count(*) - sum(category) as lowCount
, 100.0*sum(category)/count(*) as highPct
, 100.0*(count(*)-sum(category))/count(*) as lowPct
from cte
group by cte.OwnerName
OwnerName taskCount highCount lowCount lowPct highPct
-------------------- ----------- ----------- ----------- --------------------------------------- ---------------------------------------
Ella 3 2 1 66.666666666666 33.333333333333
Sam 1 1 0 100.000000000000 0.000000000000
Sara 1 0 1 0.000000000000 100.000000000000

Answer 3

Take your current query, and instead of querying the table directly, query a CTE or derived table that simply does a SELECT DISTINCT from the table.

Answer 4

You could try this
WITH nonDup AS (
SELECT DISTINCT [TaskId], [OwnerName], [WorkerName], [Category]
FROM mytable t1
WHERE NOT EXISTS(SELECT 1 FROM mytable t2 WHERE t1.TaskID = t2.TaskID and t2.OwnerName <> t2.WorkerName)
),
calc AS (
SELECT
OwnerName,
SUM(Category) AS UniqueHighTasks,
SUM(CASE WHEN Category = 0 THEN 1 ELSE 0 END) AS UniqueLowTasks
FROM nonDup
GROUP BY OwnerName
)
SELECT OwnerName,UniqueHighTasks,UniqueLowTasks,
CASE WHEN UniqueHighTasks+ UniqueLowTasks<> 0 THEN UniqueHighTasks*1.0/(UniqueHighTasks+ UniqueLowTasks) END AS [%High],
CASE WHEN UniqueHighTasks+ UniqueLowTasks<> 0 THEN UniqueLowTasks*1.0/(UniqueHighTasks+ UniqueLowTasks) END AS [%Low]
FROM calc