TSQL query is running slow, how to speed it up? - sql

I have a sql query for a report, it includes a few sub queries. it runs very slow. I tried a few ways (like use join instead of subquery, add a few more index). but none of them worked. Here is the query:
declare #time_from datetime
declare #time_to datetime
set #time_from ='2012-01-01'
set #time_to = '2014-01-01'
select a.a_id, c.c_id, c.c_chat_line_id, a.a_first_name, a.a_last_name
,(select isnull(SUM(ac.ac_amount),0) from t_actress_credit ac join t_order o on o.o_id = ac.order_id where o.o_status = 1 and ac.actress_id = a.a_id and ac.ac_time>=#time_from and ac.ac_time<=#time_to) as credit
,(select isnull(SUM(ac.ac_amount),0) from t_actress_credit ac join t_order o on o.o_id = ac.order_id where o.o_status = 1 and ac.ac_is_paid = 1 and ac.actress_id = a.a_id and ac.ac_time>=#time_from and ac.ac_time<=#time_to) as paid_credit
,(select COUNT(1) from t_message pm join t_call_log l1 on pm.call_log_id = l1.c_id where pm.m_type = 2 and l1.caller_id = c.c_id and pm.m_time>=#time_from and pm.m_time<=#time_to) as pmsg_sent
,(select COUNT(1) from t_message pm join t_call_log l2 on pm.m_to_call_log_id = l2.c_id where pm.m_type = 2 and l2.caller_id = c.c_id and pm.m_time>=#time_from and pm.m_time<=#time_to) as pmsg_received
,(select COUNT(1) from t_message pm join t_call_log l3 on pm.call_log_id = l3.c_id where pm.m_type = 1 and l3.caller_id = c.c_id and pm.m_time>=#time_from and pm.m_time<=#time_to) as lcmsg_sent
,(select COUNT(1) from t_message pm join t_call_log l4 on pm.m_to_call_log_id = l4.c_id where pm.m_type = 1 and l4.caller_id = c.c_id and pm.m_time>=#time_from and pm.m_time<=#time_to) as lcmsg_received
,(select COUNT(1) from t_actress_live_minute where actress_id = a.a_id and alm_time>=#time_from and alm_time<=#time_to ) as live_calls
,(select isnull(SUM(alm_minutes),0) from t_actress_live_minute where actress_id = a.a_id and alm_time>=#time_from and alm_time<=#time_to) as live_call_minutes
,(select isnull(count(1),0) from t_call_log l where l.caller_id = c.c_id and l.c_time_out is not null and c_time_in >=#time_from and c_time_in <= #time_to) as total_calls
,(select isnull(SUM(DATEDIFF(minute, l.c_time_in, l.c_time_out)),0) from t_call_log l where c_time_in >=#time_from and c_time_in <= #time_to and l.caller_id = c.c_id and l.c_time_out is not null ) as total_call_minutes
from t_actress a
join t_caller c on c.c_id = a.caller_id
group by a.a_id,c.c_id, c.c_chat_line_id, a.a_first_name, a.a_last_name
Can any one give some suggestions?
Thanks a lot!
Alan

You could try combining subqueries that pull from the same table or set of tables into a single subquery. To account for variations in the conditions, you could use conditional aggregation (employing CASE expressions).
I can see four, possibly five, such groups in your query. Here it is rewritten to use four subqueries:
SELECT
a.a_id,
c.c_id,
c.c_chat_line_id,
a.a_first_name,
a.a_last_name,
ISNULL(cr.credit , 0) AS credit
ISNULL(cr.paid_credit , 0) AS paid_credit
ISNULL(m.pmsg_sent , 0) AS pmsg_sent,
ISNULL(m.pmsg_received , 0) AS pmsg_received,
ISNULL(m.lcmsg_sent , 0) AS lcmsg_sent,
ISNULL(m.lcmsg_received , 0) AS lcmsg_received,
ISNULL(alm.live_calls , 0) AS live_calls,
ISNULL(alm.live_call_minutes, 0) AS live_call_minutes,
ISNULL(l.total_calls , 0) AS total_calls,
ISNULL(l.total_call_minutes , 0) AS total_call_minutes,
FROM t_actress AS a
INNER JOIN t_caller AS c
ON c.c_id = a.caller_id
LEFT JOIN (
SELECT
ac.actress_id,
SUM( ac.ac_amount ) AS credit,
SUM(CASE ac.ac_is_paid WHEN 1 THEN ac.ac_amount END) AS paid_credit
FROM t_actress_credit AS ac
JOIN t_order o ON o.o_id = ac.order_id
WHERE o.o_status = 1
AND ac.ac_time BETWEEN #time_from AND #time_to
GROUP BY ac.actress_id
) AS ac
ON ac.actress_id = a.a_id
LEFT JOIN (
SELECT
l.caller_id,
COUNT(CASE WHEN m. call_log_id = l1.c_id AND m.m_type = 2 THEN 1 END) AS pmsg_sent,
COUNT(CASE WHEN m.m_to_call_log_id = l2.c_id AND m.m_type = 2 THEN 1 END) AS pmsg_received,
COUNT(CASE WHEN m. call_log_id = l3.c_id AND m.m_type = 1 THEN 1 END) AS lcmsg_sent,
COUNT(CASE WHEN m.m_to_call_log_id = l4.c_id AND m.m_type = 1 THEN 1 END) AS lcmsg_received
FROM t_message AS m
JOIN t_call_log AS l ON l.c_id IN (m.call_log_id, m.m_to_call_log_id)
WHERE m.m_type IN (1, 2)
AND m.m_time BETWEEN #time_from AND #time_to
GROUP BY l.caller_id
) AS m
ON m.caller_id = c.c_id
LEFT JOIN (
SELECT
actress_id,
COUNT(*) AS live_calls,
SUM(alm_minutes) AS live_call_minutes
FROM t_actress_live_minute
WHERE alm_time BETWEEN #time_from AND #time_to
GROUP BY actress_id
) AS alm
ON alm.actress_id = a.a_id
LEFT JOIN (
SELECT
caller_id,
COUNT(*) AS total_calls,
SUM(DATEDIFF(MINUTE, c_time_in, c_time_out)) AS total_call_minutes
FROM t_call_log
WHERE c_time_out IS NOT NULL
AND c_time_in BETWEEN #time_from AND #time_to
GROUP BY caller_id
) AS l
ON l.actress_id = a.a_id
;
It could be five subqueries if you split the m subquery into two by joining separately on call_log_id and on m_to_call_log_id (and thus potentially giving the query planner more room for optimisation), i.e. instead of
LEFT JOIN (
SELECT
l.caller_id,
COUNT(CASE WHEN m. call_log_id = l1.c_id AND m.m_type = 2 THEN 1 END) AS pmsg_sent,
COUNT(CASE WHEN m.m_to_call_log_id = l2.c_id AND m.m_type = 2 THEN 1 END) AS pmsg_received,
COUNT(CASE WHEN m. call_log_id = l3.c_id AND m.m_type = 1 THEN 1 END) AS lcmsg_sent,
COUNT(CASE WHEN m.m_to_call_log_id = l4.c_id AND m.m_type = 1 THEN 1 END) AS lcmsg_received
FROM t_message AS m
JOIN t_call_log AS l ON l.c_id IN (m.call_log_id, m.m_to_call_log_id)
WHERE m.m_type IN (1, 2)
AND m.m_time BETWEEN #time_from AND #time_to
GROUP BY l.caller_id
) AS m
ON m.caller_id = c.c_id
it would be
LEFT JOIN (
SELECT
l.caller_id,
COUNT(CASE WHEN m.call_log_id = l1.c_id AND m.m_type = 2 THEN 1 END) AS pmsg_sent,
COUNT(CASE WHEN m.call_log_id = l3.c_id AND m.m_type = 1 THEN 1 END) AS lcmsg_sent,
FROM t_message AS m
JOIN t_call_log AS l ON l.c_id = m.call_log_id
WHERE m.m_type IN (1, 2)
AND m.m_time BETWEEN #time_from AND #time_to
GROUP BY l.caller_id
) AS mf
ON mf.caller_id = c.c_id
LEFT JOIN (
SELECT
l.caller_id,
COUNT(CASE WHEN m.m_to_call_log_id = l2.c_id AND m.m_type = 2 THEN 1 END) AS pmsg_received,
COUNT(CASE WHEN m.m_to_call_log_id = l4.c_id AND m.m_type = 1 THEN 1 END) AS lcmsg_received
FROM t_message AS m
JOIN t_call_log AS l ON l.c_id = m.m_to_call_log_id
WHERE m.m_type IN (1, 2)
AND m.m_time BETWEEN #time_from AND #time_to
GROUP BY l.caller_id
) AS mt
ON mt.caller_id = c.c_id
changing also the corresponding references in the main SELECT clause.
I'm not sure whether which of the variations is better, you'll need to test both to find out.
Note that I've omitted the main query's GROUP BY clause. It seems unnecessary both in your query and in mine, because, as far as I can see, it includes primary keys from both t_actress and t_caller and those combinations would be unique anyway. I assume that the GROUP BY is a leftover from your previous attempts at rewriting the query using joins.

thanks for your reply. I tried your way, it is still slow. here is what I did and finally works. I basically put all the sub queries into table, and then join the table at the end. not sure why, but it is faster: here is the code;
-- total calls
declare #t_call table(
a_id bigint,
total_calls bigint,
total_call_minutes bigint
);
insert into #t_call
SELECT a_id, COUNT(1) AS total_calls, isnull(SUM(DATEDIFF(MINUTE, c_time_in, c_time_out)),0) AS total_call_minutes
FROM t_actress aa
join t_call_log l on aa.caller_id = l.caller_id and c_time_in BETWEEN #time_from AND #time_to and c_time_out IS NOT NULL
GROUP BY a_id;
-- total live minutes
declare #t_live table(
a_id bigint,
live_calls bigint,
live_call_minutes bigint
);
insert into #t_live
SELECT a_id, COUNT(*) AS live_calls, isnull(SUM(alm_minutes),0) AS live_call_minutes
FROM t_actress a
join t_actress_live_minute alm on alm.actress_id = a.a_id and alm_time BETWEEN #time_from AND #time_to
GROUP BY a_id
-- total message by caller
declare #t_cm table(
caller_id bigint,
pmsg_sent bigint,
pmsg_received bigint,
lcmsg_sent bigint,
lcmsg_received bigint
)
insert into #t_cm
SELECT l.caller_id,
COUNT(CASE WHEN m.call_log_id = l.c_id AND m.m_type = 2 THEN 1 END) AS _pmsg_sent,
COUNT(CASE WHEN m.m_to_call_log_id = l.c_id AND m.m_type = 2 THEN 1 END) AS _pmsg_received,
COUNT(CASE WHEN m.call_log_id = l.c_id AND m.m_type = 1 THEN 1 END) AS _lcmsg_sent,
COUNT(CASE WHEN m.m_to_call_log_id = l.c_id AND m.m_type = 1 THEN 1 END) AS _lcmsg_received
FROM t_message m
join t_call_log l on l.c_id in (m.call_log_id, m.m_to_call_log_id)
where m.m_time BETWEEN #time_from AND #time_to
GROUP BY l.caller_id
-- total message by actress
declare #t_msg table(
a_id bigint,
pmsg_sent bigint,
pmsg_received bigint,
lcmsg_sent bigint,
lcmsg_received bigint
)
insert into #t_msg
select a_id, isnull(SUM(cm.pmsg_sent),0), isnull(SUM(cm.pmsg_received),0), isnull(SUM(cm.lcmsg_sent),0), isnull(SUM(cm.lcmsg_received),0)
from t_actress a
join #t_cm cm on a.caller_id = cm.caller_id
group by a_id
-- total credit
declare #t_credit table(
a_id bigint,
credit money,
paid_credit money
)
insert into #t_credit
SELECT a_id, isnull(SUM(ac.ac_amount),0) AS credit, isnull(SUM(CASE ac.ac_is_paid WHEN 1 THEN ac.ac_amount else 0 END),0) AS paid_credit
FROM t_actress a
join t_actress_credit ac on ac.actress_id = a.a_id AND ac.ac_time BETWEEN #time_from AND #time_to
JOIN t_order o ON o.o_id = ac.order_id and o_status = 1
GROUP BY a_id
-- the report
select a.a_id, cl.c_id, cl.c_chat_line_id, a.a_first_name, a.a_last_name,
isnull(ac.credit,0) credit, isnull(ac.paid_credit,0) paid_credit,
isnull(m.pmsg_sent,0) pmsg_sent, isnull(m.pmsg_received,0) pmsg_received, isnull(m.lcmsg_sent,0) lcmsg_sent, isnull(m.lcmsg_received,0) lcmsg_received,
isnull(l.live_calls,0) live_calls, isnull(l.live_call_minutes,0) live_call_minutes,
isnull(c.total_calls,0) total_calls, isnull(c.total_call_minutes,0) total_call_minutes
from t_actress a
join t_caller cl on cl.c_id = a.caller_id
left outer join #t_call c on c.a_id = a.a_id
left outer join #t_live l on l.a_id = a.a_id
left outer join #t_msg m on m.a_id = a.a_id
left outer join #t_credit ac on ac.a_id = a.a_id
order by a_id

Related

Subquery returned more than 1 value. This is not permitted when the subquery follows =, !=, <, <= , >, >= orwhen the subquery is used as an expression

I am having this error message. I have tried many other ways but can't resolve the issue.
I would be really grateful if someone could look at this :
;WITH progression
AS
(
SELECT
w.CustomerID,
CASE WHEN SUM(CASE WHEN w.workflowoutcomeid = 8 THEN 1 ELSE 0 END) > 0 THEN 'Yes' ELSE 'No' END AS [PG01],
CASE WHEN SUM(CASE WHEN w.workflowoutcomeid = 11 THEN 1 ELSE 0 END) > 0 THEN 'Yes' ELSE 'No' END AS [PG03],
CASE WHEN SUM(CASE WHEN w.workflowoutcomeid = 14 THEN 1 ELSE 0 END) > 0 THEN 'Yes' ELSE 'No' END AS [PG04],
CASE WHEN SUM(CASE WHEN w.workflowoutcomeid = 17 THEN 1 ELSE 0 END) > 0 THEN 'Yes' ELSE 'No' END AS [PG05],
CASE WHEN SUM(CASE WHEN w.workflowoutcomeid = 9 THEN 1 ELSE 0 END) > 0 THEN 'Yes' ELSE 'No' END AS [in_work_review]
FROM
ABC.dbo.tblWorkflow w
WHERE
w.Deleted IS NULL
AND
w.workflowqueueid = 4
AND
w.workflowoutcomeid IN (8, 11, 14, 17, 9)
GROUP BY
w.CustomerID
),
contact_data
AS
(
SELECT
CustomerID, [Email], [Mobile], [Home]
FROM
(
SELECT
CustomerID,
CASE
WHEN ContactTypeID = 1 THEN 'Home'
WHEN ContactTypeID = 2 THEN 'Mobile'
WHEN ContactTypeID = 5 THEN 'Email'
END AS ContactTypeDescription,
ContactValue
FROM ABC.dbo.tblCustomerContact
WHERE ContactTypeID IN (1,2,5)
) base
PIVOT
(
MAX(ContactValue) FOR ContactTypeDescription IN ([Home],[Mobile],[Email])
) pvt
),
appointment
AS
(
SELECT
n.[Key] AS CustomerID,
MAX(CASE WHEN n.AppointmentStatusID IN (2,4) THEN n.ActionDate ELSE NULL END) AS [Last_Completed_Attended_Appointment],
MAX(CASE WHEN n.AppointmentStatusID = 1 THEN n.ActionDate ELSE NULL END) AS [Next Pending Appointment]
FROM ABC.dbo.tblNote n
WHERE n.AppointmentTypeID = 6 AND n.AppointmentStatusID IN (1,2,4)
GROUP BY n.[Key]
)
SELECT
m.Firstname + ' ' + m.Lastname AS [Manager],
u.Firstname + ' ' + u.Lastname AS [Adviser],
c.CustomerID,
c.GivenName + ' ' + c.FamilyName AS [Customer Name],
g.Gender,
e.EthnicityName AS Ethnicity,
com.CompanyName,
NULL AS DeliverySite,
d.[Name] AS District,
css.ServiceStatus,
contact_data.Email,
uad.Line1 AS AddressLine1,
uad.Line2 AS AddressLine2,
uad.Line3 AS AddressLine3,
uad.Postcode,
uad.AlternativePostcode,
uad.Town,
ISNULL(contact_data.mobile, contact_data.home) AS Phone,
c.StartDate,
(SELECT MIN(wh.MGCReviewerModifiedDate) AS [ST01_Approved_Date]
FROM ABC.dbo.tblWorkflow w
INNER JOIN ABC.dbo.tblWorkflowHistory wh
ON w.WorkflowID = wh.WorkflowID
WHERE wh.WorkflowQueueID = 4 AND wh.MGCReviewerModifiedDate IS NOT NULL
AND wh.Deleted IS NULL AND w.WorkflowOutcomeID = 1 AND w.WorkflowQueueID = 4
AND w.Deleted IS NULL AND w.CustomerID = c.CustomerID
GROUP BY w.WorkflowID, w.CustomerID) AS ST01_Approved_Date,
qual.LearningAimTitle,
qual.LearningAimCompletionStatus,
qual.LearningAimOutcomeStatus,
mwp.WorkExperienceTitle ,
mwp.WorkExperienceStartDate,
mwp.WorkExperienceEndDate,
mwp.learningaimcompletionstatus as [Work_Ex_CompletionStatus],
mwp.learningaimoutcomestatus as [Work_Ex_OutcomeStatus],
p.PG01 AS [PG01_Start(Job Start Approved/Claimed ?)],
p.in_work_review AS [PG01_In_work_review(Job Outcome Approved/Claimed ?)],
p.PG03 AS [PG03 – Education Approved / Claimed?],
p.PG04 AS [PG04 – Apprenticeship Approved / Claimed?],
p.PG05 AS [PG05– Apprenticeship Approved / Claimed?],
a.Last_Completed_Attended_Appointment,
a.[Next Pending Appointment],
FLOOR(DATEDIFF(day, c.DateOfBirth, GETDATE()) / 365.25) as CustomerAge
FROM ABC.dbo.tblCustomer c
LEFT JOIN ABC.dbo.tblUser u ON c.OwnerID = u.UserID
LEFT JOIN ABC.dbo.tblUser m ON u.ManagerID = m.UserID
LEFT JOIN ABC.dbo.tlkpGender g ON c.GenderID = g.GenderID
LEFT JOIN ABC.dbo.tlkpEthnicity e ON c.EthnicityID = e.EthnicityID
LEFT JOIN ABC.dbo.tblCompany com ON c.CompanyId = com.[CompanyID]
LEFT JOIN ABC.dbo.tblCustomerAddress cad ON c.CustomerID = cad.CustomerID AND cad.EffectiveTo IS NULL
LEFT JOIN ABC.dbo.tblUKAddress uad ON uad.UKaddressID = cad.UKaddressID
LEFT JOIN PostcodeESyNCS.dbo.tblPostcode po ON uad.Postcode = po.Postcode
LEFT JOIN PostcodeESyNCS.dbo.tlkpDistrict d ON po.DistrictId = d.DistrictId
LEFT JOIN ABC.dbo.tlkpCustomerServiceStatus css ON c.CustomerServiceStatusID = css.CustomerServiceStatusID
LEFT JOIN progression p ON c.CustomerID = p.CustomerID
LEFT JOIN contact_data ON c.CustomerID = contact_data.CustomerID
OUTER APPLY
(
SELECT TOP 1
l.learningaimid,
aim.LearningAimTitle,
aim.isfullqualification,
st.LearningAimCompletionStatus,
aos.LearningAimOutcomeStatus
FROM ABC.dbo.tbllearning l
LEFT JOIN ABC.dbo.tlkplearningaim aim on aim.learningaimid = l.learningaimid
LEFT JOIN ABC.dbo.tlkplearningaimcompletionstatus st on st.learningaimcompletionstatusid = l.learningaimcompletionstatusid
LEFT JOIN ABC.dbo.tlkpLearningAimOutcomeStatus aos on aos.learningaimoutcomestatusid = l.learningaimoutcomestatusid
WHERE aim.learningaimtypeid = 1 AND l.customerid = c.customerid
ORDER BY l.StartDate DESC
) qual
OUTER APPLY
(
SELECT TOP 1
l.learningaimid,
REPLACE(aim.LearningAimTitle,',',' ') as WorkExperienceTitle,
aim.isfullqualification,
st.LearningAimCompletionStatus,
outcome.LearningAimOutcomeStatus,
l.StartDate as WorkExperienceStartDate,
l.ActualEndDate as WorkExperienceEndDate
FROM ABC.dbo.tbllearning l
LEFT JOIN ABC.dbo.tlkplearningaim aim ON aim.learningaimid=l.learningaimid
LEFT JOIN ABC.dbo.tlkplearningaimcompletionstatus st ON st.learningaimcompletionstatusid=l.learningaimcompletionstatusid
LEFT JOIN ABC.dbo.tlkpLearningAimOutcomeStatus outcome ON outcome.learningaimoutcomestatusid= l.learningaimoutcomestatusid
WHERE aim.LearningAimID IN (SELECT la.LearningAimID
FROM ABC.dbo.tlkpLearningAim la
WHERE la.LearningAimTypeID = 2
and la.LearningAimTitle like '%Work%')
AND l.customerid = c.customerid
ORDER BY StartDate DESC
) AS mwp
LEFT JOIN appointment a ON c.CustomerID = a.CustomerID
WHERE
c.Deleted IS NULL
I am getting the following error:
Msg 512, Level 16, State 1, Line 2
Subquery returned more than 1 value. This is not permitted when the subquery follows =, !=, <, <= , >, >= or when the subquery is used as an expression.
Warning: Null value is eliminated by an aggregate or other SET operation.
The only place where I see that this could be happening is the definition of ST01_Approved_Date:
(SELECT MIN(wh.MGCReviewerModifiedDate) AS [ST01_Approved_Date]
FROM ABC.dbo.tblWorkflow w JOIN
ABC.dbo.tblWorkflowHistory wh
ON w.WorkflowID = wh.WorkflowID
WHERE wh.WorkflowQueueID = 4 AND wh.MGCReviewerModifiedDate IS NOT NULL AND
wh.Deleted IS NULL AND w.WorkflowOutcomeID = 1 AND w.WorkflowQueueID = 4 AND
w.Deleted IS NULL AND w.CustomerID = c.CustomerID
GROUP BY w.WorkflowID, w.CustomerID
) AS ST01_Approved_Date,
A correlated subquery should not contain GROUP By for exactly this reason. I don't know what the logic would be, but there should probably be a condition on w.WorkFlowId to the outer query, something like:
(SELECT MIN(wh.MGCReviewerModifiedDate) AS [ST01_Approved_Date]
FROM ABC.dbo.tblWorkflow w JOIN
ABC.dbo.tblWorkflowHistory wh
ON w.WorkflowID = wh.WorkflowID
WHERE wh.WorkflowQueueID = 4 AND wh.MGCReviewerModifiedDate IS NOT NULL AND
wh.Deleted IS NULL AND w.WorkflowOutcomeID = 1 AND w.WorkflowQueueID = 4 AND
w.Deleted IS NULL AND w.CustomerID = c.CustomerID AND
w.workflowID = <outer query reference>.WorkflowId
) AS ST01_Approved_Date,

SQL Server: query optimization

I have the following query which takes around 4 minutes to execute.
DECLARE #tdate DATETIME = '2019-09-01 00:00:00.000'
SELECT c.id AS clid,
h.id AS hlid,
h.holdinNo,
c.cliendID,
c.clientName,
h.floor,
h.connect_radius
FROM [db_land].[dbo].tbl_client AS c
INNER JOIN [db_land].[dbo].tx_holding AS h
ON c.id = h.clid
WHERE h.status = 1
AND h.connect_radius IS NOT NULL
AND c.status = 1
AND h.type = 'Residential'
AND h.holdinNo NOT IN (SELECT holdingNo
FROM [db_land].[dbo].tbl_bill
WHERE year(date_month) = YEAR(#tdate)
AND MONTH(date_month) = MONTH(#tdate)
AND ( update_by IS NOT NULL
OR ispay = 1 ))
I found the inner join takes only few seconds.
SELECT c.id AS clid,
h.id AS hlid,
h.holdinNo,
c.cliendID,
c.clientName,
h.floor,
h.connect_radius
FROM [db_land].[dbo].tbl_client AS c
INNER JOIN [db_land].[dbo].tx_holding AS h
ON c.id = h.clid
WHERE h.status = 1
AND h.connect_radius IS NOT NULL
AND c.status = 1
AND h.type = 'Residential'
It's the NOT IN checking which takes a lot of time. How I can optimize this query? For me it's needed to execute the query at least with in minute.
Make sure the WHERE and JOIN clause predicates are sargable. Applying a function to a column (e.g. YEAR(date_month)) prevents indexes on the column from being used efficiently.
Try this expression instead to avoid the functions. There are other methods depending on the SQL Server version.
WHERE
date_month >= DATEADD(day, 1, DATEADD(month, -1, EOMONTH(#tdate)))
AND date_month < DATEADD(day, 1, DATEADD(month, 1, EOMONTH(#tdate)))
Try by replacing NOT IN with a LEFT JOIN of the table [db_land].[dbo].tbl_bill on all the conditions and adding in the WHERE clause holdingNo is null so the returned rows are the non matching rows:
select c.id as clid, h.id as hlid,h.holdinNo, c.cliendID, c.clientName, h.floor, h.connect_radius
from [db_land].[dbo].tbl_client as c
inner join [db_land].[dbo].tx_holding as h
on c.id= h.clid
left join [db_land].[dbo].tbl_bill as b
on b.holdingNo = h.holdinNo and year(b.date_month) = YEAR(#tdate) and MONTH(b.date_month) = MONTH(#tdate)
and (b.update_by is not null or b.ispay = 1)
where h.status = 1 and h.connect_radius is not null and c.status=1 and h.type='Residential' and b.holdingNo is null
I would recommend changing the NOT IN to NOT EXISTS and adding an index:
WHERE . . . AND
NOT EXISTS (SELECT 1
FROM [db_land].[dbo].tbl_bill b
WHERE b.holdingNo = h.holdingNo AND
b.date_month >= DATEFROMPARTS(YEAR(#tdate), MONTH(#tdate), 1) AND
b.date_month < DATEADD(month, 1, DATEFROMPARTS(YEAR(#tdate), MONTH(#tdate), 1)) AND
(b.update_by IS NOT NULL OR b.ispay = 1
)
Then the index that you want is on tbl_bill(holdingNo, date_month, update_by, ispay).
Put your sub query into temp table :
DECLARE #tdate DATETIME = '2019-09-01 00:00:00.000'
SELECT holdingNo
into #TmpholdingNo
FROM [db_land].[dbo].tbl_bill
WHERE year(date_month) = YEAR(#tdate)
AND MONTH(date_month) = MONTH(#tdate)
AND ( update_by IS NOT NULL
OR ispay = 1 )
SELECT c.id AS clid,
h.id AS hlid,
h.holdinNo,
c.cliendID,
c.clientName,
h.floor,
h.connect_radius
FROM [db_land].[dbo].tbl_client AS c
INNER JOIN [db_land].[dbo].tx_holding AS h
ON c.id = h.clid
WHERE h.status = 1
AND h.connect_radius IS NOT NULL
AND c.status = 1
AND h.type = 'Residential'
AND h.holdinNo NOT IN (SELECT holdingNo from #TmpholdingNo)
drop table #TmpholdingNo
Rather than using functions in your WHERE clause try calculating the start and end filter dates, using OPTION (RECOMPILE) can help SQL to use the actual values of your variables in your query plan. I would also change NOT IN to NOT EXISTS:
DECLARE #tdate DATETIME = '2019-09-01 00:00:00.000'
DECLARE #startDate DATE = DATEFROMPARTS(YEAR(#tdate), MONTH(#tdate), 1)
DECLARE #endDate DATE = DATEADD(day,1,EOMONTH(#tdate))
SELECT c.id AS clid,
h.id AS hlid,
h.holdinNo,
c.cliendID,
c.clientName,
h.floor,
h.connect_radius
FROM [db_land].[dbo].tbl_client AS c
INNER JOIN [db_land].[dbo].tx_holding AS h
ON c.id = h.clid
WHERE h.status = 1
AND h.connect_radius IS NOT NULL
AND c.status = 1
AND h.type = 'Residential'
AND NOT EXISTS (SELECT holdingNo
FROM [db_land].[dbo].tbl_bill
WHERE holdingNo = h.holdinNo AND
date_month >= #startDate AND
date_month < #endDate AND
AND ( update_by IS NOT NULL
OR ispay = 1 ))
OPTION (RECOMPILE)
give a try try this:
select main.* from
(SELECT c.id AS clid,
h.id AS hlid,
h.holdinNo,
c.cliendID,
c.clientName,
h.floor,
h.connect_radius
FROM [db_land].[dbo].tbl_client AS c
INNER JOIN [db_land].[dbo].tx_holding AS h
ON c.id = h.clid
WHERE h.status = 1
AND h.connect_radius IS NOT NULL
AND c.status = 1
AND h.type = 'Residential')main
left join
(select holdingNo from
(SELECT holdingNo, update_by, ispay
FROM [db_land].[dbo].tbl_bill
WHERE year(date_month) = YEAR(#tdate)
AND MONTH(date_month) = MONTH(#tdate))bill1
where update_by IS NOT NULL OR ispay = 1)bill2
on main.holdinNo = bill2.holdinNo
where bill2.holdinNo is null
put the filter list at variable,then them apply the filter
DECLARE #filter TABLE INSERT INTO #filter SELECT FROM [db_land].[dbo].tbl_bill
them apply the filter
DECLARE #tdate DATETIME = '2019-09-01 00:00:00.000'
SELECT c.id AS clid,
h.id AS hlid,
h.holdinNo,
c.cliendID,
c.clientName,
h.floor,
h.connect_radius
FROM [db_land].[dbo].tbl_client AS c
INNER JOIN [db_land].[dbo].tx_holding AS h ON c.id= h.clid
WHERE h.status=1
AND h.connect_radius IS NOT NULL
AND c.status=1
AND h.type='Residential'
AND h.holdinNo NOT IN (filter)

SQL Server query slow - how do optimize it?

I would like some help to optimize this query to be faster.
This query produces a view that latter will be showed in a table in a website.
This query is slow, and I am trying to make it faster.
The only thing I tried till now is to reduce the amount of columns I retrieve for the table.
This is the query:
SELECT TOP (100) PERCENT Id, MAX(BusinessTitle) AS BusinessTitle, MAX(ClientName) AS ClientName, MAX(ClientType) AS Type, MAX(CreatedWhen) AS CreatedWhen, MAX(CASE WHEN C.[CreatedBy] IS NULL
THEN 'Client' ELSE 'Admin' END) AS CreatedBy, CAST(MAX(CASE WHEN C.IsDisabled = 1 THEN 1 ELSE 0 END) AS BIT) AS IsDisabled, MAX(ReferenceSource) AS ReferenceSource, MAX(OtherReferenceSource)
AS OtherReferenceSource, MAX(Address) AS Address,
(SELECT MAX(T.FirstName + ' ' + T.LastName) AS Expr1
FROM dbo.ApplicationUsers AS A INNER JOIN
dbo.Therapists AS T ON A.UserName = MAX(C.ClientName) AND A.Id = T.ApplicationUserId) AS ClientAdmin,
(SELECT MAX(A.Email) AS Expr1
FROM dbo.ApplicationUsers AS A INNER JOIN
dbo.Therapists AS T ON A.UserName = MAX(C.ClientName) AND A.Id = T.ApplicationUserId) AS Email,
(SELECT MAX(Name) AS Expr1
FROM dbo.Cities AS CY
WHERE (Id = MAX(C.CityId))) AS City,
(SELECT COUNT(*) AS Expr1
FROM dbo.Patients AS P
WHERE (ClientId = C.Id)) AS TotalPatientCount,
(SELECT COUNT(*) AS Expr1
FROM dbo.Patients AS P
WHERE (ClientId = C.Id) AND (IsDeleted = 0) AND (IsDisabled = 0)) AS ActivePatientCount,
(SELECT MAX(CreatedWhen) AS Expr1
FROM dbo.Patients AS P
WHERE (ClientId = C.Id)) AS LastPatientAddition,
(SELECT COUNT(*) AS Expr1
FROM dbo.Treatments AS T
WHERE (ClientId = C.Id)) AS TotalTreatmentCount,
(SELECT MAX(CreatedWhen) AS Expr1
FROM dbo.Treatments AS T
WHERE (ClientId = C.Id)) AS LastTreatmentAddition,
(SELECT COUNT(*) AS Expr1
FROM dbo.Therapists AS T
WHERE (ClientId = C.Id)) AS TotalTherapistCount,
(SELECT COUNT(*) AS Expr1
FROM dbo.Therapists AS T INNER JOIN
dbo.ApplicationUsers AS A ON T.ClientId = C.Id AND T.ApplicationUserId = A.Id
WHERE (A.IsDeleted = 0) AND (A.IsDisabled = 0)) AS ActiveTherapistCount,
(SELECT MAX(A.CreatedWhen) AS Expr1
FROM dbo.Therapists AS T INNER JOIN
dbo.ApplicationUsers AS A ON T.ClientId = C.Id AND T.ApplicationUserId = A.Id) AS LastTherapistAddition,
(SELECT MAX(A.LastLoginDate) AS Expr1
FROM dbo.Therapists AS T INNER JOIN
dbo.ApplicationUsers AS A ON T.ClientId = C.Id AND T.ApplicationUserId = A.Id
WHERE (A.LastLoginDate IS NOT NULL)) AS TherapistLastLoginDate, CAST((CASE WHEN
((SELECT COUNT(S.[Id])
FROM [dbo].[ClientSubscriptions] AS S
WHERE ((S.[ClientId] = C.[Id]) AND (S.[IsDeleted] = 0) AND ((S.[SubscriptionEnd] IS NULL) OR
(S.[SubscriptionEnd] > GETDATE())))) > 0) THEN 1 ELSE 0 END) AS BIT) AS HasActiveSubscription,
(SELECT MAX(SubscriptionEnd) AS Expr1
FROM dbo.ClientSubscriptions AS S
WHERE (ClientId = C.Id) AND (IsDeleted = 0) AND (SubscriptionEnd IS NULL OR
SubscriptionEnd > GETDATE())) AS LastValidSubscriptionEnd, CAST((CASE WHEN
((SELECT COUNT(S.[Id])
FROM [dbo].[ClientSubscriptions] AS S
WHERE ((S.[ClientId] = C.[Id]) AND (S.[IsDeleted] = 0) AND ((S.[SubscriptionEnd] IS NULL) OR
(S.[SubscriptionEnd] > GETDATE())) AND (S.[Id] <>
(SELECT MIN(S2.[Id])
FROM [dbo].[ClientSubscriptions] AS S2
WHERE ((S2.[ClientId] = C.[Id]) AND (S2.[IsDeleted] = 0)))))) > 0) THEN 1 ELSE 0 END) AS BIT) AS IsPayingCustomer, COALESCE
((SELECT MAX(MonthlyPrice) AS Expr1
FROM dbo.ClientSubscriptions AS S
WHERE (ClientId = C.Id) AND (IsDeleted = 0) AND (SubscriptionEnd IS NULL OR
SubscriptionEnd > GETDATE()) AND (MonthlyPrice > 0)), 0.00) AS ActiveSubscriptionMonthlyPrice, MAX(ClientStatus) AS Status, MAX(Phone1) AS Phone, MAX(Phone2) AS Phone2,
(SELECT Code
FROM dbo.DiscountCoupons AS DC
WHERE (Code =
(SELECT TOP (1) DiscountCouponCode
FROM dbo.ClientPayments AS CP
WHERE (ClientId = C.Id)
ORDER BY Id))) AS DiscountCouponCode,
(SELECT IssuedTo
FROM dbo.DiscountCoupons AS DC
WHERE (Code =
(SELECT TOP (1) DiscountCouponCode
FROM dbo.ClientPayments AS CP
WHERE (ClientId = C.Id)
ORDER BY Id))) AS DiscountCouponIssuedTo,
(SELECT ClientDiscount
FROM dbo.DiscountCoupons AS DC
WHERE (Code =
(SELECT TOP (1) DiscountCouponCode
FROM dbo.ClientPayments AS CP
WHERE (ClientId = C.Id)
ORDER BY Id))) AS DiscountCouponClientDiscount, COALESCE
((SELECT COUNT(Id) AS Expr1
FROM dbo.ClientFiles AS F
WHERE (ClientId = C.Id)), 0) AS TotalFilesCount, COALESCE
((SELECT SUM(FileSize) AS Expr1
FROM dbo.ClientFiles AS F
WHERE (ClientId = C.Id)), 0) / 1048576.0 AS TotalFilesSize, CAST(MAX(CASE WHEN C.CrmEnded = 1 THEN 1 ELSE 0 END) AS BIT) AS CrmEnded, MAX(CrmStatus) AS CrmStatus, MAX(CrmUnuseReason)
AS CrmUnuseReason,
(SELECT COUNT(1) AS Expr1
FROM dbo.Tipulog_Crm_Calls_new AS CC
WHERE (Cust_id = C.Id)) AS CrmCallCount
FROM dbo.Clients AS C
WHERE (IsDeleted = 0)
GROUP BY Id
I will add a second answer, which is the complete sql. This has of course not been tested as we have no access to your data, but I think you should be able to debug it yourself. There are many pointers in this code that should show you how to go.
The basic thing is to take out all of the correlated queries and put them as subqueries. The only reason to do this is all the Max/Min you use - I would look at those as if they are not necessary depending on your data then you should take them out and join to the tables directly. All the subqueries are left joins - again make them normal joins if you can depending on your data.
Also took out the outside group by Id, as 99% sure this is not necessary, as is the Top 100% bit.
SELECT BusinessTitle, ClientName, ClientType AS Type, CreatedWhen,
CASE WHEN C.[CreatedBy] IS NULL THEN 'Client' ELSE 'Admin' END) AS CreatedBy,
CAST(CASE WHEN C.IsDisabled = 1 THEN 1 ELSE 0 END AS BIT) AS IsDisabled,
ReferenceSource, OtherReferenceSource, Address,
ApplicationByName.FullName AS ClientAdmin,
ApplicationByName.Email AS Email,
Cities.Name AS City,
Patients.TotalPatientCount,
Patients.ActivePatientCount,
Patients.LastPatientAddition,
Treatments.TotalTreatmentCount,
Treatments.LastTreatmentAddition,
Therapists.TotalTherapistCount,
Therapists.ActiveTherapistCount,
Therapists.LastTherapistAddition,
Therapists.TherapistLastLoginDate
CAST(CASE WHEN Subscriptions.SubscriptionCount>0 then 1 else 0 end as BIT) as HasActiveSubscription,
Subscriptions.LastValidSubscriptionEnd
CAST(Subscriptions.IsPayingCustomer AS BIT) AS IsPayingCustomer,
COALESCE(ActiveSubscriptionMonthlyPrice,0) as ActiveSubscriptionMonthlyPrice
ClientStatus AS Status, Phone1 AS Phone, Phone2 AS Phone2,
ClientPayments.DiscountCouponCode,
DiscountCoupons.IssuedTo AS DiscountCouponIssuedTo,
DiscountCoupons.ClientDiscount AS DiscountCouponClientDiscount,
COALESCE(ClientFiles.TotalFilesCount,0) AS TotalFilesCount,
COALESCE(ClientFiles.TotalFilesSize,0) AS TotalFilesSize,
CAST((CASE WHEN C.CrmEnded = 1 THEN 1 ELSE 0 END) AS BIT) AS CrmEnded,
CrmStatus, CrmUnuseReason,
Crm_Calls.CrmCallCount
FROM dbo.Clients AS C
left join (
select A.UserName,
max(T.FirstName + ' ' + T.LastName) as FullName,
max(A.Email) as Email
from dbo.ApplicationUsers A
join dbo.Therapists T on T.ApplicationUserId=A.Id
group by A.Username
) ApplicationByName on ApplicationByName.UserName=C.ClientName
join dbo.Cities on Cities.ID=c.CityID
left join (
SELECT ClientId,
COUNT(*) AS TotalPatientCount,
sum(case when IsDeleted = 0 AND IsDisabled = 0 then 1 else 0 end) AS ActivePatientCount,
MAX(CreatedWhen) AS LastPatientAddition
FROM dbo.Patients
GROUP BY ClientId
) Patients on Patients.ClientId = C.Id
left join (
SELECT ClientId,
COUNT(*) AS TotalTreatmentCount,
MAX(CreatedWhen) AS LastTreatmentAddition
FROM dbo.Treatments
GROUP BY ClientId
) Treatments on Treatments.ClientID = C.Id
left join (
select T.ClientId,
count(distinct T.Id) as TotalTherapistCount,
sum(case when A.IsDeleted = 0 AND A.IsDisabled = 0 then 1 else 0 end) as ActiveTherapistCount,
max(A.CreatedWhen) as LastTherapistAddition,
max(A.LastLoginDate) as TherapistLastLoginDate
from Therapists T
left join dbo.ApplicationUsers A on A.Id=T.ApplicationUserId
group by T.ClientId
) Therapists on Therapists.ClientID = C.Id
left join (
SELECT S.ClientId,
count(*) as SubscriptionCount,
MAX(SubscriptionEnd) as LastValidSubscriptionEnd,
MAX(case when MinSub.Id!=S.ID then 1 else 0 end as IsPayingCustomer,
max(case when MonthlyPrice>0 then 0 end) as ActiveSubscriptionMonthlyPrice
FROM dbo.ClientSubscriptions S
join (
select ClientId, min(Id) as Id
from dbo.ClientSubscriptions
where IsDeleted=0
group by ClientId
) MinSub on MinSub.ClientId=ClientSubscriptions.ClientId
where IsDeleted=0 and (SubscriptionEnd is null or SubscriptionEnd>getdate())
group by ClientId
) Subscriptions on Subscriptions.ClientId=C.Id
left join (
select ClientId,
DiscountCouponCode,
row_number() over(partition by ClientId, order by Id) rn
from dbo.ClientPayments
) ClientPayments on ClientPayments.ClientId=C.ID and rn=1
left join dbo.DiscountCoupons on DiscountCoupons.Code=ClientPayments.DiscountCouponCode
left join (
select ClientId,
count(*) as TotalFilesCount,
sum(FileSize)/1048576.0 as TotalFilesSize
from dbo.ClientFiles
group by ClientId
) ClientFiles on ClientFiles.ClientId=Client.Id
left join (
SELECT Cust_id, COUNT(1) AS CrmCallCount
FROM dbo.Tipulog_Crm_Calls_new
group by Cust_id
) Crm_Calls on Crm_Calls.Cust_id=C.Id
WHERE C.IsDeleted = 0
This is a very partial answer, but you asked how to refer to a table once instead of multiple times in multiple subqueries.
This is an example of how you would replace all those subqueries to the Patients & Treatments tables, and also the cities table. You really need to learn about joins.
FROM dbo.Clients AS C
join dbo.Cities on Cities.ID=c.CityID
left join (
SELECT ClientId,
COUNT(*) AS TotalPatientCount,
sum(case when IsDeleted = 0 AND IsDisabled = 0 then 1 else 0 end) AS ActivePatientCount,
MAX(CreatedWhen) AS LastPatientAddition
FROM dbo.Patients
GROUP BY ClientId
) Patients on Patients.ClientId = C.Id
left join (
SELECT ClientId,
COUNT(*) AS TotalTreatmentCount,
MAX(CreatedWhen) AS LastTreatmentAddition
FROM dbo.Treatments
GROUP BY ClientId
) Treatments on Treatments.ClientID = C.Id
Then your column list replaces the subqueries to Patients and City like this:
Cities.Name AS City,
Patients.TotalPatientCount,
Patients.ActivePatientCount,
Patients.LastPatientAddition,
Treatments.TotalTreatmentCount,
Treatments.LastTreatmentAddition,
That should at least give you an idea.

How to convert correlated sub query containing duplicate table to non-correlated one?

I have to convert the correlated sub-query to non-correlated sub-query cuz of performance issues .
like that :
The correlated sub-query :(So slow ) returns 4000 row
SELECT a.personid,a.name,b.conid,d.condat,e.connam
FROM main_empr a INNER JOIN coninr b
ON a.personid = b.personid AND a.calc_year = b.calc_year
INNER JOIN mainconinr c
ON b.conid = c.conid
INNER JOIN coninr d
ON a.personid = d.personid AND a.calc_year = d.calc_year
INNER JOIN mainconinr e
ON d.conid = e.conid
WHERE c.active_flag = 1 and c.endreward_flag = 1
AND d.condat = (SELECT MIN(bb.condat) FROM coninr bb WHERE bb.personid = b.personid AND bb.calc_year = b.calc_year AND ((bb.conid > 0 AND bb.conid < 4 ) OR (bb.conid IN(16,6) )) )
AND b.condat = (SELECT MAX(bb.condat) FROM coninr bb WHERE bb.personid = b.personid AND bb.calc_year = b.calc_year AND ((bb.conid > 0 AND bb.conid < 4 ) OR (bb.conid IN(16,6) )) )
AND ( 0 = ( SELECT COUNT(*) FROM servmain x WHERE x.personid = a.personid AND x.calc_year = a.calc_year )
OR b.condat > ( SELECT MAX(x.serv_date) FROM servmain x WHERE x.personid = a.personid AND x.calc_year = a.calc_year ) )
AND a.calc_year = 2018
The non-correlated query :returns about 12300 rows!!
SELECT a.personid,a.name,b.conid,d.condat,e.connam
FROM main_empr a INNER JOIN
coninr b
ON a.personid = b.personid AND a.calc_year = b.calc_year
INNER JOIN mainconinr c
ON b.conid = c.conid
INNER JOIN coninr d
ON a.personid = d.personid AND a.calc_year = d.calc_year
INNER JOIN mainconinr e ON d.conid = e.conid
INNER JOIN
(SELECT MAX(bb.condat) AS condat ,bb.personid,bb.calc_year ,bb.conid
FROM coninr bb
GROUP BY bb.personid,bb.calc_year,bb.conid
)Max_cont
ON Max_cont.personid = b.personid AND Max_cont.calc_year = b.calc_year AND Max_cont.condat = b.condat AND ((Max_cont.conid > 0 AND Max_cont.conid < 4 ) OR (Max_cont.conid IN(16,6) ))
INNER JOIN
(SELECT MIN(dd.condat) AS condat ,dd.personid,dd.calc_year,dd.conid
FROM coninr dd GROUP BY dd.personid,dd.calc_year,dd.conid
)Min_cont
ON Min_cont.personid = d.personid AND Min_cont.calc_year = d.calc_year AND Min_cont.condat = d.condat AND ((Min_cont.conid > 0 AND Min_cont.conid < 4 ) OR (Min_cont.conid IN(16,6) ))
WHERE c.active_flag = 1 and c.endreward_flag = 1
AND ( 0 = ( SELECT COUNT(*) FROM servmain x WHERE x.personid = a.personid AND x.calc_year = a.calc_year )
OR b.condat > ( SELECT MAX(x.serv_date) FROM servmain x WHERE x.personid = a.personid AND x.calc_year = a.calc_year ) )
AND a.calc_year = 2018
The problem is :
I use the coninr table twice to get the last and the first contract date in the same row .
It works fine in the first query but it was so slow because of the correlated sub-query,but in the second query it brings more than one row for the same person one of them for the first contract date and the other for the last one !!
How to fix this problem ?
This looks reasonable, but I've no way to know how it'll perform:
SELECT a.personid,a.name,b.conid,d.condat,e.connam
FROM main_empr a INNER JOIN coninr b
ON a.personid = b.personid AND a.calc_year = b.calc_year
INNER JOIN mainconinr c
ON b.conid = c.conid
INNER JOIN coninr d
ON a.personid = d.personid AND a.calc_year = d.calc_year
INNER JOIN mainconinr e
ON d.conid = e.conid
inner join
(
SELECT bb.personid, bb.calc_year, bb.conid, MIN(bb.condat) MinDate, MAX(bb.condat) MaxDate
FROM coninr bb WHERE
where (bb.conid > 0 and bb.conid < 4) or (bb.conid in (6, 16))
group by bb.personid, bb.calc_year, bb.conid
) zz on d.concat = zz.MinDate and b.condat = zz.MaxDate and b.personid = zz.personid and b.calc_year = zz.calc_year
left outer join
(
select s.personid, s.calc_year, max(s.serv_date) MaxServDate
from servmain s
group by s.personid, s.calc_year
) s on a.personid = s.personid and a.calc_year = s.calc_year
WHERE c.active_flag = 1 and c.endreward_flag = 1
and (s.MaxServDate is null or b.condat ? s.MaxServDate
AND a.calc_year = 2018
You don't need two queries for table coninr, you can get min and max in the same query with the group by. Also, for ServMain, doing a left outer join and putting in the where that either it's null (equivalent to count(*) = 0) or is less than b.condat takes care of that.

Query for logistic regression, multiple where exists

A logistic regression is a composed of a uniquely identifying number, followed by multiple binary variables (always 1 or 0) based on whether or not a person meets certain criteria. Below I have a query that lists several of these binary conditions. With only four such criteria the query takes a little longer to run than what I would think. Is there a more efficient approach than below? Note. tblicd is a large table lookup table with text representations of 15k+ rows. The query makes no real sense, just a proof of concept. I have the proper indexes on my composite keys.
select patient.patientid
,case when exists
(
select c.patientid from tblclaims as c
inner join patient as p on p.patientid=c.patientid
and c.admissiondate = p.admissiondate
and c.dischargedate = p.dischargedate
where patient.patientid = p.patientid
group by c.patientid
having count(*) > 1000
)
then '1' else '0'
end as moreThan1000
,case when exists
(
select c.patientid from tblclaims as c
inner join patient as p on p.patientid=c.patientid
and c.admissiondate = p.admissiondate
and c.dischargedate = p.dischargedate
where patient.patientid = p.patientid
group by c.patientid
having count(*) > 1500
)
then '1' else '0'
end as moreThan1500
,case when exists
(
select distinct picd.patientid from patienticd as picd
inner join patient as p on p.patientid= picd.patientid
and picd.admissiondate = p.admissiondate
and picd.dischargedate = p.dischargedate
inner join tblicd as t on t.icd_id = picd.icd_id
where t.descrip like '%diabetes%' and patient.patientid = picd.patientid
)
then '1' else '0'
end as diabetes
,case when exists
(
select r.patientid, count(*) from patient as r
where r.patientid = patient.patientid
group by r.patientid
having count(*) >1
)
then '1' else '0'
end
from patient
order by moreThan1000 desc
I would start by using subqueries in the from clause:
select q.patientid, moreThan1000, moreThan1500,
(case when d.patientid is not null then 1 else 0 end),
(case when pc.patientid is not null then 1 else 0 end)
from patient p left outer join
(select c.patientid,
(case when count(*) > 1000 then 1 else 0 end) as moreThan1000,
(case when count(*) > 1500 then 1 else 0 end) as moreThan1500
from tblclaims as c inner join
patient as p
on p.patientid=c.patientid and
c.admissiondate = p.admissiondate and
c.dischargedate = p.dischargedate
group by c.patientid
) q
on p.patientid = q.patientid left outer join
(select distinct picd.patientid
from patienticd as picd inner join
patient as p
on p.patientid= picd.patientid and
picd.admissiondate = p.admissiondate and
picd.dischargedate = p.dischargedate inner join
tblicd as t
on t.icd_id = picd.icd_id
where t.descrip like '%diabetes%'
) d
on p.patientid = d.patientid left outer join
(select r.patientid, count(*) as cnt
from patient as r
group by r.patientid
having count(*) >1
) pc
on p.patientid = pc.patientid
order by 2 desc
You can then probably simplify these subqueries more by combining them (for instance "p" and "pc" on the outer query can be combined into one). However, without the correlated subqueries, SQL Server should find it easier to optimize the queries.
Example of left joins as requested...
SELECT
patientid,
ISNULL(CondA.ConditionA,0) as IsConditionA,
ISNULL(CondB.ConditionB,0) as IsConditionB,
....
FROM
patient
LEFT JOIN
(SELECT DISTINCT patientid, 1 as ConditionA from ... where ... ) CondA
ON patient.patientid = CondA.patientID
LEFT JOIN
(SELECT DISTINCT patientid, 1 as ConditionB from ... where ... ) CondB
ON patient.patientid = CondB.patientID
If your Condition queries only return a maximum one row, you can simplify them down to
(SELECT patientid, 1 as ConditionA from ... where ... ) CondA