T-SQL Two counts with different where clause - tsql

I want to count values on a table with different where clauses and wondering if there is a better way of doing it.
In this code i count one value.
SELECT v.name, count(v.value) AS v1
FROM dbo.table as v
WHERE v.organisationID = 2
AND v.datecreated > '2018-01-01'
AND v.datecreated < '2018-05-01'
AND v.value = 1
GROUP BY v.name
I also want to count all rows with value = 2
my way of doing it is like this with a sub select.
SELECT v.name, count(v.value) AS v1, (SELECT v2.name, count(v2.value)
FROM dbo.table as v2
WHERE v2.organisationID = 2
AND v2.datecreated > '2018-01-01'
AND v2.datecreated < '2018-05-01'
AND v2.value = 2
GROUP BY v2.name) AS v2
FROM dbo.table as v
WHERE v.organisationID = 2
AND v.datecreated > '2018-01-01'
AND v.datecreated < '2018-05-01'
AND v.value = 1
GROUP BY v.name
The table contains > 100 millions rows so I really want the fastest way. I use clustered columnstore index on the table.
Is there some way of doing it whitout sub-select.
Pseudo code:
SELECT v.name, count(v.value where v.value=1) AS v1, count(v.value where v.value=2) AS v2
FROM dbo.table as v
WHERE v.organisationID = 2
AND v.datecreated > '2018-01-01'
AND v.datecreated < '2018-05-01'
GROUP BY v.name


Yes, just use a CASE expression:
SELECT v.name,
SUM(CASE WHEN v.value = 1 THEN 1 ELSE 0 END) AS v1,
SUM(CASE WHEN v.value = 2 THEN 1 ELSE 0 END) AS v2
FROM dbo.table as v
WHERE v.organisationID = 2
AND v.datecreated > '2018-01-01'
AND v.datecreated < '2018-05-01'
AND v.value IN (1,2)
GROUP BY v.name
;

Related

Count the number of instances the time is above average time

Here is my code:
arrival_cluster_raw as (
SELECT
routes.uc_id ,
cg.cluster_id ,
cg.cluster_centroid ,
routes.imei ,
routes.time_created::date as campaign_date,
min(routes.time_created) as m_per_imei_cluster
FROM cluster_groups as cg
group by 1,2,3,4,5
)
,
arrival_cluster_final as
(
select uc_id, campaign_date, cluster_id, cluster_centroid , date_trunc('second', AVG(m_per_imei_cluster::TIME)) as avg_arrival_time,
count(case when m_per_imei_cluster::TIME < (select AVG(m_per_imei_cluster::TIME) from arrival_cluster_raw) then 1 else null END) as "num_of_arrival_teams_before_avg_time"
,count(case when m_per_imei_cluster::TIME > (select AVG(m_per_imei_cluster::TIME) from arrival_cluster_raw) then 1 else null END) as "num_of_arrival_teams_after_avg_time"
FROM arrival_cluster_raw
group by uc_id,cluster_id, cluster_centroid ,campaign_date
)
The problem is that in the "arrival_cluster_final", the average value of the entire cluster
is being compared whereas I want to compare the average value for the combination of uc_id,cluster_id, cluster_centroid ,campaign_date

--can you try this one.
WITH arrival_cluster_raw AS (
SELECT
routes.uc_id,
cg.cluster_id,
cg.cluster_centroid,
routes.imei,
routes.time_created::date AS campaign_date,
min(routes.time_created) AS m_per_imei_cluster
FROM
cluster_groups AS cg
JOIN routes ON routes.uc_id = cg.id --assume the way you want join.
GROUP BY
1,2,3,4,5
),
arrival_cluster_final AS (
SELECT
uc_id,
cluster_id,
cluster_centroid,
imei,
campaign_date,
date_trunc('second', (avg(m_per_imei_cluster) OVER w))
,count( CASE WHEN (avg(m_per_imei_cluster) OVER w) < m_per_imei_cluster THEN
1
ELSE
NULL
END) AS num_of_arrival_teams_before_avg_time
,count(
CASE WHEN (avg(m_per_imei_cluster) OVER w) > m_per_imei_cluster THEN
1
ELSE
NULL
END) AS num_of_arrival_teams_after_avg_time
FROM
arrival_cluster_raw
WINDOW w AS (PARTITION BY uc_id,
cluster_id,
cluster_centroid,
campaign_date))
SELECT * FROM arrival_cluster_final ORDER BY 1;

How to select fields using alias name?

I have an select:
SELECT
tb_dim_equipe.no_equipe "EQUIPE",
tb_dim_profissional.no_profissional "PROFISSIONAL",
no_cidadao "CIDADÃO",
a.nu_cns "CNS",
sum(case when co_dim_tempo >= 20190100 and co_dim_tempo <= 20200131 then 1 else 0 end) as "TOTAL"
from (
SELECT no_cidadao,
tb_fat_cad_individual.nu_cns,
tb_fat_cad_individual.co_dim_profissional,
tb_fat_cad_individual.co_dim_equipe from tb_fat_cidadao_pec
join tb_fat_cad_individual on tb_fat_cad_individual.nu_cns = tb_fat_cidadao_pec.nu_cns
join tb_fat_cidadao on tb_fat_cad_individual.co_seq_fat_cad_individual = tb_fat_cidadao.co_fat_cad_individual
where st_mudou = 0
and st_vivo = 1
and st_gestante = 1
and tb_fat_cidadao.co_dim_tempo_validade = 30001231) a
left join (
SELECT tb_fat_atendimento_individual.nu_cns,
tb_fat_atendimento_individual.co_dim_tempo
from tb_fat_atendimento_individual
join tb_dim_tempo on tb_dim_tempo.co_seq_dim_tempo = tb_fat_atendimento_individual.co_dim_tempo
where co_seq_dim_tempo >= 20190100
and co_seq_dim_tempo <= 20200131
and ds_filtro_ciaps like '%ABP001%'
union SELECT tb_fat_proced_atend.nu_cns,
tb_fat_proced_atend.co_dim_tempo
from tb_fat_proced_atend
join tb_dim_tempo on tb_dim_tempo.co_seq_dim_tempo = tb_fat_proced_atend.co_dim_tempo
where co_seq_dim_tempo >= 20190100
and co_seq_dim_tempo <= 20200131
and ds_filtro_procedimento like '%0301010110%') b
on a.nu_cns = b.nu_cns
join tb_dim_equipe on tb_dim_equipe.co_seq_dim_equipe = a.co_dim_equipe
join tb_dim_profissional on tb_dim_profissional.co_seq_dim_profissional = a.co_dim_profissional
group by no_equipe, no_profissional, no_cidadao, a.nu_cns
order by no_equipe, no_profissional, no_cidadao
This return to me five columns EQUIPE, PROFISSIONAL, CIDADÃO, CNS and TOTAL
I want to create a new select command like this:
SELECT sum(c.TOTAL) from *query above* c
but I receive the error that column not exists.
How I can use a select with the names of alias columns EQUIPE, PROFISSIONAL, CIDADÃO, CNS and TOTAL?

Just like in the alias, you need to quote the column identifier if it is all-uppercase:
SELECT sum(c."TOTAL") from /*query above*/ c
-- ^ ^

Capture First Character of Last Group of 1s in a Binary Series Part II: Multiple IDs

I have data something like this:
ID 1 1 1 1 1 1 1 1 1 1 1 1
Month J F M A M J J A S O N D
Status 1 0 0 1 0 1 0 0 1 1 1 1
ID 2 2 2 2 2 2 2 2 2 2 2 2
Month J F M A M J J A S O N D
Status 1 0 1 0 1 0 1 0 1 0 1 1
ID 3 3 3 3 3 3 3 3 3 3 3 3
Month J F M A M J J A S O N D
Status 0 0 0 0 0 0 0 0 0 0 0 1
Using t-SQL, I am trying to capture the month corresponding to the first STATUS = 1 in the last group of 1s for each ID, i.e., September, November and December in this example.
Here is the code I'm using:
IF OBJECT_ID('tempdb..#Temp1') IS NOT NULL DROP TABLE #Temp1
;WITH PARTITIONED1 AS
(SELECT t0.ID
, t0.Year_Month
, LAST_VALUE(t0.Year_Month) OVER (PARTITION BY t0.Account_Number ORDER BY t0.Year_Month) AS STATUS
, ROW_NUMBER() OVER (PARTITION BY t0.Account_Number ORDER BY t0.Year_Month) AS rn1
FROM #Temp0 t0
)
SELECT *
INTO #Temp1
FROM PARTITIONED1 p1
ORDER BY t0.ID
, t0.Year_Month
IF OBJECT_ID('tempdb..#Temp') IS NOT NULL DROP TABLE #Temp
SELECT *
INTO #Temp
FROM #Temp1 t1
WHERE t1.rn1 = (SELECT MAX(b.rn1) + 1 FROM #Temp1 b WHERE b.STATUS = 0)
GROUP BY t1.ID
, t1.Year_Month
, t1.rn1
However, this just returns the last instance where STATUS = 1 is achieved overall as the first 1 of the last group of 1s, in this case January.
I've tried using CASE statements and grouping in various combinations (hence the intermediate step reading the data into #Temp1), but have not been able to get results for all three IDs; is anyone able to assist?
Thanks in advance!

Assuming Ju for June and Jl for July:
--Sample Data
IF OBJECT_ID('tempdb..#Temp0') IS NOT NULL DROP TABLE #Temp0
CREATE TABLE #Temp0 (ID INT, Year_Month VARCHAR(1), Status INT)
INSERT INTO #Temp0
VALUES(1,'J',1),(1,'F',0),(1,'M',0),(1,'A',1),(1,'M',0),(1,'J',1),(1,'J',0),(1,'A',0),(1,'S',1),(1,'O',1),(1,'N',1),(1,'D',1),(2,'J',1),(2,'F',0),(2,'M',1),(2,'A',0),(2,'M',1),(2,'J',0),(2,'J',1),(2,'A',0),(2,'S',1),(2,'O',0),(2,'N',1),(2,'D',1),(3,'J',0),(3,'F',0),(3,'M',0),(3,'A',0),(3,'M',0),(3,'J',0),(3,'J',0),(3,'A',0),(3,'S',0),(3,'O',0),(3,'N',0),(3,'D',1);
--Query
WITH A
AS ( SELECT *,
CASE Year_Month
WHEN 'J' THEN 1
WHEN 'F' THEN 2
WHEN 'M' THEN 3
WHEN 'A' THEN 4
WHEN 'M' THEN 5
WHEN 'Ju' THEN 6
WHEN 'Jl' THEN 7
WHEN 'A' THEN 8
WHEN 'S' THEN 9
WHEN 'O' THEN 10
WHEN 'N' THEN 11
WHEN 'D' THEN 12
END
AS MonthNumber
FROM #Temp0 ),
StartingPoints
AS ( SELECT ID,
Year_Month,
MonthNumber,
Status
FROM A
WHERE NOT EXISTS
(
SELECT 1
FROM A
AS B
WHERE B.ID=A.ID
AND B.Status=A.Status-1
) ),
MonthRanking
AS ( SELECT A.*,
ROW_NUMBER( ) OVER( PARTITION BY A.ID ORDER BY A.MonthNumber )
AS rownum
FROM A
INNER JOIN
(
SELECT ID,
MAX( MonthNumber )+1
AS StartOfLastGroup
FROM StartingPoints
GROUP BY ID
)
AS B
ON A.ID=B.ID
AND A.MonthNumber>=B.StartOfLastGroup )
SELECT *
FROM MonthRanking
WHERE rownum=1;
Results:
If Month Names are recorded in Full as in July, June then this would work as well:
WITH StartingPoints
AS (SELECT ID,
Year_Month,
MonthNUmber = MONTH('01-'+Year_Month+'-2010'),
Status
FROM #Temp0
WHERE NOT EXISTS
(
SELECT 1
FROM #Temp0 AS B
WHERE B.ID = #Temp0.ID
AND B.Status = #Temp0.Status - 1
)),
MonthRanking
AS (SELECT A.*,
ROW_NUMBER() OVER(PARTITION BY A.ID ORDER BY MONTH('01-'+A.Year_Month+'-2010')) AS rownum
FROM #Temp0 AS A
INNER JOIN
(
SELECT ID,
MAX(MonthNumber) + 1 AS StartOfLastGroup
FROM StartingPoints
GROUP BY ID
) AS B ON A.ID = B.ID
AND MONTH('01-'+A.Year_Month+'-2010') >= B.StartOfLastGroup)
SELECT *
FROM MonthRanking
WHERE rownum = 1;
Results:
And if we assume that the data is as Iamdave assumes then it simply like so:
WITH StartingPoints
AS (SELECT ID,
Year_Month,
Status
FROM #Temp0
WHERE NOT EXISTS
(
SELECT 1
FROM #Temp0 AS B
WHERE B.ID = #Temp0.ID
AND B.Status = #Temp0.Status - 1
)),
MonthRanking
AS (SELECT A.*,
ROW_NUMBER() OVER(PARTITION BY A.ID ORDER BY Year_Month) AS rownum
FROM #Temp0 AS A
INNER JOIN
(
SELECT ID,
MAX(Year_Month) + 1 AS StartOfLastGroup
FROM StartingPoints
GROUP BY ID
) AS B ON A.ID = B.ID
AND A.Year_Month >= B.StartOfLastGroup)
SELECT *
FROM MonthRanking
WHERE rownum = 1;
Results:

You can do this with a couple derived tables that stack two window functions on top of one another (which can't be done in the same select). I have assumed that your data is slightly different to the table you have provided, based on the column names in your query. If they are not as I have them below, I strongly recommend having a look at how you store your data:
declare #t table(ID int, YearMonth int,StatusValue bit);
insert into #t values (1,201501,1),(1,201502,0),(1,201503,0),(1,201504,1),(1,201505,0),(1,201506,1),(1,201507,0),(1,201508,0),(1,201509,1),(1,201510,1),(1,201511,1),(1,201512,1),(2,201601,1),(2,201602,0),(2,201603,1),(2,201604,0),(2,201605,1),(2,201606,0),(2,201607,1),(2,201608,0),(2,201609,1),(2,201610,0),(2,201611,1),(2,201612,1),(3,201701,0),(3,201702,0),(3,201703,0),(3,201704,0),(3,201705,0),(3,201706,0),(3,201707,0),(3,201708,0),(3,201709,0),(3,201710,0),(3,201711,0),(3,201712,1);
with c as
(
select ID
,YearMonth
,StatusValue
,case when StatusValue = 1
and lead(StatusValue,1,1) over (partition by ID
order by YearMonth desc) = 0
then 1
else 0
end as c
from #t
), sc as
(
select ID
,YearMonth
,StatusValue
,sum(c) over (partition by ID order by YearMonth desc) as sc
from c
where c = 1
)
select ID
,YearMonth
,StatusValue
from sc
where sc = 1
order by ID;
Output:
+----+-----------+-------------+
| ID | YearMonth | StatusValue |
+----+-----------+-------------+
| 1 | 201509 | 1 |
| 2 | 201611 | 1 |
| 3 | 201712 | 1 |
+----+-----------+-------------+

How to append CTE results to main query output?

I've created a TSQL query that pulls from two sets of tables in my database. The tables in the Common Table Expression are different from the tables in the main query. I'm joining on MRN and need the end result to contain accounts from both sets of tables. I've written the following query to this end:
with cteHosp as(
select Distinct p.EncounterNumber, p.MRN, p.AdmitAge
from HospitalPatients p
inner join Eligibility e on p.MRN = e.MRN
inner join HospChgDtl c on p.pt_id = c.pt_id
inner join HospitalDiagnoses d on p.pt_id = d.pt_id
where p.AdmitAge >=12
and d.dx_cd in ('G89.4','R52.1','R52.2','Z00.129')
)
Select Distinct a.AccountNo, a.dob, DATEDIFF(yy, a.dob, GETDATE()) as Age
from RHCCPTDetail c
inner join RHCAppointments a on c.ClaimID = a.ClaimID
inner join Eligibility e on c.hl7Id = e.MRN
full outer join cteHosp on e.MRN = cteHosp.MRN
where DATEDIFF(yy, a.dob, getdate()) >= 12
and left(c.PriDiag,7) in ('G89.4','R52.1','R52.2', 'Z00.129')
or (
DATEDIFF(yy, a.dob, getdate()) >= 12
and LEFT(c.DiagCode2,7) in ('G89.4','R52.1','R52.2','Z00.129')
)
or (
DATEDIFF(yy, a.dob, getdate()) >= 12
and LEFT(c.DiagCode3,7) in ('G89.4','R52.1','R52.2','Z00.129')
)
or (
DATEDIFF(yy, a.dob, getdate()) >= 12
and LEFT(c.DiagCode4,7) in ('G89.4','R52.1','R52.2','Z00.129')
)
order by AccountNo
How do I merge together the output of both the common table expression and the main query into one set of results?

Merge performs inserts, updates or deletes. I believe you want to join the cte. If so, here is an example.
Notice the cteBatch is joined to the Main query below.
with
cteBatch (BatchID,BatchDate,Creator,LogID)
as
(
select
BatchID
,dateadd(day,right(BatchID,3) -1,
cast(cast(left(BatchID,4) as varchar(4))
+ '-01-01' as date)) BatchDate
,Creator
,LogID
from tblPriceMatrixBatch b
unpivot
(
LogID
for Logs in (LogIDISI,LogIDTG,LogIDWeb)
)u
)
Select
0 as isCurrent
,i.InterfaceID
,i.InterfaceName
,b.BatchID
,b.BatchDate
,case when isdate(l.start) = 0 and isdate(l.[end]) = 0 then 'Scheduled'
when isdate(l.start) = 1 and isdate(l.[end]) = 0 then 'Running'
when isdate(l.start) = 1 and isdate(l.[end]) = 1 and isnull(l.haserror,0) = 1 then 'Failed'
when isdate(l.start) = 1 and isdate(l.[end]) = 1 and isnull(l.haserror,0) != 1 then 'Success'
else 'idunno' end as stat
,l.Start as StartTime
,l.[end] as CompleteTime
,b.Creator as Usr
from EOCSupport.dbo.Interfaces i
join EOCSupport.dbo.Logs l
on i.InterfaceID = l.InterfaceID
join cteBatch b
on b.logid = l.LogID

how to select top 10 without duplicates

Using SQL Server 2012
I need to select TOP 10 Producer based on a ProducerCode. But the data is messed up, users were entering same Producers just spelled differently and with the same ProducerCode.
So I just need TOP 10, so if the ProducerCode is repeating, I just want to pick the first one in a list.
How can I achieve that?
Sample of my data
;WITH cte_TopWP --T
AS
(
SELECT distinct ProducerCode, Producer,SUM(premium) as NetWrittenPremium,
SUM(CASE WHEN PolicyType = 'New Business' THEN Premium ELSE 0 END) as NewBusiness1,
SUM(CASE WHEN PolicyType = 'Renewal' THEN Premium ELSE 0 END) as Renewal1,
SUM(CASE WHEN PolicyType = 'Rewrite' THEN Premium ELSE 0 END) as Rewrite1
FROM ProductionReportMetrics
WHERE YEAR(EffectiveDate) = 2016 AND TransactionType = 'Policy' AND CompanyLine = 'Arch Insurance Company'--AND ProducerType = 'Wholesaler'
GROUP BY ProducerCode,Producer
)
,
cte_Counts --C
AS
(
SELECT distinct ProducerCode, ProducerName, COUNT (distinct ControlNo) as Submissions2,
SUM(CASE WHEN QuotedPremium IS NOT NULL THEN 1 ELSE 0 END) as Quoted2,
SUM(CASE WHEN Type = 'New Business' AND Status IN ('Bound','Cancelled','Notice of Cancellation') THEN 1 ELSE 0 END ) as NewBusiness2,
SUM(CASE WHEN Type = 'Renewal' AND Status IN ('Bound','Cancelled','Notice of Cancellation') THEN 1 ELSE 0 END ) as Renewal2,
SUM(CASE WHEN Type = 'Rewrite' AND Status IN ('Bound','Cancelled','Notice of Cancellation') THEN 1 ELSE 0 END ) as Rewrite2,
SUM(CASE WHEN Status = 'Declined' THEN 1 ELSE 0 END ) as Declined2
FROM ClearanceReportMetrics
WHERE YEAR(EffectiveDate)=2016 AND CompanyLine = 'Arch Insurance Company'
GROUP BY ProducerCode,ProducerName
)
SELECT top 10 RANK() OVER (ORDER BY NetWrittenPremium desc) as Rank,
t.ProducerCode,
c.ProducerName as 'Producer',
NetWrittenPremium,
t.NewBusiness1,
t.Renewal1,
t.Rewrite1,
c.[NewBusiness2]+c.[Renewal2]+c.[Rewrite2] as PolicyCount,
c.Submissions2,
c.Quoted2,
c.[NewBusiness2],
c.Renewal2,
c.Rewrite2,
c.Declined2
FROM cte_TopWP t --LEFT OUTER JOIN tblProducers p on t.ProducerCode=p.ProducerCode
LEFT OUTER JOIN cte_Counts c ON t.ProducerCode=c.ProducerCode

You should use ROW_NUMBER to fix your issue.
https://msdn.microsoft.com/en-us/library/ms186734.aspx
A good example of this is the following answer:
https://dba.stackexchange.com/a/22198
Here's the code example from the answer.
SELECT * FROM
(
SELECT acss_lookup.ID AS acss_lookupID,
ROW_NUMBER() OVER
(PARTITION BY your_distinct_column ORDER BY any_column_you_think_is_appropriate)
as num,
acss_lookup.product_lookupID AS acssproduct_lookupID,
acss_lookup.region_lookupID AS acssregion_lookupID,
acss_lookup.document_lookupID AS acssdocument_lookupID,
product.ID AS product_ID,
product.parent_productID AS productparent_product_ID,
product.label AS product_label,
product.displayheading AS product_displayheading,
product.displayorder AS product_displayorder,
product.display AS product_display,
product.ignorenewupdate AS product_ignorenewupdate,
product.directlink AS product_directlink,
product.directlinkURL AS product_directlinkURL,
product.shortdescription AS product_shortdescription,
product.logo AS product_logo,
product.thumbnail AS product_thumbnail,
product.content AS product_content,
product.pdf AS product_pdf,
product.language_lookupID AS product_language_lookupID,
document.ID AS document_ID,
document.shortdescription AS document_shortdescription,
document.language_lookupID AS document_language_lookupID,
document.document_note AS document_document_note,
document.displayheading AS document_displayheading
FROM acss_lookup
INNER JOIN product ON (acss_lookup.product_lookupID = product.ID)
INNER JOIN document ON (acss_lookup.document_lookupID = document.ID)
)a
WHERE a.num = 1
ORDER BY product_displayheading ASC;

You could do this:
SELECT ProducerCode, MIN(Producer) AS Producer, ...
GROUP BY ProducerCode