How to join table to table created from query - sql

I query to get the top 5 results of IPs and then i want to get for each IP, the countries and others fields related to it by join.
select actual_ip, actual_country_code, actual_country_name, organization FROM "public"."bus_request" inner join (
select top 5 actual_ip, count(*) FROM "public"."bus_request"
where app_name = 'xxxxx' and request_score>0 and date >= '2019-06-07' and event_type <> 'browser_js'
group by actual_ip order by count desc ) as temp on actual_ip = temp.actual_ip
SQL Error [500310] [42702]: [Amazon](500310) Invalid operation: column reference "actual_ip" is ambiguous;

Not sure exactly which DBMS you're using, but try resolving the ambiguity by specifying the table, e.g.:
select busreq.actual_ip, actual_country_code, actual_country_name, organization FROM "public"."bus_request" as busreq inner join (
select top 5 actual_ip, count(*) FROM "public"."bus_request"
where app_name = 'xxxxx' and request_score>0 and date >= '2019-06-07' and event_type <> 'browser_js'
group by actual_ip order by count desc ) as temp on busreq.actual_ip = temp.actual_ip
(you may need to disambiguate the inner use of actual_ip - but hopefully not.)

You should always qualify all column references in a query that references more than one table. In addition, you should use table aliases so the query is easier to write and to read:
select br.actual_ip, br.actual_country_code, br.actual_country_name, br.organization
from "public"."bus_request" br inner join
(select top 5 br2.actual_ip, count(*)
from "public"."bus_request" br2
where br2.app_name = 'xxxxx' and
br2.request_score > 0 and
br2.date >= '2019-06-07' and
br2.event_type <> 'browser_js'
group by br2.actual_ip
order by count(*) desc
) br2
on br2.actual_ip = br.actual_ip;

Related

Syntax error to combine left join and select

I'm getting a syntax error at Left Join. So in trying to combine the two, i used the left join and the brackets. I'm not sure where the problem is:
SELECT DISTINCT a.order_id
FROM fact.outbound AS a
ORDER BY Rand()
LIMIT 5
LEFT JOIN (
SELECT
outbound.marketplace_name,
outbound.product_type,
outbound.mpid,
outbound.order_id,
outbound.sku,
pbdh.mpid,
pbdh.product_type,
pbdh.validated_exp_reach,
pbdh.ultimate_sales_rank_de,
pbdh.ultimate_sales_rank_fr,
(
pbdh.very_good_stock_count + good_stock_count + new_Stock_count
) as total_stock
FROM
fact.outbound AS outbound
LEFT JOIN reporting_layer.pricing_bi_data_historisation AS pbdh ON outbound.mpid = pbdh.mpid
AND trunc(outbound.ordered_date) = trunc(pbdh.importdate)
WHERE
outbound.ordered_date > '2022-01-01'
AND pbdh.importdate > '2022-01-01'
LIMIT
5
) AS b ON a.orderid = b.order_id
Error:
You have an error in your SQL syntax; it seems the error is around: 'LEFT JOIN ( SELECT outbound.marketplace_name, outbound.product_t' at line 9
What could be the reason?
Place the first limit logic into a separate subquery, and then join the two subqueries:
SELECT DISTINCT a.order_id
FROM
(
SELECT order_id
FROM fact.outbound
ORDER BY Rand()
LIMIT 5
) a
LEFT JOIN
(
SELECT
outbound.marketplace_name,
outbound.product_type,
outbound.mpid,
outbound.order_id,
outbound.sku,
pbdh.mpid,
pbdh.product_type,
pbdh.validated_exp_reach,
pbdh.ultimate_sales_rank_de,
pbdh.ultimate_sales_rank_fr,
(pbdh.very_good_stock_count +
good_stock_count + new_Stock_count) AS total_stock
FROM fact.outbound AS outbound
LEFT JOIN reporting_layer.pricing_bi_data_historisation AS pbdh
ON outbound.mpid = pbdh.mpid AND
TRUNC(outbound.ordered_date) = TRUNC(pbdh.importdate)
WHERE outbound.ordered_date > '2022-01-01' AND
pbdh.importdate > '2022-01-01'
-- there should be an ORDER BY clause here...
LIMIT 5
) AS b
ON a.orderid = b.order_id;
Note that the select clause of the b subquery can be reduced to just the order_id, as no values from this subquery are actually selected in the end.
You can skip the LEFT JOIN, since no b columns are selected. (And SELECT DISTINCT makes sure any duplicates are eliminated.)
SELECT DISTINCT order_id
FROM fact.outbound
ORDER BY Rand()
LIMIT 5

Joining Onto Partition Statement HANA SQL

I am trying to join two tables to the following query:
SELECT "NUMBER",
"U_ANALYZED_DATE",
"DV_SALES_ACCOUNT",
"U_USD_TOTAL_POTENTIAL_NNACV"
FROM
(select *, row_number() over ( partition by "DV_SALES_ACCOUNT" order by "U_ANALYZED_DATE" desc ) rownum
from "SURF_RT"."SALES_REQUEST")
WHERE rownum = 1
AND "DV_SALES_CATEGORY" = 'Compliance'
AND "DV_STATE" NOT IN ('Closed Canceled')
AND (YEAR("U_ANALYZED_DATE") = '2019' AND MONTH("U_ANALYZED_DATE") IN ('10','11','12')
OR YEAR("U_ANALYZED_DATE") = '2020' AND MONTH("U_ANALYZED_DATE") IN ('1','2','3'))
AND "U_USD_TOTAL_POTENTIAL_NNACV" > 0
ORDER BY "U_ANALYZED_DATE" desc
The tables should be joined as follows:
JOIN "SURF_RT"."SALES_ACCOUNT" on "SURF_RT"."SALES_ACCOUNT"."NAME" = "SURF_RT"."SALES_REQUEST"."DV_SALES_ACCOUNT"
JOIN "SURF_RT"."SALES_CONTRACT" on "SURF_RT"."SALES_CONTRACT"."DV_ACCOUNT" = "SURF_RT"."SALES_REQUEST"."DV_SALES_ACCOUNT"
I am getting an error no matter what I try and it has to be because of the partition. Does anyone know the solution here?
I suspect that you just need to alias the derived table so you can then refer to join it. In many databases this is mandatory anyway, but apparently not in Hana (otherwise your original query would not run).
But to join on a derived table (the resultset that is generated by the subquery), alias do help:
SELECT
...
FROM
(
select
*,
row_number() over ( partition by "DV_SALES_ACCOUNT" order by "U_ANALYZED_DATE" desc ) rownum
from "SURF_RT"."SALES_REQUEST"
) sr -- table alias
JOIN "SURF_RT"."SALES_ACCOUNT"
ON "SURF_RT"."SALES_ACCOUNT"."NAME" = "SURF_RT"."SALES_REQUEST"."DV_SALES_ACCOUNT"
JOIN "SURF_RT"."SALES_CONTRACT"
ON "SURF_RT"."SALES_CONTRACT"."DV_ACCOUNT" = sr."DV_SALES_ACCOUNT" --reference to the derived table
WHERE
...
Side notes:
you should use table aliases for other tables involved in the query too, in order to make the code more readable
you should also prefix each column in the query with the identifier of the table it belongs to, so the query is unambiguous (and easier to maintain)
The problem with this query is not "that the where rownum = 1 needs to be at the end" but that the OP got confused by the bracketing of SQL expression.
More specifically, trying to reference the sub-query data by specifying join conditions against the base table that is used in the sub-query:
JOIN "SURF_RT"."SALES_ACCOUNT"
on "SURF_RT"."SALES_ACCOUNT"."NAME" = "SURF_RT"."SALES_REQUEST"."DV_SALES_ACCOUNT"
JOIN "SURF_RT"."SALES_CONTRACT"
on "SURF_RT"."SALES_CONTRACT"."DV_ACCOUNT" = "SURF_RT"."SALES_REQUEST"."DV_SALES_ACCOUNT"
Since the sub-query (derived table) is used in the query and should be used for the join, it needs to be referred in the join condition, instead.
So, yes, it needs a table alias here and the join conditions need to refer to it.
SELECT
...
FROM
(select *
, row_number() over
(partition by "DV_SALES_ACCOUNT"
order by "U_ANALYZED_DATE" desc) rownum
from
"SURF_RT"."SALES_REQUEST") sr
INNER JOIN "SURF_RT"."SALES_ACCOUNT" sa
on sa."NAME" = sr."DV_SALES_ACCOUNT"
INNER JOIN "SURF_RT"."SALES_CONTRACT" sc
on sc."DV_ACCOUNT" = sr."DV_SALES_ACCOUNT"
WHERE
sr.rownum = 1
AND "DV_SALES_CATEGORY" = 'Compliance'
AND "DV_STATE" NOT IN ('Closed Canceled')
AND (YEAR("U_ANALYZED_DATE") = '2019'
AND MONTH("U_ANALYZED_DATE") IN ('10','11','12')
OR YEAR("U_ANALYZED_DATE") = '2020'
AND MONTH("U_ANALYZED_DATE") IN ('1','2','3'))
AND "U_USD_TOTAL_POTENTIAL_NNACV" > 0
ORDER BY
"U_ANALYZED_DATE" desc;
With just this little bit of standard SQL syntax and formatting of code the query got a lot easier to understand.
Now it's even obvious that the IN conditions for MONTH and YEAR should in fact be integers, not strings as these functions return integers.
SELECT
...
FROM
(SELECT *
, row_number() over
(partition by "DV_SALES_ACCOUNT"
order by "U_ANALYZED_DATE" desc) rownum
FROM
"SURF_RT"."SALES_REQUEST") sr
INNER JOIN "SURF_RT"."SALES_ACCOUNT" sa
on sa."NAME" = sr."DV_SALES_ACCOUNT"
INNER JOIN "SURF_RT"."SALES_CONTRACT" sc
on sc."DV_ACCOUNT" = sr."DV_SALES_ACCOUNT"
WHERE
sr.rownum = 1
AND "DV_SALES_CATEGORY" = 'Compliance'
AND "DV_STATE" NOT IN ('Closed Canceled')
AND ( YEAR("U_ANALYZED_DATE") = 2019
AND MONTH("U_ANALYZED_DATE") IN (10, 11, 12)
OR YEAR("U_ANALYZED_DATE") = '2020'
AND MONTH("U_ANALYZED_DATE") IN (1 , 2 , 3 )
)
AND "U_USD_TOTAL_POTENTIAL_NNACV" > 0
ORDER BY
"U_ANALYZED_DATE" DESC

How To use Where instead of Group by?

I wrote a query , that gives me this Output :
(This is Just a sample obviously the Output Table contains 300000 rows approximatly)
And This is my Query :
proc sql;
create Table Output as
select ID_User, Division_ID, sum(conta) as Tot_Items, max(Counts) as Max_Item
from (select c.ID_User , c.Div_ID as Division_ID, ro.code as Mat, count(*) as Counts
from Ods.R_Ordini o
inner join DMC.Cust_Dupl c
on User_ID = ID_User
inner join ods.R_Nlines ro
on ro.Orders_Id = o.Id_Orders AND RO.SERVICE = 0
inner join ods.R_Mat m
on ro.Mat_Id = Id_Mat and flag = 0
group by
ID_User,
C.Division_ID,
Ro.Code
Having Counts > 1
)
group by
Id_User,
Division_ID
Order by
Tot_Item DESC
;
quit;
So , What i want is to re-write this Query , but instead of the Group by i want to use the Where Condition , (WHERE=(DIVISION_ID=3)) this is the condition.
I tried several attempts , with some i got errors , and with others i did got an output , but the output was not like the original one.
any help would be much appreciated , thank you.
The SAS data set option (where=(<where-expression>)) can only be coded adjacent to a data set name. So the option would have to be applied to the data set containing the column div_id that is the basis for computed column division_id. That would be table alias c
DMC.Cust_Dupl(where=(div_id=3)) as c
Or just use a normal SQL where clause
…
)
where division_id=3
group by …
Just use WHERE DIVISION_ID=3 before group by.
select ID_User, Division_ID, sum(conta) as Tot_Items, max(Counts) as Max_Item from (select c.ID_User , c.Div_ID as Division_ID, ro.code as Mat, count(*) as Counts from Ods.R_Ordini o inner join DMC.Cust_Dupl c on User_ID = ID_User inner join ods.R_Nlines ro on ro.Orders_Id = o.Id_Orders AND RO.SERVICE = 0 inner join ods.R_Mat m on ro.Mat_Id = Id_Mat and flag = 0 WHERE DIVISION_ID=3 group by ID_User, C.Division_ID, Ro.Code Having Counts > 1 ) group by Id_User, Division_ID Order by Tot_Item DESC

access - row_number function?

I had this query, which gives me the desired results on postgres
SELECT
t.*,
ROW_NUMBER() OVER (PARTITION BY t."Internal_reference", t."Movement_date" ORDER BY t."Movement_date") AS "cnt"
FROM (SELECT
"Internal_reference",
MAX("Movement_date") AS maxtime
FROM dw."LO-D4_Movements"
GROUP BY "Internal_reference") r
INNER JOIN dw."LO-D4_Movements" t
ON t."Movement_date" = r.maxtime
AND t."Internal_reference" = r."Internal_reference"
Issue is I have to translate the query above on Access where the analytical function does not exist ...
I used this answer to build the query below
SELECT
t."Internal_reference",
t.from_code,
t.to_code,
t."Movement_date",
t.shipment_number,
t."PO_number",
t."Quantity",
t."Movement_value",
t."Site",
t."Import_date",
COUNT(*) AS "cnt"
FROM (
SELECT "Internal_reference",
MAX("Movement_date") AS maxtime
FROM dw."LO-D4_Movements"
GROUP BY "Internal_reference") r
LEFT OUTER JOIN dw."LO-D4_Movements" t
ON t."Movement_date" = r.maxtime AND t."Internal_reference" = r."Internal_reference"
GROUP BY
t.from_code,
t.to_code,
t."Movement_date",
t.shipment_number,
t."PO_number",
t."Quantity",
t."Movement_value",
t."Site",
t."Import_date",
t."Internal_reference"
ORDER BY t.from_code
Issue is I only have 1 in the cnt column.
I tried to tweak it by removing the internal_reference (see below)
SELECT
t.from_code,
t.to_code,
t."Movement_date",
t.shipment_number,
t."PO_number",
t."Quantity",
t."Movement_value",
t."Site",
t."Import_date",
COUNT(*) AS "cnt"
FROM (
SELECT "Internal_reference",
MAX("Movement_date") AS maxtime
FROM dw."LO-D4_Movements"
GROUP BY "Internal_reference") r
LEFT OUTER JOIN dw."LO-D4_Movements" t
ON t."Movement_date" = r.maxtime AND t."Internal_reference" = r."Internal_reference"
GROUP BY
t.from_code,
t.to_code,
t."Movement_date",
t.shipment_number,
t."PO_number",
t."Quantity",
t."Movement_value",
t."Site",
t."Import_date"
ORDER BY t.from_code
However, the results are even worse. The cnt is growing but it gives me the wrong cnt
Any help are more than welcome as I'm slow losing my sanity.
Thanks
Edit: Please find the sqlfiddle
I think Gordon-Linoff's code is close to what you want, but there are some typos I couldn't correct without a rewrite, so here's my attempt
SELECT
t1.Internal_reference,
t1.Movement_date,
t1.PO_Number as Combination_Of_Columns_Which_Make_This_Unique,
t1.Other_columns,
Count(1) AS Cnt
FROM
([LO-D4_Movements] AS t1
INNER JOIN [LO-D4_Movements] AS t2 ON
t1.Internal_reference = t2.Internal_reference AND
t1.Movement_date = t2.Movement_date)
INNER JOIN (
SELECT
t3.Internal_reference,
MAX(t3.Movement_date) AS Maxtime
FROM
[LO-D4_Movements] AS t3
GROUP BY
t3.Internal_reference
) AS r ON
t1.Internal_reference = r.Internal_reference AND
t1.Movement_date = r.Maxtime
WHERE
t1.PO_Number>=t2.PO_Number
GROUP BY
t1.Internal_reference,
t1.Movement_date,t1.PO_Number,
t1.Other_columns
ORDER BY
t1.Internal_reference,
t1.Movement_date,
Count(1);
In addition to within the max(movement_date) subquery, the main table is brought in twice. One version is the one for showing in your results, the other is for counting records to generate the sequence numbers.
Gordon said you need a unique id column for each row. And that's true if by "column" you mean to include derived columns also. Also it only needs to be unique within any combination of "internal_reference" and "Movement_date".
I've assumed, perhaps wrongly, that PO_Number will suffice. If not, concatenate with that (and some delimeters) other fields which will make it unique. The where clause will need updating to compare t1 and t2 for the "Combination of Columns which make this unique".
If, there is no appropriate combination available, I'm not sure it can be done without VBA and/or temp tables as The-Gambill suggested.
This is a real pain in MS Access, as far as I know. One method is a correlated subquery, but you need a unique id column on each row:
SELECT t.*,
(SELECT COUNT(*)
FROM (SELECT "Internal_reference", MAX("Movement_date") AS maxtime
FROM dw."LO-D4_Movements"
GROUP BY "Internal_reference"
) as t2
WHERE t2."Internal_reference" AND t."Internal_reference" AND
t2."Movement_date" = t."Movement_date" AND
t2.?? <= t.??
) as cnt
FROM (SELECT "Internal_reference", MAX("Movement_date") AS maxtime
FROM dw."LO-D4_Movements"
GROUP BY "Internal_reference"
) r INNER JOIN
dw."LO-D4_Movements" t
ON t."Movement_date" = r.maxtime AND
t."Internal_reference" = r."Internal_reference";
The ?? is for the id or creation date or something to allow the counting of rows.

Limit join to one row

I have the following query:
SELECT sum((select count(*) as itemCount) * "SalesOrderItems"."price") as amount, 'rma' as
"creditType", "Clients"."company" as "client", "Clients".id as "ClientId", "Rmas".*
FROM "Rmas" JOIN "EsnsRmas" on("EsnsRmas"."RmaId" = "Rmas"."id")
JOIN "Esns" on ("Esns".id = "EsnsRmas"."EsnId")
JOIN "EsnsSalesOrderItems" on("EsnsSalesOrderItems"."EsnId" = "Esns"."id" )
JOIN "SalesOrderItems" on("SalesOrderItems"."id" = "EsnsSalesOrderItems"."SalesOrderItemId")
JOIN "Clients" on("Clients"."id" = "Rmas"."ClientId" )
WHERE "Rmas"."credited"=false AND "Rmas"."verifyStatus" IS NOT null
GROUP BY "Clients".id, "Rmas".id;
The problem is that the table "EsnsSalesOrderItems" can have the same EsnId in different entries. I want to restrict the query to only pull the last entry in "EsnsSalesOrderItems" that has the same "EsnId".
By "last" entry I mean the following:
The one that appears last in the table "EsnsSalesOrderItems". So for example if "EsnsSalesOrderItems" has two entries with "EsnId" = 6 and "createdAt" = '2012-06-19' and '2012-07-19' respectively it should only give me the entry from '2012-07-19'.
SELECT (count(*) * sum(s."price")) AS amount
, 'rma' AS "creditType"
, c."company" AS "client"
, c.id AS "ClientId"
, r.*
FROM "Rmas" r
JOIN "EsnsRmas" er ON er."RmaId" = r."id"
JOIN "Esns" e ON e.id = er."EsnId"
JOIN (
SELECT DISTINCT ON ("EsnId") *
FROM "EsnsSalesOrderItems"
ORDER BY "EsnId", "createdAt" DESC
) es ON es."EsnId" = e."id"
JOIN "SalesOrderItems" s ON s."id" = es."SalesOrderItemId"
JOIN "Clients" c ON c."id" = r."ClientId"
WHERE r."credited" = FALSE
AND r."verifyStatus" IS NOT NULL
GROUP BY c.id, r.id;
Your query in the question has an illegal aggregate over another aggregate:
sum((select count(*) as itemCount) * "SalesOrderItems"."price") as amount
Simplified and converted to legal syntax:
(count(*) * sum(s."price")) AS amount
But do you really want to multiply with the count per group?
I retrieve the the single row per group in "EsnsSalesOrderItems" with DISTINCT ON. Detailed explanation:
Select first row in each GROUP BY group?
I also added table aliases and formatting to make the query easier to parse for human eyes. If you could avoid camel case you could get rid of all the double quotes clouding the view.
Something like:
join (
select "EsnId",
row_number() over (partition by "EsnId" order by "createdAt" desc) as rn
from "EsnsSalesOrderItems"
) t ON t."EsnId" = "Esns"."id" and rn = 1
this will select the latest "EsnId" from "EsnsSalesOrderItems" based on the column creation_date. As you didn't post the structure of your tables, I had to "invent" a column name. You can use any column that allows you to define an order on the rows that suits you.
But remember the concept of the "last row" is only valid if you specifiy an order or the rows. A table as such is not ordered, nor is the result of a query unless you specify an order by
Necromancing because the answers are outdated.
Take advantage of the LATERAL keyword introduced in PG 9.3
left | right | inner JOIN LATERAL
I'll explain with an example:
Assuming you have a table "Contacts".
Now contacts have organisational units.
They can have one OU at a point in time, but N OUs at N points in time.
Now, if you have to query contacts and OU in a time period (not a reporting date, but a date range), you could N-fold increase the record count if you just did a left join.
So, to display the OU, you need to just join the first OU for each contact (where what shall be first is an arbitrary criterion - when taking the last value, for example, that is just another way of saying the first value when sorted by descending date order).
In SQL-server, you would use cross-apply (or rather OUTER APPLY since we need a left join), which will invoke a table-valued function on each row it has to join.
SELECT * FROM T_Contacts
--LEFT JOIN T_MAP_Contacts_Ref_OrganisationalUnit ON MAP_CTCOU_CT_UID = T_Contacts.CT_UID AND MAP_CTCOU_SoftDeleteStatus = 1
--WHERE T_MAP_Contacts_Ref_OrganisationalUnit.MAP_CTCOU_UID IS NULL -- 989
-- CROSS APPLY -- = INNER JOIN
OUTER APPLY -- = LEFT JOIN
(
SELECT TOP 1
--MAP_CTCOU_UID
MAP_CTCOU_CT_UID
,MAP_CTCOU_COU_UID
,MAP_CTCOU_DateFrom
,MAP_CTCOU_DateTo
FROM T_MAP_Contacts_Ref_OrganisationalUnit
WHERE MAP_CTCOU_SoftDeleteStatus = 1
AND MAP_CTCOU_CT_UID = T_Contacts.CT_UID
/*
AND
(
(#in_DateFrom <= T_MAP_Contacts_Ref_OrganisationalUnit.MAP_KTKOE_DateTo)
AND
(#in_DateTo >= T_MAP_Contacts_Ref_OrganisationalUnit.MAP_KTKOE_DateFrom)
)
*/
ORDER BY MAP_CTCOU_DateFrom
) AS FirstOE
In PostgreSQL, starting from version 9.3, you can do that, too - just use the LATERAL keyword to achieve the same:
SELECT * FROM T_Contacts
--LEFT JOIN T_MAP_Contacts_Ref_OrganisationalUnit ON MAP_CTCOU_CT_UID = T_Contacts.CT_UID AND MAP_CTCOU_SoftDeleteStatus = 1
--WHERE T_MAP_Contacts_Ref_OrganisationalUnit.MAP_CTCOU_UID IS NULL -- 989
LEFT JOIN LATERAL
(
SELECT
--MAP_CTCOU_UID
MAP_CTCOU_CT_UID
,MAP_CTCOU_COU_UID
,MAP_CTCOU_DateFrom
,MAP_CTCOU_DateTo
FROM T_MAP_Contacts_Ref_OrganisationalUnit
WHERE MAP_CTCOU_SoftDeleteStatus = 1
AND MAP_CTCOU_CT_UID = T_Contacts.CT_UID
/*
AND
(
(__in_DateFrom <= T_MAP_Contacts_Ref_OrganisationalUnit.MAP_KTKOE_DateTo)
AND
(__in_DateTo >= T_MAP_Contacts_Ref_OrganisationalUnit.MAP_KTKOE_DateFrom)
)
*/
ORDER BY MAP_CTCOU_DateFrom
LIMIT 1
) AS FirstOE
Try using a subquery in your ON clause. An abstract example:
SELECT
*
FROM table1
JOIN table2 ON table2.id = (
SELECT id FROM table2 WHERE table2.table1_id = table1.id LIMIT 1
)
WHERE
...