Imagine I have a query like the following one:
SELECT
u.ID,
( SELECT
COUNT(*)
FROM
POSTS p
WHERE
p.USER_ID = u.ID
AND p.TYPE = 1
) AS interesting_posts,
( SELECT
COUNT(*)
FROM
POSTS p
WHERE
p.USER_ID = u.ID
AND p.TYPE = 2
) AS boring_posts,
( SELECT
COUNT(*)
FROM
COMMENTS c
WHERE
c.USER_ID = u.ID
AND c.TYPE = 1
) AS interesting_comments,
( SELECT
COUNT(*)
FROM
COMMENTS c
WHERE
c.USER_ID = u.ID
AND c.TYPE = 2
) AS boring_comments
FROM
USERS u;
( Hopefully it's correct because I just came up with it and didn't test it )
where I try to calculate the number of interesting and boring posts and comments that the user has.
Now, the problem with this query is that we have 2 sequential scans on both the posts and comments table and I wonder if there is a way to avoid that?
I could probably LEFT JOIN both posts and comments to the users table and do some aggregation but it's gonna generate a lot of rows before aggregation and I am not sure if that's a good way to go.
Aggregate posts and comments and outer join them to the users table.
select
u.id as user_id,
coaleasce(p.interesting, 0) as interesting_posts,
coaleasce(p.boring, 0) as boring_posts,
coaleasce(c.interesting, 0) as interesting_comments,
coaleasce(c.boring, 0) as boring_comments
from users u
left join
(
select
user_id,
count(case when type = 1 then 1 end) as interesting,
count(case when type = 2 then 1 end) as boring
from posts
group by user_id
) p on p.user_id = u.id
left join
(
select
user_id,
count(case when type = 1 then 1 end) as interesting,
count(case when type = 2 then 1 end) as boring
from comments
group by user_id
) c on c.user_id = u.id;
compare results and execution plan (here you scan posts once):
with c as (
select distinct
count(1) filter (where TYPE = 1) over (partition by USER_ID) interesting_posts
, count(1) filter (where TYPE = 2) over (partition by USER_ID) boring_posts
, USER_ID
)
, p as (select USER_ID,max(interesting_posts) interesting_posts, max(boring_posts) boring_posts from c)
SELECT
u.ID, interesting_posts,boring_posts
, ( SELECT
COUNT(*)
FROM
COMMENTS c
WHERE
c.USER_ID = u.ID
) AS comments
FROM
USERS u
JOIN p on p.USER_ID = u.ID
Related
I have a table that stores user info such as:
I need to write a query that returns the results in the following format:
I tried doing a LEFT JOIN for each status but that didn't work, any thoughts on how to get the expected results?
if number of statuses is fixed you can do this
Select
id user_id,
open_status,
open_status_date,
inprogress_status,
inprogress_status_date,
complete_status,
complete_status_date
from
(select user_id id from yourTable group by user_id) U left join
(select user_id id, status open_status, status_date open_status_date
from yourTable where status = 'Open') O on U.id = O.id left join
(select user_id id, status inprogress_status, status_date inprogress_status_date
from yourTable where status = 'InProgress') P on U.id = P.id left join
(select user_id id, status complete_status, status_date complete_status_date
from yourTable where status = 'Complete') C on U.id = C.id
Order by id
Break into inline views and join. But this may be not the most efficient way.
ALSO NOTE: if each user definitely has at least "Open" status, you can skip first U inline view and start with O
You want to use a pivot, like this:
select * from test
PIVOT(
max(status_date)
FOR status
IN (
'Open',
'In Progress',
'Complete'
)
)
order by user_id
Suppose every user has a "Open" status
With
open as (select * from table where status = 'Open'),
inp as (select * from table where status = 'In Progress'),
comp as (select * from table where status = 'Complete')
select o.user_id,o.status open_status, o.status_date open_status_date,i.status InProgress_status, i.status_date InProgress_status_date,c.status complete_status, c.status_date complete_status_date
from open o, inp i, comp c
where o.user_id=i.user_id(+)
and o.user_id=c.user_id(+)
I am trying to rank users on my system based on the user's totalArticleViews and the user's totalArticles on my system. The ranking should be based on the formula (totalArticleViews + ( totalArticles * 500 )) / 100
I have a system that allows users to post articles, a record is created every time any of these articles are read by anyone. My database has the following tables. users, articles, reads.
I have tried to get the views to insert into the formula, but i'm having issues getting all the users articles and multiplying it by 500 to insert into the formula to rank them all
with article_views AS (
SELECT article_id, COUNT(reads.id) AS views, 1 * 500 AS points
FROM reads
WHERE article_id IN (
SELECT id FROM articles WHERE articles.published_on IS NOT NULL AND
articles.deleted_at IS NULL
)
GROUP BY article_id
),
published AS (
SELECT COUNT(articles.id) AS TotalArticle, COUNT(articles.id) * 500 AS
points
FROM articles
WHERE published_on IS NOT NULL AND deleted_at IS NULL
GROUP BY articles.user_id
)
SELECT
users.id AS user_id,
ROUND((SUM(article_views.views) + () ) / 100.0, 2) AS points,
ROW_NUMBER() OVER (ORDER BY ROUND((SUM(article_views.views) + ()) /
100.0, 2) DESC)
FROM users
LEFT JOIN articles ON users.id = articles.user_id
LEFT JOIN reads ON articles.id = reads.article_id
LEFT JOIN article_views ON reads.article_id = article_views.article_id
WHERE
users.id IN (SELECT user_id FROM role_user WHERE role_id = 2)
AND status = 'ACTIVE'
GROUP BY users.id
ORDER BY points DESC NULLS LAST
I'm stuck at this point
(SUM(article_views.views) + () ) / 100.0, 2)
Simply use the published CTE by including the GROUP BY column user_id in SELECT and then joining published to users by this field in main level query.
WITH article_views AS (
SELECT r.article_id,
COUNT(r.id) AS views,
1 * 500 AS points
FROM reads r
WHERE r.article_id IN (
SELECT id
FROM articles a
WHERE a.published_on IS NOT NULL
AND a.deleted_at IS NULL
)
GROUP BY r.article_id
),
published AS (
SELECT a.user_id,
COUNT(a.id) AS TotalArticle,
COUNT(a.id) * 500 AS points
FROM articles a
WHERE a.published_on IS NOT NULL
AND a.deleted_at IS NULL
GROUP BY a.user_id
)
SELECT u.id AS user_id,
ROUND((SUM(av.views) + (p.TotalArticle)) / 100.0, 2) AS points,
ROW_NUMBER() OVER (ORDER BY ROUND((SUM(av.views) + (p.points))
/ 100.0, 2) DESC) AS rn
FROM users u
LEFT JOIN articles a ON u.id = a.user_id
LEFT JOIN reads r ON a.id = r.article_id
LEFT JOIN article_views av ON r.article_id = av.article_id
LEFT JOIN published p ON u.id = p.user_id
WHERE u.id IN (
SELECT user_id FROM role_user WHERE role_id = 2
)
AND u.status = 'ACTIVE'
GROUP BY u.id
ORDER BY points DESC NULLS LAST
I have an SQL query that joins 3 tables to return me the required data. The query is as follows:
SELECT (s.user_created,
u.first_name,
u.last_name,
u.email,
s.school_name,
p.plan_name,
substring( a.message, 11), u.phone1)
FROM cb_school s
inner join ugrp_user u
on s.user_created = u.user_id
inner join cb_plan p
on s.current_plan = p.plan_id
inner join audit a
on u.user_id = a.user_id
where s.type = 'sample'
and a.module_short = 'sample-user'
and s.created_time > current_timestamp - interval '10 day';
The query works fine if all the attributes are present. Now for few of my rows, the following value would be a.module_short = 'sample-user' missing. But since I have included it as an AND condition, those rows will not be returned. I am trying to return an empty string for that field if it is present, else the value as per my current query. Is there any way to achieve this.
Think you could possibly use a CASE WHEN statement, like this:
SELECT CASE WHEN a.module_short = 'sample-user' THEN a.module_short
ELSE '' END AS a.module_short
FROM TableA
you can use COALESCE it returns the first not null.
SELECT COALESCE(a.module_short,'')
FROM TableA AS a
SELECT (s.user_created,
u.first_name,
u.last_name,
u.email,
s.school_name,
p.plan_name,
substring( a.message, 11), u.phone1)
FROM cb_school s
INNER JOIN ugrp_user u
ON s.user_created = u.user_id
INNER JOIN cb_plan p
ON s.current_plan = p.plan_id
INNER JOIN audit a
ON u.user_id = a.user_id
AND a.module_short = 'sample-user'
WHERE s.type = 'sample'
AND s.created_time > current_timestamp - interval '10 day';
You want to show all users that have at least one module_short.
If the module_short contains 'sample-user' then it should show it, else it should show NULL as module_short. You only want 1 row per user, even if it has multiple module_shorts.
You can use a CTE, ROW_NUMBER() and the CASE clause for this question.
Example Question
I have 3 tables.
Users: Users with an ID
Modules: Modules with an ID
UserModules: The link between users and modules. You user can have multiple models.
I need a query that returns me all users that have at least 1 module with 2 columns UserName and ModuleName.
I only one 1 row for each user. The ModuleName should only display SQL if the user has that module. Else it should display no module.
Example Tables:
Users:
id name
1 Manuel
2 John
3 Doe
Modules:
id module
1 StackOverflow
2 SQL
3 StackExchange
4 SomethingElse
UserModules:
id module_id user_id
1 1 2
2 1 3
4 2 2
5 2 3
6 3 1
7 3 3
8 4 1
9 4 3
Example Query:
with CTE as (
select
u.name as UserName
, CASE
WHEN m.module = 'SQL' THEN 'SQL' ELSE NULL END as ModuleName
, ROW_NUMBER() OVER(PARTITION BY u.id
ORDER BY (CASE
WHEN m.module = 'SQL' THEN 'Ja' ELSE NULL END) DESC) as rn
from UserModules as um
inner join Users as u
on um.user_id = u.id
inner join Modules as m
on um.module_id = m.id
)
select UserName, ModuleName from CTE
where rn = 1
Example Result:
UserName ModuleName
Manuel NULL
John SQL
Doe SQL
Your query would look like this:
with UsersWithRownumbersBasedOnModule_short as (
SELECT s.user_created,
u.first_name,
u.last_name,
u.email,
s.school_name,
p.plan_name,
substring( a.message, 11),
u.phone1)
CASE
WHEN a.module_short = 'sample-user'
THEN a.module_short
ELSE NULL
END AS ModuleShort
ROW_NUMBER() OVER(PARTITION BY u.user_id ORDER BY (
CASE
WHEN a.module_short = 'sample-user'
THEN a.module_short
ELSE NULL
END) DESC) as rn
FROM cb_school s
inner join ugrp_user u
on s.user_created = u.user_id
inner join cb_plan p
on s.current_plan = p.plan_id
inner join audit a
on u.user_id = a.user_id
where s.type = 'sample'
and s.created_time > current_timestamp - interval '10 day';)
select * from UsersWithRownumbersBasedOnModule_short
where rn = 1
PS: I removed a lose bracket after SELECT and your SUBSTRING() is missing 1 parameter, it needs 3.
I'm quite certain I've painted myself into a corner and I can't figure my way out.
The Users table and OrderHistories tables both have 1+ million records:
SELECT
u.Id ,
u.Email AS EmailAddress ,
c.Address_Address1 AS "Address 1" ,
(
SELECT
COUNT(*)
FROM
dbo.OrderHistories oh
WHERE
oh.UserId = u.UserName
) AS NumberOfOrders ,
Carts.SubtotalAmount AS CartTotal ,
(
SELECT
MAX(oh.CreateDate)
FROM
dbo.OrderHistories AS oh
WHERE
oh.UserId = u.Id
) AS LastOrderDate ,
(
SELECT
LastOrders.SubtotalAmount AS LastOrderSubtotal
FROM
(
SELECT
UserId ,
CreateDate ,
SubtotalAmount ,
MAX(CreateDate) OVER ( PARTITION BY UserId ) MyLastOrderDate
FROM
Users u
INNER JOIN dbo.OrderHistories oh
ON u.Id = oh.UserId
) AS LastOrders
WHERE
LastOrders.MyLastOrderDate = LastOrders.CreateDate
AND LastOrders.UserId = u.Id
) AS LastOrderSubtotal
FROM
Users u
INNER JOIN Customers AS c
ON u.Id = c.Id
LEFT JOIN dbo.Carts
ON c.Id = Carts.CustomerId
This particular subquery is my current problem (EXTREMELY inefficient), but I'm not experienced enough to understand exactly why, or how I should be doing it instead (I can't get there from here!):
(
SELECT
LastOrders.SubtotalAmount AS LastOrderSubtotal
FROM
(
SELECT
UserId ,
CreateDate ,
SubtotalAmount ,
MAX(CreateDate) OVER ( PARTITION BY UserId ) MyLastOrderDate
FROM
Users u
INNER JOIN dbo.OrderHistories oh
ON u.Id = oh.UserId
) AS LastOrders
WHERE
LastOrders.MyLastOrderDate = LastOrders.CreateDate
AND LastOrders.UserId = u.Id
) AS LastOrderSubtotal
Anyone mind telling me how terrible I am and then segue right into a suggested improvement?
Just from looking at your query, you may be able to simplify it using cross apply() like so:
select
u.Id
, EmailAddress = u.Email
, [Address 1] = c.Address_Address1
, CartTotal = Carts.SubtotalAmount
, NumberOfOrders = oh.NumberOfOrders
, LastOrderDate = oh.CreateDate
, LastOrderSubtotal = oh.SubtotalAmount
from Users u
inner join Customers AS c
on u.Id = c.Id
left join dbo.Carts
on c.Id = Carts.CustomerId
cross apply (
select top 1
i.CreateDate
, i.SubtotalAmount
, NumberOfOrders = count(*) over (partition by i.UserId)
from dbo.OrderHistories i
where i.UserId = u.Id
order by i.CreateDate desc
) as oh
If you want rows that may not have an OrderHistory, switch to outer apply().
Reference:
apply() - msdn
The power of T-SQL's APPLY operator - Rob Farley
APPLY: It Slices! It Dices! It Does It All! - Brad Shulz
I'm generating a data set that looks like this
category user total
1 jonesa 0
2 jonesa 0
3 jonesa 0
1 smithb 0
2 smithb 0
3 smithb 5
1 brownc 2
2 brownc 3
3 brownc 4
Where a particular user has 0 records in all categories is it possible to remove their rows form the set? If a user has some activity like smithb does, I'd like to keep all of their records. Even the zeroes rows. Not sure how to go about that, I thought a CASE statement may be of some help but I'm not sure, this is pretty complicated for me. Here is my query
SELECT DISTINCT c.category,
u.user_name,
CASE WHEN (
SELECT COUNT(e.entry_id)
FROM category c1
INNER JOIN entry e1
ON c1.category_id = e1.category_id
WHERE c1.category_id = c.category_id
AND e.user_name = u.user_name
AND e1.entered_date >= TO_DATE ('20140625','YYYYMMDD')
AND e1.entered_date <= TO_DATE ('20140731', 'YYYYMMDD')) > 0 -- I know this won't work
THEN 'Yes'
ELSE NULL
END AS TOTAL
FROM user u
INNER JOIN role r
ON u.id = r.user_id
AND r.id IN (1,2),
category c
LEFT JOIN entry e
ON c.category_id = e.category_id
WHERE c.category_id NOT IN (19,20)
I realise the case statement won't work, but it was an attempt on how this might be possible. I'm really not sure if it's possible or the best direction. Appreciate any guidance.
Try this:
delete from t1
where user in (
select user
from t1
group by user
having count(distinct category) = sum(case when total=0 then 1 else 0 end) )
The sub query can get all the users fit your removal requirement.
count(distinct category) get how many category a user have.
sum(case when total=0 then 1 else 0 end) get how many rows with activities a user have.
There are a number of ways to do this, but the less verbose the SQL is, the harder it may be for you to follow along with the logic. For that reason, I think that using multiple Common Table Expressions will avoid the need to use redundant joins, while being the most readable.
-- assuming user_name and category_name are unique on [user] and [category] respectively.
WITH valid_categories (category_id, category_name) AS
(
-- get set of valid categories
SELECT c.category_id, c.category AS category_name
FROM category c
WHERE c.category_id NOT IN (19,20)
),
valid_users ([user_name]) AS
(
-- get set of users who belong to valid roles
SELECT u.[user_name]
FROM [user] u
WHERE EXISTS (
SELECT *
FROM [role] r
WHERE u.id = r.[user_id] AND r.id IN (1,2)
)
),
valid_entries (entry_id, [user_name], category_id, entry_count) AS
(
-- provides a flag of 1 for easier aggregation
SELECT e.[entry_id], e.[user_name], e.category_id, CAST( 1 AS INT) AS entry_count
FROM [entry] e
WHERE e.entered_date BETWEEN TO_DATE('20140625','YYYYMMDD') AND TO_DATE('20140731', 'YYYYMMDD')
-- determines if entry is within date range
),
user_categories ([user_name], category_id, category_name) AS
( SELECT u.[user_name], c.category_id, c.category_name
FROM valid_users u
-- get the cartesian product of users and categories
CROSS JOIN valid_categories c
-- get only users with a valid entry
WHERE EXISTS (
SELECT *
FROM valid_entries e
WHERE e.[user_name] = u.[user_name]
)
)
/*
You can use these for testing.
SELECT COUNT(*) AS valid_categories_count
FROM valid_categories
SELECT COUNT(*) AS valid_users_count
FROM valid_users
SELECT COUNT(*) AS valid_entries_count
FROM valid_entries
SELECT COUNT(*) AS users_with_entries_count
FROM valid_users u
WHERE EXISTS (
SELECT *
FROM user_categories uc
WHERE uc.user_name = u.user_name
)
SELECT COUNT(*) AS users_without_entries_count
FROM valid_users u
WHERE NOT EXISTS (
SELECT *
FROM user_categories uc
WHERE uc.user_name = u.user_name
)
SELECT uc.[user_name], uc.[category_name], e.[entry_count]
FROM user_categories uc
INNER JOIN valid_entries e ON (uc.[user_name] = e.[user_name] AND uc.[category_id] = e.[category_id])
*/
-- Finally, the results:
SELECT uc.[user_name], uc.[category_name], SUM(NVL(e.[entry_count],0)) AS [entry_count]
FROM user_categories uc
LEFT OUTER JOIN valid_entries e ON (uc.[user_name] = e.[user_name] AND uc.[category_id] = e.[category_id])
Here's another method:
WITH totals AS (
SELECT
c.category,
u.user_name,
COUNT(e.entry_id) AS total,
SUM(COUNT(e.entry_id)) OVER (PARTITION BY u.user_name) AS user_total
FROM
user u
INNER JOIN
role r ON u.id = r.user_id
CROSS JOIN
category c
LEFT JOIN
entry e ON c.category_id = e.category_id
AND u.user_name = e.user_name
AND e1.entered_date >= TO_DATE ('20140625', 'YYYYMMDD')
AND e1.entered_date <= TO_DATE ('20140731', 'YYYYMMDD')
WHERE
r.id IN (1, 2)
AND c.category_id IN (19, 20)
GROUP BY
c.category,
u.user_name
)
SELECT
category,
user_name,
total
FROM
totals
WHERE
user_total > 0
;
The totals derived table calculates the totals per user and category as well as totals across all categories per user (using SUM() OVER ...). The main query returns only rows where the user total is greater than zero.