I need to get counts of some rows with ORDER BY.
how can I get count of the rows
what are before orderId = 50
(I see answer is 3, but I need to have mysql query how to get it)
I have mysql query like this:
select c.id as customerId, o.id as orderId from orders o
inner join customers c on (c.id=o.customerId)
order by c.id asc, o.id desc
this query outputs:
customerId orderId
19 36
19 35
19 34
31 50
31 49
31 48
53 73
53 72
SQL DEMO
SELECT Max(rn)
FROM (
select customerId,
orderId ,
#row := if( orderid = 50,
null,
#row + 1 ) as rn
from orders o
cross join ( SELECT #row := 0 ) as vars
order by customerId asc, orderId desc
) t
if can use row_number
SELECT MIN(rn) - 1 as cnt
FROM (
select customerId,
orderId ,
row_number() over (order by customerId asc, orderId desc ) as rn
from orders
) t
WHERE orderId = 50;
Related
Was wondering if there is a way to get the sum of the stock_case column for items with the same date_of_export ?
Updated with fiddle here and some relevant data:
https://www.db-fiddle.com/f/szC1Ftj3ZGEC24gSYp6ad4/4
The expected output would be this:
This is the query used
SELECT
st.product_code,
st.date_of_export,
st.best_before_date,
st.stock_case,
(
SELECT
SUM(st2.stock_case)
FROM
stock_tracking AS st2
WHERE
st2.product_code IN ('MGN003')
AND MONTH(st2.date_of_export) IN (07)
AND YEAR(st2.date_of_export) IN (2018)
AND st2.stock_case != 0
) AS total
FROM
stock_tracking st
WHERE
product_code IN ('MGN003')
AND MONTH(st.date_of_export) IN (07)
AND YEAR(st.date_of_export) IN (2018)
AND stock_case != 0
and my results
Would like to have a total column like 16, 16, 16, ... , 19, etc
For another case I used a subquery like so
SELECT
d.products_name,
stock_case,
st.date_of_export,
st.best_before_date,
st.product_code,
(SELECT
SUM(st2.stock_case)
FROM
stock_tracking AS st2
WHERE
DATE(st2.date_of_export) = (SELECT
DATE(tmp.last_update)
FROM
(SELECT
date_of_export AS last_update
FROM
stock_tracking
ORDER BY date_of_export DESC
LIMIT 1) AS tmp
WHERE
product_code = 'MGN003')) AS total
FROM
stock_tracking st
LEFT JOIN
products AS p ON p.products_model = st.product_code
LEFT JOIN
products_description AS d ON d.products_id = p.products_id
WHERE
product_code = 'MGN003'
AND d.language_id = 2
AND DATE(st.date_of_export) = (SELECT
DATE(tmp.last_update)
FROM
(SELECT
date_of_export AS last_update
FROM
stock_tracking AS st
ORDER BY date_of_export DESC
LIMIT 1) AS tmp)
with this result:
You can write a subquery to sum(stock_case) by date_of_export, then self join on Date, then you can get your expect result.
SELECT
s.product_name,
s.date_of_export,
s.best_before_date,
s.product_code,
s.stock_case,
t.totle
FROM
stock_tracking s
INNER JOIN
(
SELECT SUM(stock_case) totle,date_of_export dt
FROM stock_tracking
where
product_code = 'MGN003'
AND MONTH(date_of_export) =07
AND YEAR(date_of_export) =2018
AND stock_case != 0
GROUP BY date_of_export
) t on DATE_FORMAT(s.date_of_export, "%d-%m-%Y") = DATE_FORMAT(t.dt, "%d-%m-%Y")
where
s.product_code = 'MGN003'
AND MONTH(s.date_of_export) =07
AND YEAR(s.date_of_export) =2018
AND s.stock_case != 0
sqlfiddle
Without giving you the exact answer: You should think in the direction of:
SELECT SUM(column) FROM table WHERE ... GROUP BY date
or
SELECT SUM(column), DISTINCT date FROM table WHERE ...
So lookup the way GROUP BY and DISTINCT work :-)
Let us suppose we have following tables
product_id | quantity
1 | 250
2 | 150
3 | 120
4 | 300
5 | 301
How do we know that the item number of 401th in SQL? (the answer should be product_id : 3). The query should return the product_id
Let us assume also the row has been in order
You can use Correlated query to find cummulative sum and then filter range using between to find the required slot:
select product_id
from (
select a.*,
coalesce((
select sum(quantity)
from your_table b
where b.product_id < a.product_id
), 0) + 1 cquant1,
(
select sum(quantity)
from your_table b
where b.product_id <= a.product_id
) cquant2
from your_table a
) t
where 401 between cquant1 and cquant2;
Demo
You can also use user variable for this:
select *
from (
select product_id,
#sum1 := #sum1 + coalesce((
select quantity
from your_table x
where x.product_id < t.product_id
order by x.product_id desc limit 1
), 0) as cquantity1,
#sum2 := #sum2 + quantity as cquantity2
from your_table t,
(select #sum1 := 0, #sum2 := 0) t2
order by product_id
) t
where 401 between cquantity1 and cquantity2;
Demo
In case of ORACLE, this will not work with SQLServer
This is by using LAG and SUM OVER() functions,
SELECT PRODUCT_ID FROM
(
SELECT PRODUCT_ID
, LAG(CUM_QUAN, 1, 0) OVER (ORDER BY PRODUCT_ID) AS START_QUAN
, CUM_QUAN END_QUAN
FROM
(
SELECT PRODUCT_ID
, QUANTITY
, SUM(QUANTITY) OVER (ORDER BY PRODUCT_ID) AS CUM_QUAN
FROM YOUR_TABLE
)
) WHERE 401 BETWEEN START_QUAN AND END_QUAN
You can do this with variables by getting a cumulative sum. However, Gurv's answer is way too complicated.
I think this is the simplest way:
select t.*
from (select t.*, (#s := #s + quantity) as running_quantity
from t cross join
(select #s := 0) params
order by product_id
) t
where 401 < running_quantity and
401 >= running_quantity - quantity;
So I was taking a test recently with some higher level SQL problems. I only have what I would consider "intermediate" experience in SQL and I've been working on this for a day or so now. I just can't figure it out.
Here's the problem:
You have a table with 4 columns as such:
EmployeeID int unique
EmployeeType int
EmployeeSalary int
Created date
Goal: I need to retrieve the difference between the latest two EmployeeSalary for any EmployeeType with more than 1 entry. It has to be done in one statement (nested queries are fine).
Example Data Set: http://sqlfiddle.com/#!9/0dfc7
EmployeeID | EmployeeType | EmployeeSalary | Created
-----------|--------------|----------------|--------------------
1 | 53 | 50 | 2015-11-15 00:00:00
2 | 66 | 20 | 2014-11-11 04:20:23
3 | 66 | 30 | 2015-11-03 08:26:21
4 | 66 | 10 | 2013-11-02 11:32:47
5 | 78 | 70 | 2009-11-08 04:47:47
6 | 78 | 45 | 2006-11-01 04:42:55
So for this data set, the proper return would be:
EmployeeType | EmployeeSalary
-------------|---------------
66 | 10
78 | 25
The 10 comes from subtracting the latest two EmployeeSalary values (30 - 20) for the EmployeeType of 66. The 25 comes from subtracting the latest two EmployeeSalary values (70-45) for EmployeeType of 78. We skip EmployeeID 53 completely because it only has one value.
This one has been destroying my brain. Any clues?
Thanks!
How to make really simple query complex?
One funny way(not best performance) to do it is:
SELECT final.EmployeeType, SUM(salary) AS difference
FROM (
SELECT b.EmployeeType, b.EmployeeSalary AS salary
FROM tab b
JOIN (SELECT EmployeeType, GROUP_CONCAT(EmployeeSalary ORDER BY Created DESC) AS c
FROM tab
GROUP BY EmployeeType
HAVING COUNT(*) > 1) AS sub
ON b.EmployeeType = sub.EmployeeType
AND FIND_IN_SET(b.EmployeeSalary, sub.c) = 1
UNION ALL
SELECT b.EmployeeType, -b.EmployeeSalary AS salary
FROM tab b
JOIN (SELECT EmployeeType, GROUP_CONCAT(EmployeeSalary ORDER BY Created DESC) AS c
FROM tab
GROUP BY EmployeeType
HAVING COUNT(*) > 1) AS sub
ON b.EmployeeType = sub.EmployeeType
AND FIND_IN_SET(b.EmployeeSalary, sub.c) = 2
) AS final
GROUP BY final.EmployeeType;
SqlFiddleDemo
EDIT:
The keypoint is MySQL doesn't support windowed function so you need to use equivalent code:
For example solution in SQL Server:
SELECT EmployeeType, SUM(CASE rn WHEN 1 THEN EmployeeSalary
ELSE -EmployeeSalary END) AS difference
FROM (SELECT *,
ROW_NUMBER() OVER(PARTITION BY EmployeeType ORDER BY Created DESC) AS rn
FROM #tab
) AS sub
WHERE rn IN (1,2)
GROUP BY EmployeeType
HAVING COUNT(EmployeeType) > 1
LiveDemo
And MySQL equivalent:
SELECT EmployeeType, SUM(CASE rn WHEN 1 THEN EmployeeSalary
ELSE -EmployeeSalary END) AS difference
FROM (
SELECT t1.EmployeeType, t1.EmployeeSalary,
count(t2.Created) + 1 as rn
FROM #tab t1
LEFT JOIN #tab t2
ON t1.EmployeeType = t2.EmployeeType
AND t1.Created < t2.Created
GROUP BY t1.EmployeeType, t1.EmployeeSalary
) AS sub
WHERE rn IN (1,2)
GROUP BY EmployeeType
HAVING COUNT(EmployeeType) > 1;
LiveDemo2
The dataset of the fiddle is different from the example above, which is confusing (not to mention a little perverse). Anyway, there's lots of ways to skin this particular cat. Here's one (not the fastest, however):
SELECT a.employeetype, ABS(a.employeesalary-b.employeesalary) diff
FROM
( SELECT x.*
, COUNT(*) rank
FROM employees x
JOIN employees y
ON y.employeetype = x.employeetype
AND y.created >= x.created
GROUP
BY x.employeetype
, x.created
) a
JOIN
( SELECT x.*
, COUNT(*) rank
FROM employees x
JOIN employees y
ON y.employeetype = x.employeetype
AND y.created >= x.created
GROUP
BY x.employeetype
, x.created
) b
ON b.employeetype = a.employeetype
AND b.rank = a.rank+1
WHERE a.rank = 1;
a very similar but faster solution looks like this (although you sometimes need to assign different variables between tables a and b - for reasons I still don't fully understand)...
SELECT a.employeetype
, ABS(a.employeesalary-b.employeesalary) diff
FROM
( SELECT x.*
, CASE WHEN #prev = x.employeetype THEN #i:=#i+1 ELSE #i:=1 END i
, #prev := x.employeetype prev
FROM employees x
, (SELECT #prev := 0, #i:=1) vars
ORDER
BY x.employeetype
, x.created DESC
) a
JOIN
( SELECT x.*
, CASE WHEN #prev = x.employeetype THEN #i:=#i+1 ELSE #i:=1 END i
, #prev := x.employeetype prev
FROM employees x
, (SELECT #prev := 0, #i:=1) vars
ORDER
BY x.employeetype
, x.created DESC
) b
ON b.employeetype = a.employeetype
AND b.i = a.i + 1
WHERE a.i = 1;
So I'll show you what I'm trying to do and explain my problem, there may be an answer different to the approach I'm trying to take.
The query I'm trying to perform is as follows:
SELECT *
FROM report_keywords rk
WHERE rk.report_id = 231
AND (
SELECT SUM(t.conv) FROM (
SELECT conv FROM report_keywords t2 WHERE t2.campaign_id = rk.campaign_id ORDER BY conv DESC LIMIT 10
) t
) >= 30
GROUP BY rk.campaign_id
The error I get is
Unknown column 'rk.campaign_id' in 'where clause'
Obviously this is saying that the table alias rk is not making it to the subsubquery. What I'm trying to do is get all of the campaigns where the sum of the top 10 conversions is greater than or equal to 30.
The relevant table structure is:
id INT,
report_id INT,
campaign_id INT,
conv INT
Any help would be greatly appreciated.
Update
Thanks to Kickstart I was able to do what I wanted. Here's my final query:
SELECT campaign_id, SUM(conv) as sum_conv
FROM (
SELECT campaign_id, conv, #Sequence := if(campaign_id = #campaign_id, #Sequence + 1, 1) AS aSequence, #campaign_id := campaign_id
FROM report_keywords
CROSS JOIN (SELECT #Sequence := 0, #campaign_id := 0) Sub1
WHERE report_id = 231
ORDER BY campaign_id, conv DESC
) t
WHERE aSequence <= 10
GROUP BY campaign_id
HAVING sum_conv >= 30
Possibly use a user variable to add a sequence number to get the latest 10 records for each one, then use SUM to get the count of those.
Something like this:-
SELECT rk.*
FROM report_keywords rk
INNER JOIN
(
SELECT campaign_id, SUM(conv) AS SumConv
FROM
(
SELECT campaign_id, conv, #Sequence := if(campaign_id = #campaign_id, #Sequence + 1, 1) AS aSequence, #campaign_id := campaign_id
FROM report_keywords
CROSS JOIN (SELECT #Sequence := 0, #campaign_id := "") Sub1
ORDER BY campaign_id, conv
) Sub2
WHERE aSequence <= 10
GROUP BY campaign_id
) Sub3
ON rk.campaign_id = Sub3.campaign_id AND Sub3.SumConv >= 30
WHERE rk.report_id = 231
I have a table orders like this:
customer_id order_date
10 2012-01-01
11 2012-01-02
10 2012-01-02
12 2012-01-03
11 2012-01-04
12 2012-02-01
11 2012-02-04
13 2012-02-05
14 2012-02-06
How can I get a cumulative average over time (per month) like this:
order date count orders count customers (customer_id)
2012-01 1 1 (12)
2012-01 2 2 (10,11)
2012-02 1 2 (13,14)
2012-02 2 2 (10,12
2012-02 3 2 (11)
showing how the number of customers vs. number of orders per customer develops over time.
The following query gives me the wanted information - but not over time. How can I iterate the query over time?
SELECT number_of_orders, count(*) as amount FROM (
SELECT o.customer_id, count(*) as number_of_orders
FROM orders o
GROUP BY o.customer_id) as t1
GROUP BY number_of_orders
Update:
have now build the following PHP code to generate what I need, wonder if that could be done using cumulative counts like on http://www.freeopenbook.com/mysqlcookbook/mysqlckbk-chp-12-sect-14.html
$year = 2011;
for ($cnt_months = 1; $cnt_months <= 12; $cnt_months++) {
$cnt_months_str = ($cnt_months < 10) ? '0'.$cnt_months : $cnt_months;
$raw_query = "SELECT number_of_orders, count(*) as amount
FROM (
SELECT
o.customer_id,
count(*) as number_of_orders
FROM orders o
where Date_Format( o.order_date, '%Y%m' ) >= " . $year . "01 and Date_Format( o.order_date, '%Y%m' ) <= " . $year . $cnt_months_str . "
GROUP BY o.customer_id) as t1
GROUP BY number_of_orders";
$query = db_query($raw_query);
while ($row = db_fetch_array($query)) {
$data[$cnt_months_str][$row['number_of_orders']] = array($row['number_of_orders'], (int)$row['amount']);
}
}
A good starting point is
SELECT
order_date,
COUNT(*) AS distinctOrders,
COUNT(DISTINCT customer_id) AS distinctCustomers,
GROUP_CONCAT(DISTINCT customer_id ASC) AS customerIDs
FROM orders
GROUP BY order_date ASC
This will give you the order_date, the number of orders on that date, the number of customers on that date, and the list of customer ids on that date.
Just looking at a way to tally up on a month by month basis. So taking this forward I've used a subquery to tally up as it goes
SELECT
ordersPerDate.*,
IF(
MONTH(ordersPerDate.order_date)=#thisMonth,
#runningTotal := #runningTotal+ordersPerDate.distinctOrders,
#runningTotal := 0
) AS ordersInThisMonth,
#thisMonth := MONTH(ordersPerDate.order_date)
FROM
(
SELECT
#thisMonth := 0,
#runningTotal := 0
) AS variableInit,
(
SELECT
order_date,
COUNT(*) AS distinctOrders,
COUNT(DISTINCT customer_id) AS distinctCustomers,
GROUP_CONCAT(DISTINCT customer_id ASC) AS customerIDs
FROM orders
GROUP BY order_date ASC
) AS ordersPerDate
And finally to clean it up, wrapped it in yet another subquery just to return the rows desired rather than the internal variables
Grouping on individual days
SELECT
collatedData.order_date,
collatedData.ordersInThisMonth AS count_orders,
collatedData.distinctCustomers AS count_customers,
collatedData.customerIDs AS customer_ids
FROM (
SELECT
ordersPerDate.*,
IF(
MONTH(ordersPerDate.order_date)=#thisMonth,
#runningTotal := #runningTotal+ordersPerDate.distinctOrders,
#runningTotal := 0
) AS ordersInThisMonth,
#thisMonth := MONTH(ordersPerDate.order_date)
FROM
(
SELECT
#thisMonth := 0,
#runningTotal := 0
) AS variableInit,
(
SELECT
order_date,
COUNT(*) AS distinctOrders,
COUNT(DISTINCT customer_id) AS distinctCustomers,
GROUP_CONCAT(DISTINCT customer_id) AS customerIDs
FROM orders
GROUP BY order_date ASC
) AS ordersPerDate
) AS collatedData
And now finally, following additional information from the OP, the end product
Grouping on calendar months
// Top level will sanitise the output
SELECT
collatedData.orderYear,
collatedData.orderMonth,
collatedData.distinctOrders,
collatedData.ordersInThisMonth AS count_orders,
collatedData.distinctCustomers AS count_customers,
collatedData.customerIDs AS customer_ids
FROM (
// This level up will iterate through calculating running totals
SELECT
ordersPerDate.*,
IF(
(ordersPerDate.orderYear,ordersPerDate.orderMonth) = (#thisYear,#thisMonth),
#runningTotal := #runningTotal+ordersPerDate.distinctOrders*ordersPerDate.distinctCustomers,
#runningTotal := 0
) AS ordersInThisMonth,
#thisMonth := ordersPerDate.orderMonth,
#thisYear := ordersPerDate.orderYear
FROM
(
SELECT
#thisMonth := 0,
#thisYear := 0,
#runningTotal := 0
) AS variableInit,
(
// Next level up will collate this to get per year, month, and per number of orders
SELECT
ordersPerDatePerUser.orderYear,
ordersPerDatePerUser.orderMonth,
ordersPerDatePerUser.distinctOrders,
COUNT(DISTINCT ordersPerDatePerUser.customer_id) AS distinctCustomers,
GROUP_CONCAT(ordersPerDatePerUser.customer_id) AS customerIDs
FROM (
// Inner query will get the number of orders for each year, month, and customer
SELECT
YEAR(order_date) AS orderYear,
MONTH(order_date) AS orderMonth,
customer_id,
COUNT(*) AS distinctOrders
FROM orders
GROUP BY orderYear ASC, orderMonth ASC, customer_id ASC
) AS ordersPerDatePerUser
GROUP BY
ordersPerDatePerUser.orderYear ASC,
ordersPerDatePerUser.orderMonth ASC,
ordersPerDatePerUser.distinctOrders DESC
) AS ordersPerDate
) AS collatedData
SELECT
substr(order_date,1,7) AS order_period,
count(*) AS number_of_orders,
count(DISTINCT orders.customer_id) AS number_of_customers,
GROUP_CONCAT(DISTINCT orders.customer_id) AS customers
FROM orders
GROUP BY substr(order_date,1,7)