Related
We have this column in the table named "pricehistory"
1634913730;48.38,1634916509;48.38,1635162352;37.96,1635177904;49.14,1635337722;1219.98,1635340811;27.17
that is an example data.
first is the timestamp than after ; is the price at this timestamp
But i want the average price from every timestamp in a select... is that possible?
I dont find any similiar examples somewhere and my tries to select doesnt work... i am not so good with sql
so i want average of all prices behind that ; and before ,
The , split the timestamp and prices
Some test data :
create table test ( id int not null, pricehistory text not null );
insert into test values ( 1, '1634913730;48.38,1634916509;48.38,1635162352;37.96,1635177904;49.14,1635337722;1219.98,1635340811;27.17' );
insert into test values ( 2, '1634913731;42.42,1634916609;21.21' );
If your RDBMS has some splitting function
Then it's quite easy, just split and use AVG. Here is an example using PostgreSQL :
SELECT id, AVG(SUBSTRING(v, 12, 42)::decimal) AS average
FROM test
INNER JOIN LATERAL regexp_split_to_table(pricehistory, E',') t(v) ON TRUE
GROUP BY id;
Then you get:
id | average
----+----------------------
2 | 31.8150000000000000
1 | 238.5016666666666667
(2 rows)
Otherwise
You can use a CTE to split the values manually. This is a bit more involved. Here is an example using PostgreSQL again :
WITH RECURSIVE T AS (
SELECT id,
-- We get the last value ...
SUBSTRING(pricehistory, LENGTH(pricehistory) - STRPOS(REVERSE(pricehistory), ',') + 2) AS oneprice,
pricehistory AS remaining
FROM test
UNION ALL
-- ... as we get the other values from the recursive CTE.
SELECT id,
LEFT(remaining, STRPOS(remaining, ',') - 1),
SUBSTRING(remaining, STRPOS(remaining, ',') + 1)
FROM T
WHERE STRPOS(remaining, ',') > 0
)
SELECT id, AVG(SUBSTRING(oneprice, 12)::decimal) AS average
FROM T
GROUP BY id;
Then you get:
id | average
----+----------------------
2 | 31.8150000000000000
1 | 238.5016666666666667
(2 rows)
MySql >= 8.0
I used Recursive Common Table Expressions (cte) to split pricehistory string by ','. Then I split price from timestamp by ';', cast price as decimal(10,2) and group by id to get average price by id.
WITH RECURSIVE
cte AS (SELECT id,
SUBSTRING_INDEX(pricehistory, ',', 1) AS price,
CASE WHEN POSITION(',' IN pricehistory) > 0
THEN SUBSTR(pricehistory, POSITION(',' IN pricehistory) + 1)
ELSE NULL END AS rest
FROM t
UNION ALL
SELECT id,
SUBSTRING_INDEX(rest, ',', 1) AS price,
CASE WHEN POSITION(',' IN rest) > 0
THEN SUBSTR(rest, POSITION(',' IN rest) + 1)
ELSE NULL END AS rest
FROM cte
WHERE rest IS NOT NULL)
SELECT id, AVG(CAST(SUBSTR(price, POSITION(';' IN price) + 1) AS decimal(10,2))) AS price_average
FROM cte
GROUP BY id;
A similar way to do the same (using regular expressions functions):
WITH RECURSIVE
cte AS (SELECT Id, concat(pricehistory, ',') AS pricehistory FROM t),
unnest AS (SELECT id,
pricehistory,
1 AS i,
REGEXP_SUBSTR(pricehistory, ';[0-9.]*,', 1, 1) AS price
FROM cte
UNION ALL
SELECT id,
pricehistory,
i + 1,
REGEXP_SUBSTR(pricehistory, ';[0-9.]*,', 1, i + 1)
FROM unnest
WHERE REGEXP_SUBSTR(pricehistory, ';[0-9.]*,', 1, i + 1) IS NOT NULL)
SELECT id, AVG(CAST(SUBSTR(price, 2, LENGTH(price) - 2) AS decimal(10,2))) AS price_average
FROM unnest
GROUP BY id;
you don't write what DBMS you are using.
In MS SQL-SERVER you can write something like this.
Create a function to convert string to multiple rows, and then use that in the query.
CREATE or ALTER FUNCTION dbo.BreakStringIntoRows (#CommadelimitedString varchar(1000), #Separator VARCHAR(1))
RETURNS #Result TABLE (Column1 VARCHAR(max))
AS
BEGIN
DECLARE #IntLocation INT
WHILE (CHARINDEX(#Separator, #CommadelimitedString, 0) > 0)
BEGIN
SET #IntLocation = CHARINDEX(#Separator, #CommadelimitedString, 0)
INSERT INTO #Result (Column1)
--LTRIM and RTRIM to ensure blank spaces are removed
SELECT RTRIM(LTRIM(SUBSTRING(#CommadelimitedString, 0, #IntLocation)))
SET #CommadelimitedString = STUFF(#CommadelimitedString, 1, #IntLocation, '')
END
INSERT INTO #Result (Column1)
SELECT RTRIM(LTRIM(#CommadelimitedString))--LTRIM and RTRIM to ensure blank spaces are removed
RETURN
END
create table test1 ( id int not null, pricehistory varchar(max) not null );
insert into test1 values ( 1, '1634913730;48.38,1634916509;48.38,1635162352;37.96,1635177904;49.14,1635337722;1219.98,1635340811;27.17' );
insert into test1 values ( 2, '1634913731;42.42,1634916609;21.21' );
Select *,
(
Select avg(CAST(RTRIM(LTRIM(SUBSTRING(column1, 0, CHARINDEX(';', column1, 0)))) as decimal)) From dbo.BreakStringIntoRows(pricehistory, ',')
) as AVG
FRom test1
sample output:
I am trying to get string between second and third instance of ",," using SQL SELECT.
Apparently functions substring and charindex are useful, and I have tried them but the problem is that I need the string between those specific ",,"s and the length of the strings between them can change.
Can't find working example anywhere.
Here is an example:
Table: test
Column: Column1
Row1: cat1,,cat2,,cat3,,cat4,,cat5
Row2: dogger1,,dogger2,,dogger3,,dogger4,,dogger5
Result: cat3dogger3
Here is my closest attempt, it works if the strings are same length every time, but they aren't:
SELECT SUBSTRING(column1,LEN(LEFT(column1,CHARINDEX(',,', column1,12)+2)),LEN(column1) - LEN(LEFT(column1,CHARINDEX(',,', column1,20)+2)) - LEN(RIGHT(column1,CHARINDEX(',,', (REVERSE(column1)))))) AS column1
FROM testi
Just repeat sub-string 3 times, each time moving onto the next ",," e.g.
select
-- Substring till the third ',,'
substring(z.col1, 1, patindex('%,,%',z.col1)-1)
from (values ('cat1,,cat2,,cat3,,cat4,,cat5'),('dogger1,,dogger2,,dogger3,,dogger4,,dogger5')) x (col1)
-- Substring from the first ',,'
cross apply (values (substring(x.col1,patindex('%,,%',x.col1)+2,len(x.col1)))) y (col1)
-- Substring from the second ',,'
cross apply (values (substring(y.col1,patindex('%,,%',y.col1)+2,len(y.col1)))) z (col1);
And just to reiterate, this is a terrible way to store data, so the best solution is to store it properly.
Here is an alternative solution using charindex. The base idea is the same as in Dale K's an answer, but instead of cutting the string, we specify the start_location for the search by using the third, optional parameter, of charindex. This way, we get the location of each separator, and could slip each value off from the main string.
declare #vtest table (column1 varchar(200))
insert into #vtest ( column1 ) values('dogger1,,dogger2,,dogger3,,dogger4,,dogger5')
insert into #vtest ( column1 ) values('cat1,,cat2,,cat3,,cat4,,cat5')
declare #separetor char(2) = ',,'
select
t.column1
, FI.FirstInstance
, SI.SecondInstance
, TI.ThirdInstance
, iif(TI.ThirdInstance is not null, substring(t.column1, SI.SecondInstance + 2, TI.ThirdInstance - SI.SecondInstance - 2), null)
from
#vtest t
cross apply (select nullif(charindex(#separetor, t.column1), 0) FirstInstance) FI
cross apply (select nullif(charindex(#separetor, t.column1, FI.FirstInstance + 2), 0) SecondInstance) SI
cross apply (select nullif(charindex(#separetor, t.column1, SI.SecondInstance + 2), 0) ThirdInstance) TI
For transparency, I saved the separator string in a variable.
By default the charindex returns 0 if the search string is not present, so I overwrite it with the value null, by using nullif
IMHO, SQL Server 2016 and its JSON support in the best option here.
SQL
-- DDL and sample data population, start
DECLARE #tbl TABLE (ID INT IDENTITY PRIMARY KEY, Tokens VARCHAR(500));
INSERT INTO #tbl VALUES
('cat1,,cat2,,cat3,,cat4,,cat5'),
('dogger1,,dogger2,,dogger3,,dogger4,,dogger5');
-- DDL and sample data population, end
WITH rs AS
(
SELECT *
, '["' + REPLACE(Tokens
, ',,', '","')
+ '"]' AS jsondata
FROM #tbl
)
SELECT rs.ID, rs.Tokens
, JSON_VALUE(jsondata, '$[2]') AS ThirdToken
FROM rs;
Output
+----+---------------------------------------------+------------+
| ID | Tokens | ThirdToken |
+----+---------------------------------------------+------------+
| 1 | cat1,,cat2,,cat3,,cat4,,cat5 | cat3 |
| 2 | dogger1,,dogger2,,dogger3,,dogger4,,dogger5 | dogger3 |
+----+---------------------------------------------+------------+
It´s the same as #"Yitzhak Khabinsky" but i think it looks clearer
WITH CTE_Data
AS(
SELECT 'cat1,,cat2,,cat3,,cat4,,cat5' AS [String]
UNION
SELECT 'dogger1,,dogger2,,dogger3,,dogger4,,dogger5' AS [String]
)
SELECT
A.[String]
,Value3 = JSON_VALUE('["'+ REPLACE(A.[String], ',,', '","') + '"]', '$[2]')
FROM CTE_Data AS A
I need to replace values within a formula stored as a string in SQL.
Example formulas stored in a column:
'=AA+BB/DC'
'=-(AA+CC)'
'=AA/BB+DD'
I have values for AA, BB etc. stored in another table.
Can I find and replace 'AA', 'BB' and so forth from within the formulas with numeric values to actually calculate the formula?
I assume I also need to replace the arithmetic operators ('+' , '/') from strings to actual signs, and if so is there a way to do it?
Desired Result
Assuming: AA = 10, BB = 20, DC = 5
I would need
'=AA+BB/DC' converted to 10+20/5 and a final output of 14
Please note that formulas can change in the future so I would need something resilient to that.
Thank you!
Okay, so this is a real hack, but I was intrigued by your question. You could turn my example into a function and then refactor it to your specific needs.
Note: using TRANSLATE requires SQL Server 2017. This could be a deal-breaker for you right there. TRANSLATE simplifies the replacement process greatly.
This example is just that--an example. A hack. Performance issues are unknown. You still need to do your diligence with testing.
-- Create a mock-up of the values table/data.
DECLARE #Values TABLE ( [key] VARCHAR(2), [val] INT );
INSERT INTO #Values ( [key], [val] ) VALUES
( 'AA', 10 ), ( 'BB', 20 ), ( 'CC', 6 ), ( 'DC', 5 );
-- Variable passed in to function.
DECLARE #formula VARCHAR(255) = '=(AA+BB)/DC';
-- Remove unnecessary mathmatical characters from the formula values.
DECLARE #vals VARCHAR(255) = REPLACE ( TRANSLATE ( #formula, '=()', '___' ), '_', '' );
-- Remove any leading mathmatical operations from #vals.
WHILE PATINDEX ( '[A-Z]', LEFT ( #vals, 1 ) ) = 0
SET #vals = SUBSTRING ( #vals, 2, LEN ( #vals ) );
-- Use SQL hack to replace placeholder values with actual values...
SELECT #formula = REPLACE ( #formula, fx.key_val, v.val )
FROM (
SELECT
[value] AS [key_val],
ROW_NUMBER() OVER ( ORDER BY ( SELECT NULL ) ) AS [key_id]
FROM STRING_SPLIT ( TRANSLATE ( #vals, '+/*-', ',,,,' ), ',' )
) AS fx
INNER JOIN #Values v
ON Fx.[key_val] = v.[key]
ORDER BY
fx.[key_id]
-- Return updated formula.
SELECT #formula AS RevisedFormula;
-- Return the result (remove the equals sign).
SET #formula = FORMATMESSAGE ( 'SELECT %s AS FormulaResult;', REPLACE ( #formula, '=', '' ) );
EXEC ( #formula );
SELECT #formula AS RevisedFormula; returns:
+----------------+
| RevisedFormula |
+----------------+
| =(10+20)/5 |
+----------------+
The last part of my example uses EXEC to do the math. You cannot use EXEC in a function.
-- Return the result (remove the equals sign).
SET #formula = FORMATMESSAGE ( 'SELECT %s AS FormulaResult;', REPLACE ( #formula, '=', '' ) );
EXEC ( #formula );
Returns
+---------------+
| FormulaResult |
+---------------+
| 6 |
+---------------+
Changing the formula value to =-(AA+CC) returns:
+----------------+
| RevisedFormula |
+----------------+
| =-(10+6) |
+----------------+
+---------------+
| FormulaResult |
+---------------+
| -16 |
+---------------+
It's probably worth noting to pay attention to math order in your formulas. Your original example of =AA+BB/DC returns 14, not the 6 that may have been expected. I updated your formula to =(AA+BB)/DC for my example.
I am new to SQL
If I have a column like this
ID
00001234
00012345
00001235
00123456
I want to see a column of ID without '0' Like this
ID
1234
12345
1235
123456
How can I start? any advice?
In SQL Server you can use:
SELECT ID,
REPLACE(LTRIM(REPLACE(ID, '0', ' ') ), ' ', '0')
FROM mytable
The above can be easily adjusted to any other RDBMS you may use.
Cast it to Bigint and cast it back to varchar
Note:Assumption: RDBMS SQL SERVER, ID is of character type
SELECT * INTO #TAB FROM (
select '00001234' ID
UNION ALL
select '00012345'
UNION ALL
select '00001235'
UNION ALL
select '00123456'
)A
SELECT CAST(CAST(ID AS BIGINT) AS VARCHAR(50)) FROM #TAB
I was wondering about the possibility to count the null columns of row in SQL, I have a table Customer that has nullable values, simply I want a query that return an int of the number of null columns for certain row(certain customer).
This method assigns a 1 or 0 for null columns, and adds them all together. Hopefully you don't have too many nullable columns to add up here...
SELECT
((CASE WHEN col1 IS NULL THEN 1 ELSE 0 END)
+ (CASE WHEN col2 IS NULL THEN 1 ELSE 0 END)
+ (CASE WHEN col3 IS NULL THEN 1 ELSE 0 END)
...
...
+ (CASE WHEN col10 IS NULL THEN 1 ELSE 0 END)) AS sum_of_nulls
FROM table
WHERE Customer=some_cust_id
Note, you can also do this perhaps a little more syntactically cleanly with IF() if your RDBMS supports it.
SELECT
(IF(col1 IS NULL, 1, 0)
+ IF(col2 IS NULL, 1, 0)
+ IF(col3 IS NULL, 1, 0)
...
...
+ IF(col10 IS NULL, 1, 0)) AS sum_of_nulls
FROM table
WHERE Customer=some_cust_id
I tested this pattern against a table and it appears to work properly.
My answer builds on Michael Berkowski's answer, but to avoid having to type out hundreds of column names, what I did was this:
Step 1: Get a list of all of the columns in your table
SELECT COLUMN_NAME FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_NAME = 'myTable';
Step 2: Paste the list in Notepad++ (any editor that supports regular expression replacement will work). Then use this replacement pattern
Search:
^(.*)$
Replace:
\(CASE WHEN \1 IS NULL THEN 1 ELSE 0 END\) +
Step 3: Prepend SELECT identityColumnName, and change the very last + to AS NullCount FROM myTable and optionally add an ORDER BY...
SELECT
identityColumnName,
(CASE WHEN column001 IS NULL THEN 1 ELSE 0 END) +
-- ...
(CASE WHEN column200 IS NULL THEN 1 ELSE 0 END) AS NullCount
FROM
myTable
ORDER BY
NullCount DESC
For ORACLE-DBMS only.
You can use the NVL2 function:
NVL2( string1, value_if_not_null, value_if_null )
Here is a select with a similiar approach as Michael Berkowski suggested:
SELECT (NVL2(col1, 0, 1)
+ NVL2(col2, 0, 1)
+ NVL2(col3, 0, 1)
...
...
+ NVL2(col10, 0, 1)
) AS sum_of_nulls
FROM table
WHERE Customer=some_cust_id
A more generic approach would be to write a PL/SQL-block and use dynamic SQL. You have to build a SELECT string with the NVL2 method from above for every column in the all_tab_columns of a specific table.
Unfortunately, in a standard SQL statement you will have to enter each column you want to test, to test all programatically you could use T-SQL. A word of warning though, ensure you are working with genuine NULLS, you can have blank stored values that the database will not recognise as a true NULL (I know this sounds strange).
You can avoid this by capturing the blank values and the NULLS in a statement like this:
CASE WHEN col1 & '' = '' THEN 1 ELSE 0 END
Or in some databases such as Oracle (not sure if there are any others) you would use:
CASE WHEN col1 || '' = '' THEN 1 ELSE 0 END
You don't state RDBMS. For SQL Server 2008...
SELECT CustomerId,
(SELECT COUNT(*) - COUNT(C)
FROM (VALUES(CAST(Col1 AS SQL_VARIANT)),
(Col2),
/*....*/
(Col9),
(Col10)) T(C)) AS NumberOfNulls
FROM Customer
Depending on what you want to do, and if you ignore mavens, and if you use SQL Server 2012, you could to it another way. .
The total number of candidate columns ("slots") must be known.
1. Select all the known "slots" column by column (they're known).
2. Unpivot that result to get a
table with one row per original column. This works because the null columns don't
unpivot, and you know all the column names.
3. Count(*) the result to get the number of non-nulls;
subtract from that to get your answer.
Like this, for 4 "seats" in a car
select 'empty seats' = 4 - count(*)
from
(
select carId, seat1,seat2,seat3,seat4 from cars where carId = #carId
) carSpec
unpivot (FieldValue FOR seat in ([seat1],[seat2],[seat3],[seat4])) AS results
This is useful if you may need to do more later than just count the number of non-null columns, as it gives you a way to manipulate the columns as a set too.
This will give you the number of columns which are not null. you can apply this appropriately
SELECT ISNULL(COUNT(col1),'') + ISNULL(COUNT(col2),'') +ISNULL(COUNT(col3),'')
FROM TABLENAME
WHERE ID=1
The below script gives you the NULL value count within a row i.e. how many columns do not have values.
{SELECT
*,
(SELECT COUNT(*)
FROM (VALUES (Tab.Col1)
,(Tab.Col2)
,(Tab.Col3)
,(Tab.Col4)) InnerTab(Col)
WHERE Col IS NULL) NullColumnCount
FROM (VALUES(1,2,3,4)
,(NULL,2,NULL,4)
,(1,NULL,NULL,NULL)) Tab(Col1,Col2,Col3,Col4) }
Just to demonstrate I am using an inline table in my example.
Try to cast or convert all column values to a common type it will help you to compare the column of different type.
I haven't tested it yet, but I'd try to do it using a PL\SQL function
CREATE OR REPLACE TYPE ANYARRAY AS TABLE OF ANYDATA
;
CREATE OR REPLACE Function COUNT_NULL
( ARR IN ANYARRAY )
RETURN number
IS
cnumber number ;
BEGIN
for i in 1 .. ARR.count loop
if ARR(i).column_value is null then
cnumber := cnumber + 1;
end if;
end loop;
RETURN cnumber;
EXCEPTION
WHEN OTHERS THEN
raise_application_error
(-20001,'An error was encountered - '
||SQLCODE||' -ERROR- '||SQLERRM);
END
;
Then use it in a select query like this
CREATE TABLE TEST (A NUMBER, B NUMBER, C NUMBER);
INSERT INTO TEST (NULL,NULL,NULL);
INSERT INTO TEST (1 ,NULL,NULL);
INSERT INTO TEST (1 ,2 ,NULL);
INSERT INTO TEST (1 ,2 ,3 );
SELECT ROWNUM,COUNT_NULL(A,B,C) AS NULL_COUNT FROM TEST;
Expected output
ROWNUM | NULL_COUNT
-------+-----------
1 | 3
2 | 2
3 | 1
4 | 0
This is how i tried
CREATE TABLE #temptablelocal (id int NOT NULL, column1 varchar(10) NULL, column2 varchar(10) NULL, column3 varchar(10) NULL, column4 varchar(10) NULL, column5 varchar(10) NULL, column6 varchar(10) NULL);
INSERT INTO #temptablelocal
VALUES (1,
NULL,
'a',
NULL,
'b',
NULL,
'c')
SELECT *
FROM #temptablelocal
WHERE id =1
SELECT count(1) countnull
FROM
(SELECT a.ID,
b.column_title,
column_val = CASE b.column_title
WHEN 'column1' THEN a.column1
WHEN 'column2' THEN a.column2
WHEN 'column3' THEN a.column3
WHEN 'column4' THEN a.column4
WHEN 'column5' THEN a.column5
WHEN 'column6' THEN a.column6
END
FROM
( SELECT id,
column1,
column2,
column3,
column4,
column5,
column6
FROM #temptablelocal
WHERE id =1 ) a
CROSS JOIN
( SELECT 'column1'
UNION ALL SELECT 'column2'
UNION ALL SELECT 'column3'
UNION ALL SELECT 'column4'
UNION ALL SELECT 'column5'
UNION ALL SELECT 'column6' ) b (column_title) ) AS pop WHERE column_val IS NULL
DROP TABLE #temptablelocal
Similary, but dynamically:
drop table if exists myschema.table_with_nulls;
create table myschema.table_with_nulls as
select
n1::integer,
n2::integer,
n3::integer,
n4::integer,
c1::character varying,
c2::character varying,
c3::character varying,
c4::character varying
from
(
values
(1,2,3,4,'a','b','c','d'),
(1,2,3,null,'a','b','c',null),
(1,2,null,null,'a','b',null,null),
(1,null,null,null,'a',null,null,null)
) as test_records(n1, n2, n3, n4, c1, c2, c3, c4);
drop function if exists myschema.count_nulls(varchar,varchar);
create function myschema.count_nulls(schemaname varchar, tablename varchar) returns void as
$BODY$
declare
calc varchar;
sqlstring varchar;
begin
select
array_to_string(array_agg('(' || trim(column_name) || ' is null)::integer'),' + ')
into
calc
from
information_schema.columns
where
table_schema in ('myschema')
and table_name in ('table_with_nulls');
sqlstring = 'create temp view count_nulls as select *, ' || calc || '::integer as count_nulls from myschema.table_with_nulls';
execute sqlstring;
return;
end;
$BODY$ LANGUAGE plpgsql STRICT;
select * from myschema.count_nulls('myschema'::varchar,'table_with_nulls'::varchar);
select
*
from
count_nulls;
Though I see that I didn't finish parametising the function.
My answer builds on Drew Chapin's answer, but with changes to get the result using a single script:
use <add_database_here>;
Declare #val Varchar(MAX);
Select #val = COALESCE(#val + str, str) From
(SELECT
'(CASE WHEN '+COLUMN_NAME+' IS NULL THEN 1 ELSE 0 END) +' str
FROM INFORMATION_SCHEMA.COLUMNS WHERE TABLE_NAME = '<add table name here>'
) t1 -- getting column names and adding the case when to replace NULLs for zeros or ones
Select #val = SUBSTRING(#val,1,LEN(#val) - 1) -- removing trailling add sign
Select #val = 'SELECT <add_identity_column_here>, ' + #val + ' AS NullCount FROM <add table name here>' -- adding the 'select' for the column identity, the 'alias' for the null count column, and the 'from'
EXEC (#val) --executing the resulting sql
With ORACLE:
Number_of_columns - json_value( json_array( comma separated list of columns ), '$.size()' ) from your_table
json_array will build an array with only the non null columns and the json_query expression will give you the size of the array
There isn't a straightforward way of doing so like there would be with counting rows. Basically, you have to enumerate all the columns that might be null in one expression.
So for a table with possibly null columns a, b, c, you could do this:
SELECT key_column, COALESCE(a,0) + COALESCE(b,0) + COALESCE(c,0) null_col_count
FROM my_table