network-wide new answers per month since 2018

1

Please login or register to vote for this query.

(click on this box to dismiss)

Bioinformatics

Q&A for researchers, developers, students, teachers, and end users interested in bioinformatics

/*-- INSTRUCTIONS:
    1)  Set the columns of #AllSiteResults to what you need in the final query.
    2)  Set the @seSiteQuery text (inside the WHILE loop) to the query that will run on each site to build
        the #AllSiteResults table.
    3)  Comment out the `WHERE       (dadn.dbName = 'StackExchange.Meta'...` line if site metas are desired.
    4)  Adjust the final query if post processing is desired (optional).
*/
DECLARE @seDbName       AS NVARCHAR (max)
DECLARE @seSiteURL      AS NVARCHAR (max)
DECLARE @sitePrettyName AS NVARCHAR (max)
DECLARE @seSiteQuery    AS NVARCHAR (max)

CREATE TABLE #AllSiteResults (
      -- PUT THE COLUMNS YOU WILL USE, HERE
      -- vvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvv
      [Date] DATE,
      [Type] NVARCHAR(max),
      [NewAnswers] REAL,
      [NewQuestions] REAL
      -- ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
)

DECLARE seSites_crsr CURSOR FOR
WITH dbsAndDomainNames AS (
    SELECT      dbL.dbName
                , STRING_AGG (dbL.domainPieces, '.')    AS siteDomain
    FROM (
        SELECT      TOP 50000   -- Never be that many sites and TOP is needed for order by, below
                    name        AS dbName
                    , value     AS domainPieces
                    , row_number ()  OVER (ORDER BY (SELECT 0)) AS [rowN]
        FROM        sys.databases
        CROSS APPLY STRING_SPLIT (name, '.')
        WHERE       CASE    WHEN state_desc = 'ONLINE'
                            THEN OBJECT_ID (QUOTENAME (name) + '.[dbo].[PostNotices]', 'U') -- Pick a table unique to SE data
                    END
                    IS NOT NULL
        ORDER BY    dbName, [rowN] DESC
    ) AS dbL
    GROUP BY    dbL.dbName
)
SELECT      REPLACE (REPLACE (dadn.dbName, 'StackExchange.', ''), '.', ' ' )  AS [Site Name]
            , dadn.dbName
            , CASE  -- See https://meta.stackexchange.com/q/215071
                    WHEN dadn.dbName = 'StackExchange.Mathoverflow.Meta'
                    THEN 'https://meta.mathoverflow.net/'
                    -- Some AVP/Audio/Video/Sound kerfuffle?
                    WHEN dadn.dbName = 'StackExchange.Audio'
                    THEN 'https://video.stackexchange.com/'
                    -- Ditto
                    WHEN dadn.dbName = 'StackExchange.Audio.Meta'
                    THEN 'https://video.meta.stackexchange.com/'
                    -- Normal site
                    ELSE 'https://' + LOWER (siteDomain) + '.com/'
            END AS siteURL
FROM        dbsAndDomainNames dadn
WHERE       (dadn.dbName = 'StackExchange.Meta'  OR  dadn.dbName NOT LIKE '%Meta%')

-- Step through cursor
OPEN    seSites_crsr
FETCH   NEXT FROM seSites_crsr INTO @sitePrettyName, @seDbName, @seSiteURL
WHILE   @@FETCH_STATUS = 0
BEGIN
    -- QUERY THAT YOU WANT TO RUN ON EACH SITE, GOES HERE
    -- For example:
    -- vvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvv
    SET @seSiteQuery = '
        USE [' + @seDbName + ']
        INSERT INTO #AllSiteResults
        -- Ignore the datapoints for the current month. That data is not yet complete. Ex. Things like roomba have "lag"
        SELECT
          DATEFROMPARTS(YEAR(P.CreationDate), MONTH(P.CreationDate), 1) AS Date,
          ''average new non-deleted answers per new question'' AS Type,
          CAST(SUM(CASE WHEN P.PostTypeId = 2 THEN 1 ELSE 0 END) AS REAL) AS NewAnswerCount,
          CAST(SUM(CASE WHEN P.PostTypeId = 1 THEN 1 ELSE 0 END) AS REAL) AS NewQuestionCount
        FROM PostsWithDeleted P
        WHERE P.PostTypeId IN (1,2)
          AND YEAR(P.CreationDate) >= 2018
          AND (P.PostTypeId = 1 OR P.DeletionDate IS NULL)
        GROUP BY DATEFROMPARTS(YEAR(P.CreationDate), MONTH(P.CreationDate), 1)
        UNION
        SELECT
          DATEFROMPARTS(YEAR(P.CreationDate), MONTH(P.CreationDate), 1) AS Date,
          ''average new deleted answers per new question'' AS Type,
          CAST(SUM(CASE WHEN P.PostTypeId = 2 THEN 1 ELSE 0 END) AS REAL) AS NewAnswerCount,
          CAST(SUM(CASE WHEN P.PostTypeId = 1 THEN 1 ELSE 0 END) AS REAL) AS NewQuestionCount
        FROM PostsWithDeleted P
        WHERE P.PostTypeId IN (1,2)
          AND YEAR(P.CreationDate) >= 2018
          AND (P.PostTypeId = 1 OR P.DeletionDate IS NOT NULL)
        GROUP BY DATEFROMPARTS(YEAR(P.CreationDate), MONTH(P.CreationDate), 1)
        --ORDER BY Date
    '
    -- ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    EXEC sp_executesql @seSiteQuery

    FETCH NEXT FROM seSites_crsr INTO @sitePrettyName, @seDbName, @seSiteURL
END
CLOSE       seSites_crsr
DEALLOCATE  seSites_crsr

-- ADJUST THIS QUERY IF ANY POST PROCESSING IS DESIRED.
SELECT      MAX([Date]) AS [Date], MAX([Type]) AS [Type], SUM([NewAnswers]) / SUM([NewQuestions]) AS [AverageNewAnswersPerNewQuestion]
FROM        #AllSiteResults
GROUP BY    [Date], [Type]
ORDER BY    [Date]

Enter Parameters

Options:
Switch to meta site
loading Hold tight while we fetch your results