0

Please login or register to vote for this query.

(click on this box to dismiss)

Q&A about the site for operations research and analytics professionals, educators, and students

-- Define a table to store sampled question ids
DECLARE @question_ids table(Id int);
INSERT INTO @question_ids
SELECT TOP 100 Id
FROM Posts
WHERE
  (Title IS NOT NULL AND Body IS NOT NULL AND Tags IS NOT NULL)
  and Score > 10
ORDER BY NEWID();

-- get a random set of questions into the table defined above
SELECT TOP 100
  Posts.Id,
  Posts.Body,
  Posts.Title,
  Posts.Tags,
  Posts.CreationDate,
  Posts.Score
FROM @question_ids as QIDs
INNER JOIN Posts ON QIDs.Id = Posts.Id;

-- Download top 50K tags
SELECT TOP 50000 Id, TagName, Count
FROM Tags
WHERE TagName IS NOT NULL
ORDER BY Count DESC;

-- Counting the number of rows:
SELECT COUNT(Id) AS TotalRowCount
FROM Posts;

-- Counting the number of complete Posts:
SELECT COUNT(*) AS CompletePostsCount
FROM Posts
WHERE Title IS NOT NULL AND Tags IS NOT NULL AND Body IS NOT NULL;

-- Select random posts from a slice of 1:10 of total data selecting posts with score higher than 10 and non-empty tags, title, and comment:
DECLARE @Counter INT;
SET @Counter = (SELECT COUNT(Id) FROM Posts);

SELECT TOP 50000 Id, Body, Title, Tags, Score, CreationDate
FROM Posts
WHERE 2*@Counter/10 < Id AND Id < 3*@Counter/10
  AND Title IS NOT NULL AND Body IS NOT NULL AND Tags IS NOT NULL
  AND Score > 10
ORDER BY NEWID();

-- Random value sampling with replacement:
DECLARE @Counter2 INT;
SET @Counter2 = 1;

DECLARE @Randint INT;

WHILE (@Counter2 <= 10)
BEGIN
  SET @Randint = CAST(RAND() * (10 - 5) + 5 AS INT);
  PRINT 'The counter value is ' + CONVERT(VARCHAR, @Counter2);
  PRINT 'The random value is ' + CONVERT(VARCHAR, @Randint);

  SET @Counter2 = @Counter2 + 1;
END;


-- Select all tag synonyms:
SELECT *
FROM TagSynonyms;

fork query

edited jun 7

created jun 7 anonymous