2

Please login or register to vote for this query.

(click on this box to dismiss)

P(tag1 and tag2)/[P(tag1) P(tag2)] for 256 most popular tags, see http://bit.ly/map-of-so

Q&A about the site for builders and users of networked sensors and control devices in the contexts of smart homes, industry automation, or environmental sensors

-- for plots like this one: 
-- http://bit.ly/map-of-so
-- P(tag1 and tag2)/[P(tag1) P(tag2)] is
-- #tag1tag2 #questions / (#tag1 #tag2)

WITH

  TagCounts AS
  (
    SELECT TOP 256
      T.TagName Tag,
      count(*) TagCount
    FROM Posts P
      INNER JOIN PostTags PT ON PT.PostId = P.Id
      INNER JOIN Tags T ON T.Id = PT.TagId
    WHERE
      P.PostTypeId = 1 -- only questions
    GROUP BY
      T.TagName
    --ORDER BY
    --    TagCount DESC
  ),
  TagPairCounts AS
  (
    SELECT
      T1.TagName Tag1,
      T2.TagName Tag2,
      count(*) TagPairCount
    FROM Posts P
      INNER JOIN PostTags PT1 ON PT1.PostId = P.Id
      INNER JOIN PostTags PT2 ON PT2.PostId = P.Id 
      INNER JOIN Tags T1 ON T1.Id = PT1.TagId 
      INNER JOIN Tags T2 ON T2.Id = PT2.TagId
    WHERE
      T1.TagName < T2.TagName
    GROUP BY
      T1.TagName,
      T2.TagName
    --ORDER BY
    --    TagPairCount DESC
    )
SELECT TOP 10
    TPC.Tag1
FROM
    TagPairCounts TPC

view current version

edited oct 29 12

created oct 29 12 Piotr Migdal