BigQuery sql for GitHub Archive dataset: fork count per repo
/* fork count per repo */ | |
SELECT | |
REGEXP_REPLACE(repo.name, 'MyOrg/', '') AS repo, | |
COUNT (*) AS cnt | |
FROM ( | |
SELECT | |
type, | |
repo.name, | |
FROM | |
TABLE_DATE_RANGE([githubarchive:day.events_], TIMESTAMP('2015-01-01'), TIMESTAMP('2015-10-15') ) | |
WHERE | |
type = 'ForkEvent' | |
AND repo.name CONTAINS 'MyOrg/' | |
AND NOT REGEXP_MATCH(repo.name,'^MyOrg/SomeRepo$') ) | |
GROUP BY | |
repo | |
ORDER BY | |
cnt DESC |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment