Sample queries to GitHub BigQueries data. For the first GitHub Data Challenge.

bigqueries.sql

-- La première requète pour les projets ayant le plus de fork
SELECT repository_name, MIN(repository_forks) as mini, MAX(repository_forks) as maxi, MAX(repository_forks) - MIN(repository_forks) as diff
FROM githubarchive:github.timeline WHERE type = "ForkEvent"  AND LENGTH(actor_attributes_location) > 3  AND repository_forks > 200
GROUP BY repository_name
ORDER BY maxi DESC;

-- La deuxième requète pour la localisation et le nombre de fork en fonction du temps
SELECT created_at, actor_attributes_location, repository_forks
FROM githubarchive:github.timeline WHERE type = "ForkEvent"  AND LENGTH(actor_attributes_location) > 3 AND repository_name = "bootstrap" AND repository_owner = "twitter" AND repository_fork = "false"
ORDER BY repository_forks