Github Archive CreateEvent

CreateEvent.json

{
    "type": "CreateEvent",
    "actor": {
        "avatar_url": "https://secure.gravatar.com/avatar/8c315bedc4ab1b9aef8f9b446030daac?d=http://github.dev%2Fimages%2Fgravatars%2Fgravatar-user-420.png",
        "url": "https://api.github.dev/users/vinced45",
        "login": "vinced45",
        "id": 101286,
        "gravatar_id": "8c315bedc4ab1b9aef8f9b446030daac"
    },
    "repo": {
        "url": "https://api.github.dev/repos/vinced45/siriproxy-mashable",
        "id": 3081234,
        "name": "vinced45/siriproxy-mashable"
    },
    "public": true,
    "payload": {
        "ref_type": "repository",
        "description": "Siri Proxy Plugin to get news from Mashable",
        "master_branch": "master",
        "ref": null
    },
    "id": "1508512425",
    "created_at": "2012-01-01T00:03:28Z"
}

recommend.pig

/* Create repository event - strongest association with a repo possible */
create_events = LOAD '/tmp/CreateEvent' as (json: map[]); /* s3://github-explorer/CreateEvent */
create_ratings = FOREACH create_events GENERATE (chararray)$0#'actor_attributes'#'login' AS follower:chararray,
                                                StringConcat((chararray)$0#'repository'#'owner', '/', $0#'repository'#'name') AS repo:chararray,
                                                4.0 AS rating;