Twitter MapReduce with MongoDB+Hadoop Streaming Adapter

import.sh

curl https://stream.twitter.com/1/statuses/sample.json -u<login>:<password> | mongoimport -d test -c live

mapper.rb

#!/usr/bin/env ruby
require 'mongo-hadoop'

MongoHadoop.map do |document|
  { :_id => document['user']['time_zone'], :count => 1 }
end

reducer.rb

#!/usr/bin/env ruby
require 'mongo-hadoop'

MongoHadoop.reduce do |key, values|
  count = sum = 0

  values.each do |value|
    count += 1
    sum += value['num']
  end

  { :_id => key, :average => sum / count }
end

twit.sh

hadoop jar mongo-hadoop-streaming-assembly*.jar -mapper mapper.rb -reducer reducer.rb -inputURI mongodb://127.0.0.1/twitter.in -outputURI mongodb://127.0.0.1/twitter.out