package org.apache.hadoop.mapreduce.lib.partition;
import org.apache.hadoop.mapreduce.Partitioner;
public class HashPartitioner<K, V> extends Partitioner<K, V>{
public int getPartition(K key, V value, int numReduceTasks){
return (Key.hashCode() & Integer.MAX_VALUE) % numReduceTasks;
}
}
ユーザー数のカウント処理
user_id_list = []
ARGF.each_line do |line|
line.chomp!
user_id = line.split(‘,’)[0]
unless user_id_list.include?(user_id)
user_id_list << user_id
end
end
puts "UU数は#{user_id_list.size}です"
[/code]
