Mahout (6) - ClusteringRecommender -

org.apache.mahout.cf.taste.recommender.ClusteringRecommenderを使用する事でデータをクラスタ化し、そのクラスタ内でレコメンデーションを行う事が出来る

import java.io.File;
import java.util.Iterator;

import org.apache.mahout.cf.taste.model.DataModel;
import org.apache.mahout.cf.taste.impl.model.file.FileDataModel;
import org.apache.mahout.cf.taste.impl.similarity.TanimotoCoefficientSimilarity;
import org.apache.mahout.cf.taste.impl.recommender.TreeClusteringRecommender;
import org.apache.mahout.cf.taste.impl.recommender.NearestNeighborClusterSimilarity;
import org.apache.mahout.cf.taste.impl.common.FastIDSet;
import org.apache.mahout.cf.taste.impl.common.LongPrimitiveIterator;
import org.apache.mahout.cf.taste.similarity.UserSimilarity;
import org.apache.mahout.cf.taste.recommender.ClusteringRecommender;

public class Client {
    public static void main(String[] args) throws Exception {
        DataModel model = new FileDataModel(new File("data/data.txt"));
        UserSimilarity similar = new TanimotoCoefficientSimilarity(model);
        ClusteringRecommender recommender = new TreeClusteringRecommender(
            model,
            new NearestNeighborClusterSimilarity(similar),
            model.getNumUsers() / 2
        );

        FastIDSet[] clusters = recommender.getClusters();

        for(FastIDSet cluster : clusters) {
            if(!(cluster.size() > 1)) {
                continue;
            }

            Iterator<Long> users = cluster.iterator();

            while(users.hasNext()) {
                long user = users.next();

                System.out.println(user + " -> " + recommender.recommend(user, 10));

                /* 手動でクラスタ内での相関予測を行う場合
                LongPrimitiveIterator items = model.getItemIDs();

                while(items.hasNext()) {
                    long item = items.next();
                    float value = recommender.estimatePreference(user,item);

                    System.out.println(user + " -> " + item + " = " + value);
                }
                */
            }
        }
    }
}