nl.gridline.zieook.inx.movielens.UserVectorSplitterMapper.java Source code

Introduction

Here is the source code for nl.gridline.zieook.inx.movielens.UserVectorSplitterMapper.java

Source

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 * http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing,
 * software distributed under the License is distributed on an
 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
 * KIND, either express or implied.  See the License for the
 * specific language governing permissions and limitations
 */
package nl.gridline.zieook.inx.movielens;

import java.io.IOException;
import java.util.Iterator;
import java.util.PriorityQueue;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.mahout.cf.taste.hadoop.item.VectorOrPrefWritable;
import org.apache.mahout.cf.taste.impl.common.FastIDSet;
import org.apache.mahout.common.iterator.FileLineIterable;
import org.apache.mahout.math.VarIntWritable;
import org.apache.mahout.math.VarLongWritable;
import org.apache.mahout.math.Vector;
import org.apache.mahout.math.VectorWritable;

/**
 * [purpose]
 * <p />
 * Project zieook-movielens<br />
 * UserVectorSplitterMapper.java created 21 nov. 2011
 * <p />
 * Copyright, all rights reserved 2011 GridLine Amsterdam
 * @author <a href="mailto:job@gridline.nl">Job</a>
 * @version $Revision:$, $Date:$
 */
public class UserVectorSplitterMapper
        extends Mapper<VarLongWritable, VectorWritable, VarIntWritable, VectorOrPrefWritable> {

    public static final String USERS_FILE = "usersFile";
    public static final String MAX_PREFS_PER_USER_CONSIDERED = "maxPrefsPerUserConsidered";
    public static final int DEFAULT_MAX_PREFS_PER_USER_CONSIDERED = 10;

    private int maxPrefsPerUserConsidered;
    private FastIDSet usersToRecommendFor;

    @Override
    protected void setup(Context context) throws IOException {
        Configuration jobConf = context.getConfiguration();
        maxPrefsPerUserConsidered = jobConf.getInt(MAX_PREFS_PER_USER_CONSIDERED,
                DEFAULT_MAX_PREFS_PER_USER_CONSIDERED);
        String usersFilePathString = jobConf.get(USERS_FILE);
        if (usersFilePathString != null) {
            FSDataInputStream in = null;
            try {
                Path unqualifiedUsersFilePath = new Path(usersFilePathString);
                FileSystem fs = FileSystem.get(unqualifiedUsersFilePath.toUri(), jobConf);
                usersToRecommendFor = new FastIDSet();
                Path usersFilePath = unqualifiedUsersFilePath.makeQualified(fs);
                in = fs.open(usersFilePath);
                for (String line : new FileLineIterable(in)) {
                    usersToRecommendFor.add(Long.parseLong(line));
                }
            } finally {
                IOUtils.closeStream(in);
            }
        }
    }

    @Override
    protected void map(VarLongWritable key, VectorWritable value, Context context)
            throws IOException, InterruptedException {
        long userID = key.get();
        if (usersToRecommendFor != null && !usersToRecommendFor.contains(userID)) {
            return;
        }
        Vector userVector = maybePruneUserVector(value.get());
        Iterator<Vector.Element> it = userVector.iterateNonZero();
        VarIntWritable itemIndexWritable = new VarIntWritable();
        VectorOrPrefWritable vectorOrPref = new VectorOrPrefWritable();
        while (it.hasNext()) {
            Vector.Element e = it.next();
            itemIndexWritable.set(e.index());
            vectorOrPref.set(userID, (float) e.get());
            context.write(itemIndexWritable, vectorOrPref);
        }
    }

    private Vector maybePruneUserVector(Vector userVector) {
        if (userVector.getNumNondefaultElements() <= maxPrefsPerUserConsidered) {
            return userVector;
        }

        float smallestLargeValue = findSmallestLargeValue(userVector);

        // "Blank out" small-sized prefs to reduce the amount of partial products
        // generated later. They're not zeroed, but NaN-ed, so they come through
        // and can be used to exclude these items from prefs.
        Iterator<Vector.Element> it = userVector.iterateNonZero();
        while (it.hasNext()) {
            Vector.Element e = it.next();
            float absValue = Math.abs((float) e.get());
            if (absValue < smallestLargeValue) {
                e.set(Float.NaN);
            }
        }

        return userVector;
    }

    private float findSmallestLargeValue(Vector userVector) {
        PriorityQueue<Float> topPrefValues = new PriorityQueue<Float>(maxPrefsPerUserConsidered + 1);
        Iterator<Vector.Element> it = userVector.iterateNonZero();
        while (it.hasNext()) {
            float absValue = Math.abs((float) it.next().get());
            if (topPrefValues.size() < maxPrefsPerUserConsidered) {
                topPrefValues.add(absValue);
            } else {
                if (absValue > topPrefValues.peek()) {
                    topPrefValues.add(absValue);
                    topPrefValues.poll();
                }
            }
        }
        return topPrefValues.peek();
    }

}