Example usage for org.apache.mahout.cf.taste.hadoop.item ToUserVectorsReducer MIN_PREFERENCES_PER

Introduction

In this page you can find the example usage for org.apache.mahout.cf.taste.hadoop.item ToUserVectorsReducer MIN_PREFERENCES_PER_USER.

Prototype

String MIN_PREFERENCES_PER_USER

To view the source code for org.apache.mahout.cf.taste.hadoop.item ToUserVectorsReducer MIN_PREFERENCES_PER_USER.

Click Source Link

Usage

From source file:com.pocketx.gravity.recommender.cf.similarity.job.PreparePreferenceMatrixJob.java

License:Apache License

@Override
public int run(String[] args) throws Exception {

    addInputOption();/*  w  w w.  j  av  a 2 s  . c  o  m*/
    addOutputOption();
    addOption("maxPrefsPerUser", "mppu", "max number of preferences to consider per user, "
            + "users with more preferences will be sampled down");
    addOption("minPrefsPerUser", "mp",
            "ignore users with less preferences than this " + "(default: " + DEFAULT_MIN_PREFS_PER_USER + ')',
            String.valueOf(DEFAULT_MIN_PREFS_PER_USER));
    addOption("booleanData", "b", "Treat input as without pref values", Boolean.FALSE.toString());
    addOption("ratingShift", "rs", "shift ratings by this value", "0.0");

    Map<String, List<String>> parsedArgs = parseArguments(args);
    if (parsedArgs == null) {
        return -1;
    }

    int minPrefsPerUser = Integer.parseInt(getOption("minPrefsPerUser"));
    boolean booleanData = Boolean.valueOf(getOption("booleanData"));
    float ratingShift = Float.parseFloat(getOption("ratingShift"));
    //convert items to an internal index
    Job itemIDIndex = prepareJob(getInputPath(), getOutputPath(ITEMID_INDEX), TextInputFormat.class,
            ItemIDIndexMapper.class, VarIntWritable.class, VarLongWritable.class, ItemIDIndexReducer.class,
            VarIntWritable.class, VarLongWritable.class, SequenceFileOutputFormat.class);
    itemIDIndex.setCombinerClass(ItemIDIndexReducer.class);
    boolean succeeded = itemIDIndex.waitForCompletion(true);
    if (!succeeded) {
        return -1;
    }
    //convert user preferences into a vector per user
    Job toUserVectors = prepareJob(getInputPath(), getOutputPath(USER_VECTORS), TextInputFormat.class,
            ToItemPrefsMapper.class, VarLongWritable.class,
            booleanData ? VarLongWritable.class : EntityPrefWritable.class, ToUserVectorsReducer.class,
            VarLongWritable.class, VectorWritable.class, SequenceFileOutputFormat.class);
    toUserVectors.getConfiguration().setBoolean(RecommenderJob.BOOLEAN_DATA, booleanData);
    toUserVectors.getConfiguration().setInt(ToUserVectorsReducer.MIN_PREFERENCES_PER_USER, minPrefsPerUser);
    toUserVectors.getConfiguration().set(ToEntityPrefsMapper.RATING_SHIFT, String.valueOf(ratingShift));
    succeeded = toUserVectors.waitForCompletion(true);
    if (!succeeded) {
        return -1;
    }
    //we need the number of users later
    int numberOfUsers = (int) toUserVectors.getCounters().findCounter(ToUserVectorsReducer.Counters.USERS)
            .getValue();
    HadoopUtil.writeInt(numberOfUsers, getOutputPath(NUM_USERS), getConf());
    //build the rating matrix
    Job toItemVectors = prepareJob(getOutputPath(USER_VECTORS), getOutputPath(RATING_MATRIX),
            ToItemVectorsMapper.class, IntWritable.class, VectorWritable.class, ToItemVectorsReducer.class,
            IntWritable.class, VectorWritable.class);
    toItemVectors.setCombinerClass(ToItemVectorsReducer.class);

    /* configure sampling regarding the uservectors */
    if (hasOption("maxPrefsPerUser")) {
        int samplingSize = Integer.parseInt(getOption("maxPrefsPerUser"));
        toItemVectors.getConfiguration().setInt(ToItemVectorsMapper.SAMPLE_SIZE, samplingSize);
    }

    succeeded = toItemVectors.waitForCompletion(true);
    if (!succeeded) {
        return -1;
    }

    return 0;
}

Example usage for org.apache.mahout.cf.taste.hadoop.item ToUserVectorsReducer MIN_PREFERENCES_PER_USER

Introduction

Prototype

Usage