Example usage for org.apache.mahout.common.iterator.sequencefile PathFilters partFilter

List of usage examples for org.apache.mahout.common.iterator.sequencefile PathFilters partFilter

Introduction

In this page you can find the example usage for org.apache.mahout.common.iterator.sequencefile PathFilters partFilter.

Prototype

public static PathFilter partFilter() 

Source Link

Usage

From source file:com.elex.dmp.lda.CVB0Driver.java

License:Apache License

/**
 * @param topicModelStateTemp/*w  w  w . ja  v  a  2  s.c  om*/
 * @param iteration
 * @return {@code double[2]} where first value is perplexity and second is model weight of those
 *         documents sampled during perplexity computation, or {@code null} if no perplexity data
 *         exists for the given iteration.
 * @throws IOException
 */
public static double readPerplexity(Configuration conf, Path topicModelStateTemp, int iteration)
        throws IOException {
    Path perplexityPath = perplexityPath(topicModelStateTemp, iteration);
    FileSystem fs = FileSystem.get(perplexityPath.toUri(), conf);
    if (!fs.exists(perplexityPath)) {
        log.warn("Perplexity path {} does not exist, returning NaN", perplexityPath);
        return Double.NaN;
    }
    double perplexity = 0;
    double modelWeight = 0;
    long n = 0;
    for (Pair<DoubleWritable, DoubleWritable> pair : new SequenceFileDirIterable<DoubleWritable, DoubleWritable>(
            perplexityPath, PathType.LIST, PathFilters.partFilter(), null, true, conf)) {
        modelWeight += pair.getFirst().get();
        perplexity += pair.getSecond().get();
        n++;
    }
    log.info("Read {} entries with total perplexity {} and model weight {}",
            new Object[] { n, perplexity, modelWeight });
    return perplexity / modelWeight;
}

From source file:com.elex.dmp.lda.CVB0Driver.java

License:Apache License

private static Job writeDocTopicInference(Configuration conf, Path corpus, Path modelInput, Path output)
        throws IOException, ClassNotFoundException, InterruptedException {
    String jobName = String.format("Writing final document/topic inference from %s to %s", corpus, output);
    log.info("About to run: " + jobName);
    Job job = new Job(conf, jobName);
    job.setMapperClass(CVB0DocInferenceMapper.class);
    job.setNumReduceTasks(0);//from ww  w. j a v  a  2s .c om
    job.setInputFormatClass(SequenceFileInputFormat.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(VectorWritable.class);
    FileSystem fs = FileSystem.get(corpus.toUri(), conf);
    if (modelInput != null && fs.exists(modelInput)) {
        FileStatus[] statuses = fs.listStatus(modelInput, PathFilters.partFilter());
        URI[] modelUris = new URI[statuses.length];
        for (int i = 0; i < statuses.length; i++) {
            modelUris[i] = statuses[i].getPath().toUri();
        }
        DistributedCache.setCacheFiles(modelUris, conf);
    }
    setModelPaths(job, modelInput);//bug:mahout-1147
    FileInputFormat.addInputPath(job, corpus);
    FileOutputFormat.setOutputPath(job, output);
    job.setJarByClass(CVB0Driver.class);
    job.submit();
    return job;
}

From source file:com.elex.dmp.lda.CVB0Driver.java

License:Apache License

private static void setModelPaths(Job job, Path modelPath) throws IOException {
    Configuration conf = job.getConfiguration();
    if (modelPath == null || !FileSystem.get(modelPath.toUri(), conf).exists(modelPath)) {
        return;//from  w  ww .  java  2  s .  c  o  m
    }
    FileStatus[] statuses = FileSystem.get(modelPath.toUri(), conf).listStatus(modelPath,
            PathFilters.partFilter());
    Preconditions.checkState(statuses.length > 0, "No part files found in model path '%s'",
            modelPath.toString());
    String[] modelPaths = new String[statuses.length];
    for (int i = 0; i < statuses.length; i++) {
        modelPaths[i] = statuses[i].getPath().toUri().toString();
    }
    conf.setStrings(MODEL_PATHS, modelPaths);
}

From source file:com.luca.filipponi.tweetAnalysis.SentimentClassifier.CustomTestNaiveBayesDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    addInputOption();/* w w  w  .ja  v  a  2  s.  c  o  m*/
    addOutputOption();
    addOption(addOption(DefaultOptionCreator.overwriteOption().create()));
    addOption("model", "m", "The path to the model built during training", true);
    addOption(
            buildOption("testComplementary", "c", "test complementary?", false, false, String.valueOf(false)));
    addOption(buildOption("runSequential", "seq", "run sequential?", false, false, String.valueOf(false)));
    addOption("labelIndex", "l", "The path to the location of the label index", true);
    Map<String, List<String>> parsedArgs = parseArguments(args);
    if (parsedArgs == null) {
        return -1;
    }
    if (hasOption(DefaultOptionCreator.OVERWRITE_OPTION)) {
        HadoopUtil.delete(getConf(), getOutputPath());
    }

    boolean complementary = hasOption("testComplementary");
    boolean sequential = hasOption("runSequential");
    if (sequential) {
        FileSystem fs = FileSystem.get(getConf());
        NaiveBayesModel model = NaiveBayesModel.materialize(new Path(getOption("model")), getConf());
        AbstractNaiveBayesClassifier classifier;
        if (complementary) {
            classifier = new ComplementaryNaiveBayesClassifier(model);
        } else {
            classifier = new StandardNaiveBayesClassifier(model);
        }
        SequenceFile.Writer writer = new SequenceFile.Writer(fs, getConf(), getOutputPath(), Text.class,
                VectorWritable.class);
        SequenceFile.Reader reader = new SequenceFile.Reader(fs, getInputPath(), getConf());
        Text key = new Text();
        VectorWritable vw = new VectorWritable();
        while (reader.next(key, vw)) {
            writer.append(new Text(SLASH.split(key.toString())[1]),
                    new VectorWritable(classifier.classifyFull(vw.get())));
        }
        writer.close();
        reader.close();
    } else {
        boolean succeeded = runMapReduce(parsedArgs);
        if (!succeeded) {
            return -1;
        }
    }

    //load the labels
    Map<Integer, String> labelMap = BayesUtils.readLabelIndex(getConf(), new Path(getOption("labelIndex")));

    //loop over the results and create the confusion matrix
    SequenceFileDirIterable<Text, VectorWritable> dirIterable = new SequenceFileDirIterable<Text, VectorWritable>(
            getOutputPath(), PathType.LIST, PathFilters.partFilter(), getConf());
    ResultAnalyzer analyzer = new ResultAnalyzer(labelMap.values(), "DEFAULT");
    analyzeResults(labelMap, dirIterable, analyzer);

    log.info("{} Results: {}", complementary ? "Complementary" : "Standard NB", analyzer);
    return 0;
}

From source file:com.missionsky.scp.dataanalysis.mahout.TestNaiveBayesDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    addInputOption();/*w  ww. java  2s  . c  o m*/
    addOutputOption();
    addOption(addOption(DefaultOptionCreator.overwriteOption().create()));
    addOption("model", "m", "The path to the model built during training", true);
    addOption(
            buildOption("testComplementary", "c", "test complementary?", false, false, String.valueOf(false)));
    addOption(buildOption("runSequential", "seq", "run sequential?", false, false, String.valueOf(false)));
    addOption("labelIndex", "l", "The path to the location of the label index", true);
    Map<String, List<String>> parsedArgs = parseArguments(args);
    if (parsedArgs == null) {
        return -1;
    }
    if (hasOption(DefaultOptionCreator.OVERWRITE_OPTION)) {
        HadoopUtil.delete(getConf(), getOutputPath());
    }

    boolean complementary = hasOption("testComplementary");
    boolean sequential = hasOption("runSequential");
    if (sequential) {
        FileSystem fs = FileSystem.get(getConf());
        NaiveBayesModel model = NaiveBayesModel.materialize(new Path(getOption("model")), getConf());
        AbstractNaiveBayesClassifier classifier;
        if (complementary) {
            classifier = new ComplementaryNaiveBayesClassifier(model);
        } else {
            classifier = new StandardNaiveBayesClassifier(model);
        }
        SequenceFile.Writer writer = new SequenceFile.Writer(fs, getConf(), getOutputPath(), Text.class,
                VectorWritable.class);
        Reader reader = new Reader(fs, getInputPath(), getConf());
        Text key = new Text();
        VectorWritable vw = new VectorWritable();
        while (reader.next(key, vw)) {
            writer.append(new Text(SLASH.split(key.toString())[1]),
                    new VectorWritable(classifier.classifyFull(vw.get())));
        }
        writer.close();
        reader.close();
    } else {
        boolean succeeded = runMapReduce(parsedArgs);
        if (!succeeded) {
            return -1;
        }
    }

    //load the labels
    Map<Integer, String> labelMap = BayesUtils.readLabelIndex(getConf(), new Path(getOption("labelIndex")));

    //loop over the results and create the confusion matrix
    SequenceFileDirIterable<Text, VectorWritable> dirIterable = new SequenceFileDirIterable<Text, VectorWritable>(
            getOutputPath(), PathType.LIST, PathFilters.partFilter(), getConf());
    ResultAnalyzer analyzer = new ResultAnalyzer(labelMap.values(), "DEFAULT");
    analyzeResults(labelMap, dirIterable, analyzer);

    log.info("{} Results: {}", complementary ? "Complementary" : "Standard NB", analyzer);
    return 0;
}

From source file:com.pocketx.gravity.common.TasteHadoopUtils.java

License:Apache License

/**
 * Reads a binary mapping file/*  www . j a  va2s.co  m*/
 */
public static OpenIntLongHashMap readItemIDIndexMap(String itemIDIndexPathStr, Configuration conf) {
    OpenIntLongHashMap indexItemIDMap = new OpenIntLongHashMap();
    Path itemIDIndexPath = new Path(itemIDIndexPathStr);
    for (Pair<VarIntWritable, VarLongWritable> record : new SequenceFileDirIterable<VarIntWritable, VarLongWritable>(
            itemIDIndexPath, PathType.LIST, PathFilters.partFilter(), null, true, conf)) {
        indexItemIDMap.put(record.getFirst().get(), record.getSecond().get());
    }
    return indexItemIDMap;
}

From source file:de.tuberlin.dima.recsys.ssnmm.ratingprediction.Evaluate.java

License:Apache License

public static void main(String[] args) throws IOException {

    int numUsers = 1823179;
    int numItems = 136736;
    double mu = 3.157255412010664;

    String distributedSimilarityMatrixPath = "/home/ssc/Desktop/yahoo/similarityMatrix/";
    String itemBiasesFilePath = "/home/ssc/Desktop/yahoo/itemBiases.tsv";
    String userBiasesFilePath = "/home/ssc/Desktop/yahoo/userBiases.tsv";
    String trainingSetPath = "/home/ssc/Entwicklung/datasets/yahoo-songs/songs.tsv";
    String holdoutSetPath = "home/ssc/Entwicklung/datasets/yahoo-songs/holdout.tsv";

    Matrix similarities = new SparseRowMatrix(numItems, numItems);

    System.out.println("Reading similarities...");
    int similaritiesRead = 0;
    Configuration conf = new Configuration();
    for (Pair<IntWritable, VectorWritable> pair : new SequenceFileDirIterable<IntWritable, VectorWritable>(
            new Path(distributedSimilarityMatrixPath), PathType.LIST, PathFilters.partFilter(), conf)) {

        int item = pair.getFirst().get();
        Iterator<Vector.Element> elements = pair.getSecond().get().iterateNonZero();

        while (elements.hasNext()) {
            Vector.Element elem = elements.next();
            similarities.setQuick(item, elem.index(), elem.get());
            similaritiesRead++;/*w ww . j  a  v a2 s  . com*/
        }
    }
    System.out.println("Found " + similaritiesRead + " similarities");

    Pattern sep = Pattern.compile("\t");

    double[] itemBiases = new double[numItems];
    double[] userBiases = new double[numUsers];

    System.out.println("Reading item biases");
    for (String line : new FileLineIterable(new File(itemBiasesFilePath))) {
        String[] parts = sep.split(line);
        itemBiases[Integer.parseInt(parts[0])] = Double.parseDouble(parts[1]);
    }

    System.out.println("Reading user biases");
    for (String line : new FileLineIterable(new File(userBiasesFilePath))) {
        String[] parts = sep.split(line);
        userBiases[Integer.parseInt(parts[0])] = Double.parseDouble(parts[1]);
    }

    Iterator<Rating> trainRatings = new RatingsIterable(new File(trainingSetPath)).iterator();
    Iterator<Rating> heldOutRatings = new RatingsIterable(new File(holdoutSetPath)).iterator();

    int currentUser = 0;
    OpenIntDoubleHashMap prefs = new OpenIntDoubleHashMap();

    int usersProcessed = 0;
    RunningAverage rmse = new FullRunningAverage();
    RunningAverage mae = new FullRunningAverage();

    RunningAverage rmseBase = new FullRunningAverage();
    RunningAverage maeBase = new FullRunningAverage();

    while (trainRatings.hasNext()) {
        Rating rating = trainRatings.next();
        if (rating.user() != currentUser) {

            for (int n = 0; n < 10; n++) {
                Rating heldOutRating = heldOutRatings.next();
                Preconditions.checkState(heldOutRating.user() == currentUser);

                double preference = 0.0;
                double totalSimilarity = 0.0;
                int count = 0;

                Iterator<Vector.Element> similarItems = similarities.viewRow(heldOutRating.item())
                        .iterateNonZero();
                while (similarItems.hasNext()) {
                    Vector.Element similarity = similarItems.next();
                    int similarItem = similarity.index();
                    if (prefs.containsKey(similarItem)) {
                        preference += similarity.get() * (prefs.get(similarItem)
                                - (mu + userBiases[currentUser] + itemBiases[similarItem]));
                        totalSimilarity += Math.abs(similarity.get());
                        count++;

                    }
                }

                double baselineEstimate = mu + userBiases[currentUser] + itemBiases[heldOutRating.item()];
                double estimate = baselineEstimate;

                if (count > 1) {
                    estimate += preference / totalSimilarity;
                }

                double baseError = Math.abs(heldOutRating.rating() - baselineEstimate);
                maeBase.addDatum(baseError);
                rmseBase.addDatum(baseError * baseError);

                double error = Math.abs(heldOutRating.rating() - estimate);
                mae.addDatum(error);
                rmse.addDatum(error * error);

            }

            if (++usersProcessed % 10000 == 0) {
                System.out.println(usersProcessed + " users processed, MAE " + mae.getAverage() + ", RMSE "
                        + Math.sqrt(rmse.getAverage()) + " | baseline MAE " + maeBase.getAverage()
                        + ", baseline RMSE " + Math.sqrt(rmseBase.getAverage()));
            }

            currentUser = rating.user();
            prefs.clear();

        }
        prefs.put(rating.item(), rating.rating());

    }

    System.out.println(usersProcessed + " users processed, MAE " + mae.getAverage() + ", RMSE "
            + Math.sqrt(rmse.getAverage()) + " | baseline MAE " + maeBase.getAverage() + ", baseline RMSE "
            + Math.sqrt(rmseBase.getAverage()));
}

From source file:edu.indiana.d2i.htrc.kmeans.MemKMeansUtil.java

License:Apache License

/** Configure the mapper with the cluster info */
public static void configureWithClusterInfo(Configuration conf, Path clusterPath,
        Collection<Cluster> clusters) {
    for (Writable value : new SequenceFileDirValueIterable<Writable>(clusterPath, PathType.LIST,
            PathFilters.partFilter(), conf)) {
        Class<? extends Writable> valueClass = value.getClass();
        if (valueClass.equals(Cluster.class)) {
            // get the cluster info
            clusters.add((Cluster) value);
        } else if (valueClass.equals(Canopy.class)) {
            // get the cluster info
            Canopy canopy = (Canopy) value;
            clusters.add(new Cluster(canopy.getCenter(), canopy.getId(), canopy.getMeasure()));
        } else {// w  w w.  j  a v  a2s  .c  om
            throw new IllegalStateException("Bad value class: " + valueClass);
        }
    }
}

From source file:mlbench.bayes.BayesUtils.java

License:Apache License

public static NaiveBayesModel readModelFromDir(Path base, Configuration conf) {

    float alphaI = conf.getFloat(ThetaMapper.ALPHA_I, 1.0f);

    // read feature sums and label sums
    Vector scoresPerLabel = null;
    Vector scoresPerFeature = null;
    for (Pair<Text, VectorWritable> record : new SequenceFileDirIterable<Text, VectorWritable>(
            new Path(base, TrainNaiveBayesJob.WEIGHTS), PathType.LIST, PathFilters.partFilter(), conf)) {
        String key = record.getFirst().toString();
        VectorWritable value = record.getSecond();
        if (key.equals(TrainNaiveBayesJob.WEIGHTS_PER_FEATURE)) {
            scoresPerFeature = value.get();
        } else if (key.equals(TrainNaiveBayesJob.WEIGHTS_PER_LABEL)) {
            scoresPerLabel = value.get();
        }//from   w w w .  j  a  v a 2  s  .  c  o m
    }

    // Preconditions.checkNotNull(scoresPerFeature);
    // Preconditions.checkNotNull(scoresPerLabel);

    Matrix scoresPerLabelAndFeature = new SparseMatrix(scoresPerLabel.size(), scoresPerFeature.size());
    for (Pair<IntWritable, VectorWritable> entry : new SequenceFileDirIterable<IntWritable, VectorWritable>(
            new Path(base, TrainNaiveBayesJob.SUMMED_OBSERVATIONS), PathType.LIST, PathFilters.partFilter(),
            conf)) {
        scoresPerLabelAndFeature.assignRow(entry.getFirst().get(), entry.getSecond().get());
    }

    Vector perlabelThetaNormalizer = scoresPerLabel.like();
    /*
     * for (Pair<Text,VectorWritable> entry : new
     * SequenceFileDirIterable<Text,VectorWritable>( new Path(base,
     * TrainNaiveBayesJob.THETAS), PathType.LIST, PathFilters.partFilter(),
     * conf)) { if (entry.getFirst().toString().equals(TrainNaiveBayesJob.
     * LABEL_THETA_NORMALIZER)) { perlabelThetaNormalizer =
     * entry.getSecond().get(); } }
     * 
     * Preconditions.checkNotNull(perlabelThetaNormalizer);
     */
    return new NaiveBayesModel(scoresPerLabelAndFeature, scoresPerFeature, scoresPerLabel,
            perlabelThetaNormalizer, alphaI, false);
}

From source file:mlbench.bayes.test.BayesTest.java

License:Apache License

@SuppressWarnings("deprecation")
public static void main(String[] args) throws MPI_D_Exception, IOException, MPIException {
    parseArgs(args);//from   w  w w  .ja v a2  s.co m
    HashMap<String, String> conf = new HashMap<String, String>();
    initConf(conf);
    MPI_D.Init(args, MPI_D.Mode.Common, conf);

    if (MPI_D.COMM_BIPARTITE_O != null) {
        rank = MPI_D.Comm_rank(MPI_D.COMM_BIPARTITE_O);
        size = MPI_D.Comm_size(MPI_D.COMM_BIPARTITE_O);
        NaiveBayesModel model = NaiveBayesModel.materialize(modelPath, config);
        classifier = new StandardNaiveBayesClassifier(model);

        MPI_D.COMM_BIPARTITE_O.Barrier();
        FileSplit[] inputs = DataMPIUtil.HDFSDataLocalLocator.getTaskInputs(MPI_D.COMM_BIPARTITE_O,
                (JobConf) config, inDir, rank);

        for (int i = 0; i < inputs.length; i++) {
            FileSplit fsplit = inputs[i];
            SequenceFileRecordReader<Text, VectorWritable> kvrr = new SequenceFileRecordReader<>(config,
                    fsplit);
            Text key = kvrr.createKey();
            VectorWritable value = kvrr.createValue();
            while (kvrr.next(key, value)) {
                Vector result = classifier.classifyFull(value.get());
                MPI_D.Send(new Text(SLASH.split(key.toString())[1]), new VectorWritable(result));
            }
        }
    } else if (MPI_D.COMM_BIPARTITE_A != null) {
        int rank = MPI_D.Comm_rank(MPI_D.COMM_BIPARTITE_A);
        config.set(MAPRED_OUTPUT_DIR, outDir);
        config.set("mapred.task.id", DataMPIUtil.getHadoopTaskAttemptID().toString().toString());
        ((JobConf) config).setOutputKeyClass(Text.class);
        ((JobConf) config).setOutputValueClass(VectorWritable.class);
        TaskAttemptContext taskContext = new TaskAttemptContextImpl(config,
                DataMPIUtil.getHadoopTaskAttemptID());
        SequenceFileOutputFormat<Text, VectorWritable> outfile = new SequenceFileOutputFormat<>();
        FileSystem fs = FileSystem.get(config);

        Path output = new Path(config.get(MAPRED_OUTPUT_DIR));
        FileOutputCommitter fcommitter = new FileOutputCommitter(output, taskContext);
        RecordWriter<Text, VectorWritable> outrw = null;
        try {
            fcommitter.setupJob(taskContext);
            outrw = outfile.getRecordWriter(fs, (JobConf) config, getOutputName(rank), null);
        } catch (IOException e) {
            e.printStackTrace();
            System.err.println("ERROR: Please set the HDFS configuration properly\n");
            System.exit(-1);
        }
        Text key = null;
        VectorWritable point = null;
        Vector vector = null;
        Object[] vals = MPI_D.Recv();
        while (vals != null) {
            key = (Text) vals[0];
            point = (VectorWritable) vals[1];
            if (key != null && point != null) {
                vector = point.get();
                outrw.write(key, new VectorWritable(vector));
            }
            vals = MPI_D.Recv();
        }
        outrw.close(null);
        if (fcommitter.needsTaskCommit(taskContext)) {
            fcommitter.commitTask(taskContext);
        }

        MPI_D.COMM_BIPARTITE_A.Barrier();
        if (rank == 0) {
            // load the labels
            Map<Integer, String> labelMap = BayesUtils.readLabelIndex(config, labPath);
            // loop over the results and create the confusion matrix
            SequenceFileDirIterable<Text, VectorWritable> dirIterable = new SequenceFileDirIterable<Text, VectorWritable>(
                    output, PathType.LIST, PathFilters.partFilter(), config);
            ResultAnalyzer analyzer = new ResultAnalyzer(labelMap.values(), "DEFAULT");
            analyzeResults(labelMap, dirIterable, analyzer);
        }
    }
    MPI_D.Finalize();
}