Examples with KMeansModel de.lmu.ifi.dbs.elki.data.model.KMeansModel used on opensource projects

Example 1 with KMeansModel

use of de.lmu.ifi.dbs.elki.data.model.KMeansModel in project elki by elki-project.

the class ParallelLloydKMeans method run.

@Override
public Clustering<KMeansModel> run(Database database, Relation<V> relation) {
    DBIDs ids = relation.getDBIDs();
    // Choose initial means
    double[][] means = initializer.chooseInitialMeans(database, relation, k, getDistanceFunction());
    // Store for current cluster assignment.
    WritableIntegerDataStore assignment = DataStoreUtil.makeIntegerStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT, -1);
    double[] varsum = new double[k];
    KMeansProcessor<V> kmm = new KMeansProcessor<>(relation, distanceFunction, assignment, varsum);
    IndefiniteProgress prog = LOG.isVerbose() ? new IndefiniteProgress("K-Means iteration", LOG) : null;
    for (int iteration = 0; maxiter <= 0 || iteration < maxiter; iteration++) {
        LOG.incrementProcessed(prog);
        kmm.nextIteration(means);
        ParallelExecutor.run(ids, kmm);
        // Stop if no cluster assignment changed.
        if (!kmm.changed()) {
            break;
        }
        means = kmm.getMeans();
    }
    LOG.setCompleted(prog);
    // Wrap result
    ArrayModifiableDBIDs[] clusters = ClusteringAlgorithmUtil.partitionsFromIntegerLabels(ids, assignment, k);
    Clustering<KMeansModel> result = new Clustering<>("k-Means Clustering", "kmeans-clustering");
    for (int i = 0; i < clusters.length; i++) {
        DBIDs cids = clusters[i];
        if (cids.size() == 0) {
            continue;
        }
        KMeansModel model = new KMeansModel(means[i], varsum[i]);
        result.addToplevelCluster(new Cluster<>(cids, model));
    }
    return result;
}

Example 2 with KMeansModel

use of de.lmu.ifi.dbs.elki.data.model.KMeansModel in project elki by elki-project.

the class WithinClusterMeanDistanceQualityMeasureTest method testOverallDistance.

/**
 * Test cluster average overall distance.
 */
@Test
public void testOverallDistance() {
    Database db = makeSimpleDatabase(UNITTEST + "quality-measure-test.csv", 7);
    Relation<DoubleVector> rel = db.getRelation(TypeUtil.DOUBLE_VECTOR_FIELD);
    KMeansLloyd<DoubleVector> kmeans = // 
    new ELKIBuilder<KMeansLloyd<DoubleVector>>(KMeansLloyd.class).with(KMeans.K_ID, // 
    2).with(KMeans.INIT_ID, // 
    FirstKInitialMeans.class).build();
    // run KMeans on database
    Clustering<KMeansModel> result = kmeans.run(db);
    final NumberVectorDistanceFunction<? super DoubleVector> dist = kmeans.getDistanceFunction();
    // Test Cluster Average Overall Distance
    KMeansQualityMeasure<? super DoubleVector> overall = new WithinClusterMeanDistanceQualityMeasure();
    final double quality = overall.quality(result, dist, rel);
    assertEquals("Avarage overall distance not as expected.", 0.8888888888888888, quality, 1e-10);
}

Example 3 with KMeansModel

use of de.lmu.ifi.dbs.elki.data.model.KMeansModel in project elki by elki-project.

the class PassingDataToELKI method main.

/**
 * Main method
 *
 * @param args Command line parameters (not supported)
 */
public static void main(String[] args) {
    // Set the logging level to statistics:
    LoggingConfiguration.setStatistics();
    // Generate a random data set.
    // Note: ELKI has a nice data generator class, use that instead.
    double[][] data = new double[1000][2];
    for (int i = 0; i < data.length; i++) {
        for (int j = 0; j < data[i].length; j++) {
            data[i][j] = Math.random();
        }
    }
    // Adapter to load data from an existing array.
    DatabaseConnection dbc = new ArrayAdapterDatabaseConnection(data);
    // Create a database (which may contain multiple relations!)
    Database db = new StaticArrayDatabase(dbc, null);
    // Load the data into the database (do NOT forget to initialize...)
    db.initialize();
    // Relation containing the number vectors:
    Relation<NumberVector> rel = db.getRelation(TypeUtil.NUMBER_VECTOR_FIELD);
    // We know that the ids must be a continuous range:
    DBIDRange ids = (DBIDRange) rel.getDBIDs();
    // K-means should be used with squared Euclidean (least squares):
    SquaredEuclideanDistanceFunction dist = SquaredEuclideanDistanceFunction.STATIC;
    // Default initialization, using global random:
    // To fix the random seed, use: new RandomFactory(seed);
    RandomlyGeneratedInitialMeans init = new RandomlyGeneratedInitialMeans(RandomFactory.DEFAULT);
    // Textbook k-means clustering:
    KMeansLloyd<NumberVector> km = new // 
    KMeansLloyd<>(// 
    dist, // 
    3, /* k - number of partitions */
    0, /* maximum number of iterations: no limit */
    init);
    // K-means will automatically choose a numerical relation from the data set:
    // But we could make it explicit (if there were more than one numeric
    // relation!): km.run(db, rel);
    Clustering<KMeansModel> c = km.run(db);
    // Output all clusters:
    int i = 0;
    for (Cluster<KMeansModel> clu : c.getAllClusters()) {
        // K-means will name all clusters "Cluster" in lack of noise support:
        System.out.println("#" + i + ": " + clu.getNameAutomatic());
        System.out.println("Size: " + clu.size());
        System.out.println("Center: " + clu.getModel().getPrototype().toString());
        // Iterate over objects:
        System.out.print("Objects: ");
        for (DBIDIter it = clu.getIDs().iter(); it.valid(); it.advance()) {
            // To get the vector use:
            // NumberVector v = rel.get(it);
            // Offset within our DBID range: "line number"
            final int offset = ids.getOffset(it);
            System.out.print(" " + offset);
        // Do NOT rely on using "internalGetIndex()" directly!
        }
        System.out.println();
        ++i;
    }
}

Example 4 with KMeansModel

use of de.lmu.ifi.dbs.elki.data.model.KMeansModel in project elki by elki-project.

the class UKMeans method run.

/**
 * Run the clustering.
 *
 * @param database the Database
 * @param relation the Relation
 * @return Clustering result
 */
public Clustering<?> run(final Database database, final Relation<DiscreteUncertainObject> relation) {
    if (relation.size() <= 0) {
        return new Clustering<>("Uk-Means Clustering", "ukmeans-clustering");
    }
    // Choose initial means randomly
    DBIDs sampleids = DBIDUtil.randomSample(relation.getDBIDs(), k, rnd);
    List<double[]> means = new ArrayList<>(k);
    for (DBIDIter iter = sampleids.iter(); iter.valid(); iter.advance()) {
        means.add(ArrayLikeUtil.toPrimitiveDoubleArray(relation.get(iter).getCenterOfMass()));
    }
    // Setup cluster assignment store
    List<ModifiableDBIDs> clusters = new ArrayList<>();
    for (int i = 0; i < k; i++) {
        clusters.add(DBIDUtil.newHashSet((int) (relation.size() * 2. / k)));
    }
    WritableIntegerDataStore assignment = DataStoreUtil.makeIntegerStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT, -1);
    double[] varsum = new double[k];
    IndefiniteProgress prog = LOG.isVerbose() ? new IndefiniteProgress("UK-Means iteration", LOG) : null;
    DoubleStatistic varstat = LOG.isStatistics() ? new DoubleStatistic(this.getClass().getName() + ".variance-sum") : null;
    int iteration = 0;
    for (; maxiter <= 0 || iteration < maxiter; iteration++) {
        LOG.incrementProcessed(prog);
        boolean changed = assignToNearestCluster(relation, means, clusters, assignment, varsum);
        logVarstat(varstat, varsum);
        // Stop if no cluster assignment changed.
        if (!changed) {
            break;
        }
        // Recompute means.
        means = means(clusters, means, relation);
    }
    LOG.setCompleted(prog);
    if (LOG.isStatistics()) {
        LOG.statistics(new LongStatistic(KEY + ".iterations", iteration));
    }
    // Wrap result
    Clustering<KMeansModel> result = new Clustering<>("Uk-Means Clustering", "ukmeans-clustering");
    for (int i = 0; i < clusters.size(); i++) {
        DBIDs ids = clusters.get(i);
        if (ids.isEmpty()) {
            continue;
        }
        result.addToplevelCluster(new Cluster<>(ids, new KMeansModel(means.get(i), varsum[i])));
    }
    return result;
}

Example 5 with KMeansModel

use of de.lmu.ifi.dbs.elki.data.model.KMeansModel in project elki by elki-project.

the class KMeansBatchedLloyd method run.

@Override
public Clustering<KMeansModel> run(Database database, Relation<V> relation) {
    final int dim = RelationUtil.dimensionality(relation);
    // Choose initial means
    if (LOG.isStatistics()) {
        LOG.statistics(new StringStatistic(KEY + ".initializer", initializer.toString()));
    }
    double[][] means = initializer.chooseInitialMeans(database, relation, k, getDistanceFunction());
    // Setup cluster assignment store
    List<ModifiableDBIDs> clusters = new ArrayList<>();
    for (int i = 0; i < k; i++) {
        clusters.add(DBIDUtil.newHashSet((int) (relation.size() * 2. / k)));
    }
    WritableIntegerDataStore assignment = DataStoreUtil.makeIntegerStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT, -1);
    ArrayDBIDs[] parts = DBIDUtil.randomSplit(relation.getDBIDs(), blocks, random);
    double[][] meanshift = new double[k][dim];
    int[] changesize = new int[k];
    double[] varsum = new double[k];
    IndefiniteProgress prog = LOG.isVerbose() ? new IndefiniteProgress("K-Means iteration", LOG) : null;
    DoubleStatistic varstat = LOG.isStatistics() ? new DoubleStatistic(this.getClass().getName() + ".variance-sum") : null;
    int iteration = 0;
    for (; maxiter <= 0 || iteration < maxiter; iteration++) {
        LOG.incrementProcessed(prog);
        boolean changed = false;
        FiniteProgress pprog = LOG.isVerbose() ? new FiniteProgress("Batch", parts.length, LOG) : null;
        for (int p = 0; p < parts.length; p++) {
            // Initialize new means scratch space.
            for (int i = 0; i < k; i++) {
                Arrays.fill(meanshift[i], 0.);
            }
            Arrays.fill(changesize, 0);
            Arrays.fill(varsum, 0.);
            changed |= assignToNearestCluster(relation, parts[p], means, meanshift, changesize, clusters, assignment, varsum);
            // Recompute means.
            updateMeans(means, meanshift, clusters, changesize);
            LOG.incrementProcessed(pprog);
        }
        LOG.ensureCompleted(pprog);
        logVarstat(varstat, varsum);
        // Stop if no cluster assignment changed.
        if (!changed) {
            break;
        }
    }
    LOG.setCompleted(prog);
    if (LOG.isStatistics()) {
        LOG.statistics(new LongStatistic(KEY + ".iterations", iteration));
    }
    // Wrap result
    Clustering<KMeansModel> result = new Clustering<>("k-Means Clustering", "kmeans-clustering");
    for (int i = 0; i < clusters.size(); i++) {
        DBIDs ids = clusters.get(i);
        if (ids.size() == 0) {
            continue;
        }
        KMeansModel model = new KMeansModel(means[i], varsum[i]);
        result.addToplevelCluster(new Cluster<>(ids, model));
    }
    return result;
}