Examples with DBIDVar de.lmu.ifi.dbs.elki.database.ids.DBIDVar used on opensource projects

Example 21 with DBIDVar

use of de.lmu.ifi.dbs.elki.database.ids.DBIDVar in project elki by elki-project.

the class PROCLUS method greedy.

/**
 * Returns a piercing set of k medoids from the specified sample set.
 *
 * @param distFunc the distance function
 * @param sampleSet the sample set
 * @param m the number of medoids to be returned
 * @param random random number generator
 * @return a piercing set of m medoids from the specified sample set
 */
private ArrayDBIDs greedy(DistanceQuery<V> distFunc, DBIDs sampleSet, int m, Random random) {
    ArrayModifiableDBIDs medoids = DBIDUtil.newArray(m);
    ArrayModifiableDBIDs s = DBIDUtil.newArray(sampleSet);
    DBIDArrayIter iter = s.iter();
    DBIDVar m_i = DBIDUtil.newVar();
    int size = s.size();
    // Move a random element to the end, then pop()
    s.swap(random.nextInt(size), --size);
    medoids.add(s.pop(m_i));
    if (LOG.isDebugging()) {
        LOG.debugFiner("medoids " + medoids.toString());
    }
    // To track the current worst element:
    int worst = -1;
    double worstd = Double.NEGATIVE_INFINITY;
    // compute distances between each point in S and m_i
    WritableDoubleDataStore distances = DataStoreUtil.makeDoubleStorage(s, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP);
    for (iter.seek(0); iter.getOffset() < size; iter.advance()) {
        final double dist = distFunc.distance(iter, m_i);
        distances.putDouble(iter, dist);
        if (dist > worstd) {
            worstd = dist;
            worst = iter.getOffset();
        }
    }
    for (int i = 1; i < m; i++) {
        // choose medoid m_i to be far from previous medoids
        s.swap(worst, --size);
        medoids.add(s.pop(m_i));
        // compute distances of each point to closest medoid; track worst.
        worst = -1;
        worstd = Double.NEGATIVE_INFINITY;
        for (iter.seek(0); iter.getOffset() < size; iter.advance()) {
            double dist_new = distFunc.distance(iter, m_i);
            double dist_old = distances.doubleValue(iter);
            double dist = (dist_new < dist_old) ? dist_new : dist_old;
            distances.putDouble(iter, dist);
            if (dist > worstd) {
                worstd = dist;
                worst = iter.getOffset();
            }
        }
        if (LOG.isDebugging()) {
            LOG.debugFiner("medoids " + medoids.toString());
        }
    }
    return medoids;
}

Example 22 with DBIDVar

use of de.lmu.ifi.dbs.elki.database.ids.DBIDVar in project elki by elki-project.

the class FarthestPointsInitialMeans method chooseInitialMeans.

@Override
public <T extends NumberVector> double[][] chooseInitialMeans(Database database, Relation<T> relation, int k, NumberVectorDistanceFunction<? super T> distanceFunction) {
    // Get a distance query
    DistanceQuery<T> distQ = database.getDistanceQuery(relation, distanceFunction);
    DBIDs ids = relation.getDBIDs();
    WritableDoubleDataStore store = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP, Double.POSITIVE_INFINITY);
    // Chose first mean
    double[][] means = new double[k][];
    DBIDRef first = DBIDUtil.randomSample(ids, rnd);
    T prevmean = relation.get(first);
    means[0] = prevmean.toArray();
    // Find farthest object each.
    DBIDVar best = DBIDUtil.newVar(first);
    for (int i = (dropfirst ? 0 : 1); i < k; i++) {
        double maxdist = Double.NEGATIVE_INFINITY;
        for (DBIDIter it = ids.iter(); it.valid(); it.advance()) {
            final double prev = store.doubleValue(it);
            if (prev != prev) {
                // NaN: already chosen!
                continue;
            }
            double val = Math.min(prev, distQ.distance(prevmean, it));
            // Don't store distance to first mean, when it will be dropped below.
            if (i > 0) {
                store.putDouble(it, val);
            }
            if (val > maxdist) {
                maxdist = val;
                best.set(it);
            }
        }
        // Add new mean (and drop the initial mean when desired)
        // So it won't be chosen twice.
        store.putDouble(best, Double.NaN);
        prevmean = relation.get(best);
        means[i] = prevmean.toArray();
    }
    // Explicitly destroy temporary data.
    store.destroy();
    return means;
}

Example 23 with DBIDVar

use of de.lmu.ifi.dbs.elki.database.ids.DBIDVar in project elki by elki-project.

the class PAMInitialMeans method chooseInitialMedoids.

@Override
public DBIDs chooseInitialMedoids(int k, DBIDs ids, DistanceQuery<? super O> distQ) {
    ArrayModifiableDBIDs medids = DBIDUtil.newArray(k);
    DBIDVar bestid = DBIDUtil.newVar();
    // We need three temporary storage arrays:
    WritableDoubleDataStore mindist, bestd, tempd;
    mindist = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP);
    bestd = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP);
    tempd = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP);
    // First mean is chosen by having the smallest distance sum to all others.
    {
        double best = Double.POSITIVE_INFINITY;
        FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Choosing initial mean", ids.size(), LOG) : null;
        for (DBIDIter iter = ids.iter(); iter.valid(); iter.advance()) {
            double sum = 0, d;
            for (DBIDIter iter2 = ids.iter(); iter2.valid(); iter2.advance()) {
                sum += d = distQ.distance(iter, iter2);
                tempd.putDouble(iter2, d);
            }
            if (sum < best) {
                best = sum;
                bestid.set(iter);
                // Swap mindist and newd:
                WritableDoubleDataStore temp = mindist;
                mindist = tempd;
                tempd = temp;
            }
            LOG.incrementProcessed(prog);
        }
        LOG.ensureCompleted(prog);
        medids.add(bestid);
    }
    assert (mindist != null);
    // Subsequent means optimize the full criterion.
    FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Choosing initial centers", k, LOG) : null;
    // First one was just chosen.
    LOG.incrementProcessed(prog);
    for (int i = 1; i < k; i++) {
        double best = Double.POSITIVE_INFINITY;
        bestid.unset();
        for (DBIDIter iter = ids.iter(); iter.valid(); iter.advance()) {
            if (medids.contains(iter)) {
                continue;
            }
            double sum = 0., v;
            for (DBIDIter iter2 = ids.iter(); iter2.valid(); iter2.advance()) {
                sum += v = MathUtil.min(distQ.distance(iter, iter2), mindist.doubleValue(iter2));
                tempd.put(iter2, v);
            }
            if (sum < best) {
                best = sum;
                bestid.set(iter);
                // Swap bestd and newd:
                WritableDoubleDataStore temp = bestd;
                bestd = tempd;
                tempd = temp;
            }
        }
        if (!bestid.isSet()) {
            throw new AbortException("No median found that improves the criterion function?!? Too many infinite distances.");
        }
        medids.add(bestid);
        // Swap bestd and mindist:
        WritableDoubleDataStore temp = bestd;
        bestd = mindist;
        mindist = temp;
        LOG.incrementProcessed(prog);
    }
    LOG.ensureCompleted(prog);
    mindist.destroy();
    bestd.destroy();
    tempd.destroy();
    return medids;
}

Example 24 with DBIDVar

use of de.lmu.ifi.dbs.elki.database.ids.DBIDVar in project elki by elki-project.

the class FarthestSumPointsInitialMeans method chooseInitialMedoids.

@Override
public DBIDs chooseInitialMedoids(int k, DBIDs ids, DistanceQuery<? super O> distQ) {
    @SuppressWarnings("unchecked") final Relation<O> relation = (Relation<O>) distQ.getRelation();
    WritableDoubleDataStore store = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP, 0.);
    ArrayModifiableDBIDs means = DBIDUtil.newArray(k);
    DBIDRef first = DBIDUtil.randomSample(ids, rnd);
    means.add(first);
    DBIDVar prevmean = DBIDUtil.newVar(first);
    DBIDVar best = DBIDUtil.newVar(first);
    for (int i = (dropfirst ? 0 : 1); i < k; i++) {
        // Find farthest object:
        double maxdist = Double.NEGATIVE_INFINITY;
        for (DBIDIter it = relation.iterDBIDs(); it.valid(); it.advance()) {
            final double prev = store.doubleValue(it);
            if (prev != prev) {
                // NaN: already chosen!
                continue;
            }
            double dsum = prev + distQ.distance(prevmean, it);
            // Don't store distance to first mean, when it will be dropped below.
            if (i > 0) {
                store.putDouble(it, dsum);
            }
            if (dsum > maxdist) {
                maxdist = dsum;
                best.set(it);
            }
        }
        // Add new mean:
        if (i == 0) {
            // Remove temporary first element.
            means.clear();
        }
        // So it won't be chosen twice.
        store.putDouble(best, Double.NaN);
        prevmean.set(best);
        means.add(best);
    }
    store.destroy();
    return means;
}

Example 25 with DBIDVar

use of de.lmu.ifi.dbs.elki.database.ids.DBIDVar in project elki by elki-project.

the class KNNDD method run.

/**
 * Runs the algorithm in the timed evaluation part.
 *
 * @param relation Data relation
 */
public OutlierResult run(Relation<O> relation) {
    final DistanceQuery<O> distanceQuery = relation.getDistanceQuery(getDistanceFunction());
    final KNNQuery<O> knnQuery = relation.getKNNQuery(distanceQuery, k);
    FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("kNN distance for objects", relation.size(), LOG) : null;
    WritableDoubleDataStore knnDist = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP);
    WritableDBIDDataStore neighbor = DataStoreUtil.makeDBIDStorage(relation.getDBIDs(), DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP);
    DBIDVar var = DBIDUtil.newVar();
    // Find nearest neighbors, and store the distances.
    for (DBIDIter it = relation.iterDBIDs(); it.valid(); it.advance()) {
        final KNNList knn = knnQuery.getKNNForDBID(it, k);
        knnDist.putDouble(it, knn.getKNNDistance());
        neighbor.put(it, knn.assignVar(knn.size() - 1, var));
        LOG.incrementProcessed(prog);
    }
    LOG.ensureCompleted(prog);
    prog = LOG.isVerbose() ? new FiniteProgress("kNN distance descriptor", relation.size(), LOG) : null;
    WritableDoubleDataStore scores = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_DB);
    DoubleMinMax minmax = new DoubleMinMax();
    for (DBIDIter it = relation.iterDBIDs(); it.valid(); it.advance()) {
        // Distance
        double d = knnDist.doubleValue(it);
        // Distance of neighbor
        double nd = knnDist.doubleValue(neighbor.assignVar(it, var));
        double knndd = nd > 0 ? d / nd : d > 0 ? Double.POSITIVE_INFINITY : 1.;
        scores.put(it, knndd);
        minmax.put(knndd);
        LOG.incrementProcessed(prog);
    }
    LOG.ensureCompleted(prog);
    DoubleRelation scoreres = new MaterializedDoubleRelation("kNN Data Descriptor", "knndd-outlier", scores, relation.getDBIDs());
    OutlierScoreMeta meta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0., Double.POSITIVE_INFINITY, 1.);
    return new OutlierResult(meta, scoreres);
}