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

Example 31 with Model

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

the class ClusteringVectorParser method nextEvent.

@Override
public Event nextEvent() {
    if (nextevent != null) {
        Event ret = nextevent;
        nextevent = null;
        return ret;
    }
    try {
        while (reader.nextLineExceptComments()) {
            buf1.clear();
            lbl.clear();
            Int2IntOpenHashMap csize = new Int2IntOpenHashMap();
            String name = null;
            for (; /* initialized by nextLineExceptComments() */
            tokenizer.valid(); tokenizer.advance()) {
                try {
                    int cnum = tokenizer.getIntBase10();
                    buf1.add(cnum);
                    // Update cluster sizes:
                    csize.addTo(cnum, 1);
                } catch (NumberFormatException e) {
                    final String label = tokenizer.getSubstring();
                    lbl.add(label);
                    if (name == null) {
                        name = label;
                    }
                }
            }
            if (name == null) {
                name = "Cluster";
            }
            // Update meta on first record:
            boolean metaupdate = (range == null);
            if (range == null) {
                range = DBIDUtil.generateStaticDBIDRange(buf1.size());
            }
            if (buf1.size() != range.size()) {
                throw new AbortException("Clusterings do not contain the same number of elements!");
            }
            // Build clustering to store in the relation.
            Int2ObjectOpenHashMap<ModifiableDBIDs> clusters = new Int2ObjectOpenHashMap<>(csize.size());
            curclu = new Clustering<>(name, name);
            for (ObjectIterator<Int2IntMap.Entry> iter = csize.int2IntEntrySet().fastIterator(); iter.hasNext(); ) {
                Int2IntMap.Entry entry = iter.next();
                if (entry.getIntValue() > 0) {
                    clusters.put(entry.getIntKey(), DBIDUtil.newArray(entry.getIntValue()));
                }
            }
            DBIDArrayIter iter = range.iter();
            for (int i = 0; i < buf1.size(); i++) {
                clusters.get(buf1.getInt(i)).add(iter.seek(i));
            }
            for (ModifiableDBIDs cids : clusters.values()) {
                curclu.addToplevelCluster(new Cluster<Model>(cids, ClusterModel.CLUSTER));
            }
            // Label handling.
            if (!haslbl && !lbl.isEmpty()) {
                haslbl = true;
                metaupdate = true;
            }
            curlbl = LabelList.make(lbl);
            if (metaupdate) {
                // Force a meta update.
                nextevent = Event.NEXT_OBJECT;
                return Event.META_CHANGED;
            }
            return Event.NEXT_OBJECT;
        }
        return Event.END_OF_STREAM;
    } catch (IOException e) {
        throw new IllegalArgumentException("Error while parsing line " + reader.getLineNumber() + ".");
    }
}

Example 32 with Model

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

the class ByLabelOrAllInOneClustering method run.

@Override
public Clustering<Model> run(Database database) {
    // Prefer a true class label
    try {
        Relation<ClassLabel> relation = database.getRelation(TypeUtil.CLASSLABEL);
        return run(relation);
    } catch (NoSupportedDataTypeException e) {
    // Ignore.
    }
    try {
        Relation<ClassLabel> relation = database.getRelation(TypeUtil.GUESSED_LABEL);
        return run(relation);
    } catch (NoSupportedDataTypeException e) {
    // Ignore.
    }
    final DBIDs ids = database.getRelation(TypeUtil.ANY).getDBIDs();
    Clustering<Model> result = new Clustering<>("All-in-one trivial Clustering", "allinone-clustering");
    Cluster<Model> c = new Cluster<Model>(ids, ClusterModel.CLUSTER);
    result.addToplevelCluster(c);
    return result;
}

Example 33 with Model

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

the class TrivialAllNoise method run.

public Clustering<Model> run(Relation<?> relation) {
    final DBIDs ids = relation.getDBIDs();
    Clustering<Model> result = new Clustering<>("All-in-noise trivial Clustering", "allinnoise-clustering");
    Cluster<Model> c = new Cluster<Model>(ids, true, ClusterModel.CLUSTER);
    result.addToplevelCluster(c);
    return result;
}

Example 34 with Model

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

the class TrivialAllInOne method run.

public Clustering<Model> run(Relation<?> relation) {
    final DBIDs ids = relation.getDBIDs();
    Clustering<Model> result = new Clustering<>("All-in-one trivial Clustering", "allinone-clustering");
    Cluster<Model> c = new Cluster<Model>(ids, ClusterModel.CLUSTER);
    result.addToplevelCluster(c);
    return result;
}

Example 35 with Model

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

the class CASH method doRun.

/**
 * Runs the CASH algorithm on the specified database, this method is
 * recursively called until only noise is left.
 *
 * @param relation the Relation to run the CASH algorithm on
 * @param progress the progress object for verbose messages
 * @return a mapping of subspace dimensionalities to clusters
 */
private Clustering<Model> doRun(Relation<ParameterizationFunction> relation, FiniteProgress progress) {
    Clustering<Model> res = new Clustering<>("CASH clustering", "cash-clustering");
    final int dim = dimensionality(relation);
    // init heap
    ObjectHeap<IntegerPriorityObject<CASHInterval>> heap = new ComparableMinHeap<>();
    ModifiableDBIDs noiseIDs = DBIDUtil.newHashSet(relation.getDBIDs());
    initHeap(heap, relation, dim, noiseIDs);
    if (LOG.isVerbose()) {
        LOG.verbose(new StringBuilder().append("dim ").append(dim).append(" database.size ").append(relation.size()).toString());
    }
    // get the ''best'' d-dimensional intervals at max level
    while (!heap.isEmpty()) {
        CASHInterval interval = determineNextIntervalAtMaxLevel(heap);
        if (LOG.isVerbose()) {
            LOG.verbose("next interval in dim " + dim + ": " + interval);
        }
        // only noise left
        if (interval == null) {
            break;
        }
        // do a dim-1 dimensional run
        ModifiableDBIDs clusterIDs = DBIDUtil.newHashSet();
        if (dim > minDim + 1) {
            ModifiableDBIDs ids;
            double[][] basis_dim_minus_1;
            if (adjust) {
                ids = DBIDUtil.newHashSet();
                basis_dim_minus_1 = runDerivator(relation, dim, interval, ids);
            } else {
                ids = interval.getIDs();
                basis_dim_minus_1 = determineBasis(SpatialUtil.centroid(interval));
            }
            if (ids.size() != 0) {
                MaterializedRelation<ParameterizationFunction> db = buildDB(dim, basis_dim_minus_1, ids, relation);
                // add result of dim-1 to this result
                Clustering<Model> res_dim_minus_1 = doRun(db, progress);
                for (Cluster<Model> cluster : res_dim_minus_1.getAllClusters()) {
                    res.addToplevelCluster(cluster);
                    noiseIDs.removeDBIDs(cluster.getIDs());
                    clusterIDs.addDBIDs(cluster.getIDs());
                    processedIDs.addDBIDs(cluster.getIDs());
                }
            }
        } else // dim == minDim
        {
            LinearEquationSystem les = runDerivator(relation, dim - 1, interval.getIDs());
            Cluster<Model> c = new Cluster<Model>(interval.getIDs(), new LinearEquationModel(les));
            res.addToplevelCluster(c);
            noiseIDs.removeDBIDs(interval.getIDs());
            clusterIDs.addDBIDs(interval.getIDs());
            processedIDs.addDBIDs(interval.getIDs());
        }
        // Rebuild heap
        ArrayList<IntegerPriorityObject<CASHInterval>> heapVector = new ArrayList<>(heap.size());
        for (ObjectHeap.UnsortedIter<IntegerPriorityObject<CASHInterval>> iter = heap.unsortedIter(); iter.valid(); iter.advance()) {
            heapVector.add(iter.get());
        }
        heap.clear();
        for (IntegerPriorityObject<CASHInterval> pair : heapVector) {
            CASHInterval currentInterval = pair.getObject();
            currentInterval.removeIDs(clusterIDs);
            if (currentInterval.getIDs().size() >= minPts) {
                heap.add(new IntegerPriorityObject<>(currentInterval.priority(), currentInterval));
            }
        }
        if (progress != null) {
            progress.setProcessed(processedIDs.size(), LOG);
        }
    }
    // put noise to clusters
    if (!noiseIDs.isEmpty()) {
        if (dim == noiseDim) {
            res.addToplevelCluster(new Cluster<Model>(noiseIDs, true, ClusterModel.CLUSTER));
            processedIDs.addDBIDs(noiseIDs);
        } else if (noiseIDs.size() >= minPts) {
            LinearEquationSystem les = runDerivator(fulldatabase, dim - 1, noiseIDs);
            res.addToplevelCluster(new Cluster<Model>(noiseIDs, true, new LinearEquationModel(les)));
            processedIDs.addDBIDs(noiseIDs);
        }
    }
    if (LOG.isDebugging()) {
        StringBuilder msg = new StringBuilder();
        msg.append("noise fuer dim ").append(dim).append(": ").append(noiseIDs.size());
        for (Cluster<Model> c : res.getAllClusters()) {
            if (c.getModel() instanceof LinearEquationModel) {
                msg.append("\n Cluster: Dim: ").append(((LinearEquationModel) c.getModel()).getLes().subspacedim());
            } else {
                msg.append("\n Cluster: ").append(c.getModel().getClass().getName());
            }
            msg.append(" size: ").append(c.size());
        }
        LOG.debugFine(msg.toString());
    }
    if (progress != null) {
        progress.setProcessed(processedIDs.size(), LOG);
    }
    return res;
}