Examples with AbortException de.lmu.ifi.dbs.elki.utilities.exceptions.AbortException used on opensource projects

Example 41 with AbortException

use of de.lmu.ifi.dbs.elki.utilities.exceptions.AbortException in project elki by elki-project.

the class ComputeKNNOutlierScores method run.

@Override
public void run() {
    final Database database = inputstep.getDatabase();
    final Relation<O> relation = database.getRelation(distf.getInputTypeRestriction());
    // Ensure we don't go beyond the relation size:
    final int maxk = Math.min(this.maxk, relation.size() - 1);
    // Get a KNN query.
    final int lim = Math.min(maxk + 2, relation.size());
    KNNQuery<O> knnq = QueryUtil.getKNNQuery(relation, distf, lim);
    // Precompute kNN:
    if (!(knnq instanceof PreprocessorKNNQuery)) {
        MaterializeKNNPreprocessor<O> preproc = new MaterializeKNNPreprocessor<>(relation, distf, lim);
        preproc.initialize();
        relation.getHierarchy().add(relation, preproc);
    }
    // Test that we now get a proper index query
    knnq = QueryUtil.getKNNQuery(relation, distf, lim);
    if (!(knnq instanceof PreprocessorKNNQuery)) {
        throw new AbortException("Not using preprocessor knn query -- KNN queries using class: " + knnq.getClass());
    }
    // Warn for some known slow methods and large k:
    if (!isDisabled("LDOF") && maxk > 100) {
        LOG.verbose("Note: LODF needs O(k^2) distance computations. Use -" + Parameterizer.DISABLE_ID.getName() + " LDOF to disable.");
    }
    if (!isDisabled("FastABOD") && maxk > 100) {
        LOG.warning("Note: FastABOD needs quadratic memory. Use -" + Parameterizer.DISABLE_ID.getName() + " FastABOD to disable.");
    }
    if (!isDisabled("DWOF") && maxk > 100) {
        LOG.warning("Note: DWOF needs O(k^2) distance computations. Use -" + Parameterizer.DISABLE_ID.getName() + " DWOF to disable.");
    }
    final DBIDs ids = relation.getDBIDs();
    try (PrintStream fout = new PrintStream(outfile)) {
        // Control: print the DBIDs in case we are seeing an odd iteration
        // 
        fout.append("# Data set size: " + relation.size()).append(" data type: " + relation.getDataTypeInformation()).append(FormatUtil.NEWLINE);
        // Label outlier result (reference)
        writeResult(fout, ids, bylabel.run(database), new IdentityScaling(), "bylabel");
        final int startk = (this.startk > 0) ? this.startk : this.stepk;
        final int startkmin2 = (startk >= 2) ? startk : (startk + stepk);
        final int startkmin3 = (startk >= 3) ? startk : (startkmin2 >= 3) ? startkmin2 : (startkmin2 + stepk);
        // Output function:
        BiConsumer<String, OutlierResult> out = (kstr, result) -> writeResult(fout, ids, result, scaling, kstr);
        // KNN
        runForEachK(// 
        "KNN", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new KNNOutlier<O>(distf, k).run(database, relation), out);
        // KNN Weight
        runForEachK(// 
        "KNNW", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new KNNWeightOutlier<O>(distf, k).run(database, relation), out);
        // Run LOF
        runForEachK(// 
        "LOF", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new LOF<O>(k, distf).run(database, relation), out);
        // Run Simplified-LOF
        runForEachK(// 
        "SimplifiedLOF", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new SimplifiedLOF<O>(k, distf).run(database, relation), out);
        // LoOP
        runForEachK(// 
        "LoOP", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new LoOP<O>(k, k, distf, distf, 1.0).run(database, relation), out);
        // LDOF
        runForEachK(// 
        "LDOF", // 
        startkmin2, // 
        stepk, // 
        maxk, k -> // 
        new LDOF<O>(distf, k).run(database, relation), out);
        // Run ODIN
        runForEachK(// 
        "ODIN", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new ODIN<O>(distf, k).run(database, relation), out);
        // Run FastABOD
        runForEachK(// 
        "FastABOD", // 
        startkmin3, // 
        stepk, // 
        maxk, k -> // 
        new FastABOD<O>(new PolynomialKernelFunction(2), k).run(database, relation), out);
        // Run KDEOS with intrinsic dimensionality 2.
        runForEachK(// 
        "KDEOS", // 
        startkmin2, // 
        stepk, // 
        maxk, k -> new // 
        KDEOS<O>(// 
        distf, // 
        k, // 
        k, // 
        GaussianKernelDensityFunction.KERNEL, // 
        0., 0.5 * GaussianKernelDensityFunction.KERNEL.canonicalBandwidth(), // 
        2).run(database, relation), out);
        // Run LDF
        runForEachK(// 
        "LDF", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new LDF<O>(k, distf, GaussianKernelDensityFunction.KERNEL, 1., .1).run(database, relation), out);
        // Run INFLO
        runForEachK(// 
        "INFLO", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new INFLO<O>(distf, 1.0, k).run(database, relation), out);
        // Run COF
        runForEachK(// 
        "COF", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new COF<O>(k, distf).run(database, relation), out);
        // Run simple Intrinsic dimensionality
        runForEachK(// 
        "Intrinsic", // 
        startkmin2, // 
        stepk, // 
        maxk, k -> // 
        new IntrinsicDimensionalityOutlier<O>(distf, k, AggregatedHillEstimator.STATIC).run(database, relation), out);
        // Run IDOS
        runForEachK(// 
        "IDOS", // 
        startkmin2, // 
        stepk, // 
        maxk, k -> // 
        new IDOS<O>(distf, AggregatedHillEstimator.STATIC, k, k).run(database, relation), out);
        // Run simple kernel-density LOF variant
        runForEachK(// 
        "KDLOF", // 
        startkmin2, // 
        stepk, // 
        maxk, k -> // 
        new SimpleKernelDensityLOF<O>(k, distf, GaussianKernelDensityFunction.KERNEL).run(database, relation), out);
        // Run DWOF (need pairwise distances, too)
        runForEachK(// 
        "DWOF", // 
        startkmin2, // 
        stepk, // 
        maxk, k -> // 
        new DWOF<O>(distf, k, 1.1).run(database, relation), out);
        // Run LIC
        runForEachK(// 
        "LIC", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new LocalIsolationCoefficient<O>(distf, k).run(database, relation), out);
        // Run VOV (requires a vector field).
        if (TypeUtil.DOUBLE_VECTOR_FIELD.isAssignableFromType(relation.getDataTypeInformation())) {
            @SuppressWarnings("unchecked") final DistanceFunction<? super DoubleVector> df = (DistanceFunction<? super DoubleVector>) distf;
            @SuppressWarnings("unchecked") final Relation<DoubleVector> rel = (Relation<DoubleVector>) (Relation<?>) relation;
            runForEachK(// 
            "VOV", // 
            startk, // 
            stepk, // 
            maxk, k -> // 
            new VarianceOfVolume<DoubleVector>(k, df).run(database, rel), out);
        }
        // Run KNN DD
        runForEachK(// 
        "KNNDD", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new KNNDD<O>(distf, k).run(database, relation), out);
        // Run KNN SOS
        runForEachK(// 
        "KNNSOS", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new KNNSOS<O>(distf, k).run(relation), out);
        // Run ISOS
        runForEachK(// 
        "ISOS", // 
        startkmin2, // 
        stepk, // 
        maxk, k -> // 
        new ISOS<O>(distf, k, AggregatedHillEstimator.STATIC).run(relation), out);
    } catch (FileNotFoundException e) {
        throw new AbortException("Cannot create output file.", e);
    }
}

Example 42 with AbortException

use of de.lmu.ifi.dbs.elki.utilities.exceptions.AbortException in project elki by elki-project.

the class EvaluatePrecomputedOutlierScores method processRow.

private void processRow(PrintStream fout, NumberVector vec, String label) {
    if (checkForNaNs(vec)) {
        LOG.warning("NaN value encountered in vector " + label);
        return;
    }
    if (positive == null) {
        if (!label.matches("bylabel")) {
            throw new AbortException("No 'by label' reference outlier found, which is needed for evaluation!");
        }
        positive = new VectorNonZero(vec);
        endcg = NDCGEvaluation.STATIC.expected(positive.numPositive(), positive.getDimensionality());
        return;
    }
    AbstractVectorIter iter = reverse.matcher(label).find() ? new IncreasingVectorIter(vec) : new DecreasingVectorIter(vec);
    double rate = positive.numPositive() / (double) positive.getDimensionality();
    double auc = ROCEvaluation.STATIC.evaluate(positive, iter.seek(0));
    double avep = AveragePrecisionEvaluation.STATIC.evaluate(positive, iter.seek(0));
    double rprecision = PrecisionAtKEvaluation.RPRECISION.evaluate(positive, iter.seek(0));
    double maxf1 = MaximumF1Evaluation.STATIC.evaluate(positive, iter.seek(0));
    double dcg = DCGEvaluation.STATIC.evaluate(positive, iter.seek(0));
    double ndcg = NDCGEvaluation.STATIC.evaluate(positive, iter.seek(0));
    double adjauc = 2 * auc - 1;
    double adjrprecision = (rprecision - rate) / (1 - rate);
    double adjavep = (avep - rate) / (1 - rate);
    double adjmaxf1 = (maxf1 - rate) / (1 - rate);
    double adjdcg = (ndcg - endcg) / (1 - endcg);
    final int p = label.lastIndexOf('-');
    String prefix = label.substring(0, p);
    int k = Integer.valueOf(label.substring(p + 1));
    // Write CSV
    if (name != null) {
        fout.append('"').append(name).append("\",");
    }
    fout.append('"').append(prefix).append('"');
    fout.append(',').append(Integer.toString(k));
    fout.append(',').append(Double.toString(auc));
    fout.append(',').append(Double.toString(avep));
    fout.append(',').append(Double.toString(rprecision));
    fout.append(',').append(Double.toString(maxf1));
    fout.append(',').append(Double.toString(dcg));
    fout.append(',').append(Double.toString(ndcg));
    fout.append(',').append(Double.toString(adjauc));
    fout.append(',').append(Double.toString(adjavep));
    fout.append(',').append(Double.toString(adjrprecision));
    fout.append(',').append(Double.toString(adjmaxf1));
    fout.append(',').append(Double.toString(adjdcg));
    fout.append('\n');
}

Example 43 with AbortException

use of de.lmu.ifi.dbs.elki.utilities.exceptions.AbortException in project elki by elki-project.

the class EvaluatePrecomputedOutlierScores method run.

@Override
public void run() {
    try (// 
    FileInputStream fis = new FileInputStream(infile);
        // 
        InputStream is = new BufferedInputStream(FileUtil.tryGzipInput(fis));
        FileOutputStream fosResult = new FileOutputStream(outfile, true);
        PrintStream fout = new PrintStream(fosResult);
        FileChannel chan = fosResult.getChannel()) {
        // Setup the input stream.
        parser.initStream(is);
        // Lock the output file:
        chan.lock();
        if (chan.position() == 0L) {
            writeHeader(fout);
        } else {
            LOG.info("Appending to existing output " + outfile);
        }
        int lcol = -1, dcol = -1;
        loop: while (true) {
            BundleStreamSource.Event ev = parser.nextEvent();
            switch(ev) {
                case END_OF_STREAM:
                    break loop;
                case META_CHANGED:
                    BundleMeta meta = parser.getMeta();
                    lcol = -1;
                    dcol = -1;
                    for (int i = 0; i < meta.size(); i++) {
                        SimpleTypeInformation<?> m = meta.get(i);
                        if (TypeUtil.NUMBER_VECTOR_VARIABLE_LENGTH.isAssignableFromType(m)) {
                            if (dcol >= 0) {
                                throw new AbortException("More than one vector column.");
                            }
                            dcol = i;
                        } else if (TypeUtil.GUESSED_LABEL.isAssignableFromType(m)) {
                            if (lcol >= 0) {
                                throw new AbortException("More than one label column.");
                            }
                            lcol = i;
                        } else {
                            throw new AbortException("Unexpected data column type: " + m);
                        }
                    }
                    break;
                case NEXT_OBJECT:
                    if (lcol < 0) {
                        throw new AbortException("No label column available.");
                    }
                    if (dcol < 0) {
                        throw new AbortException("No vector column available.");
                    }
                    processRow(fout, (NumberVector) parser.data(dcol), parser.data(lcol).toString());
                    break;
            }
        }
    } catch (IOException e) {
        throw new AbortException("IO error.", e);
    }
}

Example 44 with AbortException

use of de.lmu.ifi.dbs.elki.utilities.exceptions.AbortException in project elki by elki-project.

the class EvaluateRetrievalPerformance method run.

/**
 * Run the algorithm
 *
 * @param database Database to run on (for kNN queries)
 * @param relation Relation for distance computations
 * @param lrelation Relation for class label comparison
 * @return Vectors containing mean and standard deviation.
 */
public RetrievalPerformanceResult run(Database database, Relation<O> relation, Relation<?> lrelation) {
    final DistanceQuery<O> distQuery = database.getDistanceQuery(relation, getDistanceFunction());
    final DBIDs ids = DBIDUtil.randomSample(relation.getDBIDs(), sampling, random);
    // For storing the positive neighbors.
    ModifiableDBIDs posn = DBIDUtil.newHashSet();
    // Distance storage.
    ModifiableDoubleDBIDList nlist = DBIDUtil.newDistanceDBIDList(relation.size());
    // For counting labels seen in kNN
    Object2IntOpenHashMap<Object> counters = new Object2IntOpenHashMap<>();
    // Statistics tracking
    double map = 0., mroc = 0.;
    double[] knnperf = new double[maxk];
    int samples = 0;
    FiniteProgress objloop = LOG.isVerbose() ? new FiniteProgress("Processing query objects", ids.size(), LOG) : null;
    for (DBIDIter iter = ids.iter(); iter.valid(); iter.advance()) {
        Object label = lrelation.get(iter);
        findMatches(posn, lrelation, label);
        if (posn.size() > 0) {
            computeDistances(nlist, iter, distQuery, relation);
            if (nlist.size() != relation.size() - (includeSelf ? 0 : 1)) {
                LOG.warning("Neighbor list does not have the desired size: " + nlist.size());
            }
            map += AveragePrecisionEvaluation.STATIC.evaluate(posn, nlist);
            mroc += ROCEvaluation.STATIC.evaluate(posn, nlist);
            KNNEvaluator.STATIC.evaluateKNN(knnperf, nlist, lrelation, counters, label);
            samples += 1;
        }
        LOG.incrementProcessed(objloop);
    }
    LOG.ensureCompleted(objloop);
    if (samples < 1) {
        throw new AbortException("No object matched - are labels parsed correctly?");
    }
    if (!(map >= 0) || !(mroc >= 0)) {
        throw new AbortException("NaN in MAP/ROC.");
    }
    map /= samples;
    mroc /= samples;
    LOG.statistics(new DoubleStatistic(PREFIX + ".map", map));
    LOG.statistics(new DoubleStatistic(PREFIX + ".rocauc", mroc));
    LOG.statistics(new DoubleStatistic(PREFIX + ".samples", samples));
    for (int k = 0; k < maxk; k++) {
        knnperf[k] = knnperf[k] / samples;
        LOG.statistics(new DoubleStatistic(PREFIX + ".knn-" + (k + 1), knnperf[k]));
    }
    return new RetrievalPerformanceResult(samples, map, mroc, knnperf);
}

Example 45 with AbortException

use of de.lmu.ifi.dbs.elki.utilities.exceptions.AbortException in project elki by elki-project.

the class HopkinsStatisticClusteringTendency method initializeDataExtends.

/**
 * Initialize the uniform sampling area.
 *
 * @param relation Data relation
 * @param dim Dimensionality
 * @param min Minima output array (preallocated!)
 * @param extend Data extend output array (preallocated!)
 */
protected void initializeDataExtends(Relation<NumberVector> relation, int dim, double[] min, double[] extend) {
    assert (min.length == dim && extend.length == dim);
    // from dataset
    if (minima == null || maxima == null || minima.length == 0 || maxima.length == 0) {
        double[][] minmax = RelationUtil.computeMinMax(relation);
        final double[] dmin = minmax[0], dmax = minmax[1];
        for (int d = 0; d < dim; d++) {
            min[d] = dmin[d];
            extend[d] = dmax[d] - dmin[d];
        }
        return;
    }
    if (minima.length == dim) {
        System.arraycopy(minima, 0, min, 0, dim);
    } else if (minima.length == 1) {
        Arrays.fill(min, minima[0]);
    } else {
        throw new AbortException("Invalid minima specified: expected " + dim + " got minima dimensionality: " + minima.length);
    }
    if (maxima.length == dim) {
        for (int d = 0; d < dim; d++) {
            extend[d] = maxima[d] - min[d];
        }
        return;
    } else if (maxima.length == 1) {
        for (int d = 0; d < dim; d++) {
            extend[d] = maxima[0] - min[d];
        }
        return;
    } else {
        throw new AbortException("Invalid maxima specified: expected " + dim + " got maxima dimensionality: " + maxima.length);
    }
}