Examples with TreeTargetNumericColumnData org.knime.base.node.mine.treeensemble2.data.TreeTargetNumericColumnData used on opensource projects

Example 11 with TreeTargetNumericColumnData

use of org.knime.base.node.mine.treeensemble2.data.TreeTargetNumericColumnData in project knime-core by knime.

the class AbstractGradientBoostingLearner method createResidualDataFromArray.

/**
 * Creates a {@link TreeData} object that uses the values in <b>residualData</b> as target.
 *
 * @param residualData array containing the residuals
 * @param actualData the TreeData as it is provided by the user
 * @return data using the residuals as targets
 */
protected TreeData createResidualDataFromArray(final double[] residualData, final TreeData actualData) {
    TreeTargetNumericColumnData actual = (TreeTargetNumericColumnData) actualData.getTargetColumn();
    RowKey[] rowKeysAsArray = new RowKey[actual.getNrRows()];
    for (int i = 0; i < rowKeysAsArray.length; i++) {
        rowKeysAsArray[i] = actual.getRowKeyFor(i);
    }
    TreeTargetNumericColumnMetaData metaData = actual.getMetaData();
    TreeTargetNumericColumnData residualTarget = new TreeTargetNumericColumnData(metaData, rowKeysAsArray, residualData);
    return new TreeData(getData().getColumns(), residualTarget, getData().getTreeType());
}

Example 12 with TreeTargetNumericColumnData

use of org.knime.base.node.mine.treeensemble2.data.TreeTargetNumericColumnData in project knime-core by knime.

the class MGradientBoostedTreesLearner method learn.

/**
 * {@inheritDoc}
 */
@Override
public AbstractGradientBoostingModel learn(final ExecutionMonitor exec) throws CanceledExecutionException {
    final TreeData actualData = getData();
    final GradientBoostingLearnerConfiguration config = getConfig();
    final int nrModels = config.getNrModels();
    final TreeTargetNumericColumnData actualTarget = getTarget();
    final double initialValue = actualTarget.getMedian();
    final ArrayList<TreeModelRegression> models = new ArrayList<TreeModelRegression>(nrModels);
    final ArrayList<Map<TreeNodeSignature, Double>> coefficientMaps = new ArrayList<Map<TreeNodeSignature, Double>>(nrModels);
    final double[] previousPrediction = new double[actualTarget.getNrRows()];
    Arrays.fill(previousPrediction, initialValue);
    final RandomData rd = config.createRandomData();
    final double alpha = config.getAlpha();
    TreeNodeSignatureFactory signatureFactory = null;
    final int maxLevels = config.getMaxLevels();
    // this should be the default
    if (maxLevels < TreeEnsembleLearnerConfiguration.MAX_LEVEL_INFINITE) {
        final int capacity = IntMath.pow(2, maxLevels - 1);
        signatureFactory = new TreeNodeSignatureFactory(capacity);
    } else {
        signatureFactory = new TreeNodeSignatureFactory();
    }
    exec.setMessage("Learning model");
    TreeData residualData;
    for (int i = 0; i < nrModels; i++) {
        final double[] residuals = new double[actualTarget.getNrRows()];
        for (int j = 0; j < actualTarget.getNrRows(); j++) {
            residuals[j] = actualTarget.getValueFor(j) - previousPrediction[j];
        }
        final double quantile = calculateAlphaQuantile(residuals, alpha);
        final double[] gradients = new double[residuals.length];
        for (int j = 0; j < gradients.length; j++) {
            gradients[j] = Math.abs(residuals[j]) <= quantile ? residuals[j] : quantile * Math.signum(residuals[j]);
        }
        residualData = createResidualDataFromArray(gradients, actualData);
        final RandomData rdSingle = TreeEnsembleLearnerConfiguration.createRandomData(rd.nextLong(Long.MIN_VALUE, Long.MAX_VALUE));
        final RowSample rowSample = getRowSampler().createRowSample(rdSingle);
        final TreeLearnerRegression treeLearner = new TreeLearnerRegression(getConfig(), residualData, getIndexManager(), signatureFactory, rdSingle, rowSample);
        final TreeModelRegression tree = treeLearner.learnSingleTree(exec, rdSingle);
        final Map<TreeNodeSignature, Double> coefficientMap = calcCoefficientMap(residuals, quantile, tree);
        adaptPreviousPrediction(previousPrediction, tree, coefficientMap);
        models.add(tree);
        coefficientMaps.add(coefficientMap);
        exec.setProgress(((double) i) / nrModels, "Finished level " + i + "/" + nrModels);
    }
    return new GradientBoostedTreesModel(getConfig(), actualData.getMetaData(), models.toArray(new TreeModelRegression[models.size()]), actualData.getTreeType(), initialValue, coefficientMaps);
}

Example 13 with TreeTargetNumericColumnData

use of org.knime.base.node.mine.treeensemble2.data.TreeTargetNumericColumnData in project knime-core by knime.

the class TreeNumericColumnDataTest method testCalcBestSplitRegression.

@Test
public void testCalcBestSplitRegression() throws InvalidSettingsException {
    String dataCSV = "1,2,3,4,5,6,7,8,9,10";
    String targetCSV = "1,5,4,4.3,6.5,6.5,4,3,3,4";
    TreeEnsembleLearnerConfiguration config = new TreeEnsembleLearnerConfiguration(true);
    config.setNrModels(1);
    config.setDataSelectionWithReplacement(false);
    config.setUseDifferentAttributesAtEachNode(false);
    config.setDataFractionPerTree(1.0);
    config.setColumnSamplingMode(ColumnSamplingMode.None);
    TestDataGenerator dataGen = new TestDataGenerator(config);
    RandomData rd = config.createRandomData();
    TreeTargetNumericColumnData target = TestDataGenerator.createNumericTargetColumn(targetCSV);
    TreeNumericColumnData attribute = dataGen.createNumericAttributeColumn(dataCSV, "test-col", 0);
    TreeData data = new TreeData(new TreeAttributeColumnData[] { attribute }, target, TreeType.Ordinary);
    double[] weights = new double[10];
    Arrays.fill(weights, 1.0);
    DataMemberships rootMem = new RootDataMemberships(weights, data, new DefaultDataIndexManager(data));
    SplitCandidate firstSplit = attribute.calcBestSplitRegression(rootMem, target.getPriors(rootMem, config), target, rd);
    // calculated via OpenOffice calc
    assertEquals(10.885444, firstSplit.getGainValue(), 1e-5);
    TreeNodeCondition[] firstConditions = firstSplit.getChildConditions();
    assertEquals(2, firstConditions.length);
    for (int i = 0; i < firstConditions.length; i++) {
        assertThat(firstConditions[i], instanceOf(TreeNodeNumericCondition.class));
        TreeNodeNumericCondition numCond = (TreeNodeNumericCondition) firstConditions[i];
        assertEquals(1.5, numCond.getSplitValue(), 0);
    }
    // left child contains only one row therefore only look at right child
    BitSet expectedInChild = new BitSet(10);
    expectedInChild.set(1, 10);
    BitSet inChild = attribute.updateChildMemberships(firstConditions[1], rootMem);
    assertEquals(expectedInChild, inChild);
    DataMemberships childMem = rootMem.createChildMemberships(inChild);
    SplitCandidate secondSplit = attribute.calcBestSplitRegression(childMem, target.getPriors(childMem, config), target, rd);
    assertEquals(6.883555, secondSplit.getGainValue(), 1e-5);
    TreeNodeCondition[] secondConditions = secondSplit.getChildConditions();
    for (int i = 0; i < secondConditions.length; i++) {
        assertThat(secondConditions[i], instanceOf(TreeNodeNumericCondition.class));
        TreeNodeNumericCondition numCond = (TreeNodeNumericCondition) secondConditions[i];
        assertEquals(6.5, numCond.getSplitValue(), 0);
    }
}

Example 14 with TreeTargetNumericColumnData

use of org.knime.base.node.mine.treeensemble2.data.TreeTargetNumericColumnData in project knime-core by knime.

the class TreeTargetNumericColumnDataTest method testGetPriors.

/**
 * Tests the {@link TreeTargetNumericColumnData#getPriors(DataMemberships, TreeEnsembleLearnerConfiguration)} and
 * {@link TreeTargetNumericColumnData#getPriors(double[], TreeEnsembleLearnerConfiguration)} methods.
 */
@Test
public void testGetPriors() {
    String targetCSV = "1,4,3,5,6,7,8,12,22,1";
    // irrelevant but necessary to build TreeDataObject
    String someAttributeCSV = "A,B,A,B,A,A,B,A,A,B";
    TreeEnsembleLearnerConfiguration config = new TreeEnsembleLearnerConfiguration(true);
    TestDataGenerator dataGen = new TestDataGenerator(config);
    TreeTargetNumericColumnData target = TestDataGenerator.createNumericTargetColumn(targetCSV);
    TreeNominalColumnData attribute = dataGen.createNominalAttributeColumn(someAttributeCSV, "test-col", 0);
    TreeData data = new TreeData(new TreeAttributeColumnData[] { attribute }, target, TreeType.Ordinary);
    double[] weights = new double[10];
    Arrays.fill(weights, 1.0);
    DataMemberships rootMem = new RootDataMemberships(weights, data, new DefaultDataIndexManager(data));
    RegressionPriors datMemPriors = target.getPriors(rootMem, config);
    assertEquals(6.9, datMemPriors.getMean(), DELTA);
    assertEquals(69, datMemPriors.getYSum(), DELTA);
    assertEquals(352.9, datMemPriors.getSumSquaredDeviation(), DELTA);
}

Example 15 with TreeTargetNumericColumnData

use of org.knime.base.node.mine.treeensemble2.data.TreeTargetNumericColumnData in project knime-core by knime.

the class TreeNominalColumnDataTest method testCalcBestSplitRegressionMultiway.

/**
 * Tests the method
 * {@link TreeNominalColumnData#calcBestSplitRegression(DataMemberships, RegressionPriors, TreeTargetNumericColumnData, RandomData)}
 * using multiway splits.
 *
 * @throws Exception
 */
@Test
public void testCalcBestSplitRegressionMultiway() throws Exception {
    TreeEnsembleLearnerConfiguration config = createConfig(true);
    config.setUseBinaryNominalSplits(false);
    Pair<TreeNominalColumnData, TreeTargetNumericColumnData> tennisDataRegression = tennisDataRegression(config);
    TreeNominalColumnData columnData = tennisDataRegression.getFirst();
    TreeTargetNumericColumnData targetData = tennisDataRegression.getSecond();
    TreeData treeData = createTreeDataRegression(tennisDataRegression);
    double[] rowWeights = new double[SMALL_COLUMN_DATA.length];
    Arrays.fill(rowWeights, 1.0);
    IDataIndexManager indexManager = new DefaultDataIndexManager(treeData);
    DataMemberships dataMemberships = new RootDataMemberships(rowWeights, treeData, indexManager);
    RegressionPriors priors = targetData.getPriors(rowWeights, config);
    SplitCandidate splitCandidate = columnData.calcBestSplitRegression(dataMemberships, priors, targetData, null);
    assertNotNull(splitCandidate);
    assertThat(splitCandidate, instanceOf(NominalMultiwaySplitCandidate.class));
    assertFalse(splitCandidate.canColumnBeSplitFurther());
    assertEquals(36.9643, splitCandidate.getGainValue(), 0.0001);
    NominalMultiwaySplitCandidate multiwaySplitCandidate = (NominalMultiwaySplitCandidate) splitCandidate;
    TreeNodeNominalCondition[] childConditions = multiwaySplitCandidate.getChildConditions();
    assertEquals(3, childConditions.length);
    assertEquals("S", childConditions[0].getValue());
    assertEquals("O", childConditions[1].getValue());
    assertEquals("R", childConditions[2].getValue());
}