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

Example 6 with TreeTargetNumericColumnData

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

the class LKGradientBoostedTreesLearner method calculateCoefficientMap.

private Map<TreeNodeSignature, Double> calculateCoefficientMap(final TreeModelRegression tree, final TreeData pseudoResiduals, final double numClasses) {
    final List<TreeNodeRegression> leafs = tree.getLeafs();
    final Map<TreeNodeSignature, Double> coefficientMap = new HashMap<TreeNodeSignature, Double>();
    final TreeTargetNumericColumnData pseudoTarget = (TreeTargetNumericColumnData) pseudoResiduals.getTargetColumn();
    double learningRate = getConfig().getLearningRate();
    for (TreeNodeRegression leaf : leafs) {
        final int[] indices = leaf.getRowIndicesInTreeData();
        double sumTop = 0;
        double sumBottom = 0;
        for (int index : indices) {
            double val = pseudoTarget.getValueFor(index);
            sumTop += val;
            double absVal = Math.abs(val);
            sumBottom += Math.abs(absVal) * (1 - Math.abs(absVal));
        }
        final double coefficient = (numClasses - 1) / numClasses * (sumTop / sumBottom);
        coefficientMap.put(leaf.getSignature(), learningRate * coefficient);
    }
    return coefficientMap;
}

Example 7 with TreeTargetNumericColumnData

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

the class LKGradientBoostedTreesLearner method createNumericDataFromArray.

private TreeData createNumericDataFromArray(final double[] numericData) {
    TreeData data = getData();
    TreeTargetNominalColumnData nominalTarget = (TreeTargetNominalColumnData) data.getTargetColumn();
    TreeTargetNumericColumnMetaData newMeta = new TreeTargetNumericColumnMetaData(nominalTarget.getMetaData().getAttributeName());
    TreeTargetNumericColumnData newTarget = new TreeTargetNumericColumnData(newMeta, nominalTarget.getRowKeys(), numericData);
    return new TreeData(data.getColumns(), newTarget, data.getTreeType());
}

Example 8 with TreeTargetNumericColumnData

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

the class TreeNominalColumnDataTest method testCalcBestSplitRegressionBinaryXGBoostMissingValueHandling.

/**
 * Tests the XGBoost missing value handling in case of a regression with binary splits.
 *
 * @throws Exception
 */
@Test
public void testCalcBestSplitRegressionBinaryXGBoostMissingValueHandling() throws Exception {
    final TreeEnsembleLearnerConfiguration config = createConfig(true);
    config.setMissingValueHandling(MissingValueHandling.XGBoost);
    final TestDataGenerator dataGen = new TestDataGenerator(config);
    final String noMissingCSV = "A, A, A, B, B, B, B, C, C";
    final String noMissingsTarget = "1, 2, 2, 7, 6, 5, 2, 3, 1";
    TreeNominalColumnData dataCol = dataGen.createNominalAttributeColumn(noMissingCSV, "noMissings", 0);
    TreeTargetNumericColumnData targetCol = TestDataGenerator.createNumericTargetColumn(noMissingsTarget);
    double[] weights = new double[9];
    Arrays.fill(weights, 1.0);
    int[] indices = new int[9];
    for (int i = 0; i < indices.length; i++) {
        indices[i] = i;
    }
    final RandomData rd = config.createRandomData();
    DataMemberships dataMemberships = new MockDataColMem(indices, indices, weights);
    // first test the case that there are no missing values during training (we still need to provide a missing value direction for prediction)
    SplitCandidate split = dataCol.calcBestSplitRegression(dataMemberships, targetCol.getPriors(weights, config), targetCol, rd);
    assertNotNull("SplitCandidate may not be null", split);
    assertThat(split, instanceOf(NominalBinarySplitCandidate.class));
    assertEquals("Wrong gain.", 22.755555, split.getGainValue(), 1e-5);
    assertTrue("No missing values in dataCol therefore the missedRows BitSet must be empty.", split.getMissedRows().isEmpty());
    NominalBinarySplitCandidate nomSplit = (NominalBinarySplitCandidate) split;
    TreeNodeNominalBinaryCondition[] conditions = nomSplit.getChildConditions();
    assertEquals("Binary split candidate must have two children.", 2, conditions.length);
    final String[] values = new String[] { "A", "C" };
    assertArrayEquals("Wrong values in split condition.", values, conditions[0].getValues());
    assertArrayEquals("Wrong values in split condition.", values, conditions[1].getValues());
    assertFalse("Missings should go with majority", conditions[0].acceptsMissings());
    assertTrue("Missings should go with majority", conditions[1].acceptsMissings());
    assertEquals("Wrong set logic.", SetLogic.IS_NOT_IN, conditions[0].getSetLogic());
    assertEquals("Wrong set logic.", SetLogic.IS_IN, conditions[1].getSetLogic());
    // test the case that there are missing values during training
    final String missingCSV = "A, A, A, B, B, B, B, C, C, ?";
    final String missingTarget = "1, 2, 2, 7, 6, 5, 2, 3, 1, 8";
    dataCol = dataGen.createNominalAttributeColumn(missingCSV, "missing", 0);
    targetCol = TestDataGenerator.createNumericTargetColumn(missingTarget);
    weights = new double[10];
    Arrays.fill(weights, 1.0);
    indices = new int[10];
    for (int i = 0; i < indices.length; i++) {
        indices[i] = i;
    }
    dataMemberships = new MockDataColMem(indices, indices, weights);
    split = dataCol.calcBestSplitRegression(dataMemberships, targetCol.getPriors(weights, config), targetCol, rd);
    assertNotNull("SplitCandidate may not be null.", split);
    assertThat(split, instanceOf(NominalBinarySplitCandidate.class));
    assertEquals("Wrong gain.", 36.1, split.getGainValue(), 1e-5);
    assertTrue("Conditions should handle missing values therefore the missedRows BitSet must be empty.", split.getMissedRows().isEmpty());
    nomSplit = (NominalBinarySplitCandidate) split;
    conditions = nomSplit.getChildConditions();
    assertEquals("Binary split candidate must have two children.", 2, conditions.length);
    assertArrayEquals("Wrong values in split condition.", values, conditions[0].getValues());
    assertArrayEquals("Wrong values in split condition.", values, conditions[1].getValues());
    assertTrue("Missings should go with B (because there target values are similar)", conditions[0].acceptsMissings());
    assertFalse("Missings should go with B (because there target values are similar)", conditions[1].acceptsMissings());
    assertEquals("Wrong set logic.", SetLogic.IS_NOT_IN, conditions[0].getSetLogic());
    assertEquals("Wrong set logic.", SetLogic.IS_IN, conditions[1].getSetLogic());
}

Example 9 with TreeTargetNumericColumnData

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

the class TreeNominalColumnDataTest method testCalcBestSplitRegressionMultiwayXGBoostMissingValueHandling.

/**
 * This method tests the XGBoost missing value handling in case of a regression task and multiway splits.
 *
 * @throws Exception
 */
@Test
public void testCalcBestSplitRegressionMultiwayXGBoostMissingValueHandling() throws Exception {
    final TreeEnsembleLearnerConfiguration config = createConfig(true);
    config.setMissingValueHandling(MissingValueHandling.XGBoost);
    config.setUseBinaryNominalSplits(false);
    final TestDataGenerator dataGen = new TestDataGenerator(config);
    final String noMissingCSV = "A, A, A, B, B, B, B, C, C";
    final String noMissingsTarget = "1, 2, 2, 7, 6, 5, 2, 3, 1";
    TreeNominalColumnData dataCol = dataGen.createNominalAttributeColumn(noMissingCSV, "noMissings", 0);
    TreeTargetNumericColumnData targetCol = TestDataGenerator.createNumericTargetColumn(noMissingsTarget);
    double[] weights = new double[9];
    Arrays.fill(weights, 1.0);
    int[] indices = new int[9];
    for (int i = 0; i < indices.length; i++) {
        indices[i] = i;
    }
    final RandomData rd = config.createRandomData();
    DataMemberships dataMemberships = new MockDataColMem(indices, indices, weights);
    // first test the case that there are no missing values during training (we still need to provide a missing value direction for prediction)
    SplitCandidate split = dataCol.calcBestSplitRegression(dataMemberships, targetCol.getPriors(weights, config), targetCol, rd);
    assertNotNull("SplitCandidate may not be null", split);
    assertThat(split, instanceOf(NominalMultiwaySplitCandidate.class));
    assertEquals("Wrong gain.", 22.888888, split.getGainValue(), 1e-5);
    assertTrue("No missing values in dataCol therefore the missedRows BitSet must be empty.", split.getMissedRows().isEmpty());
    NominalMultiwaySplitCandidate nomSplit = (NominalMultiwaySplitCandidate) split;
    TreeNodeNominalCondition[] conditions = nomSplit.getChildConditions();
    assertEquals("3 nominal values therefore there must be 3 children.", 3, conditions.length);
    assertEquals("Wrong value.", "A", conditions[0].getValue());
    assertEquals("Wrong value.", "B", conditions[1].getValue());
    assertEquals("Wrong value.", "C", conditions[2].getValue());
    assertFalse("Missings should go with majority", conditions[0].acceptsMissings());
    assertTrue("Missings should go with majority", conditions[1].acceptsMissings());
    assertFalse("Missings should go with majority", conditions[2].acceptsMissings());
    // test the case that there are missing values during training
    final String missingCSV = "A, A, A, B, B, B, B, C, C, ?";
    final String missingTarget = "1, 2, 2, 7, 6, 5, 2, 3, 1, 8";
    dataCol = dataGen.createNominalAttributeColumn(missingCSV, "missing", 0);
    targetCol = TestDataGenerator.createNumericTargetColumn(missingTarget);
    weights = new double[10];
    Arrays.fill(weights, 1.0);
    indices = new int[10];
    for (int i = 0; i < indices.length; i++) {
        indices[i] = i;
    }
    dataMemberships = new MockDataColMem(indices, indices, weights);
    split = dataCol.calcBestSplitRegression(dataMemberships, targetCol.getPriors(weights, config), targetCol, rd);
    assertNotNull("SplitCandidate may not be null.", split);
    assertThat(split, instanceOf(NominalMultiwaySplitCandidate.class));
    // assertEquals("Wrong gain.", 36.233333333, split.getGainValue(), 1e-5);
    assertTrue("Conditions should handle missing values therefore the missedRows BitSet must be empty.", split.getMissedRows().isEmpty());
    nomSplit = (NominalMultiwaySplitCandidate) split;
    conditions = nomSplit.getChildConditions();
    assertEquals("3 values (not counting missing values) therefore there must be 3 children.", 3, conditions.length);
    assertEquals("Wrong value.", "A", conditions[0].getValue());
    assertEquals("Wrong value.", "B", conditions[1].getValue());
    assertEquals("Wrong value.", "C", conditions[2].getValue());
    assertFalse("Missings should go with majority", conditions[0].acceptsMissings());
    assertTrue("Missings should go with majority", conditions[1].acceptsMissings());
    assertFalse("Missings should go with majority", conditions[2].acceptsMissings());
}

Example 10 with TreeTargetNumericColumnData

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

the class TreeBitVectorColumnData method calcBestSplitRegression.

/**
 * {@inheritDoc}
 */
@Override
public SplitCandidate calcBestSplitRegression(final DataMemberships dataMemberships, final RegressionPriors targetPriors, final TreeTargetNumericColumnData targetColumn, final RandomData rd) {
    final double ySumTotal = targetPriors.getYSum();
    final double nrRecordsTotal = targetPriors.getNrRecords();
    final double criterionTotal = ySumTotal * ySumTotal / nrRecordsTotal;
    final int minChildSize = getConfiguration().getMinChildSize();
    final ColumnMemberships columnMemberships = dataMemberships.getColumnMemberships(getMetaData().getAttributeIndex());
    double onWeights = 0.0;
    double offWeights = 0.0;
    double ySumOn = 0.0;
    double ySumOff = 0.0;
    while (columnMemberships.next()) {
        final double weight = columnMemberships.getRowWeight();
        if (weight < EPSILON) {
        // ignore record: not in current branch or not in sample
        } else {
            final double y = targetColumn.getValueFor(columnMemberships.getOriginalIndex());
            if (m_columnBitSet.get(columnMemberships.getIndexInColumn())) {
                onWeights += weight;
                ySumOn += weight * y;
            } else {
                offWeights += weight;
                ySumOff += weight * y;
            }
        }
    }
    if (onWeights < minChildSize || offWeights < minChildSize) {
        return null;
    }
    final double onCriterion = ySumOn * ySumOn / onWeights;
    final double offCriterion = ySumOff * ySumOff / offWeights;
    final double gain = onCriterion + offCriterion - criterionTotal;
    if (gain > 0) {
        return new BitSplitCandidate(this, gain);
    }
    return null;
}