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

Example 21 with TreeTargetNominalColumnData

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

the class TreeNominalColumnDataTest method testCalcBestSplitClassificationBinaryPCAXGBoostMissingValueHandling.

/**
 * Tests the XGBoost missing value handling in the case of binary splits calculated with the pca method (multiple classes)
 *
 * @throws Exception
 */
@Test
public void testCalcBestSplitClassificationBinaryPCAXGBoostMissingValueHandling() throws Exception {
    final TreeEnsembleLearnerConfiguration config = createConfig(false);
    config.setMissingValueHandling(MissingValueHandling.XGBoost);
    final TestDataGenerator dataGen = new TestDataGenerator(config);
    final RandomData rd = config.createRandomData();
    // test the case that there are no missing values in the training data
    final String noMissingCSV = "a, a, a, b, b, b, b, c, c";
    final String noMissingTarget = "A, B, B, C, C, C, B, A, B";
    TreeNominalColumnData dataCol = dataGen.createNominalAttributeColumn(noMissingCSV, "noMissings", 0);
    TreeTargetNominalColumnData targetCol = TestDataGenerator.createNominalTargetColumn(noMissingTarget);
    DataMemberships dataMem = createMockDataMemberships(targetCol.getNrRows());
    SplitCandidate split = dataCol.calcBestSplitClassification(dataMem, targetCol.getDistribution(dataMem, config), targetCol, rd);
    assertNotNull("There is a possible split.", split);
    assertEquals("Incorrect gain.", 0.2086, split.getGainValue(), 1e-3);
    assertThat(split, instanceOf(NominalBinarySplitCandidate.class));
    NominalBinarySplitCandidate nomSplit = (NominalBinarySplitCandidate) split;
    assertTrue("No missing values in the column.", nomSplit.getMissedRows().isEmpty());
    TreeNodeNominalBinaryCondition[] conditions = nomSplit.getChildConditions();
    assertEquals("A binary split must have 2 child conditions.", 2, conditions.length);
    String[] values = new String[] { "a", "c" };
    assertArrayEquals("Wrong values in child condition.", values, conditions[0].getValues());
    assertArrayEquals("Wrong values in child condition.", values, conditions[1].getValues());
    assertEquals("Wrong set logic.", SetLogic.IS_NOT_IN, conditions[0].getSetLogic());
    assertEquals("Wrong set logic.", SetLogic.IS_IN, conditions[1].getSetLogic());
    assertFalse("Missing values should be sent to the majority child (i.e. right)", conditions[0].acceptsMissings());
    assertTrue("Missing values should be sent to the majority child (i.e. right)", conditions[1].acceptsMissings());
    // test the case that there are missing values in the training data
    final String missingCSV = "a, a, a, b, b, b, b, c, c, ?";
    final String missingTarget = "A, B, B, C, C, C, B, A, B, C";
    dataCol = dataGen.createNominalAttributeColumn(missingCSV, "missings", 0);
    targetCol = TestDataGenerator.createNominalTargetColumn(missingTarget);
    dataMem = createMockDataMemberships(targetCol.getNrRows());
    split = dataCol.calcBestSplitClassification(dataMem, targetCol.getDistribution(dataMem, config), targetCol, rd);
    assertNotNull("There is a possible split.", split);
    assertEquals("Incorrect gain.", 0.24, split.getGainValue(), 1e-3);
    assertThat(split, instanceOf(NominalBinarySplitCandidate.class));
    nomSplit = (NominalBinarySplitCandidate) split;
    assertTrue("Split should handle missing values.", nomSplit.getMissedRows().isEmpty());
    conditions = nomSplit.getChildConditions();
    assertEquals("Wrong number of child conditions.", 2, conditions.length);
    assertArrayEquals("Wrong values in child condition.", values, conditions[0].getValues());
    assertArrayEquals("Wrong values in child condition.", values, conditions[1].getValues());
    assertEquals("Wrong set logic.", SetLogic.IS_NOT_IN, conditions[0].getSetLogic());
    assertEquals("Wrong set logic.", SetLogic.IS_IN, conditions[1].getSetLogic());
    assertTrue("Missing values should be sent to left child", conditions[0].acceptsMissings());
    assertFalse("Missing values should be sent to left child", conditions[1].acceptsMissings());
}

Example 22 with TreeTargetNominalColumnData

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

the class TreeNominalColumnDataTest method testCalcBestSplitClassificationBinary.

/**
 * Tests the method
 * {@link TreeNominalColumnData#calcBestSplitClassification(DataMemberships, ClassificationPriors, TreeTargetNominalColumnData, RandomData)}
 * using binary splits.
 *
 * @throws Exception
 */
@Test
public void testCalcBestSplitClassificationBinary() throws Exception {
    final TreeEnsembleLearnerConfiguration config = createConfig(false);
    Pair<TreeNominalColumnData, TreeTargetNominalColumnData> tennisData = tennisData(config);
    TreeNominalColumnData columnData = tennisData.getFirst();
    TreeTargetNominalColumnData targetData = tennisData.getSecond();
    assertEquals(SplitCriterion.Gini, config.getSplitCriterion());
    double[] rowWeights = new double[SMALL_COLUMN_DATA.length];
    Arrays.fill(rowWeights, 1.0);
    TreeData tennisTreeData = tennisTreeData(config);
    IDataIndexManager indexManager = new DefaultDataIndexManager(tennisTreeData);
    DataMemberships dataMemberships = new RootDataMemberships(rowWeights, tennisTreeData, indexManager);
    ClassificationPriors priors = targetData.getDistribution(rowWeights, config);
    SplitCandidate splitCandidate = columnData.calcBestSplitClassification(dataMemberships, priors, targetData, null);
    assertNotNull(splitCandidate);
    assertThat(splitCandidate, instanceOf(NominalBinarySplitCandidate.class));
    assertTrue(splitCandidate.canColumnBeSplitFurther());
    // manually via libre office calc
    assertEquals(0.0689342404, splitCandidate.getGainValue(), 0.00001);
    NominalBinarySplitCandidate binSplitCandidate = (NominalBinarySplitCandidate) splitCandidate;
    TreeNodeNominalBinaryCondition[] childConditions = binSplitCandidate.getChildConditions();
    assertEquals(2, childConditions.length);
    assertArrayEquals(new String[] { "R" }, childConditions[0].getValues());
    assertArrayEquals(new String[] { "R" }, childConditions[1].getValues());
    assertEquals(SetLogic.IS_NOT_IN, childConditions[0].getSetLogic());
    assertEquals(SetLogic.IS_IN, childConditions[1].getSetLogic());
    BitSet inChild = columnData.updateChildMemberships(childConditions[0], dataMemberships);
    DataMemberships child1Memberships = dataMemberships.createChildMemberships(inChild);
    ClassificationPriors childTargetPriors = targetData.getDistribution(child1Memberships, config);
    SplitCandidate splitCandidateChild = columnData.calcBestSplitClassification(child1Memberships, childTargetPriors, targetData, null);
    assertNotNull(splitCandidateChild);
    assertThat(splitCandidateChild, instanceOf(NominalBinarySplitCandidate.class));
    // manually via libre office calc
    assertEquals(0.0086419753, splitCandidateChild.getGainValue(), 0.00001);
    inChild = columnData.updateChildMemberships(childConditions[1], dataMemberships);
    DataMemberships child2Memberships = dataMemberships.createChildMemberships(inChild);
    childTargetPriors = targetData.getDistribution(child2Memberships, config);
    splitCandidateChild = columnData.calcBestSplitClassification(child2Memberships, childTargetPriors, targetData, null);
    assertNull(splitCandidateChild);
}

Example 23 with TreeTargetNominalColumnData

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

the class TreeNominalColumnDataTest method testCalcBestSplitClassificationMultiwayXGBoostMissingValueHandling.

/**
 * This method tests the XGBoost missing value handling for classification in case of multiway splits.
 *
 * @throws Exception
 */
@Test
public void testCalcBestSplitClassificationMultiwayXGBoostMissingValueHandling() throws Exception {
    final TreeEnsembleLearnerConfiguration config = createConfig(false);
    config.setUseBinaryNominalSplits(false);
    config.setMissingValueHandling(MissingValueHandling.XGBoost);
    final TestDataGenerator dataGen = new TestDataGenerator(config);
    final RandomData rd = config.createRandomData();
    // test the case that there are no missing values in the training data
    final String noMissingCSV = "a, a, a, b, b, b, b, c, c";
    final String noMissingTarget = "A, B, B, C, C, C, B, A, B";
    TreeNominalColumnData dataCol = dataGen.createNominalAttributeColumn(noMissingCSV, "noMissings", 0);
    TreeTargetNominalColumnData targetCol = TestDataGenerator.createNominalTargetColumn(noMissingTarget);
    DataMemberships dataMem = createMockDataMemberships(targetCol.getNrRows());
    SplitCandidate split = dataCol.calcBestSplitClassification(dataMem, targetCol.getDistribution(dataMem, config), targetCol, rd);
    assertNotNull("There is a possible split.", split);
    assertEquals("Incorrect gain.", 0.216, split.getGainValue(), 1e-3);
    assertThat(split, instanceOf(NominalMultiwaySplitCandidate.class));
    NominalMultiwaySplitCandidate nomSplit = (NominalMultiwaySplitCandidate) split;
    assertTrue("No missing values in the column.", nomSplit.getMissedRows().isEmpty());
    TreeNodeNominalCondition[] conditions = nomSplit.getChildConditions();
    assertEquals("Wrong number of child conditions.", 3, conditions.length);
    assertEquals("Wrong value in child condition.", "a", conditions[0].getValue());
    assertEquals("Wrong value in child condition.", "b", conditions[1].getValue());
    assertEquals("Wrong value in child condition.", "c", conditions[2].getValue());
    assertFalse("Missing values should be sent to the majority child (i.e. b)", conditions[0].acceptsMissings());
    assertTrue("Missing values should be sent to the majority child (i.e. b)", conditions[1].acceptsMissings());
    assertFalse("Missing values should be sent to the majority child (i.e. b)", conditions[2].acceptsMissings());
    // test the case that there are missing values in the training data
    final String missingCSV = "a, a, a, b, b, b, b, c, c, ?";
    final String missingTarget = "A, B, B, C, C, C, B, A, B, C";
    dataCol = dataGen.createNominalAttributeColumn(missingCSV, "missings", 0);
    targetCol = TestDataGenerator.createNominalTargetColumn(missingTarget);
    dataMem = createMockDataMemberships(targetCol.getNrRows());
    split = dataCol.calcBestSplitClassification(dataMem, targetCol.getDistribution(dataMem, config), targetCol, rd);
    assertNotNull("There is a possible split.", split);
    assertEquals("Incorrect gain.", 0.2467, split.getGainValue(), 1e-3);
    assertThat(split, instanceOf(NominalMultiwaySplitCandidate.class));
    nomSplit = (NominalMultiwaySplitCandidate) split;
    assertTrue("Split should handle missing values.", nomSplit.getMissedRows().isEmpty());
    conditions = nomSplit.getChildConditions();
    assertEquals("Wrong number of child conditions.", 3, conditions.length);
    assertEquals("Wrong value in child condition.", "a", conditions[0].getValue());
    assertEquals("Wrong value in child condition.", "b", conditions[1].getValue());
    assertEquals("Wrong value in child condition.", "c", conditions[2].getValue());
    assertFalse("Missing values should be sent to b", conditions[0].acceptsMissings());
    assertTrue("Missing values should be sent to b", conditions[1].acceptsMissings());
    assertFalse("Missing values should be sent to b", conditions[2].acceptsMissings());
}

Example 24 with TreeTargetNominalColumnData

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

the class TreeNominalColumnDataTest method testCalcBestSplitClassificationBinaryPCA.

/**
 * Tests the method
 * {@link TreeNominalColumnData#calcBestSplitClassification(DataMemberships, ClassificationPriors, TreeTargetNominalColumnData, RandomData)}
 * using binary splits. In this test case the data has more than two classes and the used algorithm is therefore PCA
 * based.
 *
 * @throws Exception
 */
@Test
public void testCalcBestSplitClassificationBinaryPCA() throws Exception {
    TreeEnsembleLearnerConfiguration config = createConfig(false);
    Pair<TreeNominalColumnData, TreeTargetNominalColumnData> pcaData = createPCATestData(config);
    TreeNominalColumnData columnData = pcaData.getFirst();
    TreeTargetNominalColumnData targetData = pcaData.getSecond();
    TreeData treeData = createTreeData(pcaData);
    assertEquals(SplitCriterion.Gini, config.getSplitCriterion());
    double[] rowWeights = new double[targetData.getNrRows()];
    Arrays.fill(rowWeights, 1.0);
    IDataIndexManager indexManager = new DefaultDataIndexManager(treeData);
    DataMemberships dataMemberships = new RootDataMemberships(rowWeights, treeData, indexManager);
    ClassificationPriors priors = targetData.getDistribution(rowWeights, config);
    SplitCandidate splitCandidate = columnData.calcBestSplitClassification(dataMemberships, priors, targetData, null);
    assertNotNull(splitCandidate);
    assertThat(splitCandidate, instanceOf(NominalBinarySplitCandidate.class));
    assertTrue(splitCandidate.canColumnBeSplitFurther());
    assertEquals(0.0659, splitCandidate.getGainValue(), 0.0001);
    NominalBinarySplitCandidate binarySplitCandidate = (NominalBinarySplitCandidate) splitCandidate;
    TreeNodeNominalBinaryCondition[] childConditions = binarySplitCandidate.getChildConditions();
    assertEquals(2, childConditions.length);
    assertArrayEquals(new String[] { "E" }, childConditions[0].getValues());
    assertArrayEquals(new String[] { "E" }, childConditions[1].getValues());
    assertEquals(SetLogic.IS_NOT_IN, childConditions[0].getSetLogic());
    assertEquals(SetLogic.IS_IN, childConditions[1].getSetLogic());
}

Example 25 with TreeTargetNominalColumnData

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

the class TreeTargetNominalColumnDataTest method testGetDistribution.

/**
 * Tests the {@link TreeTargetNominalColumnData#getDistribution(DataMemberships, TreeEnsembleLearnerConfiguration)}
 * and {@link TreeTargetNominalColumnData#getDistribution(double[], TreeEnsembleLearnerConfiguration)} methods.
 * @throws InvalidSettingsException
 */
@Test
public void testGetDistribution() throws InvalidSettingsException {
    String targetCSV = "A,A,A,B,B,B,A";
    String attributeCSV = "1,2,3,4,5,6,7";
    TreeEnsembleLearnerConfiguration config = new TreeEnsembleLearnerConfiguration(false);
    TestDataGenerator dataGen = new TestDataGenerator(config);
    TreeTargetNominalColumnData target = TestDataGenerator.createNominalTargetColumn(targetCSV);
    TreeNumericColumnData attribute = dataGen.createNumericAttributeColumn(attributeCSV, "test-col", 0);
    TreeData data = new TreeData(new TreeAttributeColumnData[] { attribute }, target, TreeType.Ordinary);
    double[] weights = new double[7];
    Arrays.fill(weights, 1.0);
    DataMemberships rootMemberships = new RootDataMemberships(weights, data, new DefaultDataIndexManager(data));
    // Gini
    config.setSplitCriterion(SplitCriterion.Gini);
    double expectedGini = 0.4897959184;
    double[] expectedDistribution = new double[] { 4.0, 3.0 };
    ClassificationPriors giniPriorsDatMem = target.getDistribution(rootMemberships, config);
    assertEquals(expectedGini, giniPriorsDatMem.getPriorImpurity(), DELTA);
    assertArrayEquals(expectedDistribution, giniPriorsDatMem.getDistribution(), DELTA);
    ClassificationPriors giniPriorsWeights = target.getDistribution(weights, config);
    assertEquals(expectedGini, giniPriorsWeights.getPriorImpurity(), DELTA);
    assertArrayEquals(expectedDistribution, giniPriorsWeights.getDistribution(), DELTA);
    // Information Gain
    config.setSplitCriterion(SplitCriterion.InformationGain);
    double expectedEntropy = 0.985228136;
    ClassificationPriors igPriorsDatMem = target.getDistribution(rootMemberships, config);
    assertEquals(expectedEntropy, igPriorsDatMem.getPriorImpurity(), DELTA);
    assertArrayEquals(expectedDistribution, igPriorsDatMem.getDistribution(), DELTA);
    ClassificationPriors igPriorsWeights = target.getDistribution(weights, config);
    assertEquals(expectedEntropy, igPriorsWeights.getPriorImpurity(), DELTA);
    assertArrayEquals(expectedDistribution, igPriorsWeights.getDistribution(), DELTA);
    // Information Gain Ratio
    config.setSplitCriterion(SplitCriterion.InformationGainRatio);
    // prior impurity is the same as IG
    ClassificationPriors igrPriorsDatMem = target.getDistribution(rootMemberships, config);
    assertEquals(expectedEntropy, igrPriorsDatMem.getPriorImpurity(), DELTA);
    assertArrayEquals(expectedDistribution, igrPriorsDatMem.getDistribution(), DELTA);
    ClassificationPriors igrPriorsWeights = target.getDistribution(weights, config);
    assertEquals(expectedEntropy, igrPriorsWeights.getPriorImpurity(), DELTA);
    assertArrayEquals(expectedDistribution, igrPriorsWeights.getDistribution(), DELTA);
}