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

Example 1 with DefaultDataIndexManager

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

the class TreeNominalColumnDataTest method testCalcBestSplitClassificationMultiWay.

/**
 * Tests the method
 * {@link TreeNominalColumnData#calcBestSplitClassification(DataMemberships, ClassificationPriors, TreeTargetNominalColumnData, RandomData)}
 * using multiway splits
 *
 * @throws Exception
 */
@Test
public void testCalcBestSplitClassificationMultiWay() throws Exception {
    TreeEnsembleLearnerConfiguration config = createConfig(false);
    config.setUseBinaryNominalSplits(false);
    Pair<TreeNominalColumnData, TreeTargetNominalColumnData> tennisData = tennisData(config);
    TreeNominalColumnData columnData = tennisData.getFirst();
    TreeTargetNominalColumnData targetData = tennisData.getSecond();
    TreeData treeData = createTreeData(tennisData);
    assertEquals(SplitCriterion.Gini, config.getSplitCriterion());
    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);
    ClassificationPriors priors = targetData.getDistribution(rowWeights, config);
    SplitCandidate splitCandidate = columnData.calcBestSplitClassification(dataMemberships, priors, targetData, null);
    assertNotNull(splitCandidate);
    assertThat(splitCandidate, instanceOf(NominalMultiwaySplitCandidate.class));
    assertFalse(splitCandidate.canColumnBeSplitFurther());
    // manually via libre office calc
    assertEquals(0.0744897959, splitCandidate.getGainValue(), 0.00001);
    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());
}

Example 2 with DefaultDataIndexManager

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

the class TreeNominalColumnDataTest method testCalcBestSplitCassificationBinaryTwoClassXGBoostMissingValue.

/**
 * Tests the XGBoost Missing value handling in case of a two class problem <br>
 * currently not tested because missing value handling will probably be implemented differently.
 *
 * @throws Exception
 */
// @Test
public void testCalcBestSplitCassificationBinaryTwoClassXGBoostMissingValue() throws Exception {
    final TreeEnsembleLearnerConfiguration config = createConfig(false);
    config.setMissingValueHandling(MissingValueHandling.XGBoost);
    final TestDataGenerator dataGen = new TestDataGenerator(config);
    // check correct behavior if no missing values are encountered during split search
    Pair<TreeNominalColumnData, TreeTargetNominalColumnData> twoClassTennisData = twoClassTennisData(config);
    TreeData treeData = dataGen.createTreeData(twoClassTennisData.getSecond(), twoClassTennisData.getFirst());
    IDataIndexManager indexManager = new DefaultDataIndexManager(treeData);
    double[] rowWeights = new double[TWO_CLASS_INDICES.length];
    Arrays.fill(rowWeights, 1.0);
    // DataMemberships dataMemberships = TestDataGenerator.createMockDataMemberships(TWO_CLASS_INDICES.length);
    DataMemberships dataMemberships = new RootDataMemberships(rowWeights, treeData, indexManager);
    TreeTargetNominalColumnData targetData = twoClassTennisData.getSecond();
    TreeNominalColumnData columnData = twoClassTennisData.getFirst();
    ClassificationPriors priors = targetData.getDistribution(rowWeights, config);
    RandomData rd = TestDataGenerator.createRandomData();
    SplitCandidate splitCandidate = columnData.calcBestSplitClassification(dataMemberships, priors, targetData, rd);
    assertNotNull(splitCandidate);
    assertThat(splitCandidate, instanceOf(NominalBinarySplitCandidate.class));
    NominalBinarySplitCandidate binarySplitCandidate = (NominalBinarySplitCandidate) splitCandidate;
    TreeNodeNominalBinaryCondition[] childConditions = binarySplitCandidate.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());
    // check if missing values go left
    assertTrue(childConditions[0].acceptsMissings());
    assertFalse(childConditions[1].acceptsMissings());
    // check correct behavior if missing values are encountered during split search
    String dataContainingMissingsCSV = "S,?,O,R,S,R,S,O,O,?";
    columnData = dataGen.createNominalAttributeColumn(dataContainingMissingsCSV, "column containing missing values", 0);
    treeData = dataGen.createTreeData(targetData, columnData);
    indexManager = new DefaultDataIndexManager(treeData);
    dataMemberships = new RootDataMemberships(rowWeights, treeData, indexManager);
    splitCandidate = columnData.calcBestSplitClassification(dataMemberships, priors, targetData, null);
    assertNotNull(splitCandidate);
    binarySplitCandidate = (NominalBinarySplitCandidate) splitCandidate;
    assertEquals("Gain was not as expected", 0.08, binarySplitCandidate.getGainValue(), 1e-8);
    childConditions = binarySplitCandidate.getChildConditions();
    String[] conditionValues = new String[] { "O", "?" };
    assertArrayEquals("Values in nominal condition did not match", conditionValues, childConditions[0].getValues());
    assertArrayEquals("Values in nominal condition did not match", conditionValues, childConditions[1].getValues());
    assertEquals("Wrong set logic.", SetLogic.IS_NOT_IN, childConditions[0].getSetLogic());
    assertEquals("Wrong set logic.", SetLogic.IS_IN, childConditions[1].getSetLogic());
    assertFalse("Missig values are not sent to the correct child.", childConditions[0].acceptsMissings());
    assertTrue("Missig values are not sent to the correct child.", childConditions[1].acceptsMissings());
}

Example 3 with DefaultDataIndexManager

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

the class TreeNumericColumnDataTest method testCalcBestSplitClassification.

@Test
public void testCalcBestSplitClassification() throws Exception {
    TreeEnsembleLearnerConfiguration config = createConfig();
    /* data from J. Fuernkranz, Uni Darmstadt:
         * http://www.ke.tu-darmstadt.de/lehre/archiv/ws0809/mldm/dt.pdf */
    final double[] data = asDataArray("60,70,75,85, 90, 95, 100,120,125,220");
    final String[] target = asStringArray("No,No,No,Yes,Yes,Yes,No, No, No, No");
    Pair<TreeOrdinaryNumericColumnData, TreeTargetNominalColumnData> exampleData = exampleData(config, data, target);
    RandomData rd = config.createRandomData();
    TreeNumericColumnData columnData = exampleData.getFirst();
    TreeTargetNominalColumnData targetData = exampleData.getSecond();
    assertEquals(SplitCriterion.Gini, config.getSplitCriterion());
    double[] rowWeights = new double[data.length];
    Arrays.fill(rowWeights, 1.0);
    TreeData treeData = createTreeDataClassification(exampleData);
    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, rd);
    assertNotNull(splitCandidate);
    assertThat(splitCandidate, instanceOf(NumericSplitCandidate.class));
    assertTrue(splitCandidate.canColumnBeSplitFurther());
    // libre office calc
    assertEquals(/*0.42 - 0.300 */
    0.12, splitCandidate.getGainValue(), 0.00001);
    NumericSplitCandidate numSplitCandidate = (NumericSplitCandidate) splitCandidate;
    TreeNodeNumericCondition[] childConditions = numSplitCandidate.getChildConditions();
    assertEquals(2, childConditions.length);
    assertEquals((95.0 + 100.0) / 2.0, childConditions[0].getSplitValue(), 0.0);
    assertEquals((95.0 + 100.0) / 2.0, childConditions[1].getSplitValue(), 0.0);
    assertEquals(NumericOperator.LessThanOrEqual, childConditions[0].getNumericOperator());
    assertEquals(NumericOperator.LargerThan, childConditions[1].getNumericOperator());
    double[] childRowWeights = new double[data.length];
    System.arraycopy(rowWeights, 0, childRowWeights, 0, rowWeights.length);
    BitSet inChild = columnData.updateChildMemberships(childConditions[0], dataMemberships);
    DataMemberships childMemberships = dataMemberships.createChildMemberships(inChild);
    ClassificationPriors childTargetPriors = targetData.getDistribution(childMemberships, config);
    SplitCandidate splitCandidateChild = columnData.calcBestSplitClassification(childMemberships, childTargetPriors, targetData, rd);
    assertNotNull(splitCandidateChild);
    assertThat(splitCandidateChild, instanceOf(NumericSplitCandidate.class));
    // manually via libre office calc
    assertEquals(0.5, splitCandidateChild.getGainValue(), 0.00001);
    TreeNodeNumericCondition[] childConditions2 = ((NumericSplitCandidate) splitCandidateChild).getChildConditions();
    assertEquals(2, childConditions2.length);
    assertEquals((75.0 + 85.0) / 2.0, childConditions2[0].getSplitValue(), 0.0);
    System.arraycopy(rowWeights, 0, childRowWeights, 0, rowWeights.length);
    inChild = columnData.updateChildMemberships(childConditions[1], dataMemberships);
    childMemberships = dataMemberships.createChildMemberships(inChild);
    childTargetPriors = targetData.getDistribution(childMemberships, config);
    splitCandidateChild = columnData.calcBestSplitClassification(childMemberships, childTargetPriors, targetData, rd);
    assertNull(splitCandidateChild);
}

Example 4 with DefaultDataIndexManager

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

the class TreeNumericColumnDataTest method testCalcBestSplitClassificationSplitAtEnd.

/**
 * Test splits at last possible split position - even if no change in target can be observed, see example data in
 * method body.
 * @throws Exception
 */
@Test
public void testCalcBestSplitClassificationSplitAtEnd() throws Exception {
    // Index:  1 2 3 4 5 6 7 8
    // Value:  1 1|2 2 2|3 3 3
    // Target: A A|A A A|A A B
    double[] data = asDataArray("1,1,2,2,2,3,3,3");
    String[] target = asStringArray("A,A,A,A,A,A,A,B");
    TreeEnsembleLearnerConfiguration config = createConfig();
    RandomData rd = config.createRandomData();
    Pair<TreeOrdinaryNumericColumnData, TreeTargetNominalColumnData> exampleData = exampleData(config, data, target);
    TreeNumericColumnData columnData = exampleData.getFirst();
    TreeTargetNominalColumnData targetData = exampleData.getSecond();
    double[] rowWeights = new double[data.length];
    Arrays.fill(rowWeights, 1.0);
    TreeData treeData = createTreeDataClassification(exampleData);
    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, rd);
    assertNotNull(splitCandidate);
    assertThat(splitCandidate, instanceOf(NumericSplitCandidate.class));
    assertTrue(splitCandidate.canColumnBeSplitFurther());
    // manually calculated
    assertEquals(/*0.21875 - 0.166666667 */
    0.05208, splitCandidate.getGainValue(), 0.001);
    NumericSplitCandidate numSplitCandidate = (NumericSplitCandidate) splitCandidate;
    TreeNodeNumericCondition[] childConditions = numSplitCandidate.getChildConditions();
    assertEquals(2, childConditions.length);
    assertEquals((2.0 + 3.0) / 2.0, childConditions[0].getSplitValue(), 0.0);
    assertEquals(NumericOperator.LessThanOrEqual, childConditions[0].getNumericOperator());
    double[] childRowWeights = new double[data.length];
    System.arraycopy(rowWeights, 0, childRowWeights, 0, rowWeights.length);
    BitSet inChild = columnData.updateChildMemberships(childConditions[0], dataMemberships);
    DataMemberships childMemberships = dataMemberships.createChildMemberships(inChild);
    ClassificationPriors childTargetPriors = targetData.getDistribution(childMemberships, config);
    SplitCandidate splitCandidateChild = columnData.calcBestSplitClassification(childMemberships, childTargetPriors, targetData, rd);
    assertNull(splitCandidateChild);
    System.arraycopy(rowWeights, 0, childRowWeights, 0, rowWeights.length);
    inChild = columnData.updateChildMemberships(childConditions[1], dataMemberships);
    childMemberships = dataMemberships.createChildMemberships(inChild);
    childTargetPriors = targetData.getDistribution(childMemberships, config);
    splitCandidateChild = columnData.calcBestSplitClassification(childMemberships, childTargetPriors, targetData, null);
    assertNull(splitCandidateChild);
}

Example 5 with DefaultDataIndexManager

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

the class TreeNumericColumnDataTest method testCalcBestSplitClassificationMissingValStrategy1.

/**
 * This test is outdated and will likely be removed soon.
 *
 * @throws Exception
 */
// @Test
public void testCalcBestSplitClassificationMissingValStrategy1() throws Exception {
    TreeEnsembleLearnerConfiguration config = createConfig();
    final double[] data = asDataArray("1, 2, 3, 4, 5, 6, 7, NaN, NaN, NaN");
    final String[] target = asStringArray("Y, Y, Y, Y, N, N, N, Y, Y, Y");
    Pair<TreeOrdinaryNumericColumnData, TreeTargetNominalColumnData> exampleData = exampleData(config, data, target);
    double[] rowWeights = new double[data.length];
    Arrays.fill(rowWeights, 1.0);
    RandomData rd = config.createRandomData();
    TreeNumericColumnData columnData = exampleData.getFirst();
    TreeTargetNominalColumnData targetData = exampleData.getSecond();
    TreeData treeData = createTreeDataClassification(exampleData);
    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, rd);
    assertNotNull(splitCandidate);
    assertThat(splitCandidate, instanceOf(NumericMissingSplitCandidate.class));
    assertTrue(splitCandidate.canColumnBeSplitFurther());
    assertEquals(0.42, splitCandidate.getGainValue(), 0.0001);
    TreeNodeNumericCondition[] childConditions = ((NumericMissingSplitCandidate) splitCandidate).getChildConditions();
    assertEquals(2, childConditions.length);
    assertEquals(NumericOperator.LessThanOrEqualOrMissing, childConditions[0].getNumericOperator());
    assertEquals(NumericOperator.LargerThan, childConditions[1].getNumericOperator());
    assertEquals(4.5, childConditions[0].getSplitValue(), 0.0);
}