Examples with TreeEnsembleLearnerConfiguration org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration used on opensource projects

Example 26 with TreeEnsembleLearnerConfiguration

use of org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration 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 27 with TreeEnsembleLearnerConfiguration

use of org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration 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);
}

Example 28 with TreeEnsembleLearnerConfiguration

use of org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration in project knime-core by knime.

the class SurrogatesTest method testCalculateSurrogates.

// @Test
public void testCalculateSurrogates() {
    TreeEnsembleLearnerConfiguration config = new TreeEnsembleLearnerConfiguration(false);
    SplitCandidate[] splitCandidates = createSplitCandidates(config);
    DataMemberships datMem = createDataMembershipsFormSplitCandidates(splitCandidates);
    SurrogateSplit surrogateSplit = Surrogates.calculateSurrogates(datMem, splitCandidates);
    AbstractTreeNodeSurrogateCondition[] surrogateConditions = surrogateSplit.getChildConditions();
    AbstractTreeNodeSurrogateCondition leftChildCondition = surrogateConditions[0];
    AbstractTreeNodeSurrogateCondition rightChildCondition = surrogateConditions[1];
// assertEquals("col1 < 5", leftChildCondition.getColumnCondition(1).toString());
}

Example 29 with TreeEnsembleLearnerConfiguration

use of org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration in project knime-core by knime.

the class TreeNumericColumnDataTest method testCalcBestSplitClassificationSplitAtStart.

/**
 * 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 testCalcBestSplitClassificationSplitAtStart() throws Exception {
    // Index:  1 2 3 4 5 6 7
    // Value:  1 1 1|2 2|3 3
    // Target: A A A|A A|A B
    double[] data = asDataArray("1,1,1,2,2,3,3");
    String[] target = asStringArray("A,A,A,A,B,A,B");
    TreeEnsembleLearnerConfiguration config = createConfig();
    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);
    RandomData rd = config.createRandomData();
    SplitCandidate splitCandidate = columnData.calcBestSplitClassification(dataMemberships, priors, targetData, rd);
    double gain = (1.0 - Math.pow(5.0 / 7.0, 2.0) - Math.pow(2.0 / 7.0, 2.0)) - 0.0 - 4.0 / 7.0 * (1.0 - Math.pow(2.0 / 4.0, 2.0) - Math.pow(2.0 / 4.0, 2.0));
    // manually calculated
    assertEquals(gain, splitCandidate.getGainValue(), 0.000001);
    NumericSplitCandidate numSplitCandidate = (NumericSplitCandidate) splitCandidate;
    TreeNodeNumericCondition[] childConditions = numSplitCandidate.getChildConditions();
    assertEquals(2, childConditions.length);
    assertEquals((1.0 + 2.0) / 2.0, childConditions[0].getSplitValue(), 0.0);
}

Example 30 with TreeEnsembleLearnerConfiguration

use of org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration in project knime-core by knime.

the class TreeNumericColumnDataTest method testXGBoostMissingValueHandling.

/**
 * This method tests if the conditions for child nodes are correct in case of XGBoostMissingValueHandling
 *
 * @throws Exception
 */
@Test
public void testXGBoostMissingValueHandling() throws Exception {
    TreeEnsembleLearnerConfiguration config = createConfig();
    config.setMissingValueHandling(MissingValueHandling.XGBoost);
    final TestDataGenerator dataGen = new TestDataGenerator(config);
    final RandomData rd = config.createRandomData();
    final int[] indices = new int[] { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 };
    final double[] weights = new double[10];
    Arrays.fill(weights, 1.0);
    final MockDataColMem dataMem = new MockDataColMem(indices, indices, weights);
    final String dataCSV = "1,2,2,3,4,5,6,7,NaN,NaN";
    final String target1CSV = "A,A,A,A,B,B,B,B,A,A";
    final String target2CSV = "A,A,A,A,B,B,B,B,B,B";
    final double expectedGain = 0.48;
    final TreeNumericColumnData col = dataGen.createNumericAttributeColumn(dataCSV, "testCol", 0);
    final TreeTargetNominalColumnData target1 = TestDataGenerator.createNominalTargetColumn(target1CSV);
    final SplitCandidate split1 = col.calcBestSplitClassification(dataMem, target1.getDistribution(weights, config), target1, rd);
    assertEquals("Wrong gain.", expectedGain, split1.getGainValue(), 1e-8);
    final TreeNodeCondition[] childConds1 = split1.getChildConditions();
    final TreeNodeNumericCondition numCondLeft1 = (TreeNodeNumericCondition) childConds1[0];
    assertEquals("Wrong split point.", 3.5, numCondLeft1.getSplitValue(), 1e-8);
    assertTrue("Missings were not sent in the correct direction.", numCondLeft1.acceptsMissings());
    final TreeNodeNumericCondition numCondRight1 = (TreeNodeNumericCondition) childConds1[1];
    assertEquals("Wrong split point.", 3.5, numCondRight1.getSplitValue(), 1e-8);
    assertFalse("Missings were not sent in the correct direction.", numCondRight1.acceptsMissings());
    final TreeTargetNominalColumnData target2 = TestDataGenerator.createNominalTargetColumn(target2CSV);
    final SplitCandidate split2 = col.calcBestSplitClassification(dataMem, target2.getDistribution(weights, config), target2, rd);
    assertEquals("Wrong gain.", expectedGain, split2.getGainValue(), 1e-8);
    final TreeNodeCondition[] childConds2 = split2.getChildConditions();
    final TreeNodeNumericCondition numCondLeft2 = (TreeNodeNumericCondition) childConds2[0];
    assertEquals("Wrong split point.", 3.5, numCondLeft2.getSplitValue(), 1e-8);
    assertFalse("Missings were not sent in the correct direction.", numCondLeft2.acceptsMissings());
    final TreeNodeNumericCondition numCondRight2 = (TreeNodeNumericCondition) childConds2[1];
    assertEquals("Wrong split point.", 3.5, numCondRight2.getSplitValue(), 1e-8);
    assertTrue("Missings were not sent in the correct direction.", numCondRight2.acceptsMissings());
}