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

Example 11 with ClassificationPriors

use of org.knime.base.node.mine.treeensemble2.data.ClassificationPriors 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 12 with ClassificationPriors

use of org.knime.base.node.mine.treeensemble2.data.ClassificationPriors 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 13 with ClassificationPriors

use of org.knime.base.node.mine.treeensemble2.data.ClassificationPriors 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 14 with ClassificationPriors

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

the class TreeNominalColumnDataTest method testCalcBestSplitClassificationBinaryTwoClass.

/**
 * Tests the method
 * {@link TreeNominalColumnData#calcBestSplitClassification(DataMemberships, ClassificationPriors, TreeTargetNominalColumnData, RandomData)}
 * in case of a two class problem.
 *
 * @throws Exception
 */
@Test
public void testCalcBestSplitClassificationBinaryTwoClass() throws Exception {
    TreeEnsembleLearnerConfiguration config = createConfig(false);
    config.setMissingValueHandling(MissingValueHandling.Surrogate);
    Pair<TreeNominalColumnData, TreeTargetNominalColumnData> twoClassTennisData = twoClassTennisData(config);
    TreeNominalColumnData columnData = twoClassTennisData.getFirst();
    TreeTargetNominalColumnData targetData = twoClassTennisData.getSecond();
    TreeData twoClassTennisTreeData = twoClassTennisTreeData(config);
    IDataIndexManager indexManager = new DefaultDataIndexManager(twoClassTennisTreeData);
    assertEquals(SplitCriterion.Gini, config.getSplitCriterion());
    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, twoClassTennisTreeData, 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 open office calc
    assertEquals(0.1371428, 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());
    assertFalse(childConditions[0].acceptsMissings());
    assertFalse(childConditions[1].acceptsMissings());
}

Example 15 with ClassificationPriors

use of org.knime.base.node.mine.treeensemble2.data.ClassificationPriors 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);
}