Examples with TreeNodeNumericCondition org.knime.base.node.mine.treeensemble2.model.TreeNodeNumericCondition used on opensource projects

Example 6 with TreeNodeNumericCondition

use of org.knime.base.node.mine.treeensemble2.model.TreeNodeNumericCondition 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 7 with TreeNodeNumericCondition

use of org.knime.base.node.mine.treeensemble2.model.TreeNodeNumericCondition 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());
}

Example 8 with TreeNodeNumericCondition

use of org.knime.base.node.mine.treeensemble2.model.TreeNodeNumericCondition in project knime-core by knime.

the class TreeNumericColumnDataTest method testCalcBestSplitRegression.

@Test
public void testCalcBestSplitRegression() throws InvalidSettingsException {
    String dataCSV = "1,2,3,4,5,6,7,8,9,10";
    String targetCSV = "1,5,4,4.3,6.5,6.5,4,3,3,4";
    TreeEnsembleLearnerConfiguration config = new TreeEnsembleLearnerConfiguration(true);
    config.setNrModels(1);
    config.setDataSelectionWithReplacement(false);
    config.setUseDifferentAttributesAtEachNode(false);
    config.setDataFractionPerTree(1.0);
    config.setColumnSamplingMode(ColumnSamplingMode.None);
    TestDataGenerator dataGen = new TestDataGenerator(config);
    RandomData rd = config.createRandomData();
    TreeTargetNumericColumnData target = TestDataGenerator.createNumericTargetColumn(targetCSV);
    TreeNumericColumnData attribute = dataGen.createNumericAttributeColumn(dataCSV, "test-col", 0);
    TreeData data = new TreeData(new TreeAttributeColumnData[] { attribute }, target, TreeType.Ordinary);
    double[] weights = new double[10];
    Arrays.fill(weights, 1.0);
    DataMemberships rootMem = new RootDataMemberships(weights, data, new DefaultDataIndexManager(data));
    SplitCandidate firstSplit = attribute.calcBestSplitRegression(rootMem, target.getPriors(rootMem, config), target, rd);
    // calculated via OpenOffice calc
    assertEquals(10.885444, firstSplit.getGainValue(), 1e-5);
    TreeNodeCondition[] firstConditions = firstSplit.getChildConditions();
    assertEquals(2, firstConditions.length);
    for (int i = 0; i < firstConditions.length; i++) {
        assertThat(firstConditions[i], instanceOf(TreeNodeNumericCondition.class));
        TreeNodeNumericCondition numCond = (TreeNodeNumericCondition) firstConditions[i];
        assertEquals(1.5, numCond.getSplitValue(), 0);
    }
    // left child contains only one row therefore only look at right child
    BitSet expectedInChild = new BitSet(10);
    expectedInChild.set(1, 10);
    BitSet inChild = attribute.updateChildMemberships(firstConditions[1], rootMem);
    assertEquals(expectedInChild, inChild);
    DataMemberships childMem = rootMem.createChildMemberships(inChild);
    SplitCandidate secondSplit = attribute.calcBestSplitRegression(childMem, target.getPriors(childMem, config), target, rd);
    assertEquals(6.883555, secondSplit.getGainValue(), 1e-5);
    TreeNodeCondition[] secondConditions = secondSplit.getChildConditions();
    for (int i = 0; i < secondConditions.length; i++) {
        assertThat(secondConditions[i], instanceOf(TreeNodeNumericCondition.class));
        TreeNodeNumericCondition numCond = (TreeNodeNumericCondition) secondConditions[i];
        assertEquals(6.5, numCond.getSplitValue(), 0);
    }
}

Example 9 with TreeNodeNumericCondition

use of org.knime.base.node.mine.treeensemble2.model.TreeNodeNumericCondition in project knime-core by knime.

the class LiteralConditionParser method handleSimplePredicate.

private TreeNodeColumnCondition handleSimplePredicate(final SimplePredicate simplePred, final boolean acceptsMissings) {
    String field = simplePred.getField();
    if (m_metaDataMapper.isNominal(field)) {
        NominalAttributeColumnHelper colHelper = m_metaDataMapper.getNominalColumnHelper(field);
        return new TreeNodeNominalCondition(colHelper.getMetaData(), colHelper.getRepresentation(simplePred.getValue()).getAssignedInteger(), acceptsMissings);
    } else {
        TreeNumericColumnMetaData metaData = m_metaDataMapper.getNumericColumnHelper(field).getMetaData();
        double value = Double.parseDouble(simplePred.getValue());
        return new TreeNodeNumericCondition(metaData, value, parseNumericOperator(simplePred.getOperator()), acceptsMissings);
    }
}

Example 10 with TreeNodeNumericCondition

use of org.knime.base.node.mine.treeensemble2.model.TreeNodeNumericCondition in project knime-core by knime.

the class TreeNodeNumericConditionTest method testTestCondition.

/**
 * This method tests the
 * {@link TreeNodeNominalCondition#testCondition(org.knime.base.node.mine.treeensemble2.data.PredictorRecord)}
 * method.
 *
 * @throws Exception
 */
@Test
public void testTestCondition() throws Exception {
    final TreeEnsembleLearnerConfiguration config = new TreeEnsembleLearnerConfiguration(false);
    final TestDataGenerator dataGen = new TestDataGenerator(config);
    final TreeNumericColumnData col = dataGen.createNumericAttributeColumn("1,2,3,4,4,5,6,7", "testCol", 0);
    TreeNodeNumericCondition cond = new TreeNodeNumericCondition(col.getMetaData(), 3, NumericOperator.LessThanOrEqual, false);
    final Map<String, Object> map = Maps.newHashMap();
    final String colName = col.getMetaData().getAttributeName();
    map.put(colName, 2.5);
    final PredictorRecord record = new PredictorRecord(map);
    assertTrue("2.5 was falsely rejected.", cond.testCondition(record));
    map.clear();
    map.put(colName, 3);
    assertTrue("3 was falsely rejected.", cond.testCondition(record));
    map.clear();
    map.put(colName, 4);
    assertFalse("4 was falsely accepted.", cond.testCondition(record));
    map.clear();
    map.put(colName, PredictorRecord.NULL);
    assertFalse("Missing values were falsely accepted.", cond.testCondition(record));
    cond = new TreeNodeNumericCondition(col.getMetaData(), 3, NumericOperator.LessThanOrEqual, true);
    map.clear();
    map.put(colName, 2.5);
    assertTrue("2.5 was falsely rejected.", cond.testCondition(record));
    map.clear();
    map.put(colName, 3);
    assertTrue("3 was falsely rejected.", cond.testCondition(record));
    map.clear();
    map.put(colName, 4);
    assertFalse("4 was falsely accepted.", cond.testCondition(record));
    map.clear();
    map.put(colName, PredictorRecord.NULL);
    assertTrue("Missing values were falsely rejected.", cond.testCondition(record));
    cond = new TreeNodeNumericCondition(col.getMetaData(), 4, NumericOperator.LargerThan, false);
    map.clear();
    map.put(colName, 2.5);
    assertFalse("2.5 was falsely accepted.", cond.testCondition(record));
    map.clear();
    map.put(colName, 3);
    assertFalse("3 was falsely accepted.", cond.testCondition(record));
    map.clear();
    map.put(colName, 4);
    assertFalse("4 was falsely accepted.", cond.testCondition(record));
    map.clear();
    map.put(colName, 4.01);
    assertTrue("4.01 was falsely rejected.", cond.testCondition(record));
    map.clear();
    map.put(colName, PredictorRecord.NULL);
    assertFalse("Missing values were falsely accepted.", cond.testCondition(record));
    cond = new TreeNodeNumericCondition(col.getMetaData(), 4, NumericOperator.LargerThan, true);
    map.clear();
    map.put(colName, 2.5);
    assertFalse("2.5 was falsely accepted.", cond.testCondition(record));
    map.clear();
    map.put(colName, 3);
    assertFalse("3 was falsely accepted.", cond.testCondition(record));
    map.clear();
    map.put(colName, 4.01);
    assertTrue("4 was falsely rejected.", cond.testCondition(record));
    map.clear();
    map.put(colName, PredictorRecord.NULL);
    assertTrue("Missing values were falsely rejected.", cond.testCondition(record));
}