use of org.knime.base.node.mine.treeensemble2.data.TreeData 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* This test is outdated and will likely be removed soon.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);
}
use of org.knime.base.node.mine.treeensemble2.data.TreeData 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);
}
use of org.knime.base.node.mine.treeensemble2.data.TreeData 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);
}
}
use of org.knime.base.node.mine.treeensemble2.data.TreeData in project knime-core by knime.
the class TreeTargetNumericColumnDataTest method testGetPriors.
/**
* Tests the {@link TreeTargetNumericColumnData#getPriors(DataMemberships, TreeEnsembleLearnerConfiguration)} and
* {@link TreeTargetNumericColumnData#getPriors(double[], TreeEnsembleLearnerConfiguration)} methods.
*/
@Test
public void testGetPriors() {
String targetCSV = "1,4,3,5,6,7,8,12,22,1";
// irrelevant but necessary to build TreeDataObject
String someAttributeCSV = "A,B,A,B,A,A,B,A,A,B";
TreeEnsembleLearnerConfiguration config = new TreeEnsembleLearnerConfiguration(true);
TestDataGenerator dataGen = new TestDataGenerator(config);
TreeTargetNumericColumnData target = TestDataGenerator.createNumericTargetColumn(targetCSV);
TreeNominalColumnData attribute = dataGen.createNominalAttributeColumn(someAttributeCSV, "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));
RegressionPriors datMemPriors = target.getPriors(rootMem, config);
assertEquals(6.9, datMemPriors.getMean(), DELTA);
assertEquals(69, datMemPriors.getYSum(), DELTA);
assertEquals(352.9, datMemPriors.getSumSquaredDeviation(), DELTA);
}
use of org.knime.base.node.mine.treeensemble2.data.TreeData in project knime-core by knime.
the class RootDescendantDataMembershipsTest method testCreateChildDataMemberships.
@Test
public void testCreateChildDataMemberships() {
TreeEnsembleLearnerConfiguration config = new TreeEnsembleLearnerConfiguration(false);
TestDataGenerator dataGen = new TestDataGenerator(config);
TreeData data = dataGen.createTennisData();
DefaultDataIndexManager indexManager = new DefaultDataIndexManager(data);
int nrRows = data.getNrRows();
RowSample rowSample = new DefaultRowSample(nrRows);
RootDataMemberships rootMemberships = new RootDataMemberships(rowSample, data, indexManager);
BitSet firstHalf = new BitSet(nrRows);
firstHalf.set(0, nrRows / 2);
DataMemberships firstHalfChildMemberships = rootMemberships.createChildMemberships(firstHalf);
assertThat(firstHalfChildMemberships, instanceOf(BitSetDescendantDataMemberships.class));
BitSetDescendantDataMemberships bitSetFirstHalfChildMemberships = (BitSetDescendantDataMemberships) firstHalfChildMemberships;
assertEquals(firstHalf, bitSetFirstHalfChildMemberships.getBitSet());
BitSet firstQuarter = new BitSet(nrRows);
firstQuarter.set(0, nrRows / 4);
DataMemberships firstQuarterGrandChild = firstHalfChildMemberships.createChildMemberships(firstQuarter);
assertThat(firstQuarterGrandChild, instanceOf(BitSetDescendantDataMemberships.class));
BitSetDescendantDataMemberships bitSetFirstQuarterGrandChild = (BitSetDescendantDataMemberships) firstQuarterGrandChild;
assertEquals(firstQuarter, bitSetFirstQuarterGrandChild.getBitSet());
}
Aggregations