use of org.knime.base.node.mine.treeensemble2.data.TreeNumericColumnData 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);
}
use of org.knime.base.node.mine.treeensemble2.data.TreeNumericColumnData in project knime-core by knime.
the class TreeNumericColumnDataTest method testUpdateChildMemberships.
/**
* Tests the {@link TreeNumericColumnData#updateChildMemberships(TreeNodeCondition, DataMemberships)} methods with
* different conditions including missing values.
*
* @throws Exception
*/
@Test
public void testUpdateChildMemberships() throws Exception {
final TreeEnsembleLearnerConfiguration config = createConfig();
final TestDataGenerator dataGen = new TestDataGenerator(config);
final int[] indices = new int[] { 0, 1, 2, 3, 4, 5, 6 };
final double[] weights = new double[7];
Arrays.fill(weights, 1.0);
final DataMemberships dataMem = new MockDataColMem(indices, indices, weights);
final String noMissingsCSV = "-50, -3, -2, 2, 25, 100, 101";
final TreeNumericColumnData col = dataGen.createNumericAttributeColumn(noMissingsCSV, "noMissings-col", 0);
// less than or equals
TreeNodeNumericCondition numCond = new TreeNodeNumericCondition(col.getMetaData(), -2, NumericOperator.LessThanOrEqual, false);
BitSet inChild = col.updateChildMemberships(numCond, dataMem);
BitSet expected = new BitSet(3);
expected.set(0, 3);
assertEquals("The produced BitSet is incorrect.", expected, inChild);
// greater than
numCond = new TreeNodeNumericCondition(col.getMetaData(), 10, NumericOperator.LargerThan, false);
inChild = col.updateChildMemberships(numCond, dataMem);
expected.clear();
expected.set(4, 7);
assertEquals("The produced BitSet is incorrect", expected, inChild);
// with missing values
final String missingsCSV = "-2, 0, 1, 43, 61, 66, NaN";
final TreeNumericColumnData colWithMissings = dataGen.createNumericAttributeColumn(missingsCSV, "missings-col", 0);
// less than or equal or missing
numCond = new TreeNodeNumericCondition(colWithMissings.getMetaData(), 12, NumericOperator.LessThanOrEqual, true);
inChild = colWithMissings.updateChildMemberships(numCond, dataMem);
expected.clear();
expected.set(0, 3);
expected.set(6);
assertEquals("The produced BitSet is incorrect", expected, inChild);
// less than or equals not missing
numCond = new TreeNodeNumericCondition(colWithMissings.getMetaData(), 12, NumericOperator.LessThanOrEqual, false);
inChild = colWithMissings.updateChildMemberships(numCond, dataMem);
expected.clear();
expected.set(0, 3);
assertEquals("The produced BitSet is incorrect", expected, inChild);
// larger than or missing
numCond = new TreeNodeNumericCondition(colWithMissings.getMetaData(), 43, NumericOperator.LargerThan, true);
inChild = colWithMissings.updateChildMemberships(numCond, dataMem);
expected.clear();
expected.set(4, 7);
assertEquals("The produced BitSet is incorrect", expected, inChild);
// larger than not missing
numCond = new TreeNodeNumericCondition(colWithMissings.getMetaData(), 12, NumericOperator.LargerThan, false);
inChild = colWithMissings.updateChildMemberships(numCond, dataMem);
expected.clear();
expected.set(3, 6);
assertEquals("The produced BitSet is incorrect", expected, inChild);
}
use of org.knime.base.node.mine.treeensemble2.data.TreeNumericColumnData 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);
}
use of org.knime.base.node.mine.treeensemble2.data.TreeNumericColumnData 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.TreeNumericColumnData 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);
}
Aggregations