use of org.knime.base.node.mine.treeensemble2.data.memberships.IDataIndexManager in project knime-core by knime.
the class TreeLearnerRegression method learnSingleTree.
/**
* {@inheritDoc}
*/
@Override
public TreeModelRegression learnSingleTree(final ExecutionMonitor exec, final RandomData rd) throws CanceledExecutionException {
final TreeTargetNumericColumnData targetColumn = getTargetData();
final TreeData data = getData();
final RowSample rowSampling = getRowSampling();
final TreeEnsembleLearnerConfiguration config = getConfig();
final IDataIndexManager indexManager = getIndexManager();
DataMemberships rootDataMemberships = new RootDataMemberships(rowSampling, data, indexManager);
RegressionPriors targetPriors = targetColumn.getPriors(rootDataMemberships, config);
BitSet forbiddenColumnSet = new BitSet(data.getNrAttributes());
boolean isGradientBoosting = config instanceof GradientBoostingLearnerConfiguration;
if (isGradientBoosting) {
m_leafs = new ArrayList<TreeNodeRegression>();
}
final TreeNodeSignature rootSignature = TreeNodeSignature.ROOT_SIGNATURE;
final ColumnSample rootColumnSample = getColSamplingStrategy().getColumnSampleForTreeNode(rootSignature);
TreeNodeRegression rootNode = buildTreeNode(exec, 0, rootDataMemberships, rootColumnSample, getSignatureFactory().getRootSignature(), targetPriors, forbiddenColumnSet);
assert forbiddenColumnSet.cardinality() == 0;
rootNode.setTreeNodeCondition(TreeNodeTrueCondition.INSTANCE);
if (isGradientBoosting) {
return new TreeModelRegression(rootNode, m_leafs);
}
return new TreeModelRegression(rootNode);
}
use of org.knime.base.node.mine.treeensemble2.data.memberships.IDataIndexManager in project knime-core by knime.
the class AbstractGradientBoostedTreesLearner method adaptPreviousPrediction.
/**
* Adapts the previous prediction by adding the predictions of the <b>tree</b> regulated by the respective
* coefficients in <b>coefficientMap</b>.
*
* @param previousPrediction Prediction of the previous steps
* @param tree the tree of the current iteration
* @param coefficientMap contains the coefficients for the leafs of the tree
*/
protected void adaptPreviousPrediction(final double[] previousPrediction, final TreeModelRegression tree, final Map<TreeNodeSignature, Double> coefficientMap) {
TreeData data = getData();
IDataIndexManager indexManager = getIndexManager();
for (int i = 0; i < data.getNrRows(); i++) {
PredictorRecord record = createPredictorRecord(data, indexManager, i);
previousPrediction[i] += coefficientMap.get(tree.findMatchingNode(record).getSignature());
}
}
use of org.knime.base.node.mine.treeensemble2.data.memberships.IDataIndexManager in project knime-core by knime.
the class LKGradientBoostedTreesLearner method adaptPreviousFunction.
private void adaptPreviousFunction(final double[] previousFunction, final TreeModelRegression tree, final Map<TreeNodeSignature, Double> coefficientMap) {
final TreeData data = getData();
final IDataIndexManager indexManager = getIndexManager();
for (int i = 0; i < previousFunction.length; i++) {
final PredictorRecord record = createPredictorRecord(data, indexManager, i);
final TreeNodeSignature signature = tree.findMatchingNode(record).getSignature();
previousFunction[i] += coefficientMap.get(signature);
}
}
use of org.knime.base.node.mine.treeensemble2.data.memberships.IDataIndexManager in project knime-core by knime.
the class TreeNominalColumnDataTest method testCalcBestSplitClassificationMultiWay.
/**
* Tests the method
* {@link TreeNominalColumnData#calcBestSplitClassification(DataMemberships, ClassificationPriors, TreeTargetNominalColumnData, RandomData)}
* using multiway splits
*
* @throws Exception
*/
@Test
public void testCalcBestSplitClassificationMultiWay() throws Exception {
TreeEnsembleLearnerConfiguration config = createConfig(false);
config.setUseBinaryNominalSplits(false);
Pair<TreeNominalColumnData, TreeTargetNominalColumnData> tennisData = tennisData(config);
TreeNominalColumnData columnData = tennisData.getFirst();
TreeTargetNominalColumnData targetData = tennisData.getSecond();
TreeData treeData = createTreeData(tennisData);
assertEquals(SplitCriterion.Gini, config.getSplitCriterion());
double[] rowWeights = new double[SMALL_COLUMN_DATA.length];
Arrays.fill(rowWeights, 1.0);
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, null);
assertNotNull(splitCandidate);
assertThat(splitCandidate, instanceOf(NominalMultiwaySplitCandidate.class));
assertFalse(splitCandidate.canColumnBeSplitFurther());
// manually via libre office calc
assertEquals(0.0744897959, splitCandidate.getGainValue(), 0.00001);
NominalMultiwaySplitCandidate multiWaySplitCandidate = (NominalMultiwaySplitCandidate) splitCandidate;
TreeNodeNominalCondition[] childConditions = multiWaySplitCandidate.getChildConditions();
assertEquals(3, childConditions.length);
assertEquals("S", childConditions[0].getValue());
assertEquals("O", childConditions[1].getValue());
assertEquals("R", childConditions[2].getValue());
}
use of org.knime.base.node.mine.treeensemble2.data.memberships.IDataIndexManager in project knime-core by knime.
the class TreeNominalColumnDataTest method testCalcBestSplitCassificationBinaryTwoClassXGBoostMissingValue.
/**
* Tests the XGBoost Missing value handling in case of a two class problem <br>
* currently not tested because missing value handling will probably be implemented differently.
*
* @throws Exception
*/
// @Test
public void testCalcBestSplitCassificationBinaryTwoClassXGBoostMissingValue() throws Exception {
final TreeEnsembleLearnerConfiguration config = createConfig(false);
config.setMissingValueHandling(MissingValueHandling.XGBoost);
final TestDataGenerator dataGen = new TestDataGenerator(config);
// check correct behavior if no missing values are encountered during split search
Pair<TreeNominalColumnData, TreeTargetNominalColumnData> twoClassTennisData = twoClassTennisData(config);
TreeData treeData = dataGen.createTreeData(twoClassTennisData.getSecond(), twoClassTennisData.getFirst());
IDataIndexManager indexManager = new DefaultDataIndexManager(treeData);
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, treeData, indexManager);
TreeTargetNominalColumnData targetData = twoClassTennisData.getSecond();
TreeNominalColumnData columnData = twoClassTennisData.getFirst();
ClassificationPriors priors = targetData.getDistribution(rowWeights, config);
RandomData rd = TestDataGenerator.createRandomData();
SplitCandidate splitCandidate = columnData.calcBestSplitClassification(dataMemberships, priors, targetData, rd);
assertNotNull(splitCandidate);
assertThat(splitCandidate, instanceOf(NominalBinarySplitCandidate.class));
NominalBinarySplitCandidate binarySplitCandidate = (NominalBinarySplitCandidate) splitCandidate;
TreeNodeNominalBinaryCondition[] childConditions = binarySplitCandidate.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());
// check if missing values go left
assertTrue(childConditions[0].acceptsMissings());
assertFalse(childConditions[1].acceptsMissings());
// check correct behavior if missing values are encountered during split search
String dataContainingMissingsCSV = "S,?,O,R,S,R,S,O,O,?";
columnData = dataGen.createNominalAttributeColumn(dataContainingMissingsCSV, "column containing missing values", 0);
treeData = dataGen.createTreeData(targetData, columnData);
indexManager = new DefaultDataIndexManager(treeData);
dataMemberships = new RootDataMemberships(rowWeights, treeData, indexManager);
splitCandidate = columnData.calcBestSplitClassification(dataMemberships, priors, targetData, null);
assertNotNull(splitCandidate);
binarySplitCandidate = (NominalBinarySplitCandidate) splitCandidate;
assertEquals("Gain was not as expected", 0.08, binarySplitCandidate.getGainValue(), 1e-8);
childConditions = binarySplitCandidate.getChildConditions();
String[] conditionValues = new String[] { "O", "?" };
assertArrayEquals("Values in nominal condition did not match", conditionValues, childConditions[0].getValues());
assertArrayEquals("Values in nominal condition did not match", conditionValues, childConditions[1].getValues());
assertEquals("Wrong set logic.", SetLogic.IS_NOT_IN, childConditions[0].getSetLogic());
assertEquals("Wrong set logic.", SetLogic.IS_IN, childConditions[1].getSetLogic());
assertFalse("Missig values are not sent to the correct child.", childConditions[0].acceptsMissings());
assertTrue("Missig values are not sent to the correct child.", childConditions[1].acceptsMissings());
}
Aggregations