Examples with TreeEnsembleLearnerConfiguration org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration used on opensource projects

Example 11 with TreeEnsembleLearnerConfiguration

use of org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration in project knime-core by knime.

the class TreeNominalColumnData method calcBestSplitClassificationBinaryPCA.

/**
 * Implements the approach proposed by Coppersmith et al. (1999) in their paper
 * "Partitioning Nominal Attributes in Decision Trees"
 *
 * @param membershipController
 * @param rowWeights
 * @param targetPriors
 * @param targetColumn
 * @param impCriterion
 * @param nomVals
 * @param targetVals
 * @param originalIndexInColumnList
 * @return the best binary split candidate or null if there is no valid split with positive gain
 */
private NominalBinarySplitCandidate calcBestSplitClassificationBinaryPCA(final ColumnMemberships columnMemberships, final ClassificationPriors targetPriors, final TreeTargetNominalColumnData targetColumn, final IImpurity impCriterion, final NominalValueRepresentation[] nomVals, final NominalValueRepresentation[] targetVals, final RandomData rd) {
    final TreeEnsembleLearnerConfiguration config = getConfiguration();
    final int minChildSize = config.getMinChildSize();
    final boolean useXGBoostMissingValueHandling = config.getMissingValueHandling() == MissingValueHandling.XGBoost;
    // The algorithm combines attribute values with the same class probabilities into a single attribute
    // therefore it is necessary to track the known classProbabilities
    final LinkedHashMap<ClassProbabilityVector, CombinedAttributeValues> combinedAttValsMap = new LinkedHashMap<ClassProbabilityVector, CombinedAttributeValues>();
    columnMemberships.next();
    double totalWeight = 0.0;
    boolean branchContainsMissingValues = containsMissingValues();
    int start = 0;
    final int lengthNonMissing = containsMissingValues() ? nomVals.length - 1 : nomVals.length;
    final int attToConsider = useXGBoostMissingValueHandling ? nomVals.length : lengthNonMissing;
    for (int att = 0; att < lengthNonMissing; /*attToConsider*/
    att++) {
        int end = start + m_nominalValueCounts[att];
        double attWeight = 0.0;
        final double[] classFrequencies = new double[targetVals.length];
        boolean reachedEnd = false;
        for (int index = columnMemberships.getIndexInColumn(); index < end; index = columnMemberships.getIndexInColumn()) {
            double weight = columnMemberships.getRowWeight();
            assert weight > EPSILON : "Instances in columnMemberships must have weights larger than EPSILON.";
            int instanceClass = targetColumn.getValueFor(columnMemberships.getOriginalIndex());
            classFrequencies[instanceClass] += weight;
            attWeight += weight;
            totalWeight += weight;
            if (!columnMemberships.next()) {
                // reached end of columnMemberships
                reachedEnd = true;
                if (att == nomVals.length - 1) {
                    // if the column contains no missing values, the last possible nominal value is
                    // not the missing value and therefore branchContainsMissingValues needs to be false
                    branchContainsMissingValues = branchContainsMissingValues && true;
                }
                break;
            }
        }
        start = end;
        if (attWeight < EPSILON) {
            // attribute value did not occur in this branch or sample
            continue;
        }
        final double[] classProbabilities = new double[targetVals.length];
        for (int i = 0; i < classProbabilities.length; i++) {
            classProbabilities[i] = truncateDouble(8, classFrequencies[i] / attWeight);
        }
        CombinedAttributeValues attVal = new CombinedAttributeValues(classFrequencies, classProbabilities, attWeight, nomVals[att]);
        ClassProbabilityVector classProbabilityVector = new ClassProbabilityVector(classProbabilities);
        CombinedAttributeValues knownAttVal = combinedAttValsMap.get(classProbabilityVector);
        if (knownAttVal == null) {
            combinedAttValsMap.put(classProbabilityVector, attVal);
        } else {
            knownAttVal.combineAttributeValues(attVal);
        }
        if (reachedEnd) {
            break;
        }
    }
    // account for missing values and their weight
    double missingWeight = 0.0;
    double[] missingClassCounts = null;
    // otherwise the current indexInColumn won't be larger than start
    if (columnMemberships.getIndexInColumn() >= start) {
        missingClassCounts = new double[targetVals.length];
        do {
            final double recordWeight = columnMemberships.getRowWeight();
            final int recordClass = targetColumn.getValueFor(columnMemberships.getOriginalIndex());
            missingWeight += recordWeight;
            missingClassCounts[recordClass] += recordWeight;
        } while (columnMemberships.next());
    }
    if (missingWeight > EPSILON) {
        branchContainsMissingValues = true;
    } else {
        branchContainsMissingValues = false;
    }
    ArrayList<CombinedAttributeValues> attValList = Lists.newArrayList(combinedAttValsMap.values());
    CombinedAttributeValues[] attVals = combinedAttValsMap.values().toArray(new CombinedAttributeValues[combinedAttValsMap.size()]);
    attVals = BinaryNominalSplitsPCA.calculatePCAOrdering(attVals, totalWeight, targetVals.length);
    // EigenDecomposition failed
    if (attVals == null) {
        return null;
    }
    // Start searching for split candidates
    final int highestBitPosition = containsMissingValues() ? nomVals.length - 2 : nomVals.length - 1;
    final double[] binaryImpurityValues = new double[2];
    final double[] binaryPartitionWeights = new double[2];
    double sumRemainingWeights = totalWeight;
    double sumCurrPartitionWeight = 0.0;
    RealVector targetFrequenciesCurrentPartition = MatrixUtils.createRealVector(new double[targetVals.length]);
    RealVector targetFrequenciesRemaining = MatrixUtils.createRealVector(new double[targetVals.length]);
    for (CombinedAttributeValues attVal : attValList) {
        targetFrequenciesRemaining = targetFrequenciesRemaining.add(attVal.m_classFrequencyVector);
    }
    BigInteger currPartitionBitMask = BigInteger.ZERO;
    double bestPartitionGain = Double.NEGATIVE_INFINITY;
    BigInteger bestPartitionMask = null;
    boolean isBestSplitValid = false;
    boolean missingsGoLeft = false;
    final double priorImpurity = useXGBoostMissingValueHandling ? targetPriors.getPriorImpurity() : impCriterion.getPartitionImpurity(subtractMissingClassCounts(targetPriors.getDistribution(), missingClassCounts), totalWeight);
    // no need to iterate over full list because at least one value must remain on the other side of the split
    for (int i = 0; i < attVals.length - 1; i++) {
        CombinedAttributeValues currAttVal = attVals[i];
        sumCurrPartitionWeight += currAttVal.m_totalWeight;
        sumRemainingWeights -= currAttVal.m_totalWeight;
        assert sumCurrPartitionWeight + sumRemainingWeights == totalWeight : "The weights of the partitions do not sum up to the total weight.";
        targetFrequenciesCurrentPartition = targetFrequenciesCurrentPartition.add(currAttVal.m_classFrequencyVector);
        targetFrequenciesRemaining = targetFrequenciesRemaining.subtract(currAttVal.m_classFrequencyVector);
        currPartitionBitMask = currPartitionBitMask.or(currAttVal.m_bitMask);
        boolean partitionIsRightBranch = currPartitionBitMask.testBit(highestBitPosition);
        boolean isValidSplit;
        double gain;
        boolean tempMissingsGoLeft = true;
        if (branchContainsMissingValues && useXGBoostMissingValueHandling) {
            // send missing values with partition
            boolean isValidSplitFirst = sumCurrPartitionWeight + missingWeight >= minChildSize && sumRemainingWeights >= minChildSize;
            binaryImpurityValues[0] = impCriterion.getPartitionImpurity(addMissingClassCounts(targetFrequenciesCurrentPartition.toArray(), missingClassCounts), sumCurrPartitionWeight + missingWeight);
            binaryImpurityValues[1] = impCriterion.getPartitionImpurity(targetFrequenciesRemaining.toArray(), sumRemainingWeights);
            binaryPartitionWeights[0] = sumCurrPartitionWeight + missingWeight;
            binaryPartitionWeights[1] = sumRemainingWeights;
            double postSplitImpurity = impCriterion.getPostSplitImpurity(binaryImpurityValues, binaryPartitionWeights, totalWeight + missingWeight);
            double gainFirst = impCriterion.getGain(priorImpurity, postSplitImpurity, binaryPartitionWeights, totalWeight + missingWeight);
            // send missing values with remaining
            boolean isValidSplitSecond = sumCurrPartitionWeight >= minChildSize && sumRemainingWeights + missingWeight >= minChildSize;
            binaryImpurityValues[0] = impCriterion.getPartitionImpurity(targetFrequenciesCurrentPartition.toArray(), sumCurrPartitionWeight);
            binaryImpurityValues[1] = impCriterion.getPartitionImpurity(addMissingClassCounts(targetFrequenciesRemaining.toArray(), missingClassCounts), sumRemainingWeights + missingWeight);
            binaryPartitionWeights[0] = sumCurrPartitionWeight;
            binaryPartitionWeights[1] = sumRemainingWeights + missingWeight;
            postSplitImpurity = impCriterion.getPostSplitImpurity(binaryImpurityValues, binaryPartitionWeights, totalWeight + missingWeight);
            double gainSecond = impCriterion.getGain(priorImpurity, postSplitImpurity, binaryPartitionWeights, totalWeight + missingWeight);
            // choose alternative with better gain
            if (gainFirst >= gainSecond) {
                gain = gainFirst;
                isValidSplit = isValidSplitFirst;
                tempMissingsGoLeft = !partitionIsRightBranch;
            } else {
                gain = gainSecond;
                isValidSplit = isValidSplitSecond;
                tempMissingsGoLeft = partitionIsRightBranch;
            }
        } else {
            // TODO if invalid splits should not be considered skip partition
            isValidSplit = sumCurrPartitionWeight >= minChildSize && sumRemainingWeights >= minChildSize;
            binaryImpurityValues[0] = impCriterion.getPartitionImpurity(targetFrequenciesCurrentPartition.toArray(), sumCurrPartitionWeight);
            binaryImpurityValues[1] = impCriterion.getPartitionImpurity(targetFrequenciesRemaining.toArray(), sumRemainingWeights);
            binaryPartitionWeights[0] = sumCurrPartitionWeight;
            binaryPartitionWeights[1] = sumRemainingWeights;
            double postSplitImpurity = impCriterion.getPostSplitImpurity(binaryImpurityValues, binaryPartitionWeights, totalWeight);
            gain = impCriterion.getGain(priorImpurity, postSplitImpurity, binaryPartitionWeights, totalWeight);
        }
        // use random tie breaker if gains are equal
        boolean randomTieBreaker = gain == bestPartitionGain ? rd.nextInt(0, 1) == 1 : false;
        // store if better than before or first valid split
        if (gain > bestPartitionGain || (!isBestSplitValid && isValidSplit) || randomTieBreaker) {
            if (isValidSplit || !isBestSplitValid) {
                bestPartitionGain = gain;
                bestPartitionMask = partitionIsRightBranch ? currPartitionBitMask : BigInteger.ZERO.setBit(highestBitPosition + 1).subtract(BigInteger.ONE).xor(currPartitionBitMask);
                isBestSplitValid = isValidSplit;
                if (branchContainsMissingValues) {
                    missingsGoLeft = tempMissingsGoLeft;
                // missing values are encountered during the search for the best split
                // missingsGoLeft = partitionIsRightBranch;
                } else {
                    // no missing values were encountered during the search for the best split
                    // missing values should be sent with the majority
                    missingsGoLeft = partitionIsRightBranch ? sumCurrPartitionWeight < sumRemainingWeights : sumCurrPartitionWeight >= sumRemainingWeights;
                }
            }
        }
    }
    if (isBestSplitValid && bestPartitionGain > 0.0) {
        if (useXGBoostMissingValueHandling) {
            return new NominalBinarySplitCandidate(this, bestPartitionGain, bestPartitionMask, NO_MISSED_ROWS, missingsGoLeft ? NominalBinarySplitCandidate.MISSINGS_GO_LEFT : NominalBinarySplitCandidate.MISSINGS_GO_RIGHT);
        }
        return new NominalBinarySplitCandidate(this, bestPartitionGain, bestPartitionMask, getMissedRows(columnMemberships), NominalBinarySplitCandidate.NO_MISSINGS);
    }
    return null;
}

Example 12 with TreeEnsembleLearnerConfiguration

use of org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration 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);
}

Example 13 with TreeEnsembleLearnerConfiguration

use of org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration in project knime-core by knime.

the class TreeLearnerRegression method findBestSplitsRegression.

private SplitCandidate[] findBestSplitsRegression(final int currentDepth, final DataMemberships dataMemberships, final ColumnSample columnSample, final RegressionPriors targetPriors, final BitSet forbiddenColumnSet) {
    final TreeData data = getData();
    final RandomData rd = getRandomData();
    final TreeEnsembleLearnerConfiguration config = getConfig();
    final int maxLevels = config.getMaxLevels();
    if (maxLevels != TreeEnsembleLearnerConfiguration.MAX_LEVEL_INFINITE && currentDepth >= maxLevels) {
        return null;
    }
    final int minNodeSize = config.getMinNodeSize();
    if (minNodeSize != TreeEnsembleLearnerConfiguration.MIN_NODE_SIZE_UNDEFINED) {
        if (targetPriors.getNrRecords() < minNodeSize) {
            return null;
        }
    }
    final double priorSquaredDeviation = targetPriors.getSumSquaredDeviation();
    if (priorSquaredDeviation < TreeColumnData.EPSILON) {
        return null;
    }
    final TreeTargetNumericColumnData targetColumn = getTargetData();
    ArrayList<SplitCandidate> splitCandidates = null;
    if (currentDepth == 0 && config.getHardCodedRootColumn() != null) {
        final TreeAttributeColumnData rootColumn = data.getColumn(config.getHardCodedRootColumn());
        return new SplitCandidate[] { rootColumn.calcBestSplitRegression(dataMemberships, targetPriors, targetColumn, rd) };
    } else {
        splitCandidates = new ArrayList<SplitCandidate>(columnSample.getNumCols());
        for (TreeAttributeColumnData col : columnSample) {
            if (forbiddenColumnSet.get(col.getMetaData().getAttributeIndex())) {
                continue;
            }
            SplitCandidate currentColSplit = col.calcBestSplitRegression(dataMemberships, targetPriors, targetColumn, rd);
            if (currentColSplit != null) {
                splitCandidates.add(currentColSplit);
            }
        }
    }
    Comparator<SplitCandidate> comp = new Comparator<SplitCandidate>() {

        @Override
        public int compare(final SplitCandidate arg0, final SplitCandidate arg1) {
            int compareDouble = -Double.compare(arg0.getGainValue(), arg1.getGainValue());
            return compareDouble;
        }
    };
    if (splitCandidates.isEmpty()) {
        return null;
    }
    splitCandidates.sort(comp);
    return splitCandidates.toArray(new SplitCandidate[splitCandidates.size()]);
}

Example 14 with TreeEnsembleLearnerConfiguration

use of org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration in project knime-core by knime.

the class TreeNominalColumnDataTest method createPCATestData.

private static Pair<TreeNominalColumnData, TreeTargetNominalColumnData> createPCATestData(final TreeEnsembleLearnerConfiguration config) {
    DataColumnSpec colSpec = new DataColumnSpecCreator("test-col", StringCell.TYPE).createSpec();
    final String[] attVals = new String[] { "A", "B", "C", "D", "E" };
    final String[] classes = new String[] { "T1", "T2", "T3" };
    TreeNominalColumnDataCreator colCreator = new TreeNominalColumnDataCreator(colSpec);
    DataColumnSpecCreator specCreator = new DataColumnSpecCreator("target-col", StringCell.TYPE);
    specCreator.setDomain(new DataColumnDomainCreator(Arrays.stream(classes).distinct().map(s -> new StringCell(s)).toArray(i -> new StringCell[i])).createDomain());
    DataColumnSpec targetSpec = specCreator.createSpec();
    TreeTargetColumnDataCreator targetCreator = new TreeTargetNominalColumnDataCreator(targetSpec);
    long rowKeyCounter = 0;
    final int[][] classDistributions = new int[][] { { 40, 10, 10 }, { 10, 40, 10 }, { 20, 30, 10 }, { 20, 15, 25 }, { 10, 5, 45 } };
    for (int i = 0; i < attVals.length; i++) {
        for (int j = 0; j < classes.length; j++) {
            for (int k = 0; k < classDistributions[i][j]; k++) {
                RowKey key = RowKey.createRowKey(rowKeyCounter++);
                colCreator.add(key, new StringCell(attVals[i]));
                targetCreator.add(key, new StringCell(classes[j]));
            }
        }
    }
    final TreeNominalColumnData testColData = colCreator.createColumnData(0, config);
    testColData.getMetaData().setAttributeIndex(0);
    return Pair.create(testColData, (TreeTargetNominalColumnData) targetCreator.createColumnData());
}

Example 15 with TreeEnsembleLearnerConfiguration

use of org.knime.base.node.mine.treeensemble2.node.learner.TreeEnsembleLearnerConfiguration 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());
}