Examples with PMMLPredicate org.knime.base.node.mine.decisiontree2.PMMLPredicate used on opensource projects

Example 16 with PMMLPredicate

use of org.knime.base.node.mine.decisiontree2.PMMLPredicate in project knime-core by knime.

the class DecisionTreeLearnerNodeModel method buildTree.

/**
 * Recursively induces the decision tree.
 *
 * @param table the {@link InMemoryTable} representing the data for this
 *            node to determine the split and after that perform
 *            partitioning
 * @param exec the execution context for progress information
 * @param depth the current recursion depth
 */
private DecisionTreeNode buildTree(final InMemoryTable table, final ExecutionContext exec, final int depth, final SplitQualityMeasure splitQualityMeasure, final ParallelProcessing parallelProcessing) throws CanceledExecutionException, IllegalAccessException {
    exec.checkCanceled();
    // derive this node's id from the counter
    int nodeId = m_counter.getAndIncrement();
    DataCell majorityClass = table.getMajorityClassAsCell();
    LinkedHashMap<DataCell, Double> frequencies = table.getClassFrequencies();
    // if the distribution allows for a leaf
    if (table.isPureEnough()) {
        // free memory
        table.freeUnderlyingDataRows();
        double value = m_finishedCounter.incrementAndGet(table.getSumOfWeights());
        exec.setProgress(value / m_alloverRowCount, "Created node with id " + nodeId + " at level " + depth);
        return new DecisionTreeNodeLeaf(nodeId, majorityClass, frequencies);
    } else {
        // find the best splits for all attributes
        SplitFinder splittFinder = new SplitFinder(table, splitQualityMeasure, m_averageSplitpoint.getBooleanValue(), m_minNumberRecordsPerNode.getIntValue(), m_binaryNominalSplitMode.getBooleanValue(), m_maxNumNominalsForCompleteComputation.getIntValue());
        // check for enough memory
        checkMemory();
        // get the best split among the best attribute splits
        Split split = splittFinder.getSplit();
        // if no best split could be evaluated, create a leaf node
        if (split == null || !split.isValidSplit()) {
            table.freeUnderlyingDataRows();
            double value = m_finishedCounter.incrementAndGet(table.getSumOfWeights());
            exec.setProgress(value / m_alloverRowCount, "Created node with id " + nodeId + " at level " + depth);
            return new DecisionTreeNodeLeaf(nodeId, majorityClass, frequencies);
        }
        // partition the attribute lists according to this split
        Partitioner partitioner = new Partitioner(table, split, m_minNumberRecordsPerNode.getIntValue());
        if (!partitioner.couldBeUsefulPartitioned()) {
            table.freeUnderlyingDataRows();
            double value = m_finishedCounter.incrementAndGet(table.getSumOfWeights());
            exec.setProgress(value / m_alloverRowCount, "Created node with id " + nodeId + " at level " + depth);
            return new DecisionTreeNodeLeaf(nodeId, majorityClass, frequencies);
        }
        // get the just created partitions
        InMemoryTable[] partitionTables = partitioner.getPartitionTables();
        // recursively build the  child nodes
        DecisionTreeNode[] children = new DecisionTreeNode[partitionTables.length];
        ArrayList<ParallelBuilding> threads = new ArrayList<ParallelBuilding>();
        int i = 0;
        for (InMemoryTable partitionTable : partitionTables) {
            exec.checkCanceled();
            if (partitionTable.getNumberDataRows() * m_numberAttributes < 10000 || !parallelProcessing.isThreadAvailable()) {
                children[i] = buildTree(partitionTable, exec, depth + 1, splitQualityMeasure, parallelProcessing);
            } else {
                String threadName = "Build thread, node: " + nodeId + "." + i;
                ParallelBuilding buildThread = new ParallelBuilding(threadName, partitionTable, exec, depth + 1, i, splitQualityMeasure, parallelProcessing);
                LOGGER.debug("Start new parallel building thread: " + threadName);
                threads.add(buildThread);
                buildThread.start();
            }
            i++;
        }
        // already assigned to the child array
        for (ParallelBuilding buildThread : threads) {
            children[buildThread.getThreadIndex()] = buildThread.getResultNode();
            exec.checkCanceled();
            if (buildThread.getException() != null) {
                for (ParallelBuilding buildThread2 : threads) {
                    buildThread2.stop();
                }
                throw new RuntimeException(buildThread.getException().getMessage());
            }
        }
        threads.clear();
        if (split instanceof SplitContinuous) {
            double splitValue = ((SplitContinuous) split).getBestSplitValue();
            // return new DecisionTreeNodeSplitContinuous(nodeId,
            // majorityClass, frequencies, split
            // .getSplitAttributeName(), children, splitValue);
            String splitAttribute = split.getSplitAttributeName();
            PMMLPredicate[] splitPredicates = new PMMLPredicate[] { new PMMLSimplePredicate(splitAttribute, PMMLOperator.LESS_OR_EQUAL, Double.toString(splitValue)), new PMMLSimplePredicate(splitAttribute, PMMLOperator.GREATER_THAN, Double.toString(splitValue)) };
            return new DecisionTreeNodeSplitPMML(nodeId, majorityClass, frequencies, splitAttribute, splitPredicates, children);
        } else if (split instanceof SplitNominalNormal) {
            // else the attribute is nominal
            DataCell[] splitValues = ((SplitNominalNormal) split).getSplitValues();
            // return new DecisionTreeNodeSplitNominal(nodeId, majorityClass,
            // frequencies, split.getSplitAttributeName(),
            // splitValues, children);
            int num = children.length;
            PMMLPredicate[] splitPredicates = new PMMLPredicate[num];
            String splitAttribute = split.getSplitAttributeName();
            for (int j = 0; j < num; j++) {
                splitPredicates[j] = new PMMLSimplePredicate(splitAttribute, PMMLOperator.EQUAL, splitValues[j].toString());
            }
            return new DecisionTreeNodeSplitPMML(nodeId, majorityClass, frequencies, splitAttribute, splitPredicates, children);
        } else {
            // binary nominal
            SplitNominalBinary splitNominalBinary = (SplitNominalBinary) split;
            DataCell[] splitValues = splitNominalBinary.getSplitValues();
            // return new DecisionTreeNodeSplitNominalBinary(nodeId,
            // majorityClass, frequencies, split
            // .getSplitAttributeName(), splitValues,
            // splitNominalBinary.getIntMappingsLeftPartition(),
            // splitNominalBinary.getIntMappingsRightPartition(),
            // children/* children[0]=left, ..[1] right */);
            String splitAttribute = split.getSplitAttributeName();
            int[][] indices = new int[][] { splitNominalBinary.getIntMappingsLeftPartition(), splitNominalBinary.getIntMappingsRightPartition() };
            PMMLPredicate[] splitPredicates = new PMMLPredicate[2];
            for (int j = 0; j < splitPredicates.length; j++) {
                PMMLSimpleSetPredicate pred = null;
                pred = new PMMLSimpleSetPredicate(splitAttribute, PMMLSetOperator.IS_IN);
                pred.setArrayType(PMMLArrayType.STRING);
                LinkedHashSet<String> values = new LinkedHashSet<String>();
                for (int index : indices[j]) {
                    values.add(splitValues[index].toString());
                }
                pred.setValues(values);
                splitPredicates[j] = pred;
            }
            return new DecisionTreeNodeSplitPMML(nodeId, majorityClass, frequencies, splitAttribute, splitPredicates, children);
        }
    }
}

Example 17 with PMMLPredicate

use of org.knime.base.node.mine.decisiontree2.PMMLPredicate in project knime-core by knime.

the class TreeNodeRegression method createDecisionTreeNode.

/**
 * @param metaData
 * @return
 */
public DecisionTreeNode createDecisionTreeNode(final MutableInteger idGenerator, final TreeMetaData metaData) {
    DataCell majorityCell = new StringCell(DoubleFormat.formatDouble(m_mean));
    final int nrChildren = getNrChildren();
    LinkedHashMap<DataCell, Double> distributionMap = new LinkedHashMap<DataCell, Double>();
    distributionMap.put(majorityCell, m_totalSum);
    if (nrChildren == 0) {
        return new DecisionTreeNodeLeaf(idGenerator.inc(), majorityCell, distributionMap);
    } else {
        int id = idGenerator.inc();
        DecisionTreeNode[] childNodes = new DecisionTreeNode[nrChildren];
        int splitAttributeIndex = getSplitAttributeIndex();
        assert splitAttributeIndex >= 0 : "non-leaf node has no split";
        String splitAttribute = metaData.getAttributeMetaData(splitAttributeIndex).getAttributeName();
        PMMLPredicate[] childPredicates = new PMMLPredicate[nrChildren];
        for (int i = 0; i < nrChildren; i++) {
            final TreeNodeRegression treeNode = getChild(i);
            TreeNodeCondition cond = treeNode.getCondition();
            childPredicates[i] = cond.toPMMLPredicate();
            childNodes[i] = treeNode.createDecisionTreeNode(idGenerator, metaData);
        }
        return new DecisionTreeNodeSplitPMML(id, majorityCell, distributionMap, splitAttribute, childPredicates, childNodes);
    }
}

Example 18 with PMMLPredicate

use of org.knime.base.node.mine.decisiontree2.PMMLPredicate in project knime-core by knime.

the class PMMLDecisionTreeTranslator method addKnimeTreeNode.

private DecisionTreeNode addKnimeTreeNode(final Node pmmlNode) {
    Node[] pmmlChildrenNode = pmmlNode.getNodeArray();
    // TODO Handle the case that the id from PMML might not be an integer.
    String nodeId = pmmlNode.getId();
    int id;
    try {
        id = Integer.parseInt(nodeId);
    } catch (NumberFormatException e) {
        throw new IllegalArgumentException("Only numeric node ids are supported in KNIME. Found \"" + nodeId + "\".");
    }
    if (pmmlChildrenNode.length == 0) {
        DecisionTreeNodeLeaf knimeLeaf = new DecisionTreeNodeLeaf(id, getMajorityClass(pmmlNode), getClassCount(pmmlNode));
        return knimeLeaf;
    } else {
        PMMLPredicate[] pmmlPredicates = new PMMLPredicate[pmmlChildrenNode.length];
        DecisionTreeNode[] children = new DecisionTreeNode[pmmlChildrenNode.length];
        for (int i = 0; i < pmmlChildrenNode.length; i++) {
            children[i] = addKnimeTreeNode(pmmlChildrenNode[i]);
            pmmlPredicates[i] = getPredicate(pmmlChildrenNode[i]);
        }
        DecisionTreeNodeSplitPMML knimeNode;
        if (pmmlNode.isSetDefaultChild()) {
            String defaultChild = pmmlNode.getDefaultChild();
            Integer knimeDefaultChildIndex;
            try {
                knimeDefaultChildIndex = Integer.parseInt(defaultChild);
            } catch (NumberFormatException e) {
                throw new IllegalArgumentException("Only numeric node ids are supported in KNIME. " + "Found \"" + defaultChild + "\" as defaultChild.");
            }
            knimeNode = new DecisionTreeNodeSplitPMML(id, getMajorityClass(pmmlNode), getClassCount(pmmlNode), getChildrenSplitAttribute(pmmlNode), pmmlPredicates, children, knimeDefaultChildIndex);
        } else {
            knimeNode = new DecisionTreeNodeSplitPMML(id, getMajorityClass(pmmlNode), getClassCount(pmmlNode), getChildrenSplitAttribute(pmmlNode), pmmlPredicates, children);
        }
        return knimeNode;
    }
}

Example 19 with PMMLPredicate

use of org.knime.base.node.mine.decisiontree2.PMMLPredicate in project knime-core by knime.

the class DecisionTreeLearnerNodeModel2 method buildTree.

/**
 * Recursively induces the decision tree.
 *
 * @param table the {@link InMemoryTable} representing the data for this
 *            node to determine the split and after that perform
 *            partitioning
 * @param exec the execution context for progress information
 * @param depth the current recursion depth
 */
private DecisionTreeNode buildTree(final InMemoryTable table, final ExecutionContext exec, final int depth, final SplitQualityMeasure splitQualityMeasure, final ParallelProcessing parallelProcessing, final int firstSplitCol) throws CanceledExecutionException, IllegalAccessException {
    exec.checkCanceled();
    // derive this node's id from the counter
    int nodeId = m_counter.getAndIncrement();
    DataCell majorityClass = table.getMajorityClassAsCell();
    LinkedHashMap<DataCell, Double> frequencies = table.getClassFrequencies();
    // if the distribution allows for a leaf
    if (table.isPureEnough()) {
        // free memory
        table.freeUnderlyingDataRows();
        double value = m_finishedCounter.incrementAndGet(table.getSumOfWeights());
        exec.setProgress(value / m_alloverRowCount, "Created node with id " + nodeId + " at level " + depth);
        return new DecisionTreeNodeLeaf(nodeId, majorityClass, frequencies);
    } else {
        Split split = null;
        // find best split in specified column for first split
        if (depth == 0 && m_useFirstSplitCol.getBooleanValue()) {
            if (table.isNominal(firstSplitCol)) {
                if (m_binaryNominalSplitMode.getBooleanValue()) {
                    split = new SplitNominalBinary(table, firstSplitCol, splitQualityMeasure, m_minNumberRecordsPerNode.getIntValue(), m_maxNumNominalsForCompleteComputation.getIntValue());
                } else {
                    split = new SplitNominalNormal(table, firstSplitCol, splitQualityMeasure, m_minNumberRecordsPerNode.getIntValue());
                }
            } else {
                split = new SplitContinuous(table, firstSplitCol, splitQualityMeasure, m_averageSplitpoint.getBooleanValue(), m_minNumberRecordsPerNode.getIntValue());
            }
            if (Double.isNaN(split.getBestQualityMeasure()) || split.getBestQualityMeasure() == 0.0) {
                m_warningMessageSb.append("The specified root split column \"").append(split.getSplitAttributeName()).append("\" does not contain a valid split.");
            }
        }
        if (split == null) {
            // no root split column found or selected
            // find the best splits for all attributes
            SplitFinder splittFinder = new SplitFinder(table, splitQualityMeasure, m_averageSplitpoint.getBooleanValue(), m_minNumberRecordsPerNode.getIntValue(), m_binaryNominalSplitMode.getBooleanValue(), m_maxNumNominalsForCompleteComputation.getIntValue());
            // check for enough memory
            checkMemory();
            // get the best split among the best attribute splits
            split = splittFinder.getSplit();
        }
        // if no best split could be evaluated, create a leaf node
        if (split == null || !split.isValidSplit()) {
            table.freeUnderlyingDataRows();
            double value = m_finishedCounter.incrementAndGet(table.getSumOfWeights());
            exec.setProgress(value / m_alloverRowCount, "Created node with id " + nodeId + " at level " + depth);
            return new DecisionTreeNodeLeaf(nodeId, majorityClass, frequencies);
        }
        // partition the attribute lists according to this split
        Partitioner partitioner = new Partitioner(table, split, m_minNumberRecordsPerNode.getIntValue());
        if (!partitioner.couldBeUsefulPartitioned()) {
            table.freeUnderlyingDataRows();
            double value = m_finishedCounter.incrementAndGet(table.getSumOfWeights());
            exec.setProgress(value / m_alloverRowCount, "Created node with id " + nodeId + " at level " + depth);
            return new DecisionTreeNodeLeaf(nodeId, majorityClass, frequencies);
        }
        // get the just created partitions
        InMemoryTable[] partitionTables = partitioner.getPartitionTables();
        // recursively build the  child nodes
        DecisionTreeNode[] children = new DecisionTreeNode[partitionTables.length];
        ArrayList<ParallelBuilding> threads = new ArrayList<ParallelBuilding>();
        int i = 0;
        for (InMemoryTable partitionTable : partitionTables) {
            exec.checkCanceled();
            if (partitionTable.getNumberDataRows() * m_numberAttributes < 10000 || !parallelProcessing.isThreadAvailable()) {
                children[i] = buildTree(partitionTable, exec, depth + 1, splitQualityMeasure, parallelProcessing, firstSplitCol);
            } else {
                String threadName = "Build thread, node: " + nodeId + "." + i;
                ParallelBuilding buildThread = new ParallelBuilding(threadName, partitionTable, exec, depth + 1, i, splitQualityMeasure, parallelProcessing);
                LOGGER.debug("Start new parallel building thread: " + threadName);
                threads.add(buildThread);
                buildThread.start();
            }
            i++;
        }
        // already assigned to the child array
        for (ParallelBuilding buildThread : threads) {
            children[buildThread.getThreadIndex()] = buildThread.getResultNode();
            exec.checkCanceled();
            if (buildThread.getException() != null) {
                for (ParallelBuilding buildThread2 : threads) {
                    buildThread2.stop();
                }
                throw new RuntimeException(buildThread.getException().getMessage());
            }
        }
        threads.clear();
        if (split instanceof SplitContinuous) {
            double splitValue = ((SplitContinuous) split).getBestSplitValue();
            // return new DecisionTreeNodeSplitContinuous(nodeId,
            // majorityClass, frequencies, split
            // .getSplitAttributeName(), children, splitValue);
            String splitAttribute = split.getSplitAttributeName();
            PMMLPredicate[] splitPredicates = new PMMLPredicate[] { new PMMLSimplePredicate(splitAttribute, PMMLOperator.LESS_OR_EQUAL, Double.toString(splitValue)), new PMMLSimplePredicate(splitAttribute, PMMLOperator.GREATER_THAN, Double.toString(splitValue)) };
            return new DecisionTreeNodeSplitPMML(nodeId, majorityClass, frequencies, splitAttribute, splitPredicates, children);
        } else if (split instanceof SplitNominalNormal) {
            // else the attribute is nominal
            DataCell[] splitValues = ((SplitNominalNormal) split).getSplitValues();
            // return new DecisionTreeNodeSplitNominal(nodeId, majorityClass,
            // frequencies, split.getSplitAttributeName(),
            // splitValues, children);
            int num = children.length;
            PMMLPredicate[] splitPredicates = new PMMLPredicate[num];
            String splitAttribute = split.getSplitAttributeName();
            for (int j = 0; j < num; j++) {
                splitPredicates[j] = new PMMLSimplePredicate(splitAttribute, PMMLOperator.EQUAL, splitValues[j].toString());
            }
            return new DecisionTreeNodeSplitPMML(nodeId, majorityClass, frequencies, splitAttribute, splitPredicates, children);
        } else {
            // binary nominal
            SplitNominalBinary splitNominalBinary = (SplitNominalBinary) split;
            DataCell[] splitValues = splitNominalBinary.getSplitValues();
            // return new DecisionTreeNodeSplitNominalBinary(nodeId,
            // majorityClass, frequencies, split
            // .getSplitAttributeName(), splitValues,
            // splitNominalBinary.getIntMappingsLeftPartition(),
            // splitNominalBinary.getIntMappingsRightPartition(),
            // children/* children[0]=left, ..[1] right */);
            String splitAttribute = split.getSplitAttributeName();
            int[][] indices = new int[][] { splitNominalBinary.getIntMappingsLeftPartition(), splitNominalBinary.getIntMappingsRightPartition() };
            PMMLPredicate[] splitPredicates = new PMMLPredicate[2];
            for (int j = 0; j < splitPredicates.length; j++) {
                PMMLSimpleSetPredicate pred = null;
                pred = new PMMLSimpleSetPredicate(splitAttribute, PMMLSetOperator.IS_IN);
                pred.setArrayType(PMMLArrayType.STRING);
                LinkedHashSet<String> values = new LinkedHashSet<String>();
                for (int index : indices[j]) {
                    values.add(splitValues[index].toString());
                }
                pred.setValues(values);
                splitPredicates[j] = pred;
            }
            return new DecisionTreeNodeSplitPMML(nodeId, majorityClass, frequencies, splitAttribute, splitPredicates, children);
        }
    }
}

Example 20 with PMMLPredicate

use of org.knime.base.node.mine.decisiontree2.PMMLPredicate in project knime-core by knime.

the class DecisionTreeNodeSplitPMML method saveNodeSplitInternalsToPredParams.

/**
 * {@inheritDoc}
 */
@Override
public void saveNodeSplitInternalsToPredParams(final ModelContentWO pConf) {
    int i = 0;
    for (PMMLPredicate pred : m_splitPred) {
        Config predConfig = pConf.addConfig("pred" + i++);
        pred.saveToPredParams(predConfig);
    }
}