Examples with TreeEnsembleModel org.knime.base.node.mine.treeensemble2.model.TreeEnsembleModel used on opensource projects

Example 6 with TreeEnsembleModel

use of org.knime.base.node.mine.treeensemble2.model.TreeEnsembleModel in project knime-core by knime.

the class TreeEnsembleLearnerNodeView2 method newModel.

private void newModel(final int index) {
    assert SwingUtilities.isEventDispatchThread();
    final MODEL nodeModel = getNodeModel();
    TreeEnsembleModel model = nodeModel.getEnsembleModel();
    DataTable hiliteRowSample = nodeModel.getHiliteRowSample();
    UpdateTreeWorker updateWorker = new UpdateTreeWorker(hiliteRowSample, model, index);
    UpdateTreeWorker old = m_updateWorkerRef.getAndSet(updateWorker);
    if (old != null) {
        old.cancel(true);
    }
    updateWorker.execute();
}

Example 7 with TreeEnsembleModel

use of org.knime.base.node.mine.treeensemble2.model.TreeEnsembleModel in project knime-core by knime.

the class TreeEnsembleClassificationLearnerNodeModel method execute.

/**
 * {@inheritDoc}
 */
@Override
protected PortObject[] execute(final PortObject[] inObjects, final ExecutionContext exec) throws Exception {
    BufferedDataTable t = (BufferedDataTable) inObjects[0];
    DataTableSpec spec = t.getDataTableSpec();
    final FilterLearnColumnRearranger learnRearranger = m_configuration.filterLearnColumns(spec);
    String warn = learnRearranger.getWarning();
    BufferedDataTable learnTable = exec.createColumnRearrangeTable(t, learnRearranger, exec.createSubProgress(0.0));
    DataTableSpec learnSpec = learnTable.getDataTableSpec();
    TreeEnsembleModelPortObjectSpec ensembleSpec = m_configuration.createPortObjectSpec(learnSpec);
    Map<String, DataCell> targetValueMap = ensembleSpec.getTargetColumnPossibleValueMap();
    if (targetValueMap == null) {
        throw new InvalidSettingsException("The target column does not " + "have possible values assigned. Most likely it " + "has too many different distinct values (learning an ID " + "column?) Fix it by preprocessing the table using " + "a \"Domain Calculator\".");
    }
    ExecutionMonitor readInExec = exec.createSubProgress(0.1);
    ExecutionMonitor learnExec = exec.createSubProgress(0.8);
    ExecutionMonitor outOfBagExec = exec.createSubProgress(0.1);
    TreeDataCreator dataCreator = new TreeDataCreator(m_configuration, learnSpec, learnTable.getRowCount());
    exec.setProgress("Reading data into memory");
    TreeData data = dataCreator.readData(learnTable, m_configuration, readInExec);
    m_hiliteRowSample = dataCreator.getDataRowsForHilite();
    m_viewMessage = dataCreator.getViewMessage();
    String dataCreationWarning = dataCreator.getAndClearWarningMessage();
    if (dataCreationWarning != null) {
        if (warn == null) {
            warn = dataCreationWarning;
        } else {
            warn = warn + "\n" + dataCreationWarning;
        }
    }
    readInExec.setProgress(1.0);
    exec.setMessage("Learning trees");
    TreeEnsembleLearner learner = new TreeEnsembleLearner(m_configuration, data);
    TreeEnsembleModel model;
    try {
        model = learner.learnEnsemble(learnExec);
    } catch (ExecutionException e) {
        Throwable cause = e.getCause();
        if (cause instanceof Exception) {
            throw (Exception) cause;
        }
        throw e;
    }
    TreeEnsembleModelPortObject modelPortObject = TreeEnsembleModelPortObject.createPortObject(ensembleSpec, model, exec.createFileStore(UUID.randomUUID().toString() + ""));
    learnExec.setProgress(1.0);
    exec.setMessage("Out of bag prediction");
    TreeEnsemblePredictor outOfBagPredictor = createOutOfBagPredictor(ensembleSpec, modelPortObject, spec);
    outOfBagPredictor.setOutofBagFilter(learner.getRowSamples(), data.getTargetColumn());
    ColumnRearranger outOfBagRearranger = outOfBagPredictor.getPredictionRearranger();
    BufferedDataTable outOfBagTable = exec.createColumnRearrangeTable(t, outOfBagRearranger, outOfBagExec);
    BufferedDataTable colStatsTable = learner.createColumnStatisticTable(exec.createSubExecutionContext(0.0));
    m_ensembleModelPortObject = modelPortObject;
    if (warn != null) {
        setWarningMessage(warn);
    }
    return new PortObject[] { outOfBagTable, colStatsTable, modelPortObject };
}

Example 8 with TreeEnsembleModel

use of org.knime.base.node.mine.treeensemble2.model.TreeEnsembleModel in project knime-core by knime.

the class TreeEnsembleModelExtractorNodeModel method execute.

/**
 * {@inheritDoc}
 */
@Override
protected PortObject[] execute(final PortObject[] inObjects, final ExecutionContext exec) throws Exception {
    TreeEnsembleModelPortObject treeEnsembleModel = (TreeEnsembleModelPortObject) inObjects[0];
    DataTableSpec outSpec = createOutSpec();
    BufferedDataContainer container = exec.createDataContainer(outSpec, false, 0);
    int nrModels = treeEnsembleModel.getEnsembleModel().getNrModels();
    for (int i = 0; i < nrModels; i++) {
        PMMLPortObject pmmlObject = treeEnsembleModel.createDecisionTreePMMLPortObject(i);
        DataCell cell = PMMLCellFactory.create(pmmlObject.getPMMLValue().toString());
        RowKey key = RowKey.createRowKey(i);
        container.addRowToTable(new DefaultRow(key, cell));
        exec.checkCanceled();
        exec.setProgress(i / (double) nrModels, "Exported model " + (i + 1) + "/" + nrModels);
    }
    container.close();
    return new BufferedDataTable[] { container.getTable() };
}

Example 9 with TreeEnsembleModel

use of org.knime.base.node.mine.treeensemble2.model.TreeEnsembleModel in project knime-core by knime.

the class TreeEnsembleClassificationPredictorCellFactory2 method getCells.

/**
 * {@inheritDoc}
 */
@Override
public DataCell[] getCells(final DataRow row) {
    TreeEnsembleModelPortObject modelObject = m_predictor.getModelObject();
    TreeEnsemblePredictorConfiguration cfg = m_predictor.getConfiguration();
    final TreeEnsembleModel ensembleModel = modelObject.getEnsembleModel();
    int size = 1;
    final boolean appendConfidence = cfg.isAppendPredictionConfidence();
    if (appendConfidence) {
        size += 1;
    }
    final boolean appendClassConfidences = cfg.isAppendClassConfidences();
    if (appendClassConfidences) {
        size += m_targetValueMap.size();
    }
    final boolean appendModelCount = cfg.isAppendModelCount();
    if (appendModelCount) {
        size += 1;
    }
    final boolean hasOutOfBagFilter = m_predictor.hasOutOfBagFilter();
    DataCell[] result = new DataCell[size];
    DataRow filterRow = new FilterColumnRow(row, m_learnColumnInRealDataIndices);
    PredictorRecord record = ensembleModel.createPredictorRecord(filterRow, m_learnSpec);
    if (record == null) {
        // missing value
        Arrays.fill(result, DataType.getMissingCell());
        return result;
    }
    OccurrenceCounter<String> counter = new OccurrenceCounter<String>();
    final int nrModels = ensembleModel.getNrModels();
    TreeTargetNominalColumnMetaData targetMeta = (TreeTargetNominalColumnMetaData) ensembleModel.getMetaData().getTargetMetaData();
    final double[] classProbabilities = new double[targetMeta.getValues().length];
    int nrValidModels = 0;
    for (int i = 0; i < nrModels; i++) {
        if (hasOutOfBagFilter && m_predictor.isRowPartOfTrainingData(row.getKey(), i)) {
        // ignore, row was used to train the model
        } else {
            TreeModelClassification m = ensembleModel.getTreeModelClassification(i);
            TreeNodeClassification match = m.findMatchingNode(record);
            String majorityClassName = match.getMajorityClassName();
            final float[] nodeClassProbs = match.getTargetDistribution();
            double instancesInNode = 0;
            for (int c = 0; c < nodeClassProbs.length; c++) {
                instancesInNode += nodeClassProbs[c];
            }
            for (int c = 0; c < classProbabilities.length; c++) {
                classProbabilities[c] += nodeClassProbs[c] / instancesInNode;
            }
            counter.add(majorityClassName);
            nrValidModels += 1;
        }
    }
    String bestValue = counter.getMostFrequent();
    int index = 0;
    if (bestValue == null) {
        assert nrValidModels == 0;
        Arrays.fill(result, DataType.getMissingCell());
        index = size - 1;
    } else {
        // result[index++] = m_targetValueMap.get(bestValue);
        int indexBest = -1;
        double probBest = -1;
        for (int c = 0; c < classProbabilities.length; c++) {
            double prob = classProbabilities[c];
            if (prob > probBest) {
                probBest = prob;
                indexBest = c;
            }
        }
        result[index++] = new StringCell(targetMeta.getValues()[indexBest].getNominalValue());
        if (appendConfidence) {
            // final int freqValue = counter.getFrequency(bestValue);
            // result[index++] = new DoubleCell(freqValue / (double)nrValidModels);
            result[index++] = new DoubleCell(probBest);
        }
        if (appendClassConfidences) {
            for (NominalValueRepresentation nomVal : targetMeta.getValues()) {
                double prob = classProbabilities[nomVal.getAssignedInteger()] / nrValidModels;
                result[index++] = new DoubleCell(prob);
            }
        }
    }
    if (appendModelCount) {
        result[index++] = new IntCell(nrValidModels);
    }
    return result;
}

Example 10 with TreeEnsembleModel

use of org.knime.base.node.mine.treeensemble2.model.TreeEnsembleModel in project knime-core by knime.

the class TreeEnsembleModel method load.

public static TreeEnsembleModel load(final InputStream in) throws IOException {
    // wrapping the argument (zip input) stream in a buffered stream
    // reduces read operation from, e.g. 42s to 2s
    TreeModelDataInputStream input = new TreeModelDataInputStream(new BufferedInputStream(new NonClosableInputStream(in)));
    int version = input.readInt();
    if (version > 20160114) {
        throw new IOException("Tree Ensemble version " + version + " not supported");
    }
    byte ensembleType;
    if (version == 20160114) {
        ensembleType = input.readByte();
    } else {
        ensembleType = 'r';
    }
    TreeType type = TreeType.load(input);
    TreeMetaData metaData = TreeMetaData.load(input);
    int nrModels = input.readInt();
    boolean containsClassDistribution;
    if (version == 20121019) {
        containsClassDistribution = true;
    } else {
        containsClassDistribution = input.readBoolean();
    }
    input.setContainsClassDistribution(containsClassDistribution);
    AbstractTreeModel[] models = new AbstractTreeModel[nrModels];
    boolean isRegression = metaData.isRegression();
    if (ensembleType != 'r') {
        isRegression = true;
    }
    final TreeBuildingInterner treeBuildingInterner = new TreeBuildingInterner();
    for (int i = 0; i < nrModels; i++) {
        AbstractTreeModel singleModel;
        try {
            singleModel = isRegression ? TreeModelRegression.load(input, metaData, treeBuildingInterner) : TreeModelClassification.load(input, metaData, treeBuildingInterner);
            if (input.readByte() != 0) {
                throw new IOException("Model not terminated by 0 byte");
            }
        } catch (IOException e) {
            throw new IOException("Can't read tree model " + (i + 1) + "/" + nrModels + ": " + e.getMessage(), e);
        }
        models[i] = singleModel;
    }
    TreeEnsembleModel result;
    switch(ensembleType) {
        case 'r':
            result = new TreeEnsembleModel(metaData, models, type, containsClassDistribution);
            break;
        case 'g':
            result = new GradientBoostingModel(metaData, models, type, containsClassDistribution);
            break;
        case 't':
            result = new GradientBoostedTreesModel(metaData, models, type, containsClassDistribution);
            break;
        case 'm':
            result = new MultiClassGradientBoostedTreesModel(metaData, models, type, containsClassDistribution);
            break;
        default:
            throw new IllegalStateException("Unknown ensemble type: '" + (char) ensembleType + "'");
    }
    result.loadData(input);
    // does not close the method argument stream!!
    input.close();
    return result;
}