use of org.knime.base.node.mine.treeensemble.model.TreeEnsembleModel in project knime-core by knime.
the class RandomForestClassificationLearnerNodeModel 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 = new TreeEnsembleModelPortObject(ensembleSpec, model);
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 };
}
use of org.knime.base.node.mine.treeensemble.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 = new TreeEnsembleModelPortObject(ensembleSpec, model);
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 };
}
use of org.knime.base.node.mine.treeensemble.model.TreeEnsembleModel in project knime-core by knime.
the class TreeEnsembleClassificationPredictorCellFactory 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();
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();
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);
if (appendConfidence) {
final int freqValue = counter.getFrequency(bestValue);
result[index++] = new DoubleCell(freqValue / (double) nrValidModels);
}
if (appendClassConfidences) {
for (String key : m_targetValueMap.keySet()) {
int frequency = counter.getFrequency(key);
double ratio = frequency / (double) nrValidModels;
result[index++] = new DoubleCell(ratio);
}
}
}
if (appendModelCount) {
result[index++] = new IntCell(nrValidModels);
}
return result;
}
use of org.knime.base.node.mine.treeensemble.model.TreeEnsembleModel in project knime-core by knime.
the class RandomForestRegressionLearnerNodeModel 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);
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 = new TreeEnsembleModelPortObject(ensembleSpec, model);
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 };
}
use of org.knime.base.node.mine.treeensemble.model.TreeEnsembleModel in project knime-core by knime.
the class TreeEnsembleLearnerNodeView method modelChangedInUI.
private void modelChangedInUI() {
assert SwingUtilities.isEventDispatchThread();
final MODEL nodeModel = getNodeModel();
TreeEnsembleModel ensembleModel = nodeModel.getEnsembleModel();
int nrModels = ensembleModel == null ? 0 : ensembleModel.getNrModels();
m_nrModelLabel.setText(nrModels + " model(s) in total");
int min = nrModels == 0 ? 0 : 1;
m_modelSpinner.setModel(new SpinnerNumberModel(min, min, nrModels, 1));
HiLiteHandler hdl = nodeModel.getInHiLiteHandler(0);
String warnMessage = nodeModel.getViewMessage();
if (warnMessage == null) {
m_warningLabel.setText(" ");
m_warningLabel.setVisible(false);
} else {
m_warningLabel.setText(warnMessage);
m_warningLabel.setVisible(true);
}
newHiliteHandler(hdl);
newModel(min - 1);
}
Aggregations