Examples with RandomData org.apache.commons.math.random.RandomData used on opensource projects

Example 16 with RandomData

use of org.apache.commons.math.random.RandomData in project knime-core by knime.

the class TreeNumericColumnDataTest method testCalcBestSplitClassification.

@Test
public void testCalcBestSplitClassification() throws Exception {
    TreeEnsembleLearnerConfiguration config = createConfig();
    /* data from J. Fuernkranz, Uni Darmstadt:
         * http://www.ke.tu-darmstadt.de/lehre/archiv/ws0809/mldm/dt.pdf */
    final double[] data = asDataArray("60,70,75,85, 90, 95, 100,120,125,220");
    final String[] target = asStringArray("No,No,No,Yes,Yes,Yes,No, No, No, No");
    Pair<TreeOrdinaryNumericColumnData, TreeTargetNominalColumnData> exampleData = exampleData(config, data, target);
    RandomData rd = config.createRandomData();
    TreeNumericColumnData columnData = exampleData.getFirst();
    TreeTargetNominalColumnData targetData = exampleData.getSecond();
    assertEquals(SplitCriterion.Gini, config.getSplitCriterion());
    double[] rowWeights = new double[data.length];
    Arrays.fill(rowWeights, 1.0);
    TreeData treeData = createTreeDataClassification(exampleData);
    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, rd);
    assertNotNull(splitCandidate);
    assertThat(splitCandidate, instanceOf(NumericSplitCandidate.class));
    assertTrue(splitCandidate.canColumnBeSplitFurther());
    // libre office calc
    assertEquals(/*0.42 - 0.300 */
    0.12, splitCandidate.getGainValue(), 0.00001);
    NumericSplitCandidate numSplitCandidate = (NumericSplitCandidate) splitCandidate;
    TreeNodeNumericCondition[] childConditions = numSplitCandidate.getChildConditions();
    assertEquals(2, childConditions.length);
    assertEquals((95.0 + 100.0) / 2.0, childConditions[0].getSplitValue(), 0.0);
    assertEquals((95.0 + 100.0) / 2.0, childConditions[1].getSplitValue(), 0.0);
    assertEquals(NumericOperator.LessThanOrEqual, childConditions[0].getNumericOperator());
    assertEquals(NumericOperator.LargerThan, childConditions[1].getNumericOperator());
    double[] childRowWeights = new double[data.length];
    System.arraycopy(rowWeights, 0, childRowWeights, 0, rowWeights.length);
    BitSet inChild = columnData.updateChildMemberships(childConditions[0], dataMemberships);
    DataMemberships childMemberships = dataMemberships.createChildMemberships(inChild);
    ClassificationPriors childTargetPriors = targetData.getDistribution(childMemberships, config);
    SplitCandidate splitCandidateChild = columnData.calcBestSplitClassification(childMemberships, childTargetPriors, targetData, rd);
    assertNotNull(splitCandidateChild);
    assertThat(splitCandidateChild, instanceOf(NumericSplitCandidate.class));
    // manually via libre office calc
    assertEquals(0.5, splitCandidateChild.getGainValue(), 0.00001);
    TreeNodeNumericCondition[] childConditions2 = ((NumericSplitCandidate) splitCandidateChild).getChildConditions();
    assertEquals(2, childConditions2.length);
    assertEquals((75.0 + 85.0) / 2.0, childConditions2[0].getSplitValue(), 0.0);
    System.arraycopy(rowWeights, 0, childRowWeights, 0, rowWeights.length);
    inChild = columnData.updateChildMemberships(childConditions[1], dataMemberships);
    childMemberships = dataMemberships.createChildMemberships(inChild);
    childTargetPriors = targetData.getDistribution(childMemberships, config);
    splitCandidateChild = columnData.calcBestSplitClassification(childMemberships, childTargetPriors, targetData, rd);
    assertNull(splitCandidateChild);
}

Example 17 with RandomData

use of org.apache.commons.math.random.RandomData in project knime-core by knime.

the class TreeNumericColumnDataTest method testCalcBestSplitClassificationSplitAtEnd.

/**
 * Test splits at last possible split position - even if no change in target can be observed, see example data in
 * method body.
 * @throws Exception
 */
@Test
public void testCalcBestSplitClassificationSplitAtEnd() throws Exception {
    // Index:  1 2 3 4 5 6 7 8
    // Value:  1 1|2 2 2|3 3 3
    // Target: A A|A A A|A A B
    double[] data = asDataArray("1,1,2,2,2,3,3,3");
    String[] target = asStringArray("A,A,A,A,A,A,A,B");
    TreeEnsembleLearnerConfiguration config = createConfig();
    RandomData rd = config.createRandomData();
    Pair<TreeOrdinaryNumericColumnData, TreeTargetNominalColumnData> exampleData = exampleData(config, data, target);
    TreeNumericColumnData columnData = exampleData.getFirst();
    TreeTargetNominalColumnData targetData = exampleData.getSecond();
    double[] rowWeights = new double[data.length];
    Arrays.fill(rowWeights, 1.0);
    TreeData treeData = createTreeDataClassification(exampleData);
    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, rd);
    assertNotNull(splitCandidate);
    assertThat(splitCandidate, instanceOf(NumericSplitCandidate.class));
    assertTrue(splitCandidate.canColumnBeSplitFurther());
    // manually calculated
    assertEquals(/*0.21875 - 0.166666667 */
    0.05208, splitCandidate.getGainValue(), 0.001);
    NumericSplitCandidate numSplitCandidate = (NumericSplitCandidate) splitCandidate;
    TreeNodeNumericCondition[] childConditions = numSplitCandidate.getChildConditions();
    assertEquals(2, childConditions.length);
    assertEquals((2.0 + 3.0) / 2.0, childConditions[0].getSplitValue(), 0.0);
    assertEquals(NumericOperator.LessThanOrEqual, childConditions[0].getNumericOperator());
    double[] childRowWeights = new double[data.length];
    System.arraycopy(rowWeights, 0, childRowWeights, 0, rowWeights.length);
    BitSet inChild = columnData.updateChildMemberships(childConditions[0], dataMemberships);
    DataMemberships childMemberships = dataMemberships.createChildMemberships(inChild);
    ClassificationPriors childTargetPriors = targetData.getDistribution(childMemberships, config);
    SplitCandidate splitCandidateChild = columnData.calcBestSplitClassification(childMemberships, childTargetPriors, targetData, rd);
    assertNull(splitCandidateChild);
    System.arraycopy(rowWeights, 0, childRowWeights, 0, rowWeights.length);
    inChild = columnData.updateChildMemberships(childConditions[1], dataMemberships);
    childMemberships = dataMemberships.createChildMemberships(inChild);
    childTargetPriors = targetData.getDistribution(childMemberships, config);
    splitCandidateChild = columnData.calcBestSplitClassification(childMemberships, childTargetPriors, targetData, null);
    assertNull(splitCandidateChild);
}

Example 18 with RandomData

use of org.apache.commons.math.random.RandomData in project knime-core by knime.

the class TreeNumericColumnDataTest method testCalcBestSplitClassificationMissingValStrategy1.

/**
 * This test is outdated and will likely be removed soon.
 *
 * @throws Exception
 */
// @Test
public void testCalcBestSplitClassificationMissingValStrategy1() throws Exception {
    TreeEnsembleLearnerConfiguration config = createConfig();
    final double[] data = asDataArray("1, 2, 3, 4, 5, 6, 7, NaN, NaN, NaN");
    final String[] target = asStringArray("Y, Y, Y, Y, N, N, N, Y, Y, Y");
    Pair<TreeOrdinaryNumericColumnData, TreeTargetNominalColumnData> exampleData = exampleData(config, data, target);
    double[] rowWeights = new double[data.length];
    Arrays.fill(rowWeights, 1.0);
    RandomData rd = config.createRandomData();
    TreeNumericColumnData columnData = exampleData.getFirst();
    TreeTargetNominalColumnData targetData = exampleData.getSecond();
    TreeData treeData = createTreeDataClassification(exampleData);
    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, rd);
    assertNotNull(splitCandidate);
    assertThat(splitCandidate, instanceOf(NumericMissingSplitCandidate.class));
    assertTrue(splitCandidate.canColumnBeSplitFurther());
    assertEquals(0.42, splitCandidate.getGainValue(), 0.0001);
    TreeNodeNumericCondition[] childConditions = ((NumericMissingSplitCandidate) splitCandidate).getChildConditions();
    assertEquals(2, childConditions.length);
    assertEquals(NumericOperator.LessThanOrEqualOrMissing, childConditions[0].getNumericOperator());
    assertEquals(NumericOperator.LargerThan, childConditions[1].getNumericOperator());
    assertEquals(4.5, childConditions[0].getSplitValue(), 0.0);
}

Example 19 with RandomData

use of org.apache.commons.math.random.RandomData in project knime-core by knime.

the class TreeEnsembleLearner method learnEnsemble.

public TreeEnsembleModel learnEnsemble(final ExecutionMonitor exec) throws CanceledExecutionException, ExecutionException {
    final int nrModels = m_config.getNrModels();
    final RandomData rd = m_config.createRandomData();
    final ThreadPool tp = KNIMEConstants.GLOBAL_THREAD_POOL;
    final AtomicReference<Throwable> learnThrowableRef = new AtomicReference<Throwable>();
    @SuppressWarnings("unchecked") final Future<TreeLearnerResult>[] modelFutures = new Future[nrModels];
    final int procCount = 3 * Runtime.getRuntime().availableProcessors() / 2;
    final Semaphore semaphore = new Semaphore(procCount);
    Callable<TreeLearnerResult[]> learnCallable = new Callable<TreeLearnerResult[]>() {

        @Override
        public TreeLearnerResult[] call() throws Exception {
            final TreeLearnerResult[] results = new TreeLearnerResult[nrModels];
            for (int i = 0; i < nrModels; i++) {
                semaphore.acquire();
                finishedTree(i - procCount, exec);
                checkThrowable(learnThrowableRef);
                RandomData rdSingle = TreeEnsembleLearnerConfiguration.createRandomData(rd.nextLong(Long.MIN_VALUE, Long.MAX_VALUE));
                ExecutionMonitor subExec = exec.createSubProgress(0.0);
                modelFutures[i] = tp.enqueue(new TreeLearnerCallable(subExec, rdSingle, learnThrowableRef, semaphore));
            }
            for (int i = 0; i < procCount; i++) {
                semaphore.acquire();
                finishedTree(nrModels - 1 + i - procCount, exec);
            }
            for (int i = 0; i < nrModels; i++) {
                try {
                    results[i] = modelFutures[i].get();
                } catch (Exception e) {
                    learnThrowableRef.compareAndSet(null, e);
                }
            }
            return results;
        }

        private void finishedTree(final int treeIndex, final ExecutionMonitor progMon) {
            if (treeIndex > 0) {
                progMon.setProgress(treeIndex / (double) nrModels, "Tree " + treeIndex + "/" + nrModels);
            }
        }
    };
    TreeLearnerResult[] modelResults = tp.runInvisible(learnCallable);
    checkThrowable(learnThrowableRef);
    AbstractTreeModel[] models = new AbstractTreeModel[nrModels];
    m_rowSamples = new RowSample[nrModels];
    m_columnSampleStrategies = new ColumnSampleStrategy[nrModels];
    for (int i = 0; i < nrModels; i++) {
        models[i] = modelResults[i].m_treeModel;
        m_rowSamples[i] = modelResults[i].m_rowSample;
        m_columnSampleStrategies[i] = modelResults[i].m_rootColumnSampleStrategy;
    }
    m_ensembleModel = new TreeEnsembleModel(m_config, m_data.getMetaData(), models, m_data.getTreeType());
    return m_ensembleModel;
}

Example 20 with RandomData

use of org.apache.commons.math.random.RandomData in project knime-core by knime.

the class RegressionTreeLearnerNodeModel method execute.

// /**
// * @param ensembleSpec
// * @param ensembleModel
// * @param inSpec
// * @return
// * @throws InvalidSettingsException
// */
// private TreeEnsemblePredictor createOutOfBagPredictor(final TreeEnsembleModelPortObjectSpec ensembleSpec,
// final TreeEnsembleModelPortObject ensembleModel, final DataTableSpec inSpec) throws InvalidSettingsException {
// TreeEnsemblePredictorConfiguration ooBConfig = new TreeEnsemblePredictorConfiguration(true);
// String targetColumn = m_configuration.getTargetColumn();
// String append = targetColumn + " (Out-of-bag)";
// ooBConfig.setPredictionColumnName(append);
// ooBConfig.setAppendPredictionConfidence(true);
// ooBConfig.setAppendClassConfidences(true);
// ooBConfig.setAppendModelCount(true);
// return new TreeEnsemblePredictor(ensembleSpec, ensembleModel, inSpec, ooBConfig);
// }
/**
 * {@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(0.9);
    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 tree");
    // 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;
    // }
    RandomData rd = m_configuration.createRandomData();
    TreeLearnerRegression treeLearner = new TreeLearnerRegression(m_configuration, data, rd);
    TreeModelRegression regTree = treeLearner.learnSingleTree(learnExec, rd);
    RegressionTreeModel model = new RegressionTreeModel(m_configuration, data.getMetaData(), regTree, data.getTreeType());
    RegressionTreeModelPortObjectSpec treePortObjectSpec = new RegressionTreeModelPortObjectSpec(learnSpec);
    RegressionTreeModelPortObject treePortObject = new RegressionTreeModelPortObject(model, treePortObjectSpec);
    learnExec.setProgress(1.0);
    m_treeModelPortObject = treePortObject;
    if (warn != null) {
        setWarningMessage(warn);
    }
    return new PortObject[] { treePortObject };
}