Examples with RegressionTrainingData org.knime.base.node.mine.regression.RegressionTrainingData used on opensource projects

Example 1 with RegressionTrainingData

use of org.knime.base.node.mine.regression.RegressionTrainingData in project knime-core by knime.

the class Learner method perform.

/**
 * @param data The data table.
 * @param exec The execution context used for reporting progress.
 * @return An object which holds the results.
 * @throws CanceledExecutionException when method is cancelled
 * @throws InvalidSettingsException When settings are inconsistent with the data
 */
public LogisticRegressionContent perform(final BufferedDataTable data, final ExecutionContext exec) throws CanceledExecutionException, InvalidSettingsException {
    exec.checkCanceled();
    int iter = 0;
    boolean converged = false;
    final RegressionTrainingData trainingData = new RegressionTrainingData(data, m_outSpec, m_specialColumns, true, m_targetReferenceCategory, m_sortTargetCategories, m_sortFactorsCategories);
    int targetIndex = data.getDataTableSpec().findColumnIndex(m_outSpec.getTargetCols().get(0).getName());
    final int tcC = trainingData.getDomainValues().get(targetIndex).size();
    final int rC = trainingData.getRegressorCount();
    final RealMatrix beta = new Array2DRowRealMatrix(1, (tcC - 1) * (rC + 1));
    Double loglike = 0.0;
    Double loglikeOld = 0.0;
    exec.setMessage("Iterative optimization. Processing iteration 1.");
    // main loop
    while (iter < m_maxIter && !converged) {
        RealMatrix betaOld = beta.copy();
        loglikeOld = loglike;
        // Do heavy work in a separate thread which allows to interrupt it
        // note the queue may block if no more threads are available (e.g. thread count = 1)
        // as soon as we stall in 'get' this thread reduces the number of running thread
        Future<Double> future = ThreadPool.currentPool().enqueue(new Callable<Double>() {

            @Override
            public Double call() throws Exception {
                final ExecutionMonitor progMon = exec.createSubProgress(1.0 / m_maxIter);
                irlsRls(trainingData, beta, rC, tcC, progMon);
                progMon.setProgress(1.0);
                return likelihood(trainingData.iterator(), beta, rC, tcC, exec);
            }
        });
        try {
            loglike = future.get();
        } catch (InterruptedException e) {
            future.cancel(true);
            exec.checkCanceled();
            throw new RuntimeException(e);
        } catch (ExecutionException e) {
            if (e.getCause() instanceof RuntimeException) {
                throw (RuntimeException) e.getCause();
            } else {
                throw new RuntimeException(e.getCause());
            }
        }
        if (Double.isInfinite(loglike) || Double.isNaN(loglike)) {
            throw new RuntimeException(FAILING_MSG);
        }
        exec.checkCanceled();
        // test for decreasing likelihood
        while ((Double.isInfinite(loglike) || Double.isNaN(loglike) || loglike < loglikeOld) && iter > 0) {
            converged = true;
            for (int k = 0; k < beta.getRowDimension(); k++) {
                if (abs(beta.getEntry(k, 0) - betaOld.getEntry(k, 0)) > m_eps * abs(betaOld.getEntry(k, 0))) {
                    converged = false;
                    break;
                }
            }
            if (converged) {
                break;
            }
            // half the step size of beta
            beta.setSubMatrix((beta.add(betaOld)).scalarMultiply(0.5).getData(), 0, 0);
            exec.checkCanceled();
            loglike = likelihood(trainingData.iterator(), beta, rC, tcC, exec);
            exec.checkCanceled();
        }
        // test for convergence
        converged = true;
        for (int k = 0; k < beta.getRowDimension(); k++) {
            if (abs(beta.getEntry(k, 0) - betaOld.getEntry(k, 0)) > m_eps * abs(betaOld.getEntry(k, 0))) {
                converged = false;
                break;
            }
        }
        iter++;
        LOGGER.debug("#Iterations: " + iter);
        LOGGER.debug("Log Likelihood: " + loglike);
        StringBuilder betaBuilder = new StringBuilder();
        for (int i = 0; i < beta.getRowDimension() - 1; i++) {
            betaBuilder.append(Double.toString(beta.getEntry(i, 0)));
            betaBuilder.append(", ");
        }
        if (beta.getRowDimension() > 0) {
            betaBuilder.append(Double.toString(beta.getEntry(beta.getRowDimension() - 1, 0)));
        }
        LOGGER.debug("beta: " + betaBuilder.toString());
        exec.checkCanceled();
        exec.setMessage("Iterative optimization. #Iterations: " + iter + " | Log-likelihood: " + DoubleFormat.formatDouble(loglike) + ". Processing iteration " + (iter + 1) + ".");
    }
    // The covariance matrix
    RealMatrix covMat = new QRDecomposition(A).getSolver().getInverse().scalarMultiply(-1);
    List<String> factorList = new ArrayList<String>();
    List<String> covariateList = new ArrayList<String>();
    Map<String, List<DataCell>> factorDomainValues = new HashMap<String, List<DataCell>>();
    for (int i : trainingData.getActiveCols()) {
        DataColumnSpec columnSpec = data.getDataTableSpec().getColumnSpec(i);
        if (trainingData.getIsNominal().get(i)) {
            String factor = columnSpec.getName();
            factorList.add(factor);
            List<DataCell> values = trainingData.getDomainValues().get(i);
            factorDomainValues.put(factor, values);
        } else {
            if (columnSpec.getType().isCompatible(BitVectorValue.class) || columnSpec.getType().isCompatible(ByteVectorValue.class)) {
                int length = trainingData.getVectorLengths().getOrDefault(i, 0).intValue();
                for (int j = 0; j < length; ++j) {
                    covariateList.add(columnSpec.getName() + "[" + j + "]");
                }
            } else {
                covariateList.add(columnSpec.getName());
            }
        }
    }
    final Map<? extends Integer, Integer> vectorIndexLengths = trainingData.getVectorLengths();
    final Map<String, Integer> vectorLengths = new LinkedHashMap<String, Integer>();
    for (DataColumnSpec spec : m_specialColumns) {
        int colIndex = data.getSpec().findColumnIndex(spec.getName());
        if (colIndex >= 0) {
            vectorLengths.put(spec.getName(), vectorIndexLengths.get(colIndex));
        }
    }
    // create content
    LogisticRegressionContent content = new LogisticRegressionContent(m_outSpec, factorList, covariateList, vectorLengths, m_targetReferenceCategory, m_sortTargetCategories, m_sortFactorsCategories, beta, loglike, covMat, iter);
    return content;
}

Example 2 with RegressionTrainingData

use of org.knime.base.node.mine.regression.RegressionTrainingData in project knime-core by knime.

the class Learner method perform.

/**
 * @param data The data table.
 * @param exec The execution context used for reporting progress.
 * @return An object which holds the results.
 * @throws CanceledExecutionException When method is cancelled
 * @throws InvalidSettingsException When settings are inconsistent with the data
 */
@Override
public PolyRegContent perform(final BufferedDataTable data, final ExecutionContext exec) throws CanceledExecutionException, InvalidSettingsException {
    exec.checkCanceled();
    RegressionTrainingData trainingData = new RegressionTrainingData(data, m_outSpec, m_failOnMissing);
    int regressorCount = trainingData.getRegressorCount() * m_maxExponent;
    SummaryStatistics[] stats = new SummaryStatistics[regressorCount];
    UpdatingMultipleLinearRegression regr = initStatistics(regressorCount, stats);
    exec.setProgress(0, "Estimating polynomial regression model.");
    processTable(exec, trainingData, stats, regr);
    RegressionResults result = regr.regress();
    RealMatrix beta = MatrixUtils.createRowRealMatrix(result.getParameterEstimates());
    List<String> factorList = new ArrayList<String>();
    List<String> covariateList = createCovariateListAndFillFactors(data, trainingData, factorList);
    // The covariance matrix
    RealMatrix covMat = createCovarianceMatrix(result);
    PolyRegContent content = new PolyRegContent(m_outSpec, (int) stats[0].getN(), factorList, covariateList, beta, m_offsetValue, covMat, result.getRSquared(), result.getAdjustedRSquared(), stats, m_maxExponent);
    return content;
}

Example 3 with RegressionTrainingData

use of org.knime.base.node.mine.regression.RegressionTrainingData in project knime-core by knime.

the class Learner method perform.

/**
 * @param data The data table.
 * @param exec The execution context used for reporting progress.
 * @return An object which holds the results.
 * @throws CanceledExecutionException When method is cancelled
 * @throws InvalidSettingsException When settings are inconsistent with the data
 */
@Override
public LinearRegressionContent perform(final BufferedDataTable data, final ExecutionContext exec) throws CanceledExecutionException, InvalidSettingsException {
    exec.checkCanceled();
    RegressionTrainingData trainingData = new RegressionTrainingData(data, m_outSpec, m_failOnMissing);
    final int regressorCount = Math.max(1, trainingData.getRegressorCount());
    SummaryStatistics[] stats = new SummaryStatistics[regressorCount];
    UpdatingMultipleLinearRegression regr = initStatistics(regressorCount, stats);
    processTable(exec, trainingData, stats, regr);
    List<String> factorList = new ArrayList<String>();
    List<String> covariateList = createCovariateListAndFillFactors(data, trainingData, factorList);
    try {
        RegressionResults result = regr.regress();
        RealMatrix beta = MatrixUtils.createRowRealMatrix(result.getParameterEstimates());
        // The covariance matrix
        RealMatrix covMat = createCovarianceMatrix(result);
        LinearRegressionContent content = new LinearRegressionContent(m_outSpec, (int) stats[0].getN(), factorList, covariateList, beta, m_includeConstant, m_offsetValue, covMat, result.getRSquared(), result.getAdjustedRSquared(), stats, null);
        return content;
    } catch (ModelSpecificationException e) {
        int dim = (m_includeConstant ? 1 : 0) + trainingData.getRegressorCount() + (factorList.size() > 0 ? Math.max(1, data.getDataTableSpec().getColumnSpec(factorList.get(0)).getDomain().getValues().size() - 1) : 0);
        RealMatrix beta = MatrixUtils.createRealMatrix(1, dim);
        RealMatrix covMat = MatrixUtils.createRealMatrix(dim, dim);
        // fillWithNaNs(beta);
        fillWithNaNs(covMat);
        return new LinearRegressionContent(m_outSpec, (int) stats[0].getN(), factorList, covariateList, beta, m_includeConstant, m_offsetValue, covMat, Double.NaN, Double.NaN, stats, e.getMessage());
    }
}

Example 4 with RegressionTrainingData

use of org.knime.base.node.mine.regression.RegressionTrainingData in project knime-core by knime.

the class Learner method perform.

/**
 * @param data The data table.
 * @param exec The execution context used for reporting progress.
 * @return An object which holds the results.
 * @throws CanceledExecutionException when method is cancelled
 * @throws InvalidSettingsException When settings are inconsistent with the data
 */
public LogisticRegressionContent perform(final BufferedDataTable data, final ExecutionContext exec) throws CanceledExecutionException, InvalidSettingsException {
    exec.checkCanceled();
    int iter = 0;
    boolean converged = false;
    final RegressionTrainingData trainingData = new RegressionTrainingData(data, m_outSpec, true, m_targetReferenceCategory, m_sortTargetCategories, m_sortFactorsCategories);
    int targetIndex = data.getDataTableSpec().findColumnIndex(m_outSpec.getTargetCols().get(0).getName());
    final int tcC = trainingData.getDomainValues().get(targetIndex).size();
    final int rC = trainingData.getRegressorCount();
    final RealMatrix beta = new Array2DRowRealMatrix(1, (tcC - 1) * (rC + 1));
    Double loglike = 0.0;
    Double loglikeOld = 0.0;
    exec.setMessage("Iterative optimization. Processing iteration 1.");
    // main loop
    while (iter < m_maxIter && !converged) {
        RealMatrix betaOld = beta.copy();
        loglikeOld = loglike;
        // Do heavy work in a separate thread which allows to interrupt it
        // note the queue may block if no more threads are available (e.g. thread count = 1)
        // as soon as we stall in 'get' this thread reduces the number of running thread
        Future<Double> future = ThreadPool.currentPool().enqueue(new Callable<Double>() {

            @Override
            public Double call() throws Exception {
                final ExecutionMonitor progMon = exec.createSubProgress(1.0 / m_maxIter);
                irlsRls(trainingData, beta, rC, tcC, progMon);
                progMon.setProgress(1.0);
                return likelihood(trainingData.iterator(), beta, rC, tcC, exec);
            }
        });
        try {
            loglike = future.get();
        } catch (InterruptedException e) {
            future.cancel(true);
            exec.checkCanceled();
            throw new RuntimeException(e);
        } catch (ExecutionException e) {
            if (e.getCause() instanceof RuntimeException) {
                throw (RuntimeException) e.getCause();
            } else {
                throw new RuntimeException(e.getCause());
            }
        }
        if (Double.isInfinite(loglike) || Double.isNaN(loglike)) {
            throw new RuntimeException(FAILING_MSG);
        }
        exec.checkCanceled();
        // test for decreasing likelihood
        while ((Double.isInfinite(loglike) || Double.isNaN(loglike) || loglike < loglikeOld) && iter > 0) {
            converged = true;
            for (int k = 0; k < beta.getRowDimension(); k++) {
                if (abs(beta.getEntry(k, 0) - betaOld.getEntry(k, 0)) > m_eps * abs(betaOld.getEntry(k, 0))) {
                    converged = false;
                    break;
                }
            }
            if (converged) {
                break;
            }
            // half the step size of beta
            beta.setSubMatrix((beta.add(betaOld)).scalarMultiply(0.5).getData(), 0, 0);
            exec.checkCanceled();
            loglike = likelihood(trainingData.iterator(), beta, rC, tcC, exec);
            exec.checkCanceled();
        }
        // test for convergence
        converged = true;
        for (int k = 0; k < beta.getRowDimension(); k++) {
            if (abs(beta.getEntry(k, 0) - betaOld.getEntry(k, 0)) > m_eps * abs(betaOld.getEntry(k, 0))) {
                converged = false;
                break;
            }
        }
        iter++;
        LOGGER.debug("#Iterations: " + iter);
        LOGGER.debug("Log Likelihood: " + loglike);
        StringBuilder betaBuilder = new StringBuilder();
        for (int i = 0; i < beta.getRowDimension() - 1; i++) {
            betaBuilder.append(Double.toString(beta.getEntry(i, 0)));
            betaBuilder.append(", ");
        }
        if (beta.getRowDimension() > 0) {
            betaBuilder.append(Double.toString(beta.getEntry(beta.getRowDimension() - 1, 0)));
        }
        LOGGER.debug("beta: " + betaBuilder.toString());
        exec.checkCanceled();
        exec.setMessage("Iterative optimization. #Iterations: " + iter + " | Log-likelihood: " + DoubleFormat.formatDouble(loglike) + ". Processing iteration " + (iter + 1) + ".");
    }
    // The covariance matrix
    RealMatrix covMat = new QRDecomposition(A).getSolver().getInverse().scalarMultiply(-1);
    List<String> factorList = new ArrayList<String>();
    List<String> covariateList = new ArrayList<String>();
    Map<String, List<DataCell>> factorDomainValues = new HashMap<String, List<DataCell>>();
    for (int i : trainingData.getActiveCols()) {
        if (trainingData.getIsNominal().get(i)) {
            String factor = data.getDataTableSpec().getColumnSpec(i).getName();
            factorList.add(factor);
            List<DataCell> values = trainingData.getDomainValues().get(i);
            factorDomainValues.put(factor, values);
        } else {
            covariateList.add(data.getDataTableSpec().getColumnSpec(i).getName());
        }
    }
    Matrix betaJama = new Matrix(beta.getData());
    Matrix covMatJama = new Matrix(covMat.getData());
    // create content
    LogisticRegressionContent content = new LogisticRegressionContent(m_outSpec, factorList, covariateList, m_targetReferenceCategory, m_sortTargetCategories, m_sortFactorsCategories, betaJama, loglike, covMatJama, iter);
    return content;
}