Examples with BufferedDataContainer org.knime.core.node.BufferedDataContainer used on opensource projects

Example 31 with BufferedDataContainer

use of org.knime.core.node.BufferedDataContainer in project knime-core by knime.

the class NormalizerNodeModel method calculate.

/**
 * New normalized {@link org.knime.core.data.DataTable} is created depending
 * on the mode.
 */
/**
 * @param inData The input data.
 * @param exec For BufferedDataTable creation and progress.
 * @return the result of the calculation
 * @throws Exception If the node calculation fails for any reason.
 */
protected CalculationResult calculate(final PortObject[] inData, final ExecutionContext exec) throws Exception {
    BufferedDataTable inTable = (BufferedDataTable) inData[0];
    DataTableSpec inSpec = inTable.getSpec();
    // extract selected numeric columns
    updateNumericColumnSelection(inSpec);
    Normalizer ntable = new Normalizer(inTable, m_columns);
    long rowcount = inTable.size();
    ExecutionMonitor prepareExec = exec.createSubProgress(0.3);
    AffineTransTable outTable;
    boolean fixDomainBounds = false;
    switch(m_mode) {
        case NONORM_MODE:
            return new CalculationResult(inTable, new DataTableSpec(), new AffineTransConfiguration());
        case MINMAX_MODE:
            fixDomainBounds = true;
            outTable = ntable.doMinMaxNorm(m_max, m_min, prepareExec);
            break;
        case ZSCORE_MODE:
            outTable = ntable.doZScoreNorm(prepareExec);
            break;
        case DECIMALSCALING_MODE:
            outTable = ntable.doDecimalScaling(prepareExec);
            break;
        default:
            throw new Exception("No mode set");
    }
    if (outTable.getErrorMessage() != null) {
        // something went wrong, report and throw an exception
        throw new Exception(outTable.getErrorMessage());
    }
    if (ntable.getErrorMessage() != null) {
        // something went wrong during initialization, report.
        setWarningMessage(ntable.getErrorMessage());
    }
    DataTableSpec modelSpec = FilterColumnTable.createFilterTableSpec(inSpec, m_columns);
    AffineTransConfiguration configuration = outTable.getConfiguration();
    DataTableSpec spec = outTable.getDataTableSpec();
    // the same transformation, which is not guaranteed to snap to min/max)
    if (fixDomainBounds) {
        DataColumnSpec[] newColSpecs = new DataColumnSpec[spec.getNumColumns()];
        for (int i = 0; i < newColSpecs.length; i++) {
            newColSpecs[i] = spec.getColumnSpec(i);
        }
        for (int i = 0; i < m_columns.length; i++) {
            int index = spec.findColumnIndex(m_columns[i]);
            DataColumnSpecCreator creator = new DataColumnSpecCreator(newColSpecs[index]);
            DataColumnDomainCreator domCreator = new DataColumnDomainCreator(newColSpecs[index].getDomain());
            domCreator.setLowerBound(new DoubleCell(m_min));
            domCreator.setUpperBound(new DoubleCell(m_max));
            creator.setDomain(domCreator.createDomain());
            newColSpecs[index] = creator.createSpec();
        }
        spec = new DataTableSpec(spec.getName(), newColSpecs);
    }
    ExecutionMonitor normExec = exec.createSubProgress(.7);
    BufferedDataContainer container = exec.createDataContainer(spec);
    long count = 1;
    for (DataRow row : outTable) {
        normExec.checkCanceled();
        normExec.setProgress(count / (double) rowcount, "Normalizing row no. " + count + " of " + rowcount + " (\"" + row.getKey() + "\")");
        container.addRowToTable(row);
        count++;
    }
    container.close();
    return new CalculationResult(container.getTable(), modelSpec, configuration);
}

Example 32 with BufferedDataContainer

use of org.knime.core.node.BufferedDataContainer in project knime-core by knime.

the class EnrichmentPlotterModel method execute.

/**
 * {@inheritDoc}
 */
@Override
protected BufferedDataTable[] execute(final BufferedDataTable[] inData, final ExecutionContext exec) throws Exception {
    final double rowCount = inData[0].size();
    final BufferedDataContainer areaOutCont = exec.createDataContainer(AREA_OUT_SPEC);
    final BufferedDataContainer discrateOutCont = exec.createDataContainer(DISCRATE_OUT_SPEC);
    for (int i = 0; i < m_settings.getCurveCount(); i++) {
        final ExecutionMonitor sexec = exec.createSubProgress(1.0 / m_settings.getCurveCount());
        exec.setMessage("Generating curve " + (i + 1));
        final Curve c = m_settings.getCurve(i);
        final Helper[] curve = new Helper[KnowsRowCountTable.checkRowCount(inData[0].size())];
        final int sortIndex = inData[0].getDataTableSpec().findColumnIndex(c.getSortColumn());
        final int actIndex = inData[0].getDataTableSpec().findColumnIndex(c.getActivityColumn());
        int k = 0, maxK = 0;
        for (DataRow row : inData[0]) {
            DataCell c1 = row.getCell(sortIndex);
            DataCell c2 = row.getCell(actIndex);
            if (k++ % 100 == 0) {
                sexec.checkCanceled();
                sexec.setProgress(k / rowCount);
            }
            if (c1.isMissing()) {
                continue;
            } else {
                curve[maxK] = new Helper(((DoubleValue) c1).getDoubleValue(), c2);
            }
            maxK++;
        }
        Arrays.sort(curve, 0, maxK);
        if (c.isSortDescending()) {
            for (int j = 0; j < maxK / 2; j++) {
                Helper h = curve[j];
                curve[j] = curve[maxK - j - 1];
                curve[maxK - j - 1] = h;
            }
        }
        // this is for down-sampling so that the view is faster;
        // plotting >100,000 points takes quite a long time
        final int size = Math.min(MAX_RESOLUTION, maxK);
        final double downSampleRate = maxK / (double) size;
        final double[] xValues = new double[size + 1];
        final double[] yValues = new double[size + 1];
        xValues[0] = 0;
        yValues[0] = 0;
        int lastK = 0;
        double y = 0, area = 0;
        int nextHitRatePoint = 0;
        final double[] hitRateValues = new double[DISCRATE_POINTS.length];
        final HashMap<DataCell, MutableInteger> clusters = new HashMap<DataCell, MutableInteger>();
        for (k = 1; k <= maxK; k++) {
            final Helper h = curve[k - 1];
            if (m_settings.plotMode() == PlotMode.PlotSum) {
                y += ((DoubleValue) h.b).getDoubleValue();
            } else if (m_settings.plotMode() == PlotMode.PlotHits) {
                if (!h.b.isMissing() && (((DoubleValue) h.b).getDoubleValue() >= m_settings.hitThreshold())) {
                    y++;
                }
            } else if (!h.b.isMissing()) {
                MutableInteger count = clusters.get(h.b);
                if (count == null) {
                    count = new MutableInteger(0);
                    clusters.put(h.b, count);
                }
                if (count.inc() == m_settings.minClusterMembers()) {
                    y++;
                }
            }
            area += y / maxK;
            if ((int) (k / downSampleRate) >= lastK + 1) {
                lastK++;
                xValues[lastK] = k;
                yValues[lastK] = y;
            }
            if ((nextHitRatePoint < DISCRATE_POINTS.length) && (k == (int) Math.floor(maxK * DISCRATE_POINTS[nextHitRatePoint] / 100))) {
                hitRateValues[nextHitRatePoint] = y;
                nextHitRatePoint++;
            }
        }
        xValues[xValues.length - 1] = maxK;
        yValues[yValues.length - 1] = y;
        area /= y;
        m_curves.add(new EnrichmentPlot(c.getSortColumn() + " vs " + c.getActivityColumn(), xValues, yValues, area));
        areaOutCont.addRowToTable(new DefaultRow(new RowKey(c.toString()), new DoubleCell(area)));
        for (int j = 0; j < hitRateValues.length; j++) {
            hitRateValues[j] /= y;
        }
        discrateOutCont.addRowToTable(new DefaultRow(new RowKey(c.toString()), hitRateValues));
    }
    areaOutCont.close();
    discrateOutCont.close();
    return new BufferedDataTable[] { areaOutCont.getTable(), discrateOutCont.getTable() };
}

Example 33 with BufferedDataContainer

use of org.knime.core.node.BufferedDataContainer in project knime-core by knime.

the class LogisticRegressionContent method createTablePortObject.

/**
 * Creates a BufferedDataTable with the
 * @param exec The execution context
 * @return a port object
 */
public BufferedDataTable createTablePortObject(final ExecutionContext exec) {
    DataTableSpec tableOutSpec = new DataTableSpec("Coefficients and Statistics", new String[] { "Logit", "Variable", "Coeff.", "Std. Err.", "z-score", "P>|z|" }, new DataType[] { StringCell.TYPE, StringCell.TYPE, DoubleCell.TYPE, DoubleCell.TYPE, DoubleCell.TYPE, DoubleCell.TYPE });
    BufferedDataContainer dc = exec.createDataContainer(tableOutSpec);
    List<DataCell> logits = this.getLogits();
    List<String> parameters = this.getParameters();
    int c = 0;
    for (DataCell logit : logits) {
        Map<String, Double> coefficients = this.getCoefficients(logit);
        Map<String, Double> stdErrs = this.getStandardErrors(logit);
        Map<String, Double> zScores = this.getZScores(logit);
        Map<String, Double> pValues = this.getPValues(logit);
        for (String parameter : parameters) {
            List<DataCell> cells = new ArrayList<DataCell>();
            cells.add(new StringCell(logit.toString()));
            cells.add(new StringCell(parameter));
            cells.add(new DoubleCell(coefficients.get(parameter)));
            cells.add(new DoubleCell(stdErrs.get(parameter)));
            cells.add(new DoubleCell(zScores.get(parameter)));
            cells.add(new DoubleCell(pValues.get(parameter)));
            c++;
            dc.addRowToTable(new DefaultRow("Row" + c, cells));
        }
        List<DataCell> cells = new ArrayList<DataCell>();
        cells.add(new StringCell(logit.toString()));
        cells.add(new StringCell("Constant"));
        cells.add(new DoubleCell(this.getIntercept(logit)));
        cells.add(new DoubleCell(this.getInterceptStdErr(logit)));
        cells.add(new DoubleCell(this.getInterceptZScore(logit)));
        cells.add(new DoubleCell(this.getInterceptPValue(logit)));
        c++;
        dc.addRowToTable(new DefaultRow("Row" + c, cells));
    }
    dc.close();
    return dc.getTable();
}

Example 34 with BufferedDataContainer

use of org.knime.core.node.BufferedDataContainer in project knime-core by knime.

the class LogisticRegressionContent method createTablePortObject.

/**
 * Creates a BufferedDataTable with the
 * @param exec The execution context
 * @return a port object
 */
public BufferedDataTable createTablePortObject(final ExecutionContext exec) {
    DataTableSpec tableOutSpec = new DataTableSpec("Coefficients and Statistics", new String[] { "Logit", "Variable", "Coeff.", "Std. Err.", "z-score", "P>|z|" }, new DataType[] { StringCell.TYPE, StringCell.TYPE, DoubleCell.TYPE, DoubleCell.TYPE, DoubleCell.TYPE, DoubleCell.TYPE });
    BufferedDataContainer dc = exec.createDataContainer(tableOutSpec);
    List<DataCell> logits = this.getLogits();
    List<String> parameters = this.getParameters();
    int c = 0;
    for (DataCell logit : logits) {
        Map<String, Double> coefficients = this.getCoefficients(logit);
        Map<String, Double> stdErrs = this.getStandardErrors(logit);
        Map<String, Double> zScores = this.getZScores(logit);
        Map<String, Double> pValues = this.getPValues(logit);
        for (String parameter : parameters) {
            List<DataCell> cells = new ArrayList<DataCell>();
            cells.add(new StringCell(logit.toString()));
            cells.add(new StringCell(parameter));
            cells.add(new DoubleCell(coefficients.get(parameter)));
            cells.add(new DoubleCell(stdErrs.get(parameter)));
            cells.add(new DoubleCell(zScores.get(parameter)));
            cells.add(new DoubleCell(pValues.get(parameter)));
            c++;
            dc.addRowToTable(new DefaultRow("Row" + c, cells));
        }
        List<DataCell> cells = new ArrayList<DataCell>();
        cells.add(new StringCell(logit.toString()));
        cells.add(new StringCell("Constant"));
        cells.add(new DoubleCell(this.getIntercept(logit)));
        cells.add(new DoubleCell(this.getInterceptStdErr(logit)));
        cells.add(new DoubleCell(this.getInterceptZScore(logit)));
        cells.add(new DoubleCell(this.getInterceptPValue(logit)));
        c++;
        dc.addRowToTable(new DefaultRow("Row" + c, cells));
    }
    dc.close();
    return dc.getTable();
}

Example 35 with BufferedDataContainer

use of org.knime.core.node.BufferedDataContainer in project knime-core by knime.

the class MissingValueHandling3Table method createMissingValueHandlingTable.

/**
 * Does missing value handling to the argument table given the col settings in an array and also reports progress.
 *
 * @param table the table to do missing value handling on
 * @param colSettings the settings
 * @param exec for progress/cancel and to create the buffered data table
 * @param warningBuffer To which potential warning messages are added.
 * @return a cache table, cleaned up
 * @throws CanceledExecutionException if canceled
 * @since 2.10
 */
public static BufferedDataTable createMissingValueHandlingTable(final BufferedDataTable table, final MissingValueHandling2ColSetting[] colSettings, final ExecutionContext exec, final StringBuilder warningBuffer) throws CanceledExecutionException {
    MissingValueHandling2ColSetting[] colSetting;
    try {
        colSetting = getColSetting(table.getDataTableSpec(), colSettings, false, warningBuffer);
    } catch (InvalidSettingsException ise) {
        LOGGER.coding("getColSetting method is not supposed to throw an exception, ignoring settings", ise);
        DataTableSpec s = table.getDataTableSpec();
        colSetting = new MissingValueHandling2ColSetting[s.getNumColumns()];
        for (int i = 0; i < s.getNumColumns(); i++) {
            colSetting[i] = new MissingValueHandling2ColSetting(s.getColumnSpec(i));
            colSetting[i].setMethod(MissingValueHandling2ColSetting.METHOD_NO_HANDLING);
        }
    }
    boolean needStatistics = false;
    final Set<Integer> mostFrequentColumns = new HashSet<Integer>();
    for (int i = 0; i < colSetting.length; i++) {
        MissingValueHandling2ColSetting c = colSetting[i];
        switch(c.getMethod()) {
            case MissingValueHandling2ColSetting.METHOD_MOST_FREQUENT:
                mostFrequentColumns.add(i);
            case MissingValueHandling2ColSetting.METHOD_MAX:
            case MissingValueHandling2ColSetting.METHOD_MIN:
            case MissingValueHandling2ColSetting.METHOD_MEAN:
                needStatistics = true;
                break;
            default:
        }
    }
    MyStatisticsTable myT;
    ExecutionMonitor e;
    if (needStatistics) {
        // for creating statistics table
        ExecutionContext subExec = exec.createSubExecutionContext(0.5);
        myT = new MyStatisticsTable(table, subExec) {

            // do not try to get this Iterable in the constructor, it will not work, as long as
            // Statistics3Table does the statistical computation in the constructor.
            @Override
            protected Iterable<Integer> getMostFrequentColumns() {
                return mostFrequentColumns;
            }
        };
        if (myT.m_warningMessage != null) {
            if (warningBuffer.length() > 0) {
                warningBuffer.append('\n');
            }
            warningBuffer.append(myT.m_warningMessage);
        }
        // for the iterator
        e = exec.createSubProgress(0.5);
    } else {
        myT = null;
        e = exec;
    }
    MissingValueHandling3Table mvht = new MissingValueHandling3Table(table, myT, colSetting);
    BufferedDataContainer container = exec.createDataContainer(mvht.getDataTableSpec());
    e.setMessage("Adding rows...");
    int count = 0;
    try {
        MissingValueHandling3TableIterator it = new MissingValueHandling3TableIterator(mvht, e);
        while (it.hasNext()) {
            DataRow next;
            next = it.next();
            e.setMessage("Adding row " + (count + 1) + " (\"" + next.getKey() + "\")");
            container.addRowToTable(next);
            count++;
        }
    } catch (MissingValueHandling3TableIterator.RuntimeCanceledExecutionException rcee) {
        throw rcee.getCause();
    } finally {
        container.close();
    }
    return container.getTable();
}