Examples with StatisticsTable org.knime.base.data.statistics.StatisticsTable used on opensource projects

Example 6 with StatisticsTable

use of org.knime.base.data.statistics.StatisticsTable in project knime-core by knime.

the class Normalizer method doMinMaxNorm.

/**
 * Does the Min-Max Normalization.
 *
 * @param newmax the new maximum
 * @param newmin the new minimum
 * @param exec an object to check for user cancelations. Can be
 *            <code>null</code>.
 * @throws CanceledExecutionException if user canceled
 * @return normalized DataTable
 */
public AffineTransTable doMinMaxNorm(final double newmax, final double newmin, final ExecutionMonitor exec) throws CanceledExecutionException {
    ExecutionMonitor statisticsExec = exec.createSubProgress(.5);
    StatisticsTable st;
    if (m_table instanceof StatisticsTable) {
        st = (StatisticsTable) m_table;
    } else {
        st = new StatisticsTable(m_table, statisticsExec);
    }
    checkForMissVals(st);
    DataTableSpec spec = st.getDataTableSpec();
    DataCell[] max = st.getMax();
    DataCell[] min = st.getMin();
    final double[] scales = new double[m_colindices.length];
    final double[] transforms = new double[m_colindices.length];
    final double[] mins = new double[m_colindices.length];
    final double[] maxs = new double[m_colindices.length];
    for (int i = 0; i < transforms.length; i++) {
        DataColumnSpec cSpec = spec.getColumnSpec(m_colindices[i]);
        boolean isDouble = cSpec.getType().isCompatible(DoubleValue.class);
        if (!isDouble || max[m_colindices[i]].isMissing()) {
            assert (!isDouble || min[m_colindices[i]].isMissing());
            scales[i] = Double.NaN;
            transforms[i] = Double.NaN;
            mins[i] = Double.NaN;
            maxs[i] = Double.NaN;
        } else {
            // scales and translation to [0,1]
            double maxI = ((DoubleValue) max[m_colindices[i]]).getDoubleValue();
            double minI = ((DoubleValue) min[m_colindices[i]]).getDoubleValue();
            scales[i] = (maxI == minI ? 1 : 1.0 / (maxI - minI));
            transforms[i] = -minI * scales[i];
            // scale and translation to [newmin, newmax]
            scales[i] *= (newmax - newmin);
            transforms[i] *= (newmax - newmin);
            transforms[i] += newmin;
            mins[i] = newmin;
            maxs[i] = newmax;
        }
    }
    String[] includes = getNames();
    String minS = DoubleFormat.formatDouble(newmin);
    String maxS = DoubleFormat.formatDouble(newmax);
    String summary = "Min/Max (" + minS + ", " + maxS + ") normalization " + "on " + includes.length + " column(s)";
    AffineTransConfiguration configuration = new AffineTransConfiguration(includes, scales, transforms, mins, maxs, summary);
    return new AffineTransTable(m_table, configuration);
}

Example 7 with StatisticsTable

use of org.knime.base.data.statistics.StatisticsTable in project knime-core by knime.

the class Normalizer method doZScoreNorm.

/**
 * Does the Z-Score Normalization.
 *
 * @param exec an object to check for user cancelations. Can be
 *            <code>null</code>.
 * @throws CanceledExecutionException if user canceled
 * @return the normalized DataTable
 */
public AffineTransTable doZScoreNorm(final ExecutionMonitor exec) throws CanceledExecutionException {
    ExecutionMonitor statisticsExec = exec.createSubProgress(.5);
    StatisticsTable st;
    if (m_table instanceof StatisticsTable) {
        st = (StatisticsTable) m_table;
    } else {
        st = new StatisticsTable(m_table, statisticsExec);
    }
    checkForMissVals(st);
    double[] mean = st.getMean();
    double[] stddev = st.getStandardDeviation();
    final double[] scales = new double[m_colindices.length];
    final double[] transforms = new double[m_colindices.length];
    final double[] mins = new double[m_colindices.length];
    final double[] maxs = new double[m_colindices.length];
    for (int i = 0; i < m_colindices.length; i++) {
        if (Double.isNaN(mean[m_colindices[i]])) {
            scales[i] = Double.NaN;
            transforms[i] = Double.NaN;
        } else {
            scales[i] = (stddev[m_colindices[i]] == 0.0 ? 1.0 : 1.0 / stddev[m_colindices[i]]);
            transforms[i] = -mean[m_colindices[i]] * scales[i];
        }
        mins[i] = Double.NaN;
        maxs[i] = Double.NaN;
    }
    String[] includes = getNames();
    String summary = "Z-Score (Gaussian) normalization on " + includes.length + " column(s)";
    AffineTransConfiguration configuration = new AffineTransConfiguration(includes, scales, transforms, mins, maxs, summary);
    return new AffineTransTable(m_table, configuration);
}

Example 8 with StatisticsTable

use of org.knime.base.data.statistics.StatisticsTable in project knime-core by knime.

the class PMCCNodeModel method execute.

/**
 * {@inheritDoc}
 */
@Override
protected PortObject[] execute(final PortObject[] inData, final ExecutionContext exec) throws Exception {
    final BufferedDataTable in = (BufferedDataTable) inData[0];
    // floating point operation
    final double rC = in.getRowCount();
    int[] includes = getIncludes(in.getDataTableSpec());
    String[] includeNames = m_columnIncludesList.getIncludeList().toArray(new String[0]);
    double progNormalize = 0.3;
    double progDetermine = 0.65;
    double progFinish = 1.0 - progNormalize - progDetermine;
    exec.setMessage("Normalizing data");
    final ExecutionMonitor normProg = exec.createSubProgress(progNormalize);
    FilterColumnTable filterTable = new FilterColumnTable(in, includes);
    final int l = includes.length;
    int nomCount = (l - 1) * l / 2;
    final HalfDoubleMatrix nominatorMatrix = new HalfDoubleMatrix(includes.length, /*withDiagonal*/
    false);
    nominatorMatrix.fill(Double.NaN);
    @SuppressWarnings("unchecked") final LinkedHashMap<DataCell, Integer>[] possibleValues = new LinkedHashMap[l];
    DataTableSpec filterTableSpec = filterTable.getDataTableSpec();
    for (int i = 0; i < l; i++) {
        DataColumnSpec cs = filterTableSpec.getColumnSpec(i);
        if (cs.getType().isCompatible(NominalValue.class)) {
            possibleValues[i] = new LinkedHashMap<DataCell, Integer>();
        }
    }
    final int possValueUpperBound = m_maxPossValueCountModel.getIntValue();
    // determines possible values. We can't use those from the domain
    // as the domain can also contain values not present in the data
    // but in the contingency table we need rows/columns to have at least
    // one cell with a value >= 1
    StatisticsTable statTable = new StatisticsTable(filterTable) {

        // that is sort of the constructor in this derived class
        {
            calculateAllMoments(in.getRowCount(), normProg);
        }

        @Override
        protected void calculateMomentInSubClass(final DataRow row) {
            for (int i = 0; i < l; i++) {
                if (possibleValues[i] != null) {
                    DataCell c = row.getCell(i);
                    // note: also take missing value as possible value
                    possibleValues[i].put(c, null);
                    if (possibleValues[i].size() > possValueUpperBound) {
                        possibleValues[i] = null;
                    }
                }
            }
        }
    };
    for (LinkedHashMap<DataCell, Integer> map : possibleValues) {
        if (map != null) {
            int index = 0;
            for (Map.Entry<DataCell, Integer> entry : map.entrySet()) {
                entry.setValue(index++);
            }
        }
    }
    // stores all pair-wise contingency tables,
    // contingencyTables[i] == null <--> either column of the corresponding
    // pair is non-categorical.
    // What is a contingency table?
    // http://en.wikipedia.org/wiki/Contingency_table
    int[][][] contingencyTables = new int[nomCount][][];
    // column which only contain one value - no correlation available
    LinkedHashSet<String> constantColumns = new LinkedHashSet<String>();
    int valIndex = 0;
    for (int i = 0; i < l; i++) {
        for (int j = i + 1; j < l; j++) {
            if (possibleValues[i] != null && possibleValues[j] != null) {
                int iSize = possibleValues[i].size();
                int jSize = possibleValues[j].size();
                contingencyTables[valIndex] = new int[iSize][jSize];
            }
            DataColumnSpec colSpecI = filterTableSpec.getColumnSpec(i);
            DataColumnSpec colSpecJ = filterTableSpec.getColumnSpec(j);
            DataType ti = colSpecI.getType();
            DataType tj = colSpecJ.getType();
            if (ti.isCompatible(DoubleValue.class) && tj.isCompatible(DoubleValue.class)) {
                // one of the two columns contains only one value
                if (statTable.getVariance(i) < PMCCPortObjectAndSpec.ROUND_ERROR_OK) {
                    constantColumns.add(colSpecI.getName());
                    nominatorMatrix.set(i, j, Double.NaN);
                } else if (statTable.getVariance(j) < PMCCPortObjectAndSpec.ROUND_ERROR_OK) {
                    constantColumns.add(colSpecJ.getName());
                    nominatorMatrix.set(i, j, Double.NaN);
                } else {
                    nominatorMatrix.set(i, j, 0.0);
                }
            }
            valIndex++;
        }
    }
    // to other column (will be a missing value)
    if (!constantColumns.isEmpty()) {
        String[] constantColumnNames = constantColumns.toArray(new String[constantColumns.size()]);
        NodeLogger.getLogger(getClass()).info("The following numeric " + "columns contain only one distinct value or have " + "otherwise a low standard deviation: " + Arrays.toString(constantColumnNames));
        int maxLength = 4;
        if (constantColumns.size() > maxLength) {
            constantColumnNames = Arrays.copyOf(constantColumnNames, maxLength);
            constantColumnNames[maxLength - 1] = "...";
        }
        setWarningMessage("Some columns contain only one distinct value: " + Arrays.toString(constantColumnNames));
    }
    DataTable att;
    if (statTable.getNrRows() > 0) {
        att = new Normalizer(statTable, includeNames).doZScoreNorm(// no iteration needed
        exec.createSubProgress(0.0));
    } else {
        att = statTable;
    }
    normProg.setProgress(1.0);
    exec.setMessage("Calculating correlation measure");
    ExecutionMonitor detProg = exec.createSubProgress(progDetermine);
    int rowIndex = 0;
    double[] buf = new double[l];
    DataCell[] catBuf = new DataCell[l];
    boolean containsMissing = false;
    for (DataRow r : att) {
        detProg.checkCanceled();
        for (int i = 0; i < l; i++) {
            catBuf[i] = null;
            buf[i] = Double.NaN;
            DataCell c = r.getCell(i);
            // missing value is also a possible value here
            if (possibleValues[i] != null) {
                catBuf[i] = c;
            } else if (c.isMissing()) {
                containsMissing = true;
            } else if (filterTableSpec.getColumnSpec(i).getType().isCompatible(DoubleValue.class)) {
                buf[i] = ((DoubleValue) c).getDoubleValue();
            }
        }
        valIndex = 0;
        for (int i = 0; i < l; i++) {
            for (int j = i + 1; j < l; j++) {
                double b1 = buf[i];
                double b2 = buf[j];
                if (!Double.isNaN(b1) && !Double.isNaN(b2)) {
                    double old = nominatorMatrix.get(i, j);
                    nominatorMatrix.set(i, j, old + b1 * b2);
                } else if (catBuf[i] != null && catBuf[j] != null) {
                    int iIndex = possibleValues[i].get(catBuf[i]);
                    assert iIndex >= 0 : "Value unknown in value list " + "of column " + includeNames[i] + ": " + catBuf[i];
                    int jIndex = possibleValues[j].get(catBuf[j]);
                    assert jIndex >= 0 : "Value unknown in value list " + "of column " + includeNames[j] + ": " + catBuf[j];
                    contingencyTables[valIndex][iIndex][jIndex]++;
                }
                valIndex++;
            }
        }
        rowIndex++;
        detProg.setProgress(rowIndex / rC, "Processing row " + rowIndex + " (\"" + r.getKey() + "\")");
    }
    if (containsMissing) {
        setWarningMessage("Some row(s) contained missing values.");
    }
    detProg.setProgress(1.0);
    double normalizer = 1.0 / (rC - 1.0);
    valIndex = 0;
    for (int i = 0; i < l; i++) {
        for (int j = i + 1; j < l; j++) {
            if (contingencyTables[valIndex] != null) {
                nominatorMatrix.set(i, j, computeCramersV(contingencyTables[valIndex]));
            } else if (!Double.isNaN(nominatorMatrix.get(i, j))) {
                double old = nominatorMatrix.get(i, j);
                nominatorMatrix.set(i, j, old * normalizer);
            }
            // else pair of columns is double - string (for instance)
            valIndex++;
        }
    }
    normProg.setProgress(progDetermine);
    PMCCPortObjectAndSpec pmccModel = new PMCCPortObjectAndSpec(includeNames, nominatorMatrix);
    ExecutionContext subExec = exec.createSubExecutionContext(progFinish);
    BufferedDataTable out = pmccModel.createCorrelationMatrix(subExec);
    m_correlationTable = out;
    return new PortObject[] { out, pmccModel };
}