Examples with MissingCell org.knime.core.data.MissingCell used on opensource projects

Example 1 with MissingCell

use of org.knime.core.data.MissingCell in project knime-core by knime.

the class PMMLRuleSetPredictorNodeModel method createRearranger.

/**
 * Constructs the {@link ColumnRearranger} for computing the new columns.
 *
 * @param obj The {@link PMMLPortObject} of the preprocessing model.
 * @param spec The {@link DataTableSpec} of the table.
 * @param replaceColumn Should replace the {@code outputColumnName}?
 * @param outputColumnName The output column name (which might be an existing).
 * @param addConfidence Should add the confidence values to a column?
 * @param confidenceColumnName The name of the confidence column.
 * @param validationColumnIdx Index of the validation column, {@code -1} if not specified.
 * @param processConcurrently Should be {@code false} when the statistics are to be computed.
 * @return The {@link ColumnRearranger} computing the result.
 * @throws InvalidSettingsException Problem with rules.
 */
private static ColumnRearranger createRearranger(final PMMLPortObject obj, final DataTableSpec spec, final boolean replaceColumn, final String outputColumnName, final boolean addConfidence, final String confidenceColumnName, final int validationColumnIdx, final boolean processConcurrently) throws InvalidSettingsException {
    List<Node> models = obj.getPMMLValue().getModels(PMMLModelType.RuleSetModel);
    if (models.size() != 1) {
        throw new InvalidSettingsException("Expected exactly on RuleSetModel, but got: " + models.size());
    }
    final PMMLRuleTranslator translator = new PMMLRuleTranslator();
    obj.initializeModelTranslator(translator);
    if (!translator.isScorable()) {
        throw new UnsupportedOperationException("The model is not scorable.");
    }
    final List<PMMLRuleTranslator.Rule> rules = translator.getRules();
    ColumnRearranger ret = new ColumnRearranger(spec);
    final List<DataColumnSpec> targetCols = obj.getSpec().getTargetCols();
    final DataType dataType = targetCols.isEmpty() ? StringCell.TYPE : targetCols.get(0).getType();
    DataColumnSpecCreator specCreator = new DataColumnSpecCreator(outputColumnName, dataType);
    Set<DataCell> outcomes = new LinkedHashSet<>();
    for (Rule rule : rules) {
        DataCell outcome;
        if (dataType.equals(BooleanCell.TYPE)) {
            outcome = BooleanCellFactory.create(rule.getOutcome());
        } else if (dataType.equals(StringCell.TYPE)) {
            outcome = new StringCell(rule.getOutcome());
        } else if (dataType.equals(DoubleCell.TYPE)) {
            try {
                outcome = new DoubleCell(Double.parseDouble(rule.getOutcome()));
            } catch (NumberFormatException e) {
                // ignore
                continue;
            }
        } else if (dataType.equals(IntCell.TYPE)) {
            try {
                outcome = new IntCell(Integer.parseInt(rule.getOutcome()));
            } catch (NumberFormatException e) {
                // ignore
                continue;
            }
        } else if (dataType.equals(LongCell.TYPE)) {
            try {
                outcome = new LongCell(Long.parseLong(rule.getOutcome()));
            } catch (NumberFormatException e) {
                // ignore
                continue;
            }
        } else {
            throw new UnsupportedOperationException("Unknown outcome type: " + dataType);
        }
        outcomes.add(outcome);
    }
    specCreator.setDomain(new DataColumnDomainCreator(outcomes).createDomain());
    DataColumnSpec colSpec = specCreator.createSpec();
    final RuleSelectionMethod ruleSelectionMethod = translator.getSelectionMethodList().get(0);
    final String defaultScore = translator.getDefaultScore();
    final Double defaultConfidence = translator.getDefaultConfidence();
    final DataColumnSpec[] specs;
    if (addConfidence) {
        specs = new DataColumnSpec[] { new DataColumnSpecCreator(DataTableSpec.getUniqueColumnName(ret.createSpec(), confidenceColumnName), DoubleCell.TYPE).createSpec(), colSpec };
    } else {
        specs = new DataColumnSpec[] { colSpec };
    }
    final int oldColumnIndex = replaceColumn ? ret.indexOf(outputColumnName) : -1;
    ret.append(new AbstractCellFactory(processConcurrently, specs) {

        private final List<String> m_values;

        {
            Map<String, List<String>> dd = translator.getDataDictionary();
            m_values = dd.get(targetCols.get(0).getName());
        }

        /**
         * {@inheritDoc}
         */
        @Override
        public DataCell[] getCells(final DataRow row) {
            // See http://www.dmg.org/v4-1/RuleSet.html#Rule
            switch(ruleSelectionMethod.getCriterion().intValue()) {
                case RuleSelectionMethod.Criterion.INT_FIRST_HIT:
                    {
                        Pair<DataCell, Double> resultAndConfidence = selectFirstHit(row);
                        return toCells(resultAndConfidence);
                    }
                case RuleSelectionMethod.Criterion.INT_WEIGHTED_MAX:
                    {
                        Pair<DataCell, Double> resultAndConfidence = selectWeightedMax(row);
                        return toCells(resultAndConfidence);
                    }
                case RuleSelectionMethod.Criterion.INT_WEIGHTED_SUM:
                    {
                        Pair<DataCell, Double> resultAndConfidence = selectWeightedSum(row);
                        return toCells(resultAndConfidence);
                    }
                default:
                    throw new UnsupportedOperationException(ruleSelectionMethod.getCriterion().toString());
            }
        }

        /**
         * Converts the pair to a {@link DataCell} array.
         *
         * @param resultAndConfidence The {@link Pair}.
         * @return The result and possibly the confidence.
         */
        private DataCell[] toCells(final Pair<DataCell, Double> resultAndConfidence) {
            if (!addConfidence) {
                return new DataCell[] { resultAndConfidence.getFirst() };
            }
            if (resultAndConfidence.getSecond() == null) {
                return new DataCell[] { DataType.getMissingCell(), resultAndConfidence.getFirst() };
            }
            return new DataCell[] { new DoubleCell(resultAndConfidence.getSecond()), resultAndConfidence.getFirst() };
        }

        /**
         * Computes the result and the confidence using the weighted sum method.
         *
         * @param row A {@link DataRow}
         * @return The result and the confidence.
         */
        private Pair<DataCell, Double> selectWeightedSum(final DataRow row) {
            final Map<String, Double> scoreToSumWeight = new LinkedHashMap<String, Double>();
            for (String val : m_values) {
                scoreToSumWeight.put(val, 0.0);
            }
            int matchedRuleCount = 0;
            for (final PMMLRuleTranslator.Rule rule : rules) {
                if (rule.getCondition().evaluate(row, spec) == Boolean.TRUE) {
                    ++matchedRuleCount;
                    Double sumWeight = scoreToSumWeight.get(rule.getOutcome());
                    if (sumWeight == null) {
                        throw new IllegalStateException("The score value: " + rule.getOutcome() + " is not in the data dictionary.");
                    }
                    final Double wRaw = rule.getWeight();
                    final double w = wRaw == null ? 0.0 : wRaw.doubleValue();
                    scoreToSumWeight.put(rule.getOutcome(), sumWeight + w);
                }
            }
            double maxSumWeight = Double.NEGATIVE_INFINITY;
            String bestScore = null;
            for (Entry<String, Double> entry : scoreToSumWeight.entrySet()) {
                final double d = entry.getValue().doubleValue();
                if (d > maxSumWeight) {
                    maxSumWeight = d;
                    bestScore = entry.getKey();
                }
            }
            if (bestScore == null || matchedRuleCount == 0) {
                return pair(result(defaultScore), defaultConfidence);
            }
            return pair(result(bestScore), maxSumWeight / matchedRuleCount);
        }

        /**
         * Helper method to create {@link Pair}s.
         *
         * @param f The first element.
         * @param s The second element.
         * @return The new pair.
         */
        private <F, S> Pair<F, S> pair(final F f, final S s) {
            return new Pair<F, S>(f, s);
        }

        /**
         * Computes the result and the confidence using the weighted max method.
         *
         * @param row A {@link DataRow}
         * @return The result and the confidence.
         */
        private Pair<DataCell, Double> selectWeightedMax(final DataRow row) {
            double maxWeight = Double.NEGATIVE_INFINITY;
            PMMLRuleTranslator.Rule bestRule = null;
            for (final PMMLRuleTranslator.Rule rule : rules) {
                if (rule.getCondition().evaluate(row, spec) == Boolean.TRUE) {
                    if (rule.getWeight() > maxWeight) {
                        maxWeight = rule.getWeight();
                        bestRule = rule;
                    }
                }
            }
            if (bestRule == null) {
                return pair(result(defaultScore), defaultConfidence);
            }
            bestRule.setRecordCount(bestRule.getRecordCount() + 1);
            DataCell result = result(bestRule);
            if (validationColumnIdx >= 0) {
                if (row.getCell(validationColumnIdx).equals(result)) {
                    bestRule.setNbCorrect(bestRule.getNbCorrect() + 1);
                }
            }
            Double confidence = bestRule.getConfidence();
            return pair(result, confidence == null ? defaultConfidence : confidence);
        }

        /**
         * Selects the outcome of the rule and converts it to the proper outcome type.
         *
         * @param rule A {@link Rule}.
         * @return The {@link DataCell} representing the result. (May be missing.)
         */
        private DataCell result(final PMMLRuleTranslator.Rule rule) {
            String outcome = rule.getOutcome();
            return result(outcome);
        }

        /**
         * Constructs the {@link DataCell} from its {@link String} representation ({@code outcome}) and its type.
         *
         * @param dataType The expected {@link DataType}
         * @param outcome The {@link String} representation.
         * @return The {@link DataCell}.
         */
        private DataCell result(final String outcome) {
            if (outcome == null) {
                return DataType.getMissingCell();
            }
            try {
                if (dataType.isCompatible(BooleanValue.class)) {
                    return BooleanCellFactory.create(outcome);
                }
                if (IntCell.TYPE.isASuperTypeOf(dataType)) {
                    return new IntCell(Integer.parseInt(outcome));
                }
                if (LongCell.TYPE.isASuperTypeOf(dataType)) {
                    return new LongCell(Long.parseLong(outcome));
                }
                if (DoubleCell.TYPE.isASuperTypeOf(dataType)) {
                    return new DoubleCell(Double.parseDouble(outcome));
                }
                return new StringCell(outcome);
            } catch (NumberFormatException e) {
                return new MissingCell(outcome + "\n" + e.getMessage());
            }
        }

        /**
         * Selects the first rule that matches and computes the confidence and result for the {@code row}.
         *
         * @param row A {@link DataRow}.
         * @return The result and the confidence.
         */
        private Pair<DataCell, Double> selectFirstHit(final DataRow row) {
            for (final PMMLRuleTranslator.Rule rule : rules) {
                Boolean eval = rule.getCondition().evaluate(row, spec);
                if (eval == Boolean.TRUE) {
                    rule.setRecordCount(rule.getRecordCount() + 1);
                    DataCell result = result(rule);
                    if (validationColumnIdx >= 0) {
                        if (row.getCell(validationColumnIdx).equals(result)) {
                            rule.setNbCorrect(rule.getNbCorrect() + 1);
                        }
                    }
                    Double confidence = rule.getConfidence();
                    return pair(result, confidence == null ? defaultConfidence : confidence);
                }
            }
            return pair(result(defaultScore), defaultConfidence);
        }

        /**
         * {@inheritDoc}
         */
        @Override
        public void afterProcessing() {
            super.afterProcessing();
            obj.getPMMLValue();
            RuleSetModel ruleSet = translator.getOriginalRuleSetModel();
            assert rules.size() == ruleSet.getRuleSet().getSimpleRuleList().size() + ruleSet.getRuleSet().getCompoundRuleList().size();
            if (ruleSet.getRuleSet().getSimpleRuleList().size() == rules.size()) {
                for (int i = 0; i < rules.size(); ++i) {
                    Rule rule = rules.get(i);
                    final SimpleRule simpleRuleArray = ruleSet.getRuleSet().getSimpleRuleArray(i);
                    synchronized (simpleRuleArray) /*synchronized fixes AP-6766 */
                    {
                        simpleRuleArray.setRecordCount(rule.getRecordCount());
                        if (validationColumnIdx >= 0) {
                            simpleRuleArray.setNbCorrect(rule.getNbCorrect());
                        } else if (simpleRuleArray.isSetNbCorrect()) {
                            simpleRuleArray.unsetNbCorrect();
                        }
                    }
                }
            }
        }
    });
    if (replaceColumn) {
        ret.remove(outputColumnName);
        ret.move(ret.getColumnCount() - 1 - (addConfidence ? 1 : 0), oldColumnIndex);
    }
    return ret;
}

Example 2 with MissingCell

use of org.knime.core.data.MissingCell in project knime-core by knime.

the class HistogramColumn method loadNominalHistogramsPrivate.

private static Map<Integer, HistogramNominalModel> loadNominalHistogramsPrivate(final File histogramsGz, final int[] nominalKeysSize) throws IOException, InvalidSettingsException {
    final FileInputStream is = new FileInputStream(histogramsGz);
    final GZIPInputStream inData = new GZIPInputStream(is);
    final ConfigRO config = NodeSettings.loadFromXML(inData);
    Map<Integer, HistogramNominalModel> histograms = new HashMap<Integer, HistogramNominalModel>();
    // .getConfig(HISTOGRAMS);
    ConfigRO hs = config;
    int[] nomColumnIndices = config.getIntArray(NOMINAL_COLUMNS);
    for (int colIdx : nomColumnIndices) {
        Config h = hs.getConfig(HISTOGRAM + colIdx);
        int maxCount = h.getInt(MAX_COUNT);
        int rowCount = h.getInt(ROW_COUNT);
        String colName = h.getString(COL_NAME);
        String[] values = h.getStringArray(BIN_VALUES);
        int[] binCounts = h.getIntArray(BIN_COUNTS);
        Map<DataValue, Integer> bins = new HashMap<DataValue, Integer>();
        for (int i = binCounts.length; i-- > 0; ) {
            if (values[i] == "?") {
                bins.put(new MissingCell(null), binCounts[i]);
            } else {
                bins.put(new StringCell(values[i]), binCounts[i]);
            }
        }
        HistogramNominalModel histogramData = new HistogramNominalModel(bins, colIdx, colName, rowCount);
        histogramData.setMaxCount(maxCount);
        histogramData.setRowCount(rowCount);
        // assert Math.abs(histogramData.m_width - width) < 1e-9: "histogram data width: " + histogramData.m_width + " width: " + width;
        assert nominalKeysSize[colIdx] == bins.size() : "Saved size of nominal bins: " + nominalKeysSize[colIdx] + ", restored from the file: " + bins.size();
        histograms.put(colIdx, histogramData);
    }
    return histograms;
}

Example 3 with MissingCell

use of org.knime.core.data.MissingCell in project knime-core by knime.

the class TestDataGenerator method createNominalAttributeColumn.

public TreeNominalColumnData createNominalAttributeColumn(final String[] values, final String name, final int attributeIndex) {
    DataColumnSpec colSpec = new DataColumnSpecCreator(name, StringCell.TYPE).createSpec();
    TreeNominalColumnDataCreator colCreator = new TreeNominalColumnDataCreator(colSpec);
    for (int i = 0; i < values.length; i++) {
        RowKey rowKey = RowKey.createRowKey((long) i);
        if (values[i].equals("?")) {
            colCreator.add(rowKey, new MissingCell(null));
        } else {
            colCreator.add(rowKey, new StringCell(values[i]));
        }
    }
    TreeNominalColumnData col = colCreator.createColumnData(0, m_config);
    col.getMetaData().setAttributeIndex(attributeIndex);
    return col;
}

Example 4 with MissingCell

use of org.knime.core.data.MissingCell in project knime-core by knime.

the class TreeNumericColumnDataTest method createNumericColumnData.

public static TreeOrdinaryNumericColumnData createNumericColumnData(final TreeEnsembleLearnerConfiguration config, final double[] data, final String name, final int attributeIndex) {
    DataColumnSpec colSpec = new DataColumnSpecCreator(name, DoubleCell.TYPE).createSpec();
    TreeOrdinaryNumericColumnDataCreator colCreator = new TreeOrdinaryNumericColumnDataCreator(colSpec);
    for (int i = 0; i < data.length; i++) {
        final RowKey key = RowKey.createRowKey(i);
        if (Double.isNaN(data[i])) {
            colCreator.add(key, new MissingCell(null));
        } else {
            colCreator.add(key, new DoubleCell(data[i]));
        }
    }
    return colCreator.createColumnData(attributeIndex, config);
}

Example 5 with MissingCell

use of org.knime.core.data.MissingCell in project knime-core by knime.

the class DataCellToJavaConversionTest method testCollectionTypes.

/**
 * Test ListCell(IntCell) -> Integer[] conversion.
 *
 * @throws Exception When something went wrong
 */
@Test
public void testCollectionTypes() throws Exception {
    ArrayList<DataCell> coll = new ArrayList<>();
    for (int i = 0; i < 5; ++i) {
        coll.add(new IntCell(i * i));
    }
    // collection cells can always contain missing cells.
    coll.add(new MissingCell("42"));
    final ListCell listCell = CollectionCellFactory.createListCell(coll);
    final Optional<? extends DataCellToJavaConverterFactory<? extends DataValue, Integer[]>> factory = DataCellToJavaConverterRegistry.getInstance().getConverterFactories(listCell.getType(), Integer[].class).stream().findFirst();
    assertTrue(factory.isPresent());
    final DataCellToJavaConverter<DataCell, Integer[]> converter = (DataCellToJavaConverter<DataCell, Integer[]>) factory.get().create();
    assertNotNull(converter);
    final Integer[] array = converter.convert(listCell);
    for (int i = 0; i < 5; ++i) {
        assertEquals(new Integer(i * i), array[i]);
    }
    assertNull(array[5]);
}