Examples with Discretize org.dmg.pmml.DiscretizeDocument.Discretize used on opensource projects

Example 1 with Discretize

use of org.dmg.pmml.DiscretizeDocument.Discretize in project knime-core by knime.

the class DataColumnSpecFilterPMMLNodeModel method createPMMLOut.

private PMMLPortObject createPMMLOut(final PMMLPortObject pmmlIn, final DataTableSpec outSpec, final FilterResult res) throws XmlException {
    StringBuffer warningBuffer = new StringBuffer();
    if (pmmlIn == null) {
        return new PMMLPortObject(createPMMLSpec(null, outSpec, res));
    } else {
        PMMLDocument pmmldoc;
        try (LockedSupplier<Document> supplier = pmmlIn.getPMMLValue().getDocumentSupplier()) {
            pmmldoc = PMMLDocument.Factory.parse(supplier.get());
        }
        // Inspect models to check if they use any excluded columns
        List<PMMLModelWrapper> models = PMMLModelWrapper.getModelListFromPMMLDocument(pmmldoc);
        for (PMMLModelWrapper model : models) {
            MiningSchema ms = model.getMiningSchema();
            for (MiningField mf : ms.getMiningFieldList()) {
                if (isExcluded(mf.getName(), res)) {
                    if (warningBuffer.length() != 0) {
                        warningBuffer.append("\n");
                    }
                    warningBuffer.append(model.getModelType().name() + " uses excluded column " + mf.getName());
                }
            }
        }
        ArrayList<String> warningFields = new ArrayList<String>();
        PMML pmml = pmmldoc.getPMML();
        // Now check the transformations if they exist
        if (pmml.getTransformationDictionary() != null) {
            for (DerivedField df : pmml.getTransformationDictionary().getDerivedFieldList()) {
                FieldRef fr = df.getFieldRef();
                if (fr != null && isExcluded(fr.getField(), res)) {
                    warningFields.add(fr.getField());
                }
                Aggregate a = df.getAggregate();
                if (a != null && isExcluded(a.getField(), res)) {
                    warningFields.add(a.getField());
                }
                Apply ap = df.getApply();
                if (ap != null) {
                    for (FieldRef fieldRef : ap.getFieldRefList()) {
                        if (isExcluded(fieldRef.getField(), res)) {
                            warningFields.add(fieldRef.getField());
                            break;
                        }
                    }
                }
                Discretize d = df.getDiscretize();
                if (d != null && isExcluded(d.getField(), res)) {
                    warningFields.add(d.getField());
                }
                MapValues mv = df.getMapValues();
                if (mv != null) {
                    for (FieldColumnPair fcp : mv.getFieldColumnPairList()) {
                        if (isExcluded(fcp.getField(), res)) {
                            warningFields.add(fcp.getField());
                        }
                    }
                }
                NormContinuous nc = df.getNormContinuous();
                if (nc != null && isExcluded(nc.getField(), res)) {
                    warningFields.add(nc.getField());
                }
                NormDiscrete nd = df.getNormDiscrete();
                if (nd != null && isExcluded(nd.getField(), res)) {
                    warningFields.add(nd.getField());
                }
            }
        }
        DataDictionary dict = pmml.getDataDictionary();
        List<DataField> fields = dict.getDataFieldList();
        // Apply filter to spec
        int numFields = 0;
        for (int i = fields.size() - 1; i >= 0; i--) {
            if (isExcluded(fields.get(i).getName(), res)) {
                dict.removeDataField(i);
            } else {
                numFields++;
            }
        }
        dict.setNumberOfFields(new BigInteger(Integer.toString(numFields)));
        pmml.setDataDictionary(dict);
        pmmldoc.setPMML(pmml);
        // generate warnings and set as warning message
        for (String s : warningFields) {
            if (warningBuffer.length() != 0) {
                warningBuffer.append("\n");
            }
            warningBuffer.append("Transformation dictionary uses excluded column " + s);
        }
        if (warningBuffer.length() > 0) {
            setWarningMessage(warningBuffer.toString().trim());
        }
        PMMLPortObject outport = null;
        try {
            outport = new PMMLPortObject(createPMMLSpec(pmmlIn.getSpec(), outSpec, res), pmmldoc);
        } catch (IllegalArgumentException e) {
            if (res.getIncludes().length == 0) {
                throw new IllegalArgumentException("Excluding all columns produces invalid PMML", e);
            } else {
                throw e;
            }
        }
        return outport;
    }
}

Example 2 with Discretize

use of org.dmg.pmml.DiscretizeDocument.Discretize in project knime-core by knime.

the class PMMLBinningTranslator method initializeFrom.

/**
 * {@inheritDoc}
 */
@Override
public List<Integer> initializeFrom(final DerivedField[] derivedFields) {
    m_mapper = new DerivedFieldMapper(derivedFields);
    List<Integer> consumed = new ArrayList(derivedFields.length);
    for (int i = 0; i < derivedFields.length; i++) {
        DerivedField df = derivedFields[i];
        if (!df.isSetDiscretize()) {
            // only reading discretize entries other entries are skipped
            continue;
        }
        consumed.add(i);
        Discretize discretize = df.getDiscretize();
        DiscretizeBin[] pmmlBins = discretize.getDiscretizeBinArray();
        NumericBin[] knimeBins = new NumericBin[pmmlBins.length];
        for (int j = 0; j < pmmlBins.length; j++) {
            DiscretizeBin bin = pmmlBins[j];
            String binName = bin.getBinValue();
            Interval interval = bin.getInterval();
            double leftValue = interval.getLeftMargin();
            double rightValue = interval.getRightMargin();
            Closure.Enum closure = interval.getClosure();
            boolean leftOpen = true;
            boolean rightOpen = true;
            if (Closure.OPEN_CLOSED == closure) {
                rightOpen = false;
            } else if (Closure.CLOSED_OPEN == closure) {
                leftOpen = false;
            } else if (Closure.CLOSED_CLOSED == closure) {
                leftOpen = false;
                rightOpen = false;
            }
            knimeBins[j] = new NumericBin(binName, leftOpen, leftValue, rightOpen, rightValue);
        }
        /**
         * This field contains the name of the column in KNIME that
         * corresponds to the derived field in PMML. This is necessary if
         * derived fields are defined on other derived fields and the
         * columns in KNIME are replaced with the preprocessed values.
         * In this case KNIME has to know the original names (e.g. A) while
         * PMML references to A', A'' etc.
         */
        String displayName = df.getDisplayName();
        if (displayName != null) {
            m_columnToBins.put(displayName, knimeBins);
            m_columnToAppend.put(displayName, null);
        } else if (df.getName() != null) {
            String field = m_mapper.getColumnName(discretize.getField());
            m_columnToBins.put(field, knimeBins);
            m_columnToAppend.put(field, df.getName());
        }
    }
    return consumed;
}

Example 3 with Discretize

use of org.dmg.pmml.DiscretizeDocument.Discretize in project knime-core by knime.

the class PMMLBinningTranslator method createDerivedFields.

private DerivedField[] createDerivedFields() {
    int num = m_columnToBins.size();
    DerivedField[] derivedFields = new DerivedField[num];
    int i = 0;
    for (Map.Entry<String, Bin[]> entry : m_columnToBins.entrySet()) {
        Bin[] bins = entry.getValue();
        DerivedField df = DerivedField.Factory.newInstance();
        String name = entry.getKey();
        /* The field name must be retrieved before creating a new derived
             * name for this derived field as the map only contains the
             * current mapping. */
        String fieldName = m_mapper.getDerivedFieldName(name);
        Discretize dis = df.addNewDiscretize();
        dis.setField(fieldName);
        String derivedName = m_columnToAppend.get(name);
        if (derivedName != null) {
            df.setName(derivedName);
        } else {
            df.setName(m_mapper.createDerivedFieldName(name));
            df.setDisplayName(name);
        }
        df.setOptype(OPTYPE.CATEGORICAL);
        df.setDataType(DATATYPE.STRING);
        for (int j = 0; j < bins.length; j++) {
            NumericBin knimeBin = (NumericBin) bins[j];
            boolean leftOpen = knimeBin.isLeftOpen();
            boolean rightOpen = knimeBin.isRightOpen();
            double leftValue = knimeBin.getLeftValue();
            double rightValue = knimeBin.getRightValue();
            DiscretizeBin pmmlBin = dis.addNewDiscretizeBin();
            pmmlBin.setBinValue(knimeBin.getBinName());
            Interval interval = pmmlBin.addNewInterval();
            if (!Double.isInfinite(leftValue)) {
                interval.setLeftMargin(leftValue);
            }
            if (!Double.isInfinite(rightValue)) {
                interval.setRightMargin(rightValue);
            }
            if (leftOpen && rightOpen) {
                interval.setClosure(Closure.OPEN_OPEN);
            } else if (leftOpen && !rightOpen) {
                interval.setClosure(Closure.OPEN_CLOSED);
            } else if (!leftOpen && rightOpen) {
                interval.setClosure(Closure.CLOSED_OPEN);
            } else if (!leftOpen && !rightOpen) {
                interval.setClosure(Closure.CLOSED_CLOSED);
            }
        }
        derivedFields[i++] = df;
    }
    return derivedFields;
}