Examples with FieldRef org.dmg.pmml.FieldRefDocument.FieldRef used on opensource projects

Example 6 with FieldRef

use of org.dmg.pmml.FieldRefDocument.FieldRef in project knime-core by knime.

the class PMMLStringConversionTranslator method initializeFrom.

/**
 * {@inheritDoc}
 */
@Override
@SuppressWarnings("unchecked")
public List<Integer> initializeFrom(final DerivedField[] derivedFields) {
    if (derivedFields == null) {
        return Collections.EMPTY_LIST;
    }
    int num = derivedFields.length;
    List<Integer> consumed = new ArrayList<Integer>(num);
    for (int i = 0; i < derivedFields.length; i++) {
        DerivedField df = derivedFields[i];
        /**
         * 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 (!df.isSetFieldRef()) {
            // only reading field references
            continue;
        }
        DataType dataType = PMMLDataDictionaryTranslator.getKNIMEDataType(df.getDataType());
        if (dataType.isCompatible(IntValue.class)) {
            m_parseType = IntCell.TYPE;
        } else if (dataType.isCompatible(DoubleValue.class)) {
            m_parseType = DoubleCell.TYPE;
        } else if (dataType == StringCell.TYPE) {
            m_parseType = StringCell.TYPE;
        } else {
            // only processing int, double and string conversions
            continue;
        }
        FieldRef fieldRef = df.getFieldRef();
        if (displayName != null) {
            m_includeCols.add(displayName);
        } else {
            m_includeCols.add(m_mapper.getColumnName(fieldRef.getField()));
        }
        consumed.add(i);
    }
    return consumed;
}

Example 7 with FieldRef

use of org.dmg.pmml.FieldRefDocument.FieldRef 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 8 with FieldRef

use of org.dmg.pmml.FieldRefDocument.FieldRef in project knime-core by knime.

the class MissingCellHandler method createValueReplacingDerivedField.

/**
 * Helper method for creating a derived field that replaces a field's value with a fixed value.
 * @param dataType the data type of the field.
 * @param value the replacement value for the field
 * @return the derived field
 */
protected DerivedField createValueReplacingDerivedField(final DATATYPE.Enum dataType, final String value) {
    DerivedField field = DerivedField.Factory.newInstance();
    if (dataType == org.dmg.pmml.DATATYPE.STRING || dataType == org.dmg.pmml.DATATYPE.BOOLEAN) {
        field.setOptype(org.dmg.pmml.OPTYPE.CATEGORICAL);
    } else {
        field.setOptype(org.dmg.pmml.OPTYPE.CONTINUOUS);
    }
    /*
         * Create the PMML equivalent of: "if fieldVal is missing then x else fieldVal"
         * <Apply function="if">
         *    <Apply function="isMissing">
         *        <FieldRef field="fieldVal"/>
         *    </Apply>
         *    <Constant dataType="___" value="x"/>
         *    <FieldRef field="fieldVal"/>
         * </Apply>
         */
    Apply ifApply = field.addNewApply();
    ifApply.setFunction(IF_FUNCTION_NAME);
    Apply isMissingApply = Apply.Factory.newInstance();
    FieldRef fieldRef = FieldRef.Factory.newInstance();
    fieldRef.setField(m_col.getName());
    isMissingApply.setFieldRefArray(new FieldRef[] { fieldRef });
    isMissingApply.setFunction(IS_MISSING_FUNCTION_NAME);
    ifApply.setApplyArray(new Apply[] { isMissingApply });
    Constant replacement = Constant.Factory.newInstance();
    replacement.setDataType(dataType);
    replacement.setStringValue(value);
    ifApply.setConstantArray(new Constant[] { replacement });
    ifApply.setFieldRefArray(new FieldRef[] { fieldRef });
    field.setDataType(dataType);
    field.setName(m_col.getName());
    field.setDisplayName(m_col.getName());
    return field;
}

Example 9 with FieldRef

use of org.dmg.pmml.FieldRefDocument.FieldRef in project knime-core by knime.

the class PMMLStringConversionTranslator method createDerivedFields.

private DerivedField[] createDerivedFields() {
    DATATYPE.Enum dataType = PMMLDataDictionaryTranslator.getPMMLDataType(m_parseType);
    OPTYPE.Enum optype = PMMLDataDictionaryTranslator.getOptype(m_parseType);
    int num = m_includeCols.size();
    DerivedField[] derivedFields = new DerivedField[num];
    for (int i = 0; i < num; i++) {
        DerivedField df = DerivedField.Factory.newInstance();
        String name = m_includeCols.get(i);
        df.setDisplayName(name);
        /* 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);
        df.setName(m_mapper.createDerivedFieldName(name));
        df.setDataType(dataType);
        df.setOptype(optype);
        FieldRef fieldRef = df.addNewFieldRef();
        fieldRef.setField(fieldName);
        derivedFields[i] = df;
    }
    return derivedFields;
}

Example 10 with FieldRef

use of org.dmg.pmml.FieldRefDocument.FieldRef in project knime-core by knime.

the class PMMLStringConversionTranslator method initializeFrom.

/**
 * {@inheritDoc}
 */
@Override
@SuppressWarnings("unchecked")
public List<Integer> initializeFrom(final DerivedField[] derivedFields) {
    if (derivedFields == null) {
        return Collections.EMPTY_LIST;
    }
    int num = derivedFields.length;
    List<Integer> consumed = new ArrayList<Integer>(num);
    for (int i = 0; i < derivedFields.length; i++) {
        DerivedField df = derivedFields[i];
        /**
         * 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 (!df.isSetFieldRef()) {
            // only reading field references
            continue;
        }
        DataType dataType = PMMLDataDictionaryTranslator.getKNIMEDataType(df.getDataType());
        if (dataType.isCompatible(IntValue.class)) {
            m_parseType = IntCell.TYPE;
        } else if (dataType.isCompatible(DoubleValue.class)) {
            m_parseType = DoubleCell.TYPE;
        } else if (dataType == StringCell.TYPE) {
            m_parseType = StringCell.TYPE;
        } else {
            // only processing int, double and string conversions
            continue;
        }
        FieldRef fieldRef = df.getFieldRef();
        if (displayName != null) {
            m_includeCols.add(displayName);
        } else {
            m_includeCols.add(m_mapper.getColumnName(fieldRef.getField()));
        }
        consumed.add(i);
    }
    return consumed;
}