Examples with PMMLDocument org.dmg.pmml.PMMLDocument used on opensource projects

Example 16 with PMMLDocument

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

the class PMMLRegressionModelWrapper method createPMMLDocument.

/**
 * {@inheritDoc}
 */
@Override
public PMMLDocument createPMMLDocument(final DataDictionary dataDict) {
    PMMLDocument doc = createEmptyDocument(dataDict);
    doc.getPMML().setRegressionModelArray(new RegressionModel[] { m_model });
    return doc;
}

Example 17 with PMMLDocument

use of org.dmg.pmml.PMMLDocument 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 18 with PMMLDocument

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

the class RuleEngine2PortsNodeModel method computeRearrangerWithPMML.

/**
 * @param spec
 * @param rules
 * @param flowVars
 * @param ruleIdx
 * @param outcomeIdx
 * @param confidenceIdx
 * @param weightIdx
 * @param validationIdx
 * @param outputColumnName
 * @return
 * @throws InterruptedException
 * @throws InvalidSettingsException
 */
private Pair<ColumnRearranger, PortObject> computeRearrangerWithPMML(final DataTableSpec spec, final RowInput rules, final Map<String, FlowVariable> flowVars, final int ruleIdx, final int outcomeIdx, final int confidenceIdx, final int weightIdx, final int validationIdx, final String outputColumnName) throws InterruptedException, InvalidSettingsException {
    PortObject po;
    ColumnRearranger ret;
    PMMLDocument doc = PMMLDocument.Factory.newInstance();
    final PMML pmmlObj = doc.addNewPMML();
    RuleSetModel ruleSetModel = pmmlObj.addNewRuleSetModel();
    RuleSet ruleSet = ruleSetModel.addNewRuleSet();
    List<DataType> outcomeTypes = new ArrayList<>();
    PMMLRuleParser parser = new PMMLRuleParser(spec, flowVars);
    int lineNo = 0;
    DataRow ruleRow;
    while ((ruleRow = rules.poll()) != null) {
        ++lineNo;
        DataCell rule = ruleRow.getCell(ruleIdx);
        CheckUtils.checkSetting(!rule.isMissing(), "Missing rule in row: " + ruleRow.getKey());
        if (rule instanceof StringValue) {
            StringValue ruleText = (StringValue) rule;
            String r = ruleText.getStringValue().replaceAll("[\r\n]+", " ");
            if (RuleSupport.isComment(r)) {
                continue;
            }
            if (outcomeIdx >= 0) {
                r += " => " + m_settings.asStringFailForMissing(ruleRow.getCell(outcomeIdx));
            }
            ParseState state = new ParseState(r);
            try {
                PMMLPredicate condition = parser.parseBooleanExpression(state);
                SimpleRule simpleRule = ruleSet.addNewSimpleRule();
                setCondition(simpleRule, condition);
                state.skipWS();
                state.consumeText("=>");
                state.skipWS();
                Expression outcome = parser.parseOutcomeOperand(state, null);
                simpleRule.setScore(outcome.toString());
                if (confidenceIdx >= 0) {
                    DataCell confidenceCell = ruleRow.getCell(confidenceIdx);
                    if (!confidenceCell.isMissing()) {
                        if (confidenceCell instanceof DoubleValue) {
                            DoubleValue dv = (DoubleValue) confidenceCell;
                            double confidence = dv.getDoubleValue();
                            simpleRule.setConfidence(confidence);
                        }
                    }
                }
                if (weightIdx >= 0) {
                    DataCell weightCell = ruleRow.getCell(weightIdx);
                    boolean missing = true;
                    if (!weightCell.isMissing()) {
                        if (weightCell instanceof DoubleValue) {
                            DoubleValue dv = (DoubleValue) weightCell;
                            double weight = dv.getDoubleValue();
                            simpleRule.setWeight(weight);
                            missing = false;
                        }
                    }
                    if (missing && m_settings.isHasDefaultWeight()) {
                        simpleRule.setWeight(m_settings.getDefaultWeight());
                    }
                }
                CheckUtils.checkSetting(outcome.isConstant(), "Outcome is not constant in line " + lineNo + " (" + ruleRow.getKey() + ") for rule: " + rule);
                outcomeTypes.add(outcome.getOutputType());
            } catch (ParseException e) {
                ParseException error = Util.addContext(e, r, lineNo);
                throw new InvalidSettingsException("Wrong rule in line: " + ruleRow.getKey() + "\n" + error.getMessage(), error);
            }
        } else {
            CheckUtils.checkSetting(false, "Wrong type (" + rule.getType() + ") of rule: " + rule + "\nin row: " + ruleRow.getKey());
        }
    }
    ColumnRearranger dummy = new ColumnRearranger(spec);
    if (!m_settings.isReplaceColumn()) {
        dummy.append(new SingleCellFactory(new DataColumnSpecCreator(outputColumnName, RuleEngineNodeModel.computeOutputType(outcomeTypes, computeOutcomeType(rules.getDataTableSpec()), true, m_settings.isDisallowLongOutputForCompatibility())).createSpec()) {

            @Override
            public DataCell getCell(final DataRow row) {
                return null;
            }
        });
    }
    PMMLPortObject pmml = createPMMLPortObject(doc, ruleSetModel, ruleSet, parser, dummy.createSpec());
    po = pmml;
    m_copy = copy(pmml);
    String predictionConfidenceColumn = m_settings.getPredictionConfidenceColumn();
    if (predictionConfidenceColumn == null || predictionConfidenceColumn.isEmpty()) {
        predictionConfidenceColumn = RuleEngine2PortsSettings.DEFAULT_PREDICTION_CONFIDENCE_COLUMN;
    }
    ret = PMMLRuleSetPredictorNodeModel.createRearranger(pmml, spec, m_settings.isReplaceColumn(), outputColumnName, m_settings.isComputeConfidence(), DataTableSpec.getUniqueColumnName(dummy.createSpec(), predictionConfidenceColumn), validationIdx);
    return Pair.create(ret, po);
}

Example 19 with PMMLDocument

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

the class PMMLRuleEditorNodeModel method createRearrangerAndPMMLModel.

private RearrangerAndPMMLModel createRearrangerAndPMMLModel(final DataTableSpec spec) throws ParseException, InvalidSettingsException {
    final PMMLDocument doc = PMMLDocument.Factory.newInstance();
    final PMML pmml = doc.addNewPMML();
    RuleSetModel ruleSetModel = pmml.addNewRuleSetModel();
    RuleSet ruleSet = ruleSetModel.addNewRuleSet();
    PMMLRuleParser parser = new PMMLRuleParser(spec, getAvailableInputFlowVariables());
    ColumnRearranger rearranger = createRearranger(spec, ruleSet, parser);
    PMMLPortObject ret = new PMMLPortObject(createPMMLPortObjectSpec(rearranger.createSpec(), parser.getUsedColumns()));
    // if (inData[1] != null) {
    // PMMLPortObject po = (PMMLPortObject)inData[1];
    // TransformationDictionary dict = TransformationDictionary.Factory.newInstance();
    // dict.setDerivedFieldArray(po.getDerivedFields());
    // ret.addGlobalTransformations(dict);
    // }
    PMMLRuleTranslator modelTranslator = new PMMLRuleTranslator();
    ruleSetModel.setFunctionName(MININGFUNCTION.CLASSIFICATION);
    ruleSet.setDefaultConfidence(defaultConfidenceValue());
    PMMLMiningSchemaTranslator.writeMiningSchema(ret.getSpec(), ruleSetModel);
    PMMLDataDictionaryTranslator ddTranslator = new PMMLDataDictionaryTranslator();
    ddTranslator.exportTo(doc, ret.getSpec());
    modelTranslator.initializeFrom(doc);
    ret.addModelTranslater(modelTranslator);
    ret.validate();
    return new RearrangerAndPMMLModel(rearranger, ret);
}