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

Example 16 with DataDictionary

use of org.dmg.pmml.DataDictionary in project drools by kiegroup.

the class KiePMMLClassificationTableFactoryTest method getClassificationTable.

@Test
public void getClassificationTable() {
    RegressionTable regressionTableProf = getRegressionTable(3.5, "professional");
    RegressionTable regressionTableCler = getRegressionTable(27.4, "clerical");
    OutputField outputFieldCat = getOutputField("CAT-1", ResultFeature.PROBABILITY, "CatPred-1");
    OutputField outputFieldNum = getOutputField("NUM-1", ResultFeature.PROBABILITY, "NumPred-0");
    OutputField outputFieldPrev = getOutputField("PREV", ResultFeature.PREDICTED_VALUE, null);
    String targetField = "targetField";
    DataField dataField = new DataField();
    dataField.setName(FieldName.create(targetField));
    dataField.setOpType(OpType.CATEGORICAL);
    DataDictionary dataDictionary = new DataDictionary();
    dataDictionary.addDataFields(dataField);
    RegressionModel regressionModel = new RegressionModel();
    regressionModel.setNormalizationMethod(RegressionModel.NormalizationMethod.CAUCHIT);
    regressionModel.addRegressionTables(regressionTableProf, regressionTableCler);
    regressionModel.setModelName(getGeneratedClassName("RegressionModel"));
    Output output = new Output();
    output.addOutputFields(outputFieldCat, outputFieldNum, outputFieldPrev);
    regressionModel.setOutput(output);
    MiningField targetMiningField = new MiningField();
    targetMiningField.setUsageType(MiningField.UsageType.TARGET);
    targetMiningField.setName(dataField.getName());
    MiningSchema miningSchema = new MiningSchema();
    miningSchema.addMiningFields(targetMiningField);
    regressionModel.setMiningSchema(miningSchema);
    PMML pmml = new PMML();
    pmml.setDataDictionary(dataDictionary);
    pmml.addModels(regressionModel);
    final CommonCompilationDTO<RegressionModel> source = CommonCompilationDTO.fromGeneratedPackageNameAndFields(PACKAGE_NAME, pmml, regressionModel, new HasClassLoaderMock());
    final RegressionCompilationDTO compilationDTO = RegressionCompilationDTO.fromCompilationDTORegressionTablesAndNormalizationMethod(source, regressionModel.getRegressionTables(), regressionModel.getNormalizationMethod());
    KiePMMLClassificationTable retrieved = KiePMMLClassificationTableFactory.getClassificationTable(compilationDTO);
    assertNotNull(retrieved);
    assertEquals(regressionModel.getRegressionTables().size(), retrieved.getCategoryTableMap().size());
    regressionModel.getRegressionTables().forEach(regressionTable -> assertTrue(retrieved.getCategoryTableMap().containsKey(regressionTable.getTargetCategory().toString())));
    assertEquals(regressionModel.getNormalizationMethod().value(), retrieved.getRegressionNormalizationMethod().getName());
    assertEquals(OP_TYPE.CATEGORICAL, retrieved.getOpType());
    boolean isBinary = regressionModel.getRegressionTables().size() == 2;
    assertEquals(isBinary, retrieved.isBinary());
    assertEquals(isBinary, retrieved.isBinary());
    assertEquals(targetMiningField.getName().getValue(), retrieved.getTargetField());
}

Example 17 with DataDictionary

use of org.dmg.pmml.DataDictionary in project drools by kiegroup.

the class KiePMMLClassificationTableFactoryTest method setStaticGetter.

@Test
public void setStaticGetter() throws IOException {
    String variableName = "variableName";
    RegressionTable regressionTableProf = getRegressionTable(3.5, "professional");
    RegressionTable regressionTableCler = getRegressionTable(27.4, "clerical");
    OutputField outputFieldCat = getOutputField("CAT-1", ResultFeature.PROBABILITY, "CatPred-1");
    OutputField outputFieldNum = getOutputField("NUM-1", ResultFeature.PROBABILITY, "NumPred-0");
    OutputField outputFieldPrev = getOutputField("PREV", ResultFeature.PREDICTED_VALUE, null);
    String targetField = "targetField";
    DataField dataField = new DataField();
    dataField.setName(FieldName.create(targetField));
    dataField.setOpType(OpType.CATEGORICAL);
    DataDictionary dataDictionary = new DataDictionary();
    dataDictionary.addDataFields(dataField);
    RegressionModel regressionModel = new RegressionModel();
    regressionModel.setNormalizationMethod(RegressionModel.NormalizationMethod.CAUCHIT);
    regressionModel.addRegressionTables(regressionTableProf, regressionTableCler);
    regressionModel.setModelName(getGeneratedClassName("RegressionModel"));
    Output output = new Output();
    output.addOutputFields(outputFieldCat, outputFieldNum, outputFieldPrev);
    regressionModel.setOutput(output);
    MiningField miningField = new MiningField();
    miningField.setUsageType(MiningField.UsageType.TARGET);
    miningField.setName(dataField.getName());
    MiningSchema miningSchema = new MiningSchema();
    miningSchema.addMiningFields(miningField);
    regressionModel.setMiningSchema(miningSchema);
    PMML pmml = new PMML();
    pmml.setDataDictionary(dataDictionary);
    pmml.addModels(regressionModel);
    final CommonCompilationDTO<RegressionModel> source = CommonCompilationDTO.fromGeneratedPackageNameAndFields(PACKAGE_NAME, pmml, regressionModel, new HasClassLoaderMock());
    final RegressionCompilationDTO compilationDTO = RegressionCompilationDTO.fromCompilationDTORegressionTablesAndNormalizationMethod(source, regressionModel.getRegressionTables(), regressionModel.getNormalizationMethod());
    final LinkedHashMap<String, KiePMMLTableSourceCategory> regressionTablesMap = new LinkedHashMap<>();
    regressionModel.getRegressionTables().forEach(regressionTable -> {
        String key = "defpack." + regressionTable.getTargetCategory().toString().toUpperCase();
        KiePMMLTableSourceCategory value = new KiePMMLTableSourceCategory("", regressionTable.getTargetCategory().toString());
        regressionTablesMap.put(key, value);
    });
    final MethodDeclaration staticGetterMethod = STATIC_GETTER_METHOD.clone();
    KiePMMLClassificationTableFactory.setStaticGetter(compilationDTO, regressionTablesMap, staticGetterMethod, variableName);
    String text = getFileContent(TEST_02_SOURCE);
    MethodDeclaration expected = JavaParserUtils.parseMethod(text);
    assertTrue(JavaParserUtils.equalsNode(expected, staticGetterMethod));
}

Example 18 with DataDictionary

use of org.dmg.pmml.DataDictionary in project drools by kiegroup.

the class KiePMMLRegressionTableFactoryTest method getRegressionTable.

@Test
public void getRegressionTable() {
    regressionTable = getRegressionTable(3.5, "professional");
    RegressionModel regressionModel = new RegressionModel();
    regressionModel.setNormalizationMethod(RegressionModel.NormalizationMethod.CAUCHIT);
    regressionModel.addRegressionTables(regressionTable);
    regressionModel.setModelName(getGeneratedClassName("RegressionModel"));
    String targetField = "targetField";
    DataField dataField = new DataField();
    dataField.setName(FieldName.create(targetField));
    dataField.setOpType(OpType.CATEGORICAL);
    DataDictionary dataDictionary = new DataDictionary();
    dataDictionary.addDataFields(dataField);
    MiningField miningField = new MiningField();
    miningField.setUsageType(MiningField.UsageType.TARGET);
    miningField.setName(dataField.getName());
    MiningSchema miningSchema = new MiningSchema();
    miningSchema.addMiningFields(miningField);
    regressionModel.setMiningSchema(miningSchema);
    PMML pmml = new PMML();
    pmml.setDataDictionary(dataDictionary);
    pmml.addModels(regressionModel);
    final CommonCompilationDTO<RegressionModel> source = CommonCompilationDTO.fromGeneratedPackageNameAndFields(PACKAGE_NAME, pmml, regressionModel, new HasClassLoaderMock());
    final RegressionCompilationDTO compilationDTO = RegressionCompilationDTO.fromCompilationDTORegressionTablesAndNormalizationMethod(source, new ArrayList<>(), regressionModel.getNormalizationMethod());
    KiePMMLRegressionTable retrieved = KiePMMLRegressionTableFactory.getRegressionTable(regressionTable, compilationDTO);
    assertNotNull(retrieved);
    commonEvaluateRegressionTable(retrieved, regressionTable);
}

Example 19 with DataDictionary

use of org.dmg.pmml.DataDictionary in project drools by kiegroup.

the class KiePMMLRegressionTableFactoryTest method getRegressionTableBuilder.

@Test
public void getRegressionTableBuilder() {
    regressionTable = getRegressionTable(3.5, "professional");
    RegressionModel regressionModel = new RegressionModel();
    regressionModel.setNormalizationMethod(RegressionModel.NormalizationMethod.CAUCHIT);
    regressionModel.addRegressionTables(regressionTable);
    regressionModel.setModelName(getGeneratedClassName("RegressionModel"));
    String targetField = "targetField";
    DataField dataField = new DataField();
    dataField.setName(FieldName.create(targetField));
    dataField.setOpType(OpType.CATEGORICAL);
    DataDictionary dataDictionary = new DataDictionary();
    dataDictionary.addDataFields(dataField);
    MiningField miningField = new MiningField();
    miningField.setUsageType(MiningField.UsageType.TARGET);
    miningField.setName(dataField.getName());
    MiningSchema miningSchema = new MiningSchema();
    miningSchema.addMiningFields(miningField);
    regressionModel.setMiningSchema(miningSchema);
    PMML pmml = new PMML();
    pmml.setDataDictionary(dataDictionary);
    pmml.addModels(regressionModel);
    final CommonCompilationDTO<RegressionModel> source = CommonCompilationDTO.fromGeneratedPackageNameAndFields(PACKAGE_NAME, pmml, regressionModel, new HasClassLoaderMock());
    final RegressionCompilationDTO compilationDTO = RegressionCompilationDTO.fromCompilationDTORegressionTablesAndNormalizationMethod(source, new ArrayList<>(), regressionModel.getNormalizationMethod());
    Map.Entry<String, String> retrieved = KiePMMLRegressionTableFactory.getRegressionTableBuilder(regressionTable, compilationDTO);
    assertNotNull(retrieved);
    Map<String, String> sources = new HashMap<>();
    sources.put(retrieved.getKey(), retrieved.getValue());
    commonValidateCompilation(sources);
}

Example 20 with DataDictionary

use of org.dmg.pmml.DataDictionary in project drools by kiegroup.

the class KiePMMLCharacteristicFactoryTest method getAttributeVariableDeclarationWithComplexPartialScore.

@Test
public void getAttributeVariableDeclarationWithComplexPartialScore() throws IOException {
    final String variableName = "variableName";
    Array.Type arrayType = Array.Type.STRING;
    List<String> values1 = getStringObjects(arrayType, 4);
    Attribute attribute1 = getAttribute(values1, 1);
    List<String> values2 = getStringObjects(arrayType, 4);
    Attribute attribute2 = getAttribute(values2, 2);
    CompoundPredicate compoundPredicate1 = (CompoundPredicate) attribute1.getPredicate();
    CompoundPredicate compoundPredicate2 = (CompoundPredicate) attribute2.getPredicate();
    DataDictionary dataDictionary = new DataDictionary();
    for (Predicate predicate : compoundPredicate1.getPredicates()) {
        DataField toAdd = null;
        if (predicate instanceof SimplePredicate) {
            toAdd = new DataField();
            toAdd.setName(((SimplePredicate) predicate).getField());
            toAdd.setDataType(DataType.DOUBLE);
        } else if (predicate instanceof SimpleSetPredicate) {
            toAdd = new DataField();
            toAdd.setName(((SimpleSetPredicate) predicate).getField());
            toAdd.setDataType(DataType.DOUBLE);
        }
        if (toAdd != null) {
            dataDictionary.addDataFields(toAdd);
        }
    }
    for (Predicate predicate : compoundPredicate2.getPredicates()) {
        DataField toAdd = null;
        if (predicate instanceof SimplePredicate) {
            toAdd = new DataField();
            toAdd.setName(((SimplePredicate) predicate).getField());
            toAdd.setDataType(DataType.DOUBLE);
        } else if (predicate instanceof SimpleSetPredicate) {
            toAdd = new DataField();
            toAdd.setName(((SimpleSetPredicate) predicate).getField());
            toAdd.setDataType(DataType.DOUBLE);
        }
        if (toAdd != null) {
            dataDictionary.addDataFields(toAdd);
        }
    }
    String valuesString1 = values1.stream().map(valueString -> "\"" + valueString + "\"").collect(Collectors.joining(","));
    String valuesString2 = values2.stream().map(valueString -> "\"" + valueString + "\"").collect(Collectors.joining(","));
    Characteristic characteristic = new Characteristic();
    characteristic.addAttributes(attribute1, attribute2);
    characteristic.setBaselineScore(22);
    characteristic.setReasonCode(REASON_CODE);
    BlockStmt retrieved = KiePMMLCharacteristicFactory.getCharacteristicVariableDeclaration(variableName, characteristic, getFieldsFromDataDictionary(dataDictionary));
    String text = getFileContent(TEST_01_SOURCE);
    Statement expected = JavaParserUtils.parseBlock(String.format(text, variableName, valuesString1, valuesString2, characteristic.getBaselineScore(), characteristic.getReasonCode()));
    assertTrue(JavaParserUtils.equalsNode(expected, retrieved));
    List<Class<?>> imports = Arrays.asList(KiePMMLAttribute.class, KiePMMLCharacteristic.class, KiePMMLComplexPartialScore.class, KiePMMLCompoundPredicate.class, KiePMMLConstant.class, KiePMMLSimplePredicate.class, KiePMMLSimpleSetPredicate.class, Arrays.class, Collections.class);
    commonValidateCompilationWithImports(retrieved, imports);
}