Java PMML.getDataDictionary方法代码示例

import org.dmg.pmml.PMML; //导入方法依赖的package包/类
/**
 * Validates that the encoded PMML model received matches expected schema.
 *
 * @param pmml {@link PMML} encoding of KMeans Clustering
 * @param schema expected schema attributes of KMeans Clustering
 */
public static void validatePMMLVsSchema(PMML pmml, InputSchema schema) {
  List<Model> models = pmml.getModels();
  Preconditions.checkArgument(models.size() == 1,
      "Should have exactly one model, but had %s", models.size());

  Model model = models.get(0);
  Preconditions.checkArgument(model instanceof ClusteringModel);
  Preconditions.checkArgument(model.getMiningFunction() == MiningFunction.CLUSTERING);

  DataDictionary dictionary = pmml.getDataDictionary();
  Preconditions.checkArgument(
      schema.getFeatureNames().equals(AppPMMLUtils.getFeatureNames(dictionary)),
      "Feature names in schema don't match names in PMML");

  MiningSchema miningSchema = model.getMiningSchema();
  Preconditions.checkArgument(schema.getFeatureNames().equals(
      AppPMMLUtils.getFeatureNames(miningSchema)));

}
 

import org.dmg.pmml.PMML; //导入方法依赖的package包/类
@Override
public PMMLObject popParent(){
	PMMLObject parent = super.popParent();

	if(parent instanceof Model){
		Model model = (Model)parent;

		processModel(model);
	} else

	if(parent instanceof PMML){
		PMML pmml = (PMML)parent;

		DataDictionary dataDictionary = pmml.getDataDictionary();
		if(dataDictionary != null){
			processDataDictionary(dataDictionary);
		}
	}

	return parent;
}
 

import org.dmg.pmml.PMML; //导入方法依赖的package包/类
/**
 * Validates that the encoded PMML model received matches expected schema.
 *
 * @param pmml {@link PMML} encoding of a decision forest
 * @param schema expected schema attributes of decision forest
 */
public static void validatePMMLVsSchema(PMML pmml, InputSchema schema) {
  List<Model> models = pmml.getModels();
  Preconditions.checkArgument(models.size() == 1,
                              "Should have exactly one model, but had %s", models.size());

  Model model = models.get(0);
  MiningFunction function = model.getMiningFunction();
  if (schema.isClassification()) {
    Preconditions.checkArgument(function == MiningFunction.CLASSIFICATION,
                                "Expected classification function type but got %s",
                                function);
  } else {
    Preconditions.checkArgument(function == MiningFunction.REGRESSION,
                                "Expected regression function type but got %s",
                                function);
  }

  DataDictionary dictionary = pmml.getDataDictionary();
  Preconditions.checkArgument(
      schema.getFeatureNames().equals(AppPMMLUtils.getFeatureNames(dictionary)),
      "Feature names in schema don't match names in PMML");

  MiningSchema miningSchema = model.getMiningSchema();
  Preconditions.checkArgument(schema.getFeatureNames().equals(
      AppPMMLUtils.getFeatureNames(miningSchema)));

  Integer pmmlIndex = AppPMMLUtils.findTargetIndex(miningSchema);
  if (schema.hasTarget()) {
    int schemaIndex = schema.getTargetFeatureIndex();
    Preconditions.checkArgument(
        pmmlIndex != null && schemaIndex == pmmlIndex,
        "Configured schema expects target at index %s, but PMML has target at index %s",
        schemaIndex, pmmlIndex);
  } else {
    Preconditions.checkArgument(pmmlIndex == null);
  }
}
 

import org.dmg.pmml.PMML; //导入方法依赖的package包/类
@Override
public PMML encodePMML(Model model){

	if(this.transformers.size() > 0){
		List<Model> models = new ArrayList<>(this.transformers);
		models.add(model);

		Schema schema = new Schema(null, Collections.<Feature>emptyList());

		model = MiningModelUtil.createModelChain(models, schema);
	}

	PMML pmml = super.encodePMML(model);

	DataDictionary dataDictionary = pmml.getDataDictionary();

	List<DataField> dataFields = dataDictionary.getDataFields();
	for(DataField dataField : dataFields){
		UnivariateStats univariateStats = getUnivariateStats(dataField.getName());

		if(univariateStats == null){
			continue;
		}

		ModelStats modelStats = model.getModelStats();
		if(modelStats == null){
			modelStats = new ModelStats();

			model.setModelStats(modelStats);
		}

		modelStats.addUnivariateStats(univariateStats);
	}

	return pmml;
}
 

import org.dmg.pmml.PMML; //导入方法依赖的package包/类
@Override
public VisitorAction visit(PMML pmml){
	DataDictionary dataDictionary = pmml.getDataDictionary();
	if(dataDictionary != null && dataDictionary.hasDataFields()){
		declare(pmml, dataDictionary.getDataFields());
	}

	TransformationDictionary transformationDictionary = pmml.getTransformationDictionary();
	if(transformationDictionary != null && transformationDictionary.hasDerivedFields()){
		declare(pmml, transformationDictionary.getDerivedFields());
	}

	return super.visit(pmml);
}
 

import org.dmg.pmml.PMML; //导入方法依赖的package包/类
@Test
public void cleanChained() throws Exception {
	PMML pmml = ResourceUtil.unmarshal(ChainedSegmentationTest.class);

	DataDictionary dataDictionary = pmml.getDataDictionary();

	checkFields(FieldNameUtil.create("y", "x1", "x2", "x3", "x4"), dataDictionary.getDataFields());

	DataDictionaryCleaner cleaner = new DataDictionaryCleaner();
	cleaner.applyTo(pmml);

	checkFields(FieldNameUtil.create("y", "x1", "x2", "x3"), dataDictionary.getDataFields());

	List<Model> models = pmml.getModels();
	models.clear();

	cleaner.applyTo(pmml);

	checkFields(Collections.<FieldName>emptySet(), dataDictionary.getDataFields());
}
 

import org.dmg.pmml.PMML; //导入方法依赖的package包/类
@Test
public void cleanNested() throws Exception {
	PMML pmml = ResourceUtil.unmarshal(NestedSegmentationTest.class);

	DataDictionary dataDictionary = pmml.getDataDictionary();

	checkFields(FieldNameUtil.create("y", "x1", "x2", "x3", "x4", "x5"), dataDictionary.getDataFields());

	DataDictionaryCleaner cleaner = new DataDictionaryCleaner();
	cleaner.applyTo(pmml);

	checkFields(FieldNameUtil.create("x1", "x2", "x3", "x4", "x5"), dataDictionary.getDataFields());

	List<Model> models = pmml.getModels();
	models.clear();

	cleaner.applyTo(pmml);

	checkFields(Collections.<FieldName>emptySet(), dataDictionary.getDataFields());
}
 

import org.dmg.pmml.PMML; //导入方法依赖的package包/类
protected ModelEvaluator(PMML pmml, M model){
	setPMML(Objects.requireNonNull(pmml));
	setModel(Objects.requireNonNull(model));

	DataDictionary dataDictionary = pmml.getDataDictionary();
	if(dataDictionary == null){
		throw new MissingElementException(pmml, PMMLElements.PMML_DATADICTIONARY);
	} // End if

	if(dataDictionary.hasDataFields()){
		this.dataFields = CacheUtil.getValue(dataDictionary, ModelEvaluator.dataFieldCache);
	}

	TransformationDictionary transformationDictionary = pmml.getTransformationDictionary();
	if(transformationDictionary != null && transformationDictionary.hasDerivedFields()){
		this.derivedFields = CacheUtil.getValue(transformationDictionary, ModelEvaluator.derivedFieldCache);
	} // End if

	if(transformationDictionary != null && transformationDictionary.hasDefineFunctions()){
		this.defineFunctions = CacheUtil.getValue(transformationDictionary, ModelEvaluator.defineFunctionCache);
	}

	MiningFunction miningFunction = model.getMiningFunction();
	if(miningFunction == null){
		throw new MissingAttributeException(MissingAttributeException.formatMessage(XPathUtil.formatElement(model.getClass()) + "@miningFunction"), model);
	}

	MiningSchema miningSchema = model.getMiningSchema();
	if(miningSchema == null){
		throw new MissingElementException(MissingElementException.formatMessage(XPathUtil.formatElement(model.getClass()) + "/" + XPathUtil.formatElement(MiningSchema.class)), model);
	} // End if

	if(miningSchema.hasMiningFields()){
		this.miningFields = CacheUtil.getValue(miningSchema, ModelEvaluator.miningFieldCache);
	}

	LocalTransformations localTransformations = model.getLocalTransformations();
	if(localTransformations != null && localTransformations.hasDerivedFields()){
		this.localDerivedFields = CacheUtil.getValue(localTransformations, ModelEvaluator.localDerivedFieldCache);
	}

	Targets targets = model.getTargets();
	if(targets != null && targets.hasTargets()){
		this.targets = CacheUtil.getValue(targets, ModelEvaluator.targetCache);
	}

	Output output = model.getOutput();
	if(output != null && output.hasOutputFields()){
		this.outputFields = CacheUtil.getValue(output, ModelEvaluator.outputFieldCache);
	}
}
 

import org.dmg.pmml.PMML; //导入方法依赖的package包/类
private void processRegressionModel(Model model){
	PMML pmml = getPMML();

	MiningField miningField = getTargetField(model);
	if(miningField == null){
		return;
	}

	FieldName name = miningField.getName();

	DataDictionary dataDictionary = pmml.getDataDictionary();

	DataField dataField = IndexableUtil.find(dataDictionary.getDataFields(), name);
	if(dataField == null){
		throw new MissingFieldException(name, miningField);
	}

	DataType dataType = dataField.getDataType();
	switch(dataType){
		case INTEGER:
			break;
		case FLOAT:
		case DOUBLE:
			return;
		default:
			throw new UnsupportedAttributeException(dataField, dataType);
	}

	Targets targets = model.getTargets();

	if(targets != null){
		Target target = IndexableUtil.find(targets.getTargets(), name);

		if(target != null){

			if(target.getCastInteger() != null){
				return;
			} else

			{
				target.setCastInteger(getCastInteger());
			}
		} else

		{
			targets.addTargets(createTarget(name));
		}
	} else

	{
		targets = new Targets()
			.addTargets(createTarget(name));

		model.setTargets(targets);
	}
}