Java PMMLUtil类代码示例

import org.jpmml.converter.PMMLUtil; //导入依赖的package包/类
@Override
public List<Feature> encodeFeatures(SparkMLEncoder encoder){
	RegexTokenizer transformer = getTransformer();

	if(!transformer.getGaps()){
		throw new IllegalArgumentException("Expected splitter mode, got token matching mode");
	} // End if

	if(transformer.getMinTokenLength() != 1){
		throw new IllegalArgumentException("Expected 1 as minimum token length, got " + transformer.getMinTokenLength() + " as minimum token length");
	}

	Feature feature = encoder.getOnlyFeature(transformer.getInputCol());

	TypeDefinitionField field = encoder.getField(feature.getName());

	if(transformer.getToLowercase()){
		Apply apply = PMMLUtil.createApply("lowercase", feature.ref());

		field = encoder.createDerivedField(FeatureUtil.createName("lowercase", feature), OpType.CATEGORICAL, DataType.STRING, apply);
	}

	return Collections.<Feature>singletonList(new DocumentFeature(encoder, field, transformer.getPattern()));
}
 

import org.jpmml.converter.PMMLUtil; //导入依赖的package包/类
@Override
public ClusteringModel encodeModel(Schema schema){
	KMeansModel model = getTransformer();

	List<Cluster> clusters = new ArrayList<>();

	Vector[] clusterCenters = model.clusterCenters();
	for(int i = 0; i < clusterCenters.length; i++){
		Cluster cluster = new Cluster()
			.setId(String.valueOf(i))
			.setArray(PMMLUtil.createRealArray(VectorUtil.toList(clusterCenters[i])));

		clusters.add(cluster);
	}

	ComparisonMeasure comparisonMeasure = new ComparisonMeasure(ComparisonMeasure.Kind.DISTANCE)
		.setCompareFunction(CompareFunction.ABS_DIFF)
		.setMeasure(new SquaredEuclidean());

	return new ClusteringModel(MiningFunction.CLUSTERING, ClusteringModel.ModelClass.CENTER_BASED, clusters.size(), ModelUtil.createMiningSchema(schema.getLabel()), comparisonMeasure, ClusteringModelUtil.createClusteringFields(schema.getFeatures()), clusters);
}
 

import org.jpmml.converter.PMMLUtil; //导入依赖的package包/类
@Override
public DefineFunction encodeDefineFunction(){
	TfidfTransformer transformer = getTransformer();

	DefineFunction defineFunction = super.encodeDefineFunction();

	Expression expression = defineFunction.getExpression();

	Boolean sublinearTf = transformer.getSublinearTf();
	if(sublinearTf){
		expression = PMMLUtil.createApply("+", PMMLUtil.createApply("log", expression), PMMLUtil.createConstant(1d));
	} // End if

	Boolean useIdf = transformer.getUseIdf();
	if(useIdf){
		ParameterField weight = new ParameterField(FieldName.create("weight"));

		defineFunction.addParameterFields(weight);

		expression = PMMLUtil.createApply("*", expression, new FieldRef(weight.getName()));
	}

	defineFunction.setExpression(expression);

	return defineFunction;
}
 

import org.jpmml.converter.PMMLUtil; //导入依赖的package包/类
static
private Expression encodeIfElseExpression(FunctionExpression functionExpression, VariableMap expressionFields, RExpEncoder encoder){
	FunctionExpression.Argument testArgument = functionExpression.getArgument("test", 0);

	expressionFields.putAll(testArgument);

	FunctionExpression.Argument yesArgument = functionExpression.getArgument("yes", 1);
	FunctionExpression.Argument noArgument = functionExpression.getArgument("no", 2);

	expressionFields.putAll(yesArgument);
	expressionFields.putAll(noArgument);

	// XXX: "Missing values in test give missing values in the result"
	Apply apply = PMMLUtil.createApply("if")
		.addExpressions(prepareExpression(testArgument, expressionFields, encoder))
		.addExpressions(prepareExpression(yesArgument, expressionFields, encoder), prepareExpression(noArgument, expressionFields, encoder));

	return apply;
}
 

import org.jpmml.converter.PMMLUtil; //导入依赖的package包/类
static
private Apply createHingeFunction(int dir, Feature feature, double cut){
	Expression expression;

	switch(dir){
		case -1:
			expression = PMMLUtil.createApply("-", PMMLUtil.createConstant(cut), feature.ref());
			break;
		case 1:
			expression = PMMLUtil.createApply("-", feature.ref(), PMMLUtil.createConstant(cut));
			break;
		default:
			throw new IllegalArgumentException();
	}

	return PMMLUtil.createApply("max", expression, PMMLUtil.createConstant(0d));
}
 

import org.jpmml.converter.PMMLUtil; //导入依赖的package包/类
@Override
public List<Feature> encodeFeatures(SparkMLEncoder encoder){
	PCAModel transformer = getTransformer();

	List<Feature> features = encoder.getFeatures(transformer.getInputCol());

	DenseMatrix pc = transformer.pc();
	if(pc.numRows() != features.size()){
		throw new IllegalArgumentException();
	}

	List<Feature> result = new ArrayList<>();

	for(int i = 0; i < transformer.getK(); i++){
		Apply apply = new Apply("sum");

		for(int j = 0; j < features.size(); j++){
			Feature feature = features.get(j);

			ContinuousFeature continuousFeature = feature.toContinuousFeature();

			Expression expression = continuousFeature.ref();

			Double coefficient = pc.apply(j, i);
			if(!ValueUtil.isOne(coefficient)){
				expression = PMMLUtil.createApply("*", expression, PMMLUtil.createConstant(coefficient));
			}

			apply.addExpressions(expression);
		}

		DerivedField derivedField = encoder.createDerivedField(formatName(transformer, i), OpType.CONTINUOUS, DataType.DOUBLE, apply);

		result.add(new ContinuousFeature(encoder, derivedField));
	}

	return result;
}
 

import org.jpmml.converter.PMMLUtil; //导入依赖的package包/类
@Override
public Apply createApply(){
	Double weight = getWeight();

	Apply apply = super.createApply()
		.addExpressions(PMMLUtil.createConstant(weight));

	return apply;
}
 

import org.jpmml.converter.PMMLUtil; //导入依赖的package包/类
public Apply createApply(){
	DefineFunction defineFunction = getDefineFunction();
	Feature feature = getFeature();
	String value = getValue();

	Constant constant = PMMLUtil.createConstant(value)
		.setDataType(DataType.STRING);

	return PMMLUtil.createApply(defineFunction.getName(), feature.ref(), constant);
}
 

import org.jpmml.converter.PMMLUtil; //导入依赖的package包/类
@Override
public Apply encodeApply(String function, Feature feature, int index, String term){
	TfidfTransformer transformer = getTransformer();

	Apply apply = super.encodeApply(function, feature, index, term);

	Boolean useIdf = transformer.getUseIdf();
	if(useIdf){
		Number weight = transformer.getWeight(index);

		apply.addExpressions(PMMLUtil.createConstant(weight));
	}

	return apply;
}
 

import org.jpmml.converter.PMMLUtil; //导入依赖的package包/类
@Override
public SupportVectorMachineModel encodeModel(Schema schema){
	Transformation outlier = new OutlierTransformation(){

		@Override
		public Expression createExpression(FieldRef fieldRef){
			return PMMLUtil.createApply("lessOrEqual", fieldRef, PMMLUtil.createConstant(0d));
		}
	};

	SupportVectorMachineModel supportVectorMachineModel = super.encodeModel(schema)
		.setOutput(ModelUtil.createPredictedOutput(FieldName.create("decisionFunction"), OpType.CONTINUOUS, DataType.DOUBLE, outlier));

	return supportVectorMachineModel;
}
 

import org.jpmml.converter.PMMLUtil; //导入依赖的package包/类
@Override
public ClusteringModel encodeModel(Schema schema){
	int[] shape = getClusterCentersShape();

	int numberOfClusters = shape[0];
	int numberOfFeatures = shape[1];

	List<? extends Number> clusterCenters = getClusterCenters();
	List<Integer> labels = getLabels();

	Multiset<Integer> labelCounts = HashMultiset.create();

	if(labels != null){
		labelCounts.addAll(labels);
	}

	List<Cluster> clusters = new ArrayList<>();

	for(int i = 0; i < numberOfClusters; i++){
		Cluster cluster = new Cluster()
			.setId(String.valueOf(i))
			.setSize((labelCounts.size () > 0 ? labelCounts.count(i) : null))
			.setArray(PMMLUtil.createRealArray(CMatrixUtil.getRow(clusterCenters, numberOfClusters, numberOfFeatures, i)));

		clusters.add(cluster);
	}

	ComparisonMeasure comparisonMeasure = new ComparisonMeasure(ComparisonMeasure.Kind.DISTANCE)
		.setCompareFunction(CompareFunction.ABS_DIFF)
		.setMeasure(new SquaredEuclidean());

	ClusteringModel clusteringModel = new ClusteringModel(MiningFunction.CLUSTERING, ClusteringModel.ModelClass.CENTER_BASED, numberOfClusters, ModelUtil.createMiningSchema(schema.getLabel()), comparisonMeasure, ClusteringModelUtil.createClusteringFields(schema.getFeatures()), clusters)
		.setOutput(ClusteringModelUtil.createOutput(FieldName.create("Cluster"), DataType.DOUBLE, clusters));

	return clusteringModel;
}
 

import org.jpmml.converter.PMMLUtil; //导入依赖的package包/类
static
public DiscrStats createDiscrStats(Object[] objects){
	List<Object> values = (List)asArray(objects[0]);
	List<Integer> counts = ValueUtil.asIntegers((List)asArray(objects[1]));

	ClassDictUtil.checkSize(values, counts);

	DiscrStats discrStats = new DiscrStats()
		.addArrays(PMMLUtil.createStringArray(values), PMMLUtil.createIntArray(counts));

	return discrStats;
}
 

import org.jpmml.converter.PMMLUtil; //导入依赖的package包/类
@Override
public Model encodeModel(Schema schema){
	RGenericVector kmeans = getObject();

	RDoubleVector centers = (RDoubleVector)kmeans.getValue("centers");
	RIntegerVector size = (RIntegerVector)kmeans.getValue("size");

	RIntegerVector centersDim = centers.dim();

	int rows = centersDim.getValue(0);
	int columns = centersDim.getValue(1);

	List<Cluster> clusters = new ArrayList<>();

	RStringVector rowNames = centers.dimnames(0);
	for(int i = 0; i < rowNames.size(); i++){
		Cluster cluster = new Cluster()
			.setId(String.valueOf(i + 1))
			.setName(rowNames.getValue(i))
			.setSize(size.getValue(i))
			.setArray(PMMLUtil.createRealArray(FortranMatrixUtil.getRow(centers.getValues(), rows, columns, i)));

		clusters.add(cluster);
	}

	ComparisonMeasure comparisonMeasure = new ComparisonMeasure(ComparisonMeasure.Kind.DISTANCE)
		.setCompareFunction(CompareFunction.ABS_DIFF)
		.setMeasure(new SquaredEuclidean());

	ClusteringModel clusteringModel = new ClusteringModel(MiningFunction.CLUSTERING, ClusteringModel.ModelClass.CENTER_BASED, rows, ModelUtil.createMiningSchema(schema.getLabel()), comparisonMeasure, ClusteringModelUtil.createClusteringFields(schema.getFeatures()), clusters)
		.setOutput(ClusteringModelUtil.createOutput(FieldName.create("cluster"), DataType.DOUBLE, clusters));

	return clusteringModel;
}
 

import org.jpmml.converter.PMMLUtil; //导入依赖的package包/类
private Expression encodeExpression(Feature feature){
	FieldName name = feature.getName();

	Expression expression = feature.ref();

	List<Double> ranges = this.ranges.get(name);
	if(ranges != null){
		Double min = ranges.get(0);
		Double max = ranges.get(1);

		expression = PMMLUtil.createApply("/", PMMLUtil.createApply("-", expression, PMMLUtil.createConstant(min)), PMMLUtil.createConstant(max - min));
	}

	Double mean = this.mean.get(name);
	if(mean != null){
		expression = PMMLUtil.createApply("-", expression, PMMLUtil.createConstant(mean));
	}

	Double std = this.std.get(name);
	if(std != null){
		expression = PMMLUtil.createApply("/", expression, PMMLUtil.createConstant(std));
	}

	Double median = this.median.get(name);
	if(median != null){
		expression = PMMLUtil.createApply("if", PMMLUtil.createApply("isNotMissing", new FieldRef(name)), expression, PMMLUtil.createConstant(median));
	} // End if

	if(expression instanceof FieldRef){
		return null;
	}

	return expression;
}
 

import org.jpmml.converter.PMMLUtil; //导入依赖的package包/类
@Override
public List<Feature> encodeFeatures(SparkMLEncoder encoder){
	StringIndexerModel transformer = getTransformer();

	Feature feature = encoder.getOnlyFeature(transformer.getInputCol());

	List<String> categories = new ArrayList<>();
	categories.addAll(Arrays.asList(transformer.labels()));

	String handleInvalid = transformer.getHandleInvalid();

	TypeDefinitionField field = encoder.toCategorical(feature.getName(), categories);

	if(field instanceof DataField){
		DataField dataField = (DataField)field;

		InvalidValueTreatmentMethod invalidValueTreatmentMethod;

		switch(handleInvalid){
			case "keep":
				invalidValueTreatmentMethod = InvalidValueTreatmentMethod.AS_IS;
				break;
			case "error":
				invalidValueTreatmentMethod = InvalidValueTreatmentMethod.RETURN_INVALID;
				break;
			default:
				throw new IllegalArgumentException(handleInvalid);
		}

		InvalidValueDecorator invalidValueDecorator = new InvalidValueDecorator()
			.setInvalidValueTreatment(invalidValueTreatmentMethod);

		encoder.addDecorator(dataField.getName(), invalidValueDecorator);
	} else

	if(field instanceof DerivedField){
		// Ignored
	} else

	{
		throw new IllegalArgumentException();
	}

	switch(handleInvalid){
		case "keep":
			Apply setApply = PMMLUtil.createApply("isIn", feature.ref());

			for(String category : categories){
				setApply.addExpressions(PMMLUtil.createConstant(category));
			}

			categories.add(StringIndexerModelConverter.LABEL_UNKNOWN);

			Apply apply = PMMLUtil.createApply("if", setApply, feature.ref(), PMMLUtil.createConstant(StringIndexerModelConverter.LABEL_UNKNOWN));

			field = encoder.createDerivedField(FeatureUtil.createName("handleInvalid", feature), OpType.CATEGORICAL, feature.getDataType(), apply);
			break;
		default:
			break;
	}

	return Collections.<Feature>singletonList(new CategoricalFeature(encoder, field, categories));
}