Java Schema.getLabel方法代码示例

import org.jpmml.converter.Schema; //导入方法依赖的package包/类
@Override
public MiningModel encodeMiningModel(List<Tree> trees, Integer numIteration, Schema schema){
	Schema segmentSchema = new Schema(new ContinuousLabel(null, DataType.DOUBLE), schema.getFeatures());

	List<MiningModel> miningModels = new ArrayList<>();

	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

	for(int i = 0, rows = categoricalLabel.size(), columns = (trees.size() / rows); i < rows; i++){
		MiningModel miningModel = createMiningModel(FortranMatrixUtil.getRow(trees, rows, columns, i), numIteration, segmentSchema)
			.setOutput(ModelUtil.createPredictedOutput(FieldName.create("lgbmValue(" + categoricalLabel.getValue(i) + ")"), OpType.CONTINUOUS, DataType.DOUBLE));

		miningModels.add(miningModel);
	}

	return MiningModelUtil.createClassification(miningModels, RegressionModel.NormalizationMethod.SOFTMAX, true, schema);
}
 

import org.jpmml.converter.Schema; //导入方法依赖的package包/类
@Override
public MiningModel encodeMiningModel(List<RegTree> regTrees, float base_score, Integer ntreeLimit, Schema schema){
	Schema segmentSchema = new Schema(new ContinuousLabel(null, DataType.FLOAT), schema.getFeatures());

	List<MiningModel> miningModels = new ArrayList<>();

	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

	for(int i = 0, columns = categoricalLabel.size(), rows = (regTrees.size() / columns); i < columns; i++){
		MiningModel miningModel = createMiningModel(CMatrixUtil.getColumn(regTrees, rows, columns, i), base_score, ntreeLimit, segmentSchema)
			.setOutput(ModelUtil.createPredictedOutput(FieldName.create("xgbValue(" + categoricalLabel.getValue(i) + ")"), OpType.CONTINUOUS, DataType.FLOAT));

		miningModels.add(miningModel);
	}

	return MiningModelUtil.createClassification(miningModels, RegressionModel.NormalizationMethod.SOFTMAX, true, schema);
}
 

import org.jpmml.converter.Schema; //导入方法依赖的package包/类
@Override
public GeneralRegressionModel encodeModel(Schema schema){
	GeneralizedLinearRegressionModel model = getTransformer();

	String targetCategory = null;

	MiningFunction miningFunction = getMiningFunction();
	switch(miningFunction){
		case CLASSIFICATION:
			CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

			if(categoricalLabel.size() != 2){
				throw new IllegalArgumentException();
			}

			targetCategory = categoricalLabel.getValue(1);
			break;
		default:
			break;
	}

	GeneralRegressionModel generalRegressionModel = new GeneralRegressionModel(GeneralRegressionModel.ModelType.GENERALIZED_LINEAR, miningFunction, ModelUtil.createMiningSchema(schema.getLabel()), null, null, null)
		.setDistribution(parseFamily(model.getFamily()))
		.setLinkFunction(parseLinkFunction(model.getLink()))
		.setLinkParameter(parseLinkParameter(model.getLink()));

	GeneralRegressionModelUtil.encodeRegressionTable(generalRegressionModel, schema.getFeatures(), model.intercept(), VectorUtil.toList(model.coefficients()), targetCategory);

	return generalRegressionModel;
}
 

import org.jpmml.converter.Schema; //导入方法依赖的package包/类
static
protected MiningModel createMiningModel(List<RegTree> regTrees, float base_score, Integer ntreeLimit, Schema schema){
	ContinuousLabel continuousLabel = (ContinuousLabel)schema.getLabel();

	Schema segmentSchema = schema.toAnonymousSchema();

	List<TreeModel> treeModels = new ArrayList<>();

	if(ntreeLimit != null){

		if(ntreeLimit > regTrees.size()){
			throw new IllegalArgumentException("Tree limit " + ntreeLimit + " is greater than the number of trees");
		}

		regTrees = regTrees.subList(0, ntreeLimit);
	}

	for(RegTree regTree : regTrees){
		TreeModel treeModel = regTree.encodeTreeModel(segmentSchema);

		treeModels.add(treeModel);
	}

	MiningModel miningModel = new MiningModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(continuousLabel))
		.setMathContext(MathContext.FLOAT)
		.setSegmentation(MiningModelUtil.createSegmentation(Segmentation.MultipleModelMethod.SUM, treeModels))
		.setTargets(ModelUtil.createRescaleTargets(null, ValueUtil.floatToDouble(base_score), continuousLabel));

	return miningModel;
}
 

import org.jpmml.converter.Schema; //导入方法依赖的package包/类
static
public RegressionModel createRegression(MathContext mathContext, List<? extends Feature> features, List<Double> coefficients, Double intercept, RegressionModel.NormalizationMethod normalizationMethod, Schema schema){
	ContinuousLabel continuousLabel = (ContinuousLabel)schema.getLabel();

	if(normalizationMethod != null){

		switch(normalizationMethod){
			case NONE:
			case SOFTMAX:
			case LOGIT:
			case PROBIT:
			case CLOGLOG:
			case EXP:
			case LOGLOG:
			case CAUCHIT:
				break;
			default:
				throw new IllegalArgumentException();
		}
	}

	RegressionModel regressionModel = new RegressionModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(continuousLabel), null)
		.setNormalizationMethod(normalizationMethod)
		.setMathContext(ModelUtil.simplifyMathContext(mathContext))
		.addRegressionTables(createRegressionTable(features, coefficients, intercept));

	return regressionModel;
}
 

import org.jpmml.converter.Schema; //导入方法依赖的package包/类
static
public RegressionModel createBinaryLogisticClassification(MathContext mathContext, List<? extends Feature> features, List<Double> coefficients, Double intercept, RegressionModel.NormalizationMethod normalizationMethod, boolean hasProbabilityDistribution, Schema schema){
	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

	if(categoricalLabel.size() != 2){
		throw new IllegalArgumentException();
	} // End if

	if(normalizationMethod != null){

		switch(normalizationMethod){
			case NONE:
			case LOGIT:
			case PROBIT:
			case CLOGLOG:
			case LOGLOG:
			case CAUCHIT:
				break;
			default:
				throw new IllegalArgumentException();
		}
	}

	RegressionTable activeRegressionTable = RegressionModelUtil.createRegressionTable(features, coefficients, intercept)
		.setTargetCategory(categoricalLabel.getValue(1));

	RegressionTable passiveRegressionTable = RegressionModelUtil.createRegressionTable(Collections.<Feature>emptyList(), Collections.<Double>emptyList(), null)
		.setTargetCategory(categoricalLabel.getValue(0));

	RegressionModel regressionModel = new RegressionModel(MiningFunction.CLASSIFICATION, ModelUtil.createMiningSchema(categoricalLabel), null)
		.setNormalizationMethod(normalizationMethod)
		.setMathContext(ModelUtil.simplifyMathContext(mathContext))
		.addRegressionTables(activeRegressionTable, passiveRegressionTable)
		.setOutput(hasProbabilityDistribution ? ModelUtil.createProbabilityOutput(mathContext, categoricalLabel) : null);

	return regressionModel;
}
 

import org.jpmml.converter.Schema; //导入方法依赖的package包/类
static
public <E extends Estimator & HasEstimatorEnsemble<DecisionTreeRegressor> & HasTreeOptions> MiningModel encodeGradientBoosting(E estimator, Number initialPrediction, Number learningRate, Schema schema){
	ContinuousLabel continuousLabel = (ContinuousLabel)schema.getLabel();

	List<TreeModel> treeModels = TreeModelUtil.encodeTreeModelSegmentation(estimator, MiningFunction.REGRESSION, schema);

	MiningModel miningModel = new MiningModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(continuousLabel))
		.setSegmentation(MiningModelUtil.createSegmentation(Segmentation.MultipleModelMethod.SUM, treeModels))
		.setTargets(ModelUtil.createRescaleTargets(learningRate, initialPrediction, continuousLabel));

	return TreeModelUtil.transform(estimator, miningModel);
}
 

import org.jpmml.converter.Schema; //导入方法依赖的package包/类
static
private Node encodeClassificationScore(Node node, RDoubleVector probabilities, Schema schema){
	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

	if(categoricalLabel.size() != probabilities.size()){
		throw new IllegalArgumentException();
	}

	Double maxProbability = null;

	for(int i = 0; i < categoricalLabel.size(); i++){
		String value = categoricalLabel.getValue(i);
		Double probability = probabilities.getValue(i);

		if(maxProbability == null || (maxProbability).compareTo(probability) < 0){
			node.setScore(value);

			maxProbability = probability;
		}

		ScoreDistribution scoreDistribution = new ScoreDistribution(value, probability);

		node.addScoreDistributions(scoreDistribution);
	}

	return node;
}
 

import org.jpmml.converter.Schema; //导入方法依赖的package包/类
static
private MiningModel createMiningModel(List<TreeModel> treeModels, Double initF, Schema schema){
	ContinuousLabel continuousLabel = (ContinuousLabel)schema.getLabel();

	MiningModel miningModel = new MiningModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(continuousLabel))
		.setSegmentation(MiningModelUtil.createSegmentation(Segmentation.MultipleModelMethod.SUM, treeModels))
		.setTargets(ModelUtil.createRescaleTargets(null, initF, continuousLabel));

	return miningModel;
}
 

import org.jpmml.converter.Schema; //导入方法依赖的package包/类
static
public MiningModel createClassification(List<? extends Model> models, RegressionModel.NormalizationMethod normalizationMethod, boolean hasProbabilityDistribution, Schema schema){
	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

	if(categoricalLabel.size() < 3 || categoricalLabel.size() != models.size()){
		throw new IllegalArgumentException();
	} // End if

	if(normalizationMethod != null){

		switch(normalizationMethod){
			case NONE:
			case SIMPLEMAX:
			case SOFTMAX:
				break;
			default:
				throw new IllegalArgumentException();
		}
	}

	MathContext mathContext = null;

	List<RegressionTable> regressionTables = new ArrayList<>();

	for(int i = 0; i < categoricalLabel.size(); i++){
		Model model = models.get(i);

		MathContext modelMathContext = model.getMathContext();
		if(modelMathContext == null){
			modelMathContext = MathContext.DOUBLE;
		} // End if

		if(mathContext == null){
			mathContext = modelMathContext;
		} else

		{
			if(!Objects.equals(mathContext, modelMathContext)){
				throw new IllegalArgumentException();
			}
		}

		Feature feature = MiningModelUtil.MODEL_PREDICTION.apply(model);

		RegressionTable regressionTable = RegressionModelUtil.createRegressionTable(Collections.singletonList(feature), Collections.singletonList(1d), null)
			.setTargetCategory(categoricalLabel.getValue(i));

		regressionTables.add(regressionTable);
	}

	RegressionModel regressionModel = new RegressionModel(MiningFunction.CLASSIFICATION, ModelUtil.createMiningSchema(categoricalLabel), regressionTables)
		.setNormalizationMethod(normalizationMethod)
		.setMathContext(ModelUtil.simplifyMathContext(mathContext))
		.setOutput(hasProbabilityDistribution ? ModelUtil.createProbabilityOutput(mathContext, categoricalLabel) : null);

	List<Model> segmentationModels = new ArrayList<>(models);
	segmentationModels.add(regressionModel);

	return createModelChain(segmentationModels, schema);
}
 

import org.jpmml.converter.Schema; //导入方法依赖的package包/类
@Override
public Model encodeModel(Schema schema){
	List<? extends Classifier> estimators = getEstimators();
	List<? extends Number> weights = getWeights();

	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

	List<Model> models = new ArrayList<>();

	for(Classifier estimator : estimators){
		Model model = estimator.encodeModel(schema);

		models.add(model);
	}

	String voting = getVoting();

	Segmentation.MultipleModelMethod multipleModelMethod = parseVoting(voting, (weights != null && weights.size() > 0));

	MiningModel miningModel = new MiningModel(MiningFunction.CLASSIFICATION, ModelUtil.createMiningSchema(categoricalLabel))
		.setSegmentation(MiningModelUtil.createSegmentation(multipleModelMethod, models, weights))
		.setOutput(ModelUtil.createProbabilityOutput(DataType.DOUBLE, categoricalLabel));

	return miningModel;
}
 

import org.jpmml.converter.Schema; //导入方法依赖的package包/类
@Override
public RegressionModel encodeModel(Schema schema){
	int[] shape = getCoefShape();

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

	boolean hasProbabilityDistribution = hasProbabilityDistribution();

	List<? extends Number> coef = getCoef();
	List<? extends Number> intercepts = getIntercept();

	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

	List<Feature> features = schema.getFeatures();

	if(numberOfClasses == 1){
		ClassifierUtil.checkSize(2, categoricalLabel);

		return RegressionModelUtil.createBinaryLogisticClassification(features, ValueUtil.asDoubles(CMatrixUtil.getRow(coef, numberOfClasses, numberOfFeatures, 0)), ValueUtil.asDouble(intercepts.get(0)), RegressionModel.NormalizationMethod.LOGIT, hasProbabilityDistribution, schema);
	} else

	if(numberOfClasses >= 3){
		ClassifierUtil.checkSize(numberOfClasses, categoricalLabel);

		List<RegressionTable> regressionTables = new ArrayList<>();

		for(int i = 0, rows = categoricalLabel.size(); i < rows; i++){
			RegressionTable regressionTable = RegressionModelUtil.createRegressionTable(features, ValueUtil.asDoubles(CMatrixUtil.getRow(coef, numberOfClasses, numberOfFeatures, i)), ValueUtil.asDouble(intercepts.get(i)))
				.setTargetCategory(categoricalLabel.getValue(i));

			regressionTables.add(regressionTable);
		}

		RegressionModel regressionModel = new RegressionModel(MiningFunction.CLASSIFICATION, ModelUtil.createMiningSchema(categoricalLabel), regressionTables)
			.setNormalizationMethod(RegressionModel.NormalizationMethod.LOGIT)
			.setOutput(hasProbabilityDistribution ? ModelUtil.createProbabilityOutput(DataType.DOUBLE, categoricalLabel) : null);

		return regressionModel;
	} else

	{
		throw new IllegalArgumentException();
	}
}
 

import org.jpmml.converter.Schema; //导入方法依赖的package包/类
@Override
public TreeModel encodeModel(Schema schema){
	List<?> classes = getClasses();
	List<? extends Number> classPrior = getClassPrior();
	Object constant = getConstant();
	String strategy = getStrategy();

	ClassDictUtil.checkSize(classes, classPrior);

	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

	int index;

	double[] probabilities;

	switch(strategy){
		case "constant":
			{
				index = classes.indexOf(constant);

				probabilities = new double[classes.size()];
				probabilities[index] = 1d;
			}
			break;
		case "most_frequent":
			{
				index = classPrior.indexOf(Collections.max((List)classPrior));

				probabilities = new double[classes.size()];
				probabilities[index] = 1d;
			}
			break;
		case "prior":
			{
				index = classPrior.indexOf(Collections.max((List)classPrior));

				probabilities = Doubles.toArray(classPrior);
			}
			break;
		default:
			throw new IllegalArgumentException(strategy);
	}

	Node root = new Node()
		.setPredicate(new True())
		.setScore(ValueUtil.formatValue(classes.get(index)));

	for(int i = 0; i < classes.size(); i++){
		ScoreDistribution scoreDistribution = new ScoreDistribution(ValueUtil.formatValue(classes.get(i)), probabilities[i]);

		root.addScoreDistributions(scoreDistribution);
	}

	TreeModel treeModel = new TreeModel(MiningFunction.CLASSIFICATION, ModelUtil.createMiningSchema(categoricalLabel), root)
		.setOutput(ModelUtil.createProbabilityOutput(DataType.DOUBLE, categoricalLabel));

	return treeModel;
}
 

import org.jpmml.converter.Schema; //导入方法依赖的package包/类
private MiningModel encodeProbabilityForest(RGenericVector ranger, Schema schema){
	RGenericVector forest = (RGenericVector)ranger.getValue("forest");

	final
	RStringVector levels = (RStringVector)forest.getValue("levels");

	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

	ScoreEncoder scoreEncoder = new ScoreEncoder(){

		@Override
		public void encode(Node node, Number splitValue, RNumberVector<?> terminalClassCount){

			if(splitValue.doubleValue() != 0d || (terminalClassCount == null || terminalClassCount.size() != levels.size())){
				throw new IllegalArgumentException();
			}

			Double maxProbability = null;

			for(int i = 0; i < terminalClassCount.size(); i++){
				String value = levels.getValue(i);
				Double probability = ValueUtil.asDouble(terminalClassCount.getValue(i));

				if(maxProbability == null || (maxProbability).compareTo(probability) < 0){
					node.setScore(value);

					maxProbability = probability;
				}

				ScoreDistribution scoreDisctibution = new ScoreDistribution(value, probability);

				node.addScoreDistributions(scoreDisctibution);
			}
		}
	};

	List<TreeModel> treeModels = encodeForest(forest, MiningFunction.CLASSIFICATION, scoreEncoder, schema);

	MiningModel miningModel = new MiningModel(MiningFunction.CLASSIFICATION, ModelUtil.createMiningSchema(categoricalLabel))
		.setSegmentation(MiningModelUtil.createSegmentation(Segmentation.MultipleModelMethod.AVERAGE, treeModels))
		.setOutput(ModelUtil.createProbabilityOutput(DataType.DOUBLE, categoricalLabel));

	return miningModel;
}
 

import org.jpmml.converter.Schema; //导入方法依赖的package包/类
private MiningModel encodeClassification(RGenericVector forest, final Schema schema){
	RNumberVector<?> bestvar = (RNumberVector<?>)forest.getValue("bestvar");
	RNumberVector<?> treemap = (RNumberVector<?>)forest.getValue("treemap");
	RIntegerVector nodepred = (RIntegerVector)forest.getValue("nodepred");
	RDoubleVector xbestsplit = (RDoubleVector)forest.getValue("xbestsplit");
	RIntegerVector nrnodes = (RIntegerVector)forest.getValue("nrnodes");
	RDoubleVector ntree = (RDoubleVector)forest.getValue("ntree");

	int rows = nrnodes.asScalar();
	int columns = ValueUtil.asInt(ntree.asScalar());

	final
	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

	ScoreEncoder<Integer> scoreEncoder = new ScoreEncoder<Integer>(){

		@Override
		public String encode(Integer value){
			return categoricalLabel.getValue(value - 1);
		}
	};

	Schema segmentSchema = schema.toAnonymousSchema();

	List<TreeModel> treeModels = new ArrayList<>();

	for(int i = 0; i < columns; i++){
		List<? extends Number> daughters = FortranMatrixUtil.getColumn(treemap.getValues(), 2 * rows, columns, i);

		TreeModel treeModel = encodeTreeModel(
				MiningFunction.CLASSIFICATION,
				scoreEncoder,
				FortranMatrixUtil.getColumn(daughters, rows, 2, 0),
				FortranMatrixUtil.getColumn(daughters, rows, 2, 1),
				FortranMatrixUtil.getColumn(nodepred.getValues(), rows, columns, i),
				FortranMatrixUtil.getColumn(bestvar.getValues(), rows, columns, i),
				FortranMatrixUtil.getColumn(xbestsplit.getValues(), rows, columns, i),
				segmentSchema
			);

		treeModels.add(treeModel);
	}

	MiningModel miningModel = new MiningModel(MiningFunction.CLASSIFICATION, ModelUtil.createMiningSchema(categoricalLabel))
		.setSegmentation(MiningModelUtil.createSegmentation(Segmentation.MultipleModelMethod.MAJORITY_VOTE, treeModels))
		.setOutput(ModelUtil.createProbabilityOutput(DataType.DOUBLE, categoricalLabel));

	return miningModel;
}