org.dmg.pmml.MiningFunction Java Examples

@Override
public MiningModel encodeModel(Schema schema){
	List<? extends Classifier> estimators = getEstimators();
	List<List<Integer>> estimatorsFeatures = getEstimatorsFeatures();

	Segmentation.MultipleModelMethod multipleModelMethod = Segmentation.MultipleModelMethod.AVERAGE;

	for(Classifier estimator : estimators){

		if(!estimator.hasProbabilityDistribution()){
			multipleModelMethod = Segmentation.MultipleModelMethod.MAJORITY_VOTE;

			break;
		}
	}

	MiningModel miningModel = BaggingUtil.encodeBagging(estimators, estimatorsFeatures, multipleModelMethod, MiningFunction.CLASSIFICATION, schema)
		.setOutput(ModelUtil.createProbabilityOutput(DataType.DOUBLE, (CategoricalLabel)schema.getLabel()));

	return miningModel;
}
 

/**
 * @return A synthetic {@link DataField} element describing the default target field.
 */
public DataField getDefaultDataField(){

	if(this.defaultDataField != null){
		return this.defaultDataField;
	}

	MiningFunction miningFunction = getMiningFunction();
	switch(miningFunction){
		case REGRESSION:
			MathContext mathContext = getMathContext();

			switch(mathContext){
				case FLOAT:
					return ModelManager.DEFAULT_TARGET_CONTINUOUS_FLOAT;
				default:
					return ModelManager.DEFAULT_TARGET_CONTINUOUS_DOUBLE;
			}
		case CLASSIFICATION:
		case CLUSTERING:
			return ModelManager.DEFAULT_TARGET_CATEGORICAL_STRING;
		default:
			return null;
	}
}
 

private <P extends Number> TreeModel encodeTreeModel(MiningFunction miningFunction, ScoreEncoder<P> scoreEncoder, List<? extends Number> leftDaughter, List<? extends Number> rightDaughter, List<P> nodepred, List<? extends Number> bestvar, List<Double> xbestsplit, Schema schema){
	RGenericVector randomForest = getObject();

	Node root = encodeNode(True.INSTANCE, 0, scoreEncoder, leftDaughter, rightDaughter, bestvar, xbestsplit, nodepred, new CategoryManager(), schema);

	TreeModel treeModel = new TreeModel(miningFunction, ModelUtil.createMiningSchema(schema.getLabel()), root)
		.setMissingValueStrategy(TreeModel.MissingValueStrategy.NULL_PREDICTION)
		.setSplitCharacteristic(TreeModel.SplitCharacteristic.BINARY_SPLIT);

	if(this.compact){
		Visitor visitor = new RandomForestCompactor();

		visitor.applyTo(treeModel);
	}

	return treeModel;
}
 

@Override
public MiningModel encodeModel(Schema schema){
	GBTClassificationModel model = getTransformer();

	String lossType = model.getLossType();
	switch(lossType){
		case "logistic":
			break;
		default:
			throw new IllegalArgumentException("Loss function " + lossType + " is not supported");
	}

	Schema segmentSchema = schema.toAnonymousRegressorSchema(DataType.DOUBLE);

	List<TreeModel> treeModels = TreeModelUtil.encodeDecisionTreeEnsemble(this, segmentSchema);

	MiningModel miningModel = new MiningModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(segmentSchema.getLabel()))
		.setSegmentation(MiningModelUtil.createSegmentation(Segmentation.MultipleModelMethod.WEIGHTED_SUM, treeModels, Doubles.asList(model.treeWeights())))
		.setOutput(ModelUtil.createPredictedOutput(FieldName.create("gbtValue"), OpType.CONTINUOUS, DataType.DOUBLE));

	return MiningModelUtil.createBinaryLogisticClassification(miningModel, 2d, 0d, RegressionModel.NormalizationMethod.LOGIT, false, schema);
}
 

@Override
public VisitorAction visit(TreeModel treeModel){
	MiningFunction miningFunction = treeModel.getMiningFunction();
	if(miningFunction == null){
		throw new MissingAttributeException(treeModel, PMMLAttributes.TREEMODEL_MININGFUNCTION);
	}

	switch(miningFunction){
		case REGRESSION:
			break;
		default:
			return VisitorAction.SKIP;
	}

	return super.visit(treeModel);
}
 

private List<TreeModel> encodeForest(RGenericVector forest, MiningFunction miningFunction, ScoreEncoder scoreEncoder, Schema schema){
	RNumberVector<?> numTrees = forest.getNumericElement("num.trees");
	RGenericVector childNodeIDs = forest.getGenericElement("child.nodeIDs");
	RGenericVector splitVarIDs = forest.getGenericElement("split.varIDs");
	RGenericVector splitValues = forest.getGenericElement("split.values");
	RGenericVector terminalClassCounts = forest.getGenericElement("terminal.class.counts", false);

	Schema segmentSchema = schema.toAnonymousSchema();

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

	for(int i = 0; i < ValueUtil.asInt(numTrees.asScalar()); i++){
		TreeModel treeModel = encodeTreeModel(miningFunction, scoreEncoder, (RGenericVector)childNodeIDs.getValue(i), (RNumberVector<?>)splitVarIDs.getValue(i), (RNumberVector<?>)splitValues.getValue(i), (terminalClassCounts != null ? (RGenericVector)terminalClassCounts.getValue(i) : null), segmentSchema);

		treeModels.add(treeModel);
	}

	return treeModels;
}
 

@Override
public Model encodeModel(Schema schema){
	RGenericVector ada = getObject();

	RGenericVector model = ada.getGenericElement("model");

	RGenericVector trees = model.getGenericElement("trees");
	RDoubleVector alpha = model.getDoubleElement("alpha");

	List<TreeModel> treeModels = encodeTreeModels(trees);

	MiningModel miningModel = new MiningModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(null))
		.setSegmentation(MiningModelUtil.createSegmentation(Segmentation.MultipleModelMethod.WEIGHTED_SUM, treeModels, alpha.getValues()))
		.setOutput(ModelUtil.createPredictedOutput(FieldName.create("adaValue"), OpType.CONTINUOUS, DataType.DOUBLE));

	return MiningModelUtil.createBinaryLogisticClassification(miningModel, 2d, 0d, RegressionModel.NormalizationMethod.LOGIT, true, schema);
}
 

@Override
public RPartConverter createConverter(RGenericVector rpart){
	return new RPartConverter(rpart){

		@Override
		public boolean hasScoreDistribution(){
			return false;
		}

		@Override
		public TreeModel encodeModel(Schema schema){
			TreeModel treeModel = super.encodeModel(schema)
				.setMiningFunction(MiningFunction.REGRESSION);

			return treeModel;
		}
	};
}
 

@Override
public Model encodeModel(Schema schema){
	RGenericVector boosting = getObject();

	RGenericVector trees = boosting.getGenericElement("trees");
	RDoubleVector weights = boosting.getDoubleElement("weights");

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

	List<TreeModel> treeModels = encodeTreeModels(trees);

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

	return miningModel;
}
 

@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(PMMLUtil.createRealArray(VectorUtil.toList(clusterCenters[i])))
			.setId(String.valueOf(i));

		clusters.add(cluster);
	}

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

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

static
public <E extends Estimator & HasTree> TreeModel encodeTreeModel(E estimator, PredicateManager predicateManager, ScoreDistributionManager scoreDistributionManager, MiningFunction miningFunction, Schema schema){
	Tree tree = estimator.getTree();

	int[] leftChildren = tree.getChildrenLeft();
	int[] rightChildren = tree.getChildrenRight();
	int[] features = tree.getFeature();
	double[] thresholds = tree.getThreshold();
	double[] values = tree.getValues();

	Node root = encodeNode(True.INSTANCE, predicateManager, scoreDistributionManager, 0, leftChildren, rightChildren, features, thresholds, values, miningFunction, schema);

	TreeModel treeModel = new TreeModel(miningFunction, ModelUtil.createMiningSchema(schema.getLabel()), root)
		.setSplitCharacteristic(TreeModel.SplitCharacteristic.BINARY_SPLIT);

	ClassDictUtil.clearContent(tree);

	return treeModel;
}
 

@Override
public Model encodeModel(Schema schema){
	List<? extends Regressor> estimators = getEstimators();
	List<? extends Number> weights = getWeights();

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

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

		models.add(model);
	}

	Segmentation.MultipleModelMethod multipleModelMethod = (weights != null && weights.size() > 0 ? Segmentation.MultipleModelMethod.WEIGHTED_AVERAGE : Segmentation.MultipleModelMethod.AVERAGE);

	MiningModel miningModel = new MiningModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(schema.getLabel()))
		.setSegmentation(MiningModelUtil.createSegmentation(multipleModelMethod, models, weights));

	return miningModel;
}
 

private TreeModel encodeRegression(RGenericVector frame, RIntegerVector rowNames, RIntegerVector var, RIntegerVector n, int[][] splitInfo, RNumberVector<?> splits, RIntegerVector csplit, Schema schema){
	RNumberVector<?> yval = frame.getNumericElement("yval");

	ScoreEncoder scoreEncoder = new ScoreEncoder(){

		@Override
		public Node encode(Node node, int offset){
			Number score = yval.getValue(offset);
			Number recordCount = n.getValue(offset);

			node
				.setScore(score)
				.setRecordCount(recordCount);

			return node;
		}
	};

	Node root = encodeNode(True.INSTANCE, 1, rowNames, var, n, splitInfo, splits, csplit, scoreEncoder, schema);

	TreeModel treeModel = new TreeModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(schema.getLabel()), root);

	return configureTreeModel(treeModel);
}
 

static
public TreeModel encodeTreeModel(TreePredictor treePredictor, PredicateManager predicateManager, Schema schema){
	int[] leaf = treePredictor.isLeaf();
	int[] leftChildren = treePredictor.getLeft();
	int[] rightChildren = treePredictor.getRight();
	int[] featureIdx = treePredictor.getFeatureIdx();
	double[] thresholds = treePredictor.getThreshold();
	int[] missingGoToLeft = treePredictor.getMissingGoToLeft();
	double[] values = treePredictor.getValues();

	Node root = encodeNode(True.INSTANCE, predicateManager, 0, leaf, leftChildren, rightChildren, featureIdx, thresholds, missingGoToLeft, values, schema);

	TreeModel treeModel = new TreeModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(schema.getLabel()), root)
		.setSplitCharacteristic(TreeModel.SplitCharacteristic.BINARY_SPLIT)
		.setMissingValueStrategy(TreeModel.MissingValueStrategy.DEFAULT_CHILD);

	return treeModel;
}
 

static
private MiningFunction getMiningFunction(String family){
	GeneralRegressionModel.Distribution distribution = parseFamily(family);

	switch(distribution){
		case BINOMIAL:
			return MiningFunction.CLASSIFICATION;
		case NORMAL:
		case GAMMA:
		case IGAUSS:
		case POISSON:
			return MiningFunction.REGRESSION;
		default:
			throw new IllegalArgumentException();
	}
}
 

public ClassifierManager(PMML pmml, TreeModel treeModel){
	super(pmml, treeModel);

	MiningFunction miningFunction = treeModel.getMiningFunction();
	switch(miningFunction){
		case CLASSIFICATION:
			break;
		default:
			throw new UnsupportedAttributeException(treeModel, miningFunction);
	}
}
 

@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(PMMLUtil.createRealArray(CMatrixUtil.getRow(clusterCenters, numberOfClusters, numberOfFeatures, i)))
			.setId(String.valueOf(i))
			.setSize((labelCounts.size () > 0 ? labelCounts.count(i) : null));

		clusters.add(cluster);
	}

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

	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;
}
 

@Override
public void exitNode(Node node){
	Predicate predicate = node.getPredicate();

	if(predicate instanceof True){
		Node parentNode = getParentNode();

		if(parentNode == null){
			return;
		}

		List<Node> parentChildren = parentNode.getNodes();
		if(parentChildren.size() != 1){
			return;
		}

		boolean success = parentChildren.remove(node);
		if(!success){
			throw new IllegalArgumentException();
		} // End if

		if((MiningFunction.REGRESSION).equals(this.miningFunction)){
			parentNode.setScore(null);

			initScore(parentNode, node);
		} else

		if((MiningFunction.CLASSIFICATION).equals(this.miningFunction)){
			initScoreDistribution(parentNode, node);
		} else

		{
			throw new IllegalArgumentException();
		}
	}
}
 

@Override
public MiningFunction getMiningFunction(){
	String estimatorType = getEstimatorType();

	switch(estimatorType){
		case "classifier":
			return MiningFunction.CLASSIFICATION;
		case "regressor":
			return MiningFunction.REGRESSION;
		default:
			throw new IllegalArgumentException(estimatorType);
	}
}
 

static
private MiningModel encodeModel(MiningFunction miningFunction, List<Object[]> steps, Schema schema){

	if(steps.size() < 1){
		throw new IllegalArgumentException();
	}

	Label label = schema.getLabel();
	List<? extends Feature> features = schema.getFeatures();

	Segmentation segmentation = new Segmentation(Segmentation.MultipleModelMethod.SELECT_FIRST, null);

	Scope scope = new DataFrameScope(FieldName.create("X"), features);

	for(Object[] step : steps){
		String name = TupleUtil.extractElement(step, 0, String.class);
		Estimator estimator = TupleUtil.extractElement(step, 1, Estimator.class);
		String predicate = TupleUtil.extractElement(step, 2, String.class);

		if(!(miningFunction).equals(estimator.getMiningFunction())){
			throw new IllegalArgumentException();
		}

		Predicate pmmlPredicate = PredicateTranslator.translate(predicate, scope);

		Model model = estimator.encodeModel(schema);

		Segment segment = new Segment(pmmlPredicate, model)
			.setId(name);

		segmentation.addSegments(segment);
	}

	MiningModel miningModel = new MiningModel(miningFunction, ModelUtil.createMiningSchema(label))
		.setSegmentation(segmentation);

	return miningModel;
}
 

@Override
public Model encodeModel(RDoubleVector a0, RExp beta, int column, Schema schema){
	Double intercept = a0.getValue(column);
	List<Double> coefficients = getCoefficients((S4Object)beta, column);

	GeneralRegressionModel generalRegressionModel = new GeneralRegressionModel(GeneralRegressionModel.ModelType.GENERAL_LINEAR, MiningFunction.REGRESSION, ModelUtil.createMiningSchema(schema.getLabel()), null, null, null)
		.setDistribution(GeneralRegressionModel.Distribution.POISSON);

	GeneralRegressionModelUtil.encodeRegressionTable(generalRegressionModel, schema.getFeatures(), coefficients, intercept, null);

	return generalRegressionModel;
}
 

@Override
public void exitNode(Node node){
	Predicate predicate = node.getPredicate();

	if(predicate instanceof True){
		Node parentNode = getParentNode();

		if(parentNode == null){
			return;
		}

		if((MiningFunction.REGRESSION).equals(this.miningFunction)){
			parentNode.setScore(null);

			initScore(parentNode, node);
			replaceChildWithGrandchildren(parentNode, node);
		} else

		if((MiningFunction.CLASSIFICATION).equals(this.miningFunction)){

			// Replace intermediate nodes, but not terminal nodes
			if(node.hasNodes()){
				replaceChildWithGrandchildren(parentNode, node);
			}
		} else

		{
			throw new IllegalArgumentException();
		}
	}
}
 

@Override
public NeuralNetwork encodeModel(Schema schema){
	String activation = getActivation();

	List<? extends HasArray> coefs = getCoefs();
	List<? extends HasArray> intercepts = getIntercepts();

	NeuralNetwork neuralNetwork = MultilayerPerceptronUtil.encodeNeuralNetwork(MiningFunction.REGRESSION, activation, coefs, intercepts, schema);

	return neuralNetwork;
}
 

public TreeModel encodeTreeModel(Schema schema){
    org.dmg.pmml.tree.Node root = new org.dmg.pmml.tree.Node()
            .setPredicate(new True());

    encodeNode(root, 0, schema);

    TreeModel treeModel = new TreeModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(schema.getLabel()), root)
            .setSplitCharacteristic(TreeModel.SplitCharacteristic.BINARY_SPLIT)
            .setMissingValueStrategy(TreeModel.MissingValueStrategy.NONE)
            .setMathContext(MathContext.FLOAT);

    return treeModel;
}
 

static
public <E extends Estimator & HasTree> TreeModel encodeTreeModel(E estimator, MiningFunction miningFunction, Schema schema){
	PredicateManager predicateManager = new PredicateManager();
	ScoreDistributionManager scoreDistributionManager = new ScoreDistributionManager();

	return encodeTreeModel(estimator, predicateManager, scoreDistributionManager, miningFunction, schema);
}
 

static
public <E extends Estimator & HasEstimatorEnsemble<T>, T extends Estimator & HasTree> List<TreeModel> encodeTreeModelEnsemble(E estimator, MiningFunction miningFunction, Schema schema){
	PredicateManager predicateManager = new PredicateManager();
	ScoreDistributionManager scoreDistributionManager = new ScoreDistributionManager();

	return encodeTreeModelEnsemble(estimator, predicateManager, scoreDistributionManager, miningFunction, schema);
}
 

@Override
public Model encodeModel(Schema schema){
	RGenericVector kmeans = getObject();

	RDoubleVector centers = kmeans.getDoubleElement("centers");
	RIntegerVector size = kmeans.getIntegerElement("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(PMMLUtil.createRealArray(FortranMatrixUtil.getRow(centers.getValues(), rows, columns, i)))
			.setId(String.valueOf(i + 1))
			.setName(rowNames.getValue(i))
			.setSize(size.getValue(i));

		clusters.add(cluster);
	}

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

	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;
}
 

@Override
public GeneralRegressionModel encodeModel(Schema schema){
	RGenericVector mvr = getObject();

	RDoubleVector coefficients = mvr.getDoubleElement("coefficients");
	RDoubleVector xMeans = mvr.getDoubleElement("Xmeans");
	RDoubleVector yMeans = mvr.getDoubleElement("Ymeans");
	RNumberVector<?> ncomp = mvr.getNumericElement("ncomp");

	RStringVector rowNames = coefficients.dimnames(0);
	RStringVector columnNames = coefficients.dimnames(1);
	RStringVector compNames = coefficients.dimnames(2);

	int rows = rowNames.size();
	int columns = columnNames.size();
	int components = compNames.size();

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

	List<Double> featureCoefficients = FortranMatrixUtil.getColumn(coefficients.getValues(), rows, (columns * components), 0 + (ValueUtil.asInt(ncomp.asScalar()) - 1));

	Double intercept = yMeans.getValue(0);

	for(int j = 0; j < rowNames.size(); j++){
		intercept -= (featureCoefficients.get(j) * xMeans.getValue(j));
	}

	GeneralRegressionModel generalRegressionModel = new GeneralRegressionModel(GeneralRegressionModel.ModelType.GENERALIZED_LINEAR, MiningFunction.REGRESSION, ModelUtil.createMiningSchema(schema.getLabel()), null, null, null)
		.setLinkFunction(GeneralRegressionModel.LinkFunction.IDENTITY);

	GeneralRegressionModelUtil.encodeRegressionTable(generalRegressionModel, features, featureCoefficients, intercept, null);

	return generalRegressionModel;
}
 

@Override
public Model encodeModel(RDoubleVector a0, RExp beta, int column, Schema schema){
	Double intercept = a0.getValue(column);
	List<Double> coefficients = getCoefficients((S4Object)beta, column);

	GeneralRegressionModel generalRegressionModel = new GeneralRegressionModel(GeneralRegressionModel.ModelType.GENERAL_LINEAR, MiningFunction.REGRESSION, ModelUtil.createMiningSchema(schema.getLabel()), null, null, null)
		.setDistribution(GeneralRegressionModel.Distribution.NORMAL);

	GeneralRegressionModelUtil.encodeRegressionTable(generalRegressionModel, schema.getFeatures(), coefficients, intercept, null);

	return generalRegressionModel;
}
 

@Override
public TreeModel encodeModel(Schema schema){
	TreeModel treeModel = TreeUtil.encodeTreeModel(this, MiningFunction.CLASSIFICATION, schema)
		.setOutput(ModelUtil.createProbabilityOutput(DataType.DOUBLE, (CategoricalLabel)schema.getLabel()));

	return TreeUtil.transform(this, treeModel);
}