Java MiningModel类代码示例

import org.dmg.pmml.mining.MiningModel; //导入依赖的package包/类
private List<OutputField> createNestedOutputFields(){
	MiningModel miningModel = getModel();

	Segmentation segmentation = miningModel.getSegmentation();

	List<Segment> segments = segmentation.getSegments();

	Segmentation.MultipleModelMethod multipleModelMethod = segmentation.getMultipleModelMethod();
	switch(multipleModelMethod){
		case SELECT_ALL:
			// Ignored
			break;
		case SELECT_FIRST:
			return createNestedOutputFields(getActiveHead(segments));
		case MODEL_CHAIN:
			return createNestedOutputFields(getActiveTail(segments));
		default:
			break;
	}

	return Collections.emptyList();
}
 

import org.dmg.pmml.mining.MiningModel; //导入依赖的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.dmg.pmml.mining.MiningModel; //导入依赖的package包/类
@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 = new Schema(new ContinuousLabel(null, DataType.DOUBLE), schema.getFeatures());

	List<TreeModel> treeModels = TreeModelUtil.encodeDecisionTreeEnsemble(model, 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);
}
 

import org.dmg.pmml.mining.MiningModel; //导入依赖的package包/类
protected org.dmg.pmml.Model getLastModel(org.dmg.pmml.Model model){

		if(model instanceof MiningModel){
			MiningModel miningModel = (MiningModel)model;

			Segmentation segmentation = miningModel.getSegmentation();

			MultipleModelMethod multipleModelMethod = segmentation.getMultipleModelMethod();
			switch(multipleModelMethod){
				case MODEL_CHAIN:
					List<Segment> segments = segmentation.getSegments();

					if(segments.size() > 0){
						Segment lastSegment = segments.get(segments.size() - 1);

						return lastSegment.getModel();
					}
					break;
				default:
					break;
			}
		}

		return model;
	}
 

import org.dmg.pmml.mining.MiningModel; //导入依赖的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.dmg.pmml.mining.MiningModel; //导入依赖的package包/类
static
public MiningModel createModelChain(List<? extends Model> models, Schema schema){

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

	Segmentation segmentation = createSegmentation(Segmentation.MultipleModelMethod.MODEL_CHAIN, models);

	Model lastModel = Iterables.getLast(models);

	MiningModel miningModel = new MiningModel(lastModel.getMiningFunction(), ModelUtil.createMiningSchema(schema.getLabel()))
		.setMathContext(ModelUtil.simplifyMathContext(lastModel.getMathContext()))
		.setSegmentation(segmentation);

	return miningModel;
}
 

import org.dmg.pmml.mining.MiningModel; //导入依赖的package包/类
@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;
}
 

import org.dmg.pmml.mining.MiningModel; //导入依赖的package包/类
@Override
public MiningModel encodeModel(Schema schema){
	List<? extends Regressor> estimators = getEstimators();
	List<? extends Number> estimatorWeights = getEstimatorWeights();

	Schema segmentSchema = schema.toAnonymousSchema();

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

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

		models.add(model);
	}

	MiningModel miningModel = new MiningModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(schema.getLabel()))
		.setSegmentation(MiningModelUtil.createSegmentation(MultipleModelMethod.WEIGHTED_MEDIAN, models, estimatorWeights));

	return miningModel;
}
 

import org.dmg.pmml.mining.MiningModel; //导入依赖的package包/类
@Override
public MiningModel encodeModel(Schema schema){
	RGenericVector ranger = getObject();

	RStringVector treetype = (RStringVector)ranger.getValue("treetype");

	switch(treetype.asScalar()){
		case "Regression":
			return encodeRegression(ranger, schema);
		case "Classification":
			return encodeClassification(ranger, schema);
		case "Probability estimation":
			return encodeProbabilityForest(ranger, schema);
		default:
			throw new IllegalArgumentException();
	}
}
 

import org.dmg.pmml.mining.MiningModel; //导入依赖的package包/类
private MiningModel encodeRegression(RGenericVector ranger, Schema schema){
	RGenericVector forest = (RGenericVector)ranger.getValue("forest");

	ScoreEncoder scoreEncoder = new ScoreEncoder(){

		@Override
		public void encode(Node node, Number splitValue, RNumberVector<?> terminalClassCount){
			node.setScore(ValueUtil.formatValue(splitValue));
		}
	};

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

	MiningModel miningModel = new MiningModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(schema.getLabel()))
		.setSegmentation(MiningModelUtil.createSegmentation(Segmentation.MultipleModelMethod.AVERAGE, treeModels));

	return miningModel;
}
 

import org.dmg.pmml.mining.MiningModel; //导入依赖的package包/类
@Override
public MiningModel encodeModel(Schema schema){
	RGenericVector randomForest = getObject();

	RStringVector type = (RStringVector)randomForest.getValue("type");
	RGenericVector forest = (RGenericVector)randomForest.getValue("forest");

	switch(type.asScalar()){
		case "regression":
			return encodeRegression(forest, schema);
		case "classification":
			return encodeClassification(forest, schema);
		default:
			throw new IllegalArgumentException();
	}
}
 

import org.dmg.pmml.mining.MiningModel; //导入依赖的package包/类
public static MiningModel encodeMiningModel(List<List<RegressionTree>> regTrees, float base_score, Schema schema){
    Schema segmentSchema = new Schema(new ContinuousLabel(null, DataType.FLOAT), schema.getFeatures());

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

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


    int numClasses = regTrees.size();
    for (int l=0;l<numClasses;l++){
        MiningModel miningModel = createMiningModel(regTrees.get(l), base_score, segmentSchema)
                .setOutput(ModelUtil.createPredictedOutput(FieldName.create("class_(" + categoricalLabel.getValue(l) + ")"), OpType.CONTINUOUS, DataType.FLOAT));
        miningModels.add(miningModel);
    }

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

import org.dmg.pmml.mining.MiningModel; //导入依赖的package包/类
static
protected MiningModel createMiningModel(List<RegressionTree> regTrees, float base_score, Schema schema){
    ContinuousLabel continuousLabel = (ContinuousLabel)schema.getLabel();

    Schema segmentSchema = schema.toAnonymousSchema();

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

    for(RegressionTree 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.dmg.pmml.mining.MiningModel; //导入依赖的package包/类
static
public MiningModel createModelChain(List<? extends Model> models, Schema schema){

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

    Segmentation segmentation = createSegmentation(Segmentation.MultipleModelMethod.MODEL_CHAIN, models);

    Model lastModel = Iterables.getLast(models);

    MiningModel miningModel = new MiningModel(lastModel.getMiningFunction(), ModelUtil.createMiningSchema(schema.getLabel()))
            .setMathContext(ModelUtil.simplifyMathContext(lastModel.getMathContext()))
            .setSegmentation(segmentation);

    return miningModel;
}
 

import org.dmg.pmml.mining.MiningModel; //导入依赖的package包/类
@Override
public PMMLObject popParent(){
	PMMLObject parent = super.popParent();

	if(parent instanceof MiningModel){
		MiningModel miningModel = (MiningModel)parent;

		processMiningModel(miningModel);
	} else

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

		processModel(model);
	}

	return parent;
}