org.jpmml.converter.mining.MiningModelUtil Java Examples

The following examples show how to use org.jpmml.converter.mining.MiningModelUtil. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.

Example #1

Source File: MultinomialLogisticRegression.java From jpmml-lightgbm with GNU Affero General Public License v3.0

6 votes

@Override
public MiningModel encodeMiningModel(List<Tree> trees, Integer numIteration, Schema schema){
	Schema segmentSchema = schema.toAnonymousRegressorSchema(DataType.DOUBLE);

	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);
}

Example #2

Source File: PMMLConverter.java From pyramid with Apache License 2.0

6 votes

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;
}

Example #3

Source File: BoostingConverter.java From jpmml-r with GNU Affero General Public License v3.0

6 votes

@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;
}

Example #4

Source File: RangerConverter.java From jpmml-r with GNU Affero General Public License v3.0

6 votes

private MiningModel encodeRegression(RGenericVector ranger, Schema schema){
	RGenericVector forest = ranger.getGenericElement("forest");

	ScoreEncoder scoreEncoder = new ScoreEncoder(){

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

			return node;
		}
	};

	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;
}

Example #5

Source File: AdaConverter.java From jpmml-r with GNU Affero General Public License v3.0

6 votes

@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);
}

Example #6

Source File: GBDTLRClassifier.java From jpmml-sklearn with GNU Affero General Public License v3.0

6 votes

@Override
public Model encodeModel(Schema schema){
	Classifier gbdt = getGBDT();
	MultiOneHotEncoder ohe = getOHE();
	LinearClassifier lr = getLR();

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

	SchemaUtil.checkSize(2, categoricalLabel);

	List<? extends Number> coef = lr.getCoef();
	List<? extends Number> intercept = lr.getIntercept();

	Schema segmentSchema = schema.toAnonymousSchema();

	MiningModel miningModel = GBDTUtil.encodeModel(gbdt, ohe, coef, Iterables.getOnlyElement(intercept), segmentSchema)
		.setOutput(ModelUtil.createPredictedOutput(FieldName.create("decisionFunction"), OpType.CONTINUOUS, DataType.DOUBLE));

	return MiningModelUtil.createBinaryLogisticClassification(miningModel, 1d, 0d, RegressionModel.NormalizationMethod.LOGIT, lr.hasProbabilityDistribution(), schema);
}

Example #7

Source File: AdaBoostRegressor.java From jpmml-sklearn with GNU Affero General Public License v3.0

6 votes

@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;
}

Example #8

Source File: VotingRegressor.java From jpmml-sklearn with GNU Affero General Public License v3.0

6 votes

@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;
}

Example #9

Source File: HingeClassification.java From jpmml-xgboost with GNU Affero General Public License v3.0

6 votes

@Override
public MiningModel encodeMiningModel(List<RegTree> trees, List<Float> weights, float base_score, Integer ntreeLimit, Schema schema){
	Schema segmentSchema = schema.toAnonymousRegressorSchema(DataType.FLOAT);

	Transformation transformation = new FunctionTransformation(PMMLFunctions.THRESHOLD){

		@Override
		public FieldName getName(FieldName name){
			return FieldName.create("hinge(" + name + ")");
		}

		@Override
		public Expression createExpression(FieldRef fieldRef){
			Apply apply = (Apply)super.createExpression(fieldRef);

			apply.addExpressions(PMMLUtil.createConstant(0f));

			return apply;
		}
	};

	MiningModel miningModel = createMiningModel(trees, weights, base_score, ntreeLimit, segmentSchema)
		.setOutput(ModelUtil.createPredictedOutput(FieldName.create("xgbValue"), OpType.CONTINUOUS, DataType.FLOAT, transformation));

	return MiningModelUtil.createBinaryLogisticClassification(miningModel, 1d, 0d, RegressionModel.NormalizationMethod.NONE, true, schema);
}

Example #10

Source File: MultinomialLogisticRegression.java From jpmml-xgboost with GNU Affero General Public License v3.0

6 votes

@Override
public MiningModel encodeMiningModel(List<RegTree> trees, List<Float> weights, float base_score, Integer ntreeLimit, Schema schema){
	Schema segmentSchema = schema.toAnonymousRegressorSchema(DataType.FLOAT);

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

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

	for(int i = 0, columns = categoricalLabel.size(), rows = (trees.size() / columns); i < columns; i++){
		MiningModel miningModel = createMiningModel(CMatrixUtil.getColumn(trees, rows, columns, i), (weights != null) ? CMatrixUtil.getColumn(weights, rows, columns, i) : null, 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);
}

Example #11

Source File: GBTClassificationModelConverter.java From jpmml-sparkml with GNU Affero General Public License v3.0

6 votes

@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);
}

Example #12

Source File: LinearSVCModelConverter.java From jpmml-sparkml with GNU Affero General Public License v3.0

6 votes

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

	Transformation transformation = new AbstractTransformation(){

		@Override
		public Expression createExpression(FieldRef fieldRef){
			return PMMLUtil.createApply(PMMLFunctions.THRESHOLD)
				.addExpressions(fieldRef, PMMLUtil.createConstant(model.getThreshold()));
		}
	};

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

	Model linearModel = LinearModelUtil.createRegression(this, model.coefficients(), model.intercept(), segmentSchema)
		.setOutput(ModelUtil.createPredictedOutput(FieldName.create("margin"), OpType.CONTINUOUS, DataType.DOUBLE, transformation));

	return MiningModelUtil.createBinaryLogisticClassification(linearModel, 1d, 0d, RegressionModel.NormalizationMethod.NONE, false, schema);
}

Example #13

Source File: RandomForestClassificationModelConverter.java From jpmml-sparkml with GNU Affero General Public License v3.0

5 votes

@Override
public MiningModel encodeModel(Schema schema){
	List<TreeModel> treeModels = TreeModelUtil.encodeDecisionTreeEnsemble(this, schema);

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

	return miningModel;
}

Example #14

Source File: PoissonRegression.java From jpmml-lightgbm with GNU Affero General Public License v3.0

5 votes

@Override
public MiningModel encodeMiningModel(List<Tree> trees, Integer numIteration, Schema schema){
	Schema segmentSchema = schema.toAnonymousSchema();

	MiningModel miningModel = super.encodeMiningModel(trees, numIteration, segmentSchema)
		.setOutput(ModelUtil.createPredictedOutput(FieldName.create("lgbmValue"), OpType.CONTINUOUS, DataType.DOUBLE));

	return MiningModelUtil.createRegression(miningModel, RegressionModel.NormalizationMethod.EXP, schema);
}

Example #15

Source File: BinomialLogisticRegression.java From jpmml-lightgbm with GNU Affero General Public License v3.0

5 votes

@Override
public MiningModel encodeMiningModel(List<Tree> trees, Integer numIteration, Schema schema){
	Schema segmentSchema = schema.toAnonymousRegressorSchema(DataType.DOUBLE);

	MiningModel miningModel = createMiningModel(trees, numIteration, segmentSchema)
		.setOutput(ModelUtil.createPredictedOutput(FieldName.create("lgbmValue"), OpType.CONTINUOUS, DataType.DOUBLE));

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

Example #16

Source File: GradientBoostingUtil.java From jpmml-sklearn with GNU Affero General Public License v3.0

5 votes

static
public <E extends Estimator & HasEstimatorEnsemble<TreeRegressor> & HasTreeOptions> MiningModel encodeGradientBoosting(E estimator, Number initialPrediction, Number learningRate, Schema schema){
	ContinuousLabel continuousLabel = (ContinuousLabel)schema.getLabel();

	List<TreeModel> treeModels = TreeUtil.encodeTreeModelEnsemble(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 TreeUtil.transform(estimator, miningModel);
}

Example #17

Source File: GBTRegressionModelConverter.java From jpmml-sparkml with GNU Affero General Public License v3.0

5 votes

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

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

	MiningModel miningModel = new MiningModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(schema.getLabel()))
		.setSegmentation(MiningModelUtil.createSegmentation(Segmentation.MultipleModelMethod.WEIGHTED_SUM, treeModels, Doubles.asList(model.treeWeights())));

	return miningModel;
}

Example #18

Source File: GBMConverter.java From jpmml-r with GNU Affero General Public License v3.0

5 votes

private MiningModel encodeBinaryClassification(List<TreeModel> treeModels, Double initF, double coefficient, Schema schema){
	Schema segmentSchema = schema.toAnonymousRegressorSchema(DataType.DOUBLE);

	MiningModel miningModel = createMiningModel(treeModels, initF, segmentSchema)
		.setOutput(ModelUtil.createPredictedOutput(FieldName.create("gbmValue"), OpType.CONTINUOUS, DataType.DOUBLE));

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

Example #19

Source File: ForestUtil.java From jpmml-sklearn with GNU Affero General Public License v3.0

5 votes

static
public <E extends Estimator & HasEstimatorEnsemble<T> & HasTreeOptions, T extends Estimator & HasTree> MiningModel encodeBaseForest(E estimator, Segmentation.MultipleModelMethod multipleModelMethod, MiningFunction miningFunction, Schema schema){
	List<TreeModel> treeModels = TreeUtil.encodeTreeModelEnsemble(estimator, miningFunction, schema);

	MiningModel miningModel = new MiningModel(miningFunction, ModelUtil.createMiningSchema(schema.getLabel()))
		.setSegmentation(MiningModelUtil.createSegmentation(multipleModelMethod, treeModels));

	return TreeUtil.transform(estimator, miningModel);
}

Example #20

Source File: RandomForestRegressionModelConverter.java From jpmml-sparkml with GNU Affero General Public License v3.0

5 votes

@Override
public MiningModel encodeModel(Schema schema){
	List<TreeModel> treeModels = TreeModelUtil.encodeDecisionTreeEnsemble(this, schema);

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

	return miningModel;
}

Example #21

Source File: GBMConverter.java From jpmml-r with GNU Affero General Public License v3.0

5 votes

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;
}

Example #22

Source File: GeneralizedLinearRegression.java From jpmml-xgboost with GNU Affero General Public License v3.0

5 votes

@Override
public MiningModel encodeMiningModel(List<RegTree> trees, List<Float> weights, float base_score, Integer ntreeLimit, Schema schema){
	Schema segmentSchema = schema.toAnonymousSchema();

	MiningModel miningModel = createMiningModel(trees, weights, base_score, ntreeLimit, segmentSchema)
		.setOutput(ModelUtil.createPredictedOutput(FieldName.create("xgbValue"), OpType.CONTINUOUS, DataType.FLOAT));

	return MiningModelUtil.createRegression(miningModel, RegressionModel.NormalizationMethod.EXP, schema);
}

Example #23

Source File: LogisticRegression.java From jpmml-xgboost with GNU Affero General Public License v3.0

5 votes

@Override
public MiningModel encodeMiningModel(List<RegTree> trees, List<Float> weights, float base_score, Integer ntreeLimit, Schema schema){
	Schema segmentSchema = schema.toAnonymousSchema();

	MiningModel miningModel = createMiningModel(trees, weights, base_score, ntreeLimit, segmentSchema)
		.setOutput(ModelUtil.createPredictedOutput(FieldName.create("xgbValue"), OpType.CONTINUOUS, DataType.FLOAT));

	return MiningModelUtil.createRegression(miningModel, RegressionModel.NormalizationMethod.LOGIT, schema);
}

Example #24

Source File: BinomialLogisticRegression.java From jpmml-xgboost with GNU Affero General Public License v3.0

5 votes

@Override
public MiningModel encodeMiningModel(List<RegTree> trees, List<Float> weights, float base_score, Integer ntreeLimit, Schema schema){
	Schema segmentSchema = schema.toAnonymousRegressorSchema(DataType.FLOAT);

	MiningModel miningModel = createMiningModel(trees, weights, base_score, ntreeLimit, segmentSchema)
		.setOutput(ModelUtil.createPredictedOutput(FieldName.create("xgbValue"), OpType.CONTINUOUS, DataType.FLOAT));

	return MiningModelUtil.createBinaryLogisticClassification(miningModel, 1d, 0d, RegressionModel.NormalizationMethod.LOGIT, true, schema);
}

Example #25

Source File: GBMConverter.java From jpmml-r with GNU Affero General Public License v3.0

4 votes

private MiningModel encodeMultinomialClassification(List<TreeModel> treeModels, Double initF, Schema schema){
	CategoricalLabel categoricalLabel = (CategoricalLabel)schema.getLabel();

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

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

	for(int i = 0, columns = categoricalLabel.size(), rows = (treeModels.size() / columns); i < columns; i++){
		MiningModel miningModel = createMiningModel(CMatrixUtil.getColumn(treeModels, rows, columns, i), initF, segmentSchema)
			.setOutput(ModelUtil.createPredictedOutput(FieldName.create("gbmValue(" + categoricalLabel.getValue(i) + ")"), OpType.CONTINUOUS, DataType.DOUBLE));

		miningModels.add(miningModel);
	}

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

Example #26

Source File: ModelConverter.java From jpmml-sparkml with GNU Affero General Public License v3.0

4 votes

public org.dmg.pmml.Model registerModel(SparkMLEncoder encoder){
	Schema schema = encodeSchema(encoder);

	Label label = schema.getLabel();

	org.dmg.pmml.Model model = encodeModel(schema);

	List<OutputField> sparkOutputFields = registerOutputFields(label, model, encoder);
	if(sparkOutputFields != null && sparkOutputFields.size() > 0){
		org.dmg.pmml.Model finalModel = MiningModelUtil.getFinalModel(model);

		Output output = ModelUtil.ensureOutput(finalModel);

		List<OutputField> outputFields = output.getOutputFields();

		outputFields.addAll(sparkOutputFields);
	}

	return model;
}

Example #27

Source File: BaggingConverter.java From jpmml-r with GNU Affero General Public License v3.0

4 votes

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

	RGenericVector trees = bagging.getGenericElement("trees");

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

	List<TreeModel> treeModels = encodeTreeModels(trees);

	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;
}

Example #28

Source File: RandomForestConverter.java From jpmml-r with GNU Affero General Public License v3.0

4 votes

private MiningModel encodeClassification(RGenericVector forest, Schema schema){
	RNumberVector<?> bestvar = forest.getNumericElement("bestvar");
	RNumberVector<?> treemap = forest.getNumericElement("treemap");
	RIntegerVector nodepred = forest.getIntegerElement("nodepred");
	RDoubleVector xbestsplit = forest.getDoubleElement("xbestsplit");
	RIntegerVector nrnodes = forest.getIntegerElement("nrnodes");
	RDoubleVector ntree = forest.getDoubleElement("ntree");

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

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

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

		@Override
		public Object 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;
}

Example #29

Source File: XGBoostClassificationModelConverter.java From jpmml-sparkml-xgboost with GNU Affero General Public License v3.0

4 votes

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

	Booster booster = model.nativeBooster();

	MiningModel miningModel = BoosterUtil.encodeBooster(this, booster, schema);

	RegressionModel regressionModel = (RegressionModel)MiningModelUtil.getFinalModel(miningModel);

	if(model instanceof ProbabilisticClassificationModel){
		regressionModel.setOutput(null);
	}

	return miningModel;
}

Example #30

Source File: RandomForestConverter.java From jpmml-r with GNU Affero General Public License v3.0

4 votes

private MiningModel encodeRegression(RGenericVector forest, Schema schema){
	RNumberVector<?> leftDaughter = forest.getNumericElement("leftDaughter");
	RNumberVector<?> rightDaughter = forest.getNumericElement("rightDaughter");
	RDoubleVector nodepred = forest.getDoubleElement("nodepred");
	RNumberVector<?> bestvar = forest.getNumericElement("bestvar");
	RDoubleVector xbestsplit = forest.getDoubleElement("xbestsplit");
	RIntegerVector nrnodes = forest.getIntegerElement("nrnodes");
	RNumberVector<?> ntree = forest.getNumericElement("ntree");

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

		@Override
		public Double encode(Double value){
			return value;
		}
	};

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

	Schema segmentSchema = schema.toAnonymousSchema();

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

	for(int i = 0; i < columns; i++){
		TreeModel treeModel = encodeTreeModel(
				MiningFunction.REGRESSION,
				scoreEncoder,
				FortranMatrixUtil.getColumn(leftDaughter.getValues(), rows, columns, i),
				FortranMatrixUtil.getColumn(rightDaughter.getValues(), rows, columns, i),
				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.REGRESSION, ModelUtil.createMiningSchema(schema.getLabel()))
		.setSegmentation(MiningModelUtil.createSegmentation(Segmentation.MultipleModelMethod.AVERAGE, treeModels));

	return miningModel;
}