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; }
static public TreeModel encodeTreeModel(byte[] compressedTree, PredicateManager predicateManager, Schema schema){ Label label = new ContinuousLabel(null, DataType.DOUBLE); AtomicInteger idSequence = new AtomicInteger(1); ByteBufferWrapper buffer = new ByteBufferWrapper(compressedTree); Node root = encodeNode(new True(), idSequence, compressedTree, buffer, predicateManager, new CategoryManager(), schema); TreeModel treeModel = new TreeModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(label), root) .setMissingValueStrategy(TreeModel.MissingValueStrategy.DEFAULT_CHILD); return treeModel; }
@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; } }
@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; } }
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; }
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 = TreeModelUtil.encodeTreeModelSegmentation(estimator, miningFunction, schema); MiningModel miningModel = new MiningModel(miningFunction, ModelUtil.createMiningSchema(schema.getLabel())) .setSegmentation(MiningModelUtil.createSegmentation(multipleModelMethod, treeModels)); return TreeModelUtil.transform(estimator, miningModel); } }
public TreeModel encodeTreeModel(PredicateManager predicateManager, Schema schema){ org.dmg.pmml.tree.Node root = encodeNode(new True(), predicateManager, 0, schema); TreeModel treeModel = new TreeModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(schema.getLabel()), root) .setSplitCharacteristic(TreeModel.SplitCharacteristic.BINARY_SPLIT) .setMissingValueStrategy(TreeModel.MissingValueStrategy.DEFAULT_CHILD) .setMathContext(MathContext.FLOAT); return treeModel; }
public TreeModel encodeTreeModel(PredicateManager predicateManager, Schema schema){ org.dmg.pmml.tree.Node root = encodeNode(new True(), predicateManager, 0, schema); TreeModel treeModel = new TreeModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(schema.getLabel()), root) .setSplitCharacteristic(TreeModel.SplitCharacteristic.BINARY_SPLIT) .setMissingValueStrategy(TreeModel.MissingValueStrategy.DEFAULT_CHILD) .setMathContext(MathContext.FLOAT); return treeModel; }
@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; } }
public TreeModel encodeTreeModel(PredicateManager predicateManager, Schema schema){ Node root = encodeNode(new True(), predicateManager, new CategoryManager(), 0, schema); TreeModel treeModel = new TreeModel(MiningFunction.REGRESSION, ModelUtil.createMiningSchema(schema.getLabel()), root) .setSplitCharacteristic(TreeModel.SplitCharacteristic.BINARY_SPLIT) .setMissingValueStrategy(TreeModel.MissingValueStrategy.DEFAULT_CHILD); return treeModel; }
private TreeModel encodeTreeModel(MiningFunction miningFunction, RGenericVector tree, RGenericVector c_splits, Schema schema){ Node root = encodeNode(new True(), 0, tree, c_splits, new FlagManager(), new CategoryManager(), schema); TreeModel treeModel = new TreeModel(miningFunction, ModelUtil.createMiningSchema(schema.getLabel()), root) .setSplitCharacteristic(TreeModel.SplitCharacteristic.MULTI_SPLIT); return treeModel; }
@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; } }
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 = 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); } }
@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; } }
private TreeModel encodeTreeModel(MiningFunction miningFunction, ScoreEncoder scoreEncoder, RGenericVector childNodeIDs, RNumberVector<?> splitVarIDs, RNumberVector<?> splitValues, RGenericVector terminalClassCounts, Schema schema){ RNumberVector<?> leftChildIDs = (RNumberVector<?>)childNodeIDs.getValue(0); RNumberVector<?> rightChildIDs = (RNumberVector<?>)childNodeIDs.getValue(1); Node root = encodeNode(new True(), 0, scoreEncoder, leftChildIDs, rightChildIDs, splitVarIDs, splitValues, terminalClassCounts, new CategoryManager(), schema); TreeModel treeModel = new TreeModel(miningFunction, ModelUtil.createMiningSchema(schema.getLabel()), root) .setSplitCharacteristic(TreeModel.SplitCharacteristic.BINARY_SPLIT); return treeModel; }
static private <M extends Model<M> & DecisionTreeModel> TreeModel encodeTreeModel(M model, PredicateManager predicateManager, MiningFunction miningFunction, ScoreEncoder scoreEncoder, Schema schema){ Node root = new Node() .setPredicate(new True()); encodeNode(root, model.rootNode(), predicateManager, new CategoryManager(), scoreEncoder, schema); TreeModel treeModel = new TreeModel(miningFunction, ModelUtil.createMiningSchema(schema.getLabel()), root) .setSplitCharacteristic(TreeModel.SplitCharacteristic.BINARY_SPLIT); return treeModel; }
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; }
@Override public Model encodeModel(Schema schema){ RGenericVector bagging = getObject(); RGenericVector trees = (RGenericVector)bagging.getValue("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; } }
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(new True(), 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 Model encodeModel(Schema schema){ RGenericVector ada = getObject(); RGenericVector model = (RGenericVector)ada.getValue("model"); RGenericVector trees = (RGenericVector)model.getValue("trees"); RDoubleVector alpha = (RDoubleVector)model.getValue("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, new SigmoidTransformation(-2d))); return MiningModelUtil.createBinaryLogisticClassification(miningModel, 1d, 0d, RegressionModel.NormalizationMethod.NONE, true, schema); }