hex.genmodel.algos

Class TreeBasedModel

java.lang.Object

hex.genmodel.GenModel

hex.genmodel.MojoModel

hex.genmodel.algos.TreeBasedModel

All Implemented Interfaces:

IGenModel, java.io.Serializable, IGeneratedModel

Direct Known Subclasses:

DrfModel, GbmModel

public abstract class TreeBasedModel
extends MojoModel

Common ancestor for DrfModel and GbmModel. See also: `hex.tree.SharedTreeModel` and `hex.tree.TreeVisitor` classes.

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class hex.genmodel.MojoModel

MojoModel.MojoReader

Field Summary

Fields

Modifier and Type	Field and Description
protected byte[][]	_compressed_trees
protected int	_ntrees

Fields inherited from class hex.genmodel.MojoModel

_balanceClasses, _category, _defaultThreshold, _modelClassDistrib, _nclasses, _nfeatures, _priorClassDistrib, _reader, _supervised, _uuid

Fields inherited from class hex.genmodel.GenModel

_domains, _names, _offsetColumn

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	TreeBasedModel(MojoModel.MojoReader cr, java.util.Map<java.lang.String,java.lang.Object> info, java.lang.String[] columns, java.lang.String[][] domains)

Method Summary

Methods

Modifier and Type	Method and Description
static java.lang.String	getDecisionPath(double leafAssignment)
protected void	scoreAllTrees(double[] row, double[] preds, int nClassesToScore) Score all trees and fill in the `preds` array.
static double	scoreTree(byte[] tree, double[] row, int nclasses)
static double	scoreTree(byte[] tree, double[] row, int nclasses, boolean computeLeafAssignment) Highly efficient (critical path) tree scoring Given a tree (in the form of a byte array) and the row of input data, compute either this tree's predicted value when `computeLeafAssignment` is false, or the the decision path within the tree (but no more than 64 levels) when `computeLeafAssignment` is true.

Methods inherited from class hex.genmodel.MojoModel

getModelCategory, getUUID, isSupervised, load, load, nclasses, nfeatures

Methods inherited from class hex.genmodel.GenModel

bitSetContains, correctProbabilities, GBM_rescale, getColIdx, getDomainValues, getDomainValues, getDomainValues, getHeader, getNames, getNumClasses, getNumCols, getNumResponseClasses, getPrediction, getPredsSize, getResponseIdx, getResponseName, GLM_identityInv, GLM_inverseInv, GLM_logInv, GLM_logitInv, GLM_tweedieInv, isAutoEncoder, isClassifier, KMeans_closest, KMeans_distance, KMeans_distance, KMeans_simplex, log_rescale, map, mapEnum, predict, predict, score0, score0, score0, score0, score0

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

_ntrees

protected int _ntrees

_compressed_trees

protected byte[][] _compressed_trees

Constructor Detail

TreeBasedModel

protected TreeBasedModel(MojoModel.MojoReader cr,
              java.util.Map<java.lang.String,java.lang.Object> info,
              java.lang.String[] columns,
              java.lang.String[][] domains)

Method Detail

scoreTree

public static double scoreTree(byte[] tree,
               double[] row,
               int nclasses,
               boolean computeLeafAssignment)

Highly efficient (critical path) tree scoring Given a tree (in the form of a byte array) and the row of input data, compute either this tree's predicted value when `computeLeafAssignment` is false, or the the decision path within the tree (but no more than 64 levels) when `computeLeafAssignment` is true. Note: this function is also used from the `hex.tree.CompressedTree` class in `h2o-algos` project.

scoreTree

public static double scoreTree(byte[] tree,
               double[] row,
               int nclasses)

getDecisionPath

public static java.lang.String getDecisionPath(double leafAssignment)

scoreAllTrees

protected void scoreAllTrees(double[] row,
                 double[] preds,
                 int nClassesToScore)

Score all trees and fill in the `preds` array.