hex.genmodel.algos.gbm

Class GbmMojoModel

java.lang.Object

hex.genmodel.GenModel

hex.genmodel.MojoModel

hex.genmodel.algos.tree.SharedTreeMojoModel

hex.genmodel.algos.tree.SharedTreeMojoModelWithContributions

hex.genmodel.algos.gbm.GbmMojoModel

All Implemented Interfaces:

PlattScalingMojoHelper.MojoModelWithCalibration, SharedTreeGraphConverter, TreeBackedMojoModel, IGenModel, PredictContributionsFactory, java.io.Serializable, IGeneratedModel

public final class GbmMojoModel
extends SharedTreeMojoModelWithContributions
implements SharedTreeGraphConverter

"Gradient Boosting Machine" MojoModel

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class hex.genmodel.algos.tree.SharedTreeMojoModelWithContributions

SharedTreeMojoModelWithContributions.SharedTreeContributionsPredictor

Nested classes/interfaces inherited from class hex.genmodel.algos.tree.SharedTreeMojoModel

SharedTreeMojoModel.DecisionPathTracker<T>, SharedTreeMojoModel.LeafDecisionPathTracker, SharedTreeMojoModel.LeafNodeAssignments, SharedTreeMojoModel.StringDecisionPathTracker

Field Summary

Fields

Modifier and Type	Field and Description
DistributionFamily	_family
double	_init_f
LinkFunctionType	_link_function

Fields inherited from class hex.genmodel.algos.tree.SharedTreeMojoModel

_calib_glm_beta, _compressed_trees, _compressed_trees_aux, _ntree_groups, _ntrees_per_group, _variable_importances

Fields inherited from class hex.genmodel.MojoModel

_algoName, _balanceClasses, _category, _defaultThreshold, _h2oVersion, _modelAttributes, _modelClassDistrib, _modelDescriptor, _mojo_version, _nclasses, _nfeatures, _priorClassDistrib, _supervised, _uuid

Fields inherited from class hex.genmodel.GenModel

_domains, _names, _offsetColumn, _responseColumn

Constructor Summary

Constructors

Constructor and Description
GbmMojoModel(java.lang.String[] columns, java.lang.String[][] domains, java.lang.String responseColumn)

Method Summary

Modifier and Type	Method and Description
static double	exp(double x) Sanitized exponential function - helper function.
protected PredictContributions	getContributionsPredictor(TreeSHAPPredictor<double[]> treeSHAPPredictor)
double	getInitF()
java.lang.String[]	leaf_node_assignment(double[] row)
static double	log(double x) Sanitized log function - helper function Be careful if you are changing code here - you have to change it in hex.LogExpUtils too
double[]	score0(double[] row, double[] preds) Subclasses implement the scoring logic.
double[]	score0(double[] row, double offset, double[] preds) Corresponds to `hex.tree.gbm.GbmMojoModel.score0()`
double[]	unifyPreds(double[] row, double offset, double[] preds) Transforms tree predictions into the final model predictions.

Methods inherited from class hex.genmodel.algos.tree.SharedTreeMojoModelWithContributions

makeContributionsPredictor

Methods inherited from class hex.genmodel.algos.tree.SharedTreeMojoModel

_computeGraph, calibrateClassProbabilities, computeGraph, computeGraph, computeTreeGraph, computeTreeGraph, convert, convert, getCalibGlmBeta, getDecisionPath, getDecisionPath, getDecisionPath, getDecisionPathNames, getLeafNodeAssignments, getLeafNodeId, getNTreeGroups, getNTreesPerGroup, postInit, scoreAllTrees, scoreSingleTree, scoreStagedPredictions, scoreTree, scoreTree, scoreTree0, scoreTree0, scoreTree1, scoreTree1, scoreTreeRange, treeName

Methods inherited from class hex.genmodel.MojoModel

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

Methods inherited from class hex.genmodel.GenModel

bitSetContains, bitSetIsInRange, convertDouble2Float, correctProbabilities, createAuxKey, features, GBM_rescale, getCategoricalEncoding, getColIdx, getDomainValues, getDomainValues, getDomainValues, getHeader, getModelCategories, getNames, getNumClasses, getNumCols, getNumResponseClasses, getOffsetName, getOrigDomainValues, getOrigNames, getOrigNumCols, getPrediction, getPredsSize, getPredsSize, getResponseIdx, getResponseName, GLM_identityInv, GLM_inverseInv, GLM_logInv, GLM_logitInv, GLM_ologitInv, GLM_tweedieInv, img2pixels, isAutoEncoder, isClassifier, KMeans_closest, KMeans_distance, KMeans_distance, KMeans_distances, Kmeans_preprocessData, Kmeans_preprocessData, KMeans_simplex, log_rescale, mapEnum, nCatFeatures, requiresOffset, setCats, setCats, setInput, setInput

Methods inherited from class java.lang.Object

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

Methods inherited from interface hex.genmodel.algos.tree.SharedTreeGraphConverter

convert, convert

Field Detail

_family

public DistributionFamily _family

_link_function

public LinkFunctionType _link_function

_init_f

public double _init_f

Constructor Detail

GbmMojoModel

public GbmMojoModel(java.lang.String[] columns,
                    java.lang.String[][] domains,
                    java.lang.String responseColumn)

Method Detail

getContributionsPredictor

protected PredictContributions getContributionsPredictor(TreeSHAPPredictor<double[]> treeSHAPPredictor)

Specified by:

getContributionsPredictor in class SharedTreeMojoModelWithContributions

getInitF

public double getInitF()

Specified by:

getInitF in interface TreeBackedMojoModel

Overrides:

getInitF in class SharedTreeMojoModelWithContributions

score0

public final double[] score0(double[] row,
                             double offset,
                             double[] preds)

Corresponds to `hex.tree.gbm.GbmMojoModel.score0()`

Overrides:

score0 in class GenModel

unifyPreds

public final double[] unifyPreds(double[] row,
                                 double offset,
                                 double[] preds)

Description copied from class: SharedTreeMojoModel

Transforms tree predictions into the final model predictions. For classification: converts tree preds into probability distribution and picks predicted class. For regression: projects tree prediction from link-space into the original space.

Specified by:

unifyPreds in class SharedTreeMojoModel

Parameters:

row - input row.

offset - offset.

preds - final output, same structure as of GenModel.score0(double[], double[]).

Returns:

preds array.

exp

public static double exp(double x)

Sanitized exponential function - helper function. Be careful if you are changing code here - you have to change it in hex.LogExpUtils too

Parameters:

x - value to be transform

Returns:

result of exp function

log

public static double log(double x)

Sanitized log function - helper function Be careful if you are changing code here - you have to change it in hex.LogExpUtils too

Parameters:

x - value to be transform

Returns:

result of log function

score0

public double[] score0(double[] row,
                       double[] preds)

Description copied from class: GenModel

Subclasses implement the scoring logic. The data is pre-loaded into a re-used temp array, in the order the model expects. The predictions are loaded into the re-used temp array, which is also returned. This call exactly matches the hex.Model.score0, but uses the light-weight GenModel class.

Specified by:

score0 in class GenModel

leaf_node_assignment

public java.lang.String[] leaf_node_assignment(double[] row)