hex.tree.xgboost

Class XGBoost

java.lang.Object

water.Iced

hex.ModelBuilder<XGBoostModel,XGBoostModel.XGBoostParameters,XGBoostOutput>

hex.tree.xgboost.XGBoost

All Implemented Interfaces:

java.io.Externalizable, java.io.Serializable, java.lang.Cloneable, water.Freezable

public class XGBoost
extends hex.ModelBuilder<XGBoostModel,XGBoostModel.XGBoostParameters,XGBoostOutput>

Gradient Boosted Trees Based on "Elements of Statistical Learning, Second Edition, page 387"

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class hex.ModelBuilder

hex.ModelBuilder.BuilderVisibility, hex.ModelBuilder.Driver, hex.ModelBuilder.FilterCols, hex.ModelBuilder.ValidationMessage

Field Summary

Fields inherited from class hex.ModelBuilder

_fold, _job, _messages, _nclass, _offset, _origDomains, _origNames, _parms, _priorClassDist, _removedCols, _response, _result, _train, _valid, _vresponse, _weights

Constructor Summary

Constructors

Constructor and Description
XGBoost(boolean startup_once)
XGBoost(XGBoostModel.XGBoostParameters parms)
XGBoost(XGBoostModel.XGBoostParameters parms, water.Key<XGBoostModel> key)

Method Summary

Methods

Modifier and Type	Method and Description
hex.ModelBuilder.BuilderVisibility	builderVisibility()
hex.ModelCategory[]	can_build()
static ml.dmlc.xgboost4j.java.DMatrix	convertFrametoDMatrix(water.Key<hex.DataInfo> dataInfoKey, water.fvec.Frame f, java.lang.String response, java.lang.String weight, java.lang.String fold, java.lang.String[] featureMap, boolean sparse) convert an H2O Frame to a sparse DMatrix
static int	countUnique(int[] unsortedArray)
boolean	haveMojo()
void	init(boolean expensive) Initialize the ModelBuilder, validating all arguments and preparing the training frame.
boolean	isSupervised()
protected int	nModelsInParallel()
protected hex.tree.xgboost.XGBoost.XGBoostDriver	trainModelImpl() Start the XGBoost training Job on an F/J thread.

Methods inherited from class hex.ModelBuilder

algoName, algos, bulkBuildModels, checkDistributions, checkMemoryFootPrint_impl, checkMemoryFootPrint, clearInitState, clearValidationErrors, computeCrossValidation, computePriorClassDistribution, cv_AssignFold, cv_buildModels, cv_computeAndSetOptimalParameters, cv_mainModelScores, cv_makeFramesAndBuilders, cv_makeWeights, cv_scoreCVModels, defaultKey, desiredChunks, dest, error_count, error, get, getToEigenVec, hasFoldCol, hasOffsetCol, hasWeightCol, haveMojo, havePojo, havePojo, hide, ignoreBadColumns, ignoreConstColumns, ignoreInvalidColumns, ignoreStringColumns, info, init_adaptFrameToTrain, isClassifier, isStopped, javaName, logMe, make, message, nclasses, nFoldCV, nFoldWork, numSpecialCols, paramName, rebalance, response, schemaDirectory, separateFeatureVecs, setTrain, shouldReorder, specialColNames, stop_requested, timeout, train, trainModel, trainModelNested, valid, validationErrors, vresponse, warn

Methods inherited from class water.Iced

asBytes, clone, copyOver, frozenType, read, readExternal, readJSON, reloadFromBytes, toJsonString, write, writeExternal, writeJSON

Methods inherited from class java.lang.Object

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

Constructor Detail

XGBoost

public XGBoost(XGBoostModel.XGBoostParameters parms)

XGBoost

public XGBoost(XGBoostModel.XGBoostParameters parms,
       water.Key<XGBoostModel> key)

XGBoost

public XGBoost(boolean startup_once)

Method Detail

haveMojo

public boolean haveMojo()

Overrides:

haveMojo in class hex.ModelBuilder<XGBoostModel,XGBoostModel.XGBoostParameters,XGBoostOutput>

builderVisibility

public hex.ModelBuilder.BuilderVisibility builderVisibility()

Overrides:

builderVisibility in class hex.ModelBuilder<XGBoostModel,XGBoostModel.XGBoostParameters,XGBoostOutput>

convertFrametoDMatrix

public static ml.dmlc.xgboost4j.java.DMatrix convertFrametoDMatrix(water.Key<hex.DataInfo> dataInfoKey,
                                                   water.fvec.Frame f,
                                                   java.lang.String response,
                                                   java.lang.String weight,
                                                   java.lang.String fold,
                                                   java.lang.String[] featureMap,
                                                   boolean sparse)
                                                            throws ml.dmlc.xgboost4j.java.XGBoostError

convert an H2O Frame to a sparse DMatrix

Parameters:

f - H2O Frame

response - name of the response column

weight - name of the weight column

fold - name of the fold assignment column

featureMap - featureMap[0] will be populated with the column names and types

Returns:

DMatrix

Throws:

ml.dmlc.xgboost4j.java.XGBoostError

can_build

public hex.ModelCategory[] can_build()

Specified by:

can_build in class hex.ModelBuilder<XGBoostModel,XGBoostModel.XGBoostParameters,XGBoostOutput>

isSupervised

public boolean isSupervised()

Specified by:

isSupervised in class hex.ModelBuilder<XGBoostModel,XGBoostModel.XGBoostParameters,XGBoostOutput>

nModelsInParallel

protected int nModelsInParallel()

Overrides:

nModelsInParallel in class hex.ModelBuilder<XGBoostModel,XGBoostModel.XGBoostParameters,XGBoostOutput>

trainModelImpl

protected hex.tree.xgboost.XGBoost.XGBoostDriver trainModelImpl()

Start the XGBoost training Job on an F/J thread.

Specified by:

trainModelImpl in class hex.ModelBuilder<XGBoostModel,XGBoostModel.XGBoostParameters,XGBoostOutput>

init

public void init(boolean expensive)

Initialize the ModelBuilder, validating all arguments and preparing the training frame. This call is expected to be overridden in the subclasses and each subclass will start with "super.init();". This call is made by the front-end whenever the GUI is clicked, and needs to be fast; heavy-weight prep needs to wait for the trainModel() call. Validate the learning rate and distribution family.

Overrides:

init in class hex.ModelBuilder<XGBoostModel,XGBoostModel.XGBoostParameters,XGBoostOutput>

countUnique

public static int countUnique(int[] unsortedArray)