hex.deepwater

Class DeepWater

java.lang.Object

water.Iced

hex.ModelBuilder<DeepWaterModel,DeepWaterParameters,DeepWaterModelOutput>

hex.deepwater.DeepWater

All Implemented Interfaces:

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

public class DeepWater
extends hex.ModelBuilder<DeepWaterModel,DeepWaterParameters,DeepWaterModelOutput>

Deep Learning Neural Net implementation based on MRTask

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
class	DeepWater.DeepWaterDriver

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
DeepWater(boolean startup_once)
DeepWater(DeepWaterParameters parms) Main constructor from Deep Learning parameters

Method Summary

Methods

Modifier and Type	Method and Description
hex.ModelBuilder.BuilderVisibility	builderVisibility()
hex.ModelCategory[]	can_build() Types of models we can build with DeepWater
void	cv_computeAndSetOptimalParameters(hex.ModelBuilder<DeepWaterModel,DeepWaterParameters,DeepWaterModelOutput>[] cvModelBuilders)
hex.ToEigenVec	getToEigenVec()
static boolean	haveBackend() Check whether we have any Deep Water native backends available
boolean	haveMojo()
boolean	havePojo()
protected boolean	ignoreStringColumns()
void	init(boolean expensive) Initialize the ModelBuilder, validating all arguments and preparing the training frame.
boolean	isSupervised()
protected int	nModelsInParallel()
protected DeepWater.DeepWaterDriver	trainModelImpl()

Methods inherited from class hex.ModelBuilder

algoName, algos, checkDistributions, checkMemoryFootPrint, clearInitState, clearValidationErrors, computeCrossValidation, computePriorClassDistribution, cv_AssignFold, cv_buildModels, cv_mainModelScores, cv_makeFramesAndBuilders, cv_makeWeights, cv_scoreCVModels, defaultKey, desiredChunks, dest, error_count, error, get, hasFoldCol, hasOffsetCol, hasWeightCol, hide, ignoreBadColumns, ignoreConstColumns, ignoreInvalidColumns, 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

DeepWater

public DeepWater(DeepWaterParameters parms)

Main constructor from Deep Learning parameters

DeepWater

public DeepWater(boolean startup_once)

Method Detail

haveBackend

public static boolean haveBackend()

Check whether we have any Deep Water native backends available

builderVisibility

public hex.ModelBuilder.BuilderVisibility builderVisibility()

Overrides:

builderVisibility in class hex.ModelBuilder<DeepWaterModel,DeepWaterParameters,DeepWaterModelOutput>

can_build

public hex.ModelCategory[] can_build()

Types of models we can build with DeepWater

Specified by:

can_build in class hex.ModelBuilder<DeepWaterModel,DeepWaterParameters,DeepWaterModelOutput>

haveMojo

public boolean haveMojo()

Overrides:

haveMojo in class hex.ModelBuilder<DeepWaterModel,DeepWaterParameters,DeepWaterModelOutput>

havePojo

public boolean havePojo()

Overrides:

havePojo in class hex.ModelBuilder<DeepWaterModel,DeepWaterParameters,DeepWaterModelOutput>

getToEigenVec

public hex.ToEigenVec getToEigenVec()

Overrides:

getToEigenVec in class hex.ModelBuilder<DeepWaterModel,DeepWaterParameters,DeepWaterModelOutput>

isSupervised

public boolean isSupervised()

Specified by:

isSupervised in class hex.ModelBuilder<DeepWaterModel,DeepWaterParameters,DeepWaterModelOutput>

nModelsInParallel

protected int nModelsInParallel()

Overrides:

nModelsInParallel in class hex.ModelBuilder<DeepWaterModel,DeepWaterParameters,DeepWaterModelOutput>

trainModelImpl

protected DeepWater.DeepWaterDriver trainModelImpl()

Specified by:

trainModelImpl in class hex.ModelBuilder<DeepWaterModel,DeepWaterParameters,DeepWaterModelOutput>

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 very large number of arguments in the DL Parameter directly.

Overrides:

init in class hex.ModelBuilder<DeepWaterModel,DeepWaterParameters,DeepWaterModelOutput>

ignoreStringColumns

protected boolean ignoreStringColumns()

Overrides:

ignoreStringColumns in class hex.ModelBuilder<DeepWaterModel,DeepWaterParameters,DeepWaterModelOutput>

cv_computeAndSetOptimalParameters

public void cv_computeAndSetOptimalParameters(hex.ModelBuilder<DeepWaterModel,DeepWaterParameters,DeepWaterModelOutput>[] cvModelBuilders)

Overrides:

cv_computeAndSetOptimalParameters in class hex.ModelBuilder<DeepWaterModel,DeepWaterParameters,DeepWaterModelOutput>