ai.h2o.automl.preprocessing

Class TargetEncoding

java.lang.Object

ai.h2o.automl.preprocessing.TargetEncoding

All Implemented Interfaces:

PreprocessingStep

public class TargetEncoding
extends java.lang.Object
implements PreprocessingStep

Nested Class Summary

Nested classes/interfaces inherited from interface ai.h2o.automl.preprocessing.PreprocessingStep

PreprocessingStep.Completer

Field Summary

Fields

Modifier and Type	Field and Description
static java.lang.String	CONFIG_ENABLED
static java.lang.String	CONFIG_PREPARE_CV_ONLY

Constructor Summary

Constructors

Constructor and Description
TargetEncoding(AutoML aml)

Method Summary

Modifier and Type	Method and Description
PreprocessingStep.Completer	apply(hex.Model.Parameters params, PreprocessingConfig config) applies this preprocessing step to the model parameters right before the model training starts.
static water.fvec.Vec	createFoldColumn(water.fvec.Frame fr, hex.Model.Parameters.FoldAssignmentScheme fold_assignment, int nfolds, java.lang.String responseColumn, long seed)
void	dispose() preprocessing steps are disposed by default at the end of the AutoML training session.
java.lang.String	getType()
void	prepare() preprocessing steps are prepared by default before the AutoML session starts training the first model.
void	remove() Completely remove from the system
void	setColumnCardinalityThreshold(int threshold)
void	setDefaultParams(ai.h2o.targetencoding.TargetEncoderModel.TargetEncoderParameters defaultParams)
void	setEncodeAllColumns(boolean encodeAllColumns)

Methods inherited from class java.lang.Object

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

Field Detail

CONFIG_ENABLED

public static java.lang.String CONFIG_ENABLED

CONFIG_PREPARE_CV_ONLY

public static java.lang.String CONFIG_PREPARE_CV_ONLY

Constructor Detail

TargetEncoding

public TargetEncoding(AutoML aml)

Method Detail

getType

public java.lang.String getType()

Specified by:

getType in interface PreprocessingStep

prepare

public void prepare()

Description copied from interface: PreprocessingStep

preprocessing steps are prepared by default before the AutoML session starts training the first model.

Specified by:

prepare in interface PreprocessingStep

apply

public PreprocessingStep.Completer apply(hex.Model.Parameters params,
                                         PreprocessingConfig config)

Description copied from interface: PreprocessingStep

applies this preprocessing step to the model parameters right before the model training starts.

Specified by:

apply in interface PreprocessingStep

Returns:

a function used to "complete" the preprocessing step: it is called by default at the end of the job creating model(s) from the given parms. This can mean for example cleaning the temporary artifacts that may have been created to apply the preprocessing step.

dispose

public void dispose()

Description copied from interface: PreprocessingStep

preprocessing steps are disposed by default at the end of the AutoML training session. Note that disposing here doesn't mean being removed from the system, the goal is mainly to clean resources that are not needed anymore for the current AutoML run.

Specified by:

dispose in interface PreprocessingStep

remove

public void remove()

Description copied from interface: PreprocessingStep

Completely remove from the system

Specified by:

remove in interface PreprocessingStep

setDefaultParams

public void setDefaultParams(ai.h2o.targetencoding.TargetEncoderModel.TargetEncoderParameters defaultParams)

setEncodeAllColumns

public void setEncodeAllColumns(boolean encodeAllColumns)

setColumnCardinalityThreshold

public void setColumnCardinalityThreshold(int threshold)

createFoldColumn

public static water.fvec.Vec createFoldColumn(water.fvec.Frame fr,
                                              hex.Model.Parameters.FoldAssignmentScheme fold_assignment,
                                              int nfolds,
                                              java.lang.String responseColumn,
                                              long seed)