water.bindings.pojos

Class PSVMParametersV3

java.lang.Object

water.bindings.pojos.SchemaV3

water.bindings.pojos.ModelParametersSchemaV3

water.bindings.pojos.PSVMParametersV3

public class PSVMParametersV3
extends ModelParametersSchemaV3

Field Summary

Fields

Modifier and Type	Field and Description
boolean	disableTrainingMetrics Disable calculating training metrics (expensive on large datasets)
double	factThreshold Convergence threshold of the Incomplete Cholesky Factorization (ICF)
double	feasibleThreshold Convergence threshold for primal-dual residuals in the IPM iteration
double	gamma Coefficient of the kernel (currently RBF gamma for gaussian kernel, -1 means 1/#features)
double	hyperParam Penalty parameter C of the error term
GenmodelalgospsvmKernelType	kernelType Type of used kernel
int	maxIterations Maximum number of iteration of the algorithm
double	muFactor Increasing factor mu
double	negativeWeight Weight of positive (-1) class of observations
double	positiveWeight Weight of positive (+1) class of observations
double	rankRatio Desired rank of the ICF matrix expressed as an ration of number of input rows (-1 means use sqrt(#rows)).
long	seed Seed for pseudo random number generator (if applicable)
double	surrogateGapThreshold Feasibility criterion of the surrogate duality gap (eta)
double	svThreshold Threshold for accepting a candidate observation into the set of support vectors

Fields inherited from class water.bindings.pojos.ModelParametersSchemaV3

aucType, categoricalEncoding, checkpoint, customDistributionFunc, customMetricFunc, distribution, exportCheckpointsDir, foldAssignment, foldColumn, gainsliftBins, huberAlpha, ignoreConstCols, ignoredColumns, keepCrossValidationFoldAssignment, keepCrossValidationModels, keepCrossValidationPredictions, maxCategoricalLevels, maxRuntimeSecs, modelId, nfolds, offsetColumn, parallelizeCrossValidation, quantileAlpha, responseColumn, scoreEachIteration, stoppingMetric, stoppingRounds, stoppingTolerance, trainingFrame, tweediePower, validationFrame, weightsColumn

Constructor Summary

Constructors

Constructor and Description
PSVMParametersV3() Public constructor

Method Summary

Modifier and Type	Method and Description
java.lang.String	toString() Return the contents of this object as a JSON String.

Methods inherited from class java.lang.Object

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

Field Detail

hyperParam

@SerializedName(value="hyper_param")
public double hyperParam

Penalty parameter C of the error term

kernelType

@SerializedName(value="kernel_type")
public GenmodelalgospsvmKernelType kernelType

Type of used kernel

gamma

public double gamma

Coefficient of the kernel (currently RBF gamma for gaussian kernel, -1 means 1/#features)

rankRatio

@SerializedName(value="rank_ratio")
public double rankRatio

Desired rank of the ICF matrix expressed as an ration of number of input rows (-1 means use sqrt(#rows)).

positiveWeight

@SerializedName(value="positive_weight")
public double positiveWeight

Weight of positive (+1) class of observations

negativeWeight

@SerializedName(value="negative_weight")
public double negativeWeight

Weight of positive (-1) class of observations

disableTrainingMetrics

@SerializedName(value="disable_training_metrics")
public boolean disableTrainingMetrics

Disable calculating training metrics (expensive on large datasets)

svThreshold

@SerializedName(value="sv_threshold")
public double svThreshold

Threshold for accepting a candidate observation into the set of support vectors

maxIterations

@SerializedName(value="max_iterations")
public int maxIterations

Maximum number of iteration of the algorithm

factThreshold

@SerializedName(value="fact_threshold")
public double factThreshold

Convergence threshold of the Incomplete Cholesky Factorization (ICF)

feasibleThreshold

@SerializedName(value="feasible_threshold")
public double feasibleThreshold

Convergence threshold for primal-dual residuals in the IPM iteration

surrogateGapThreshold

@SerializedName(value="surrogate_gap_threshold")
public double surrogateGapThreshold

Feasibility criterion of the surrogate duality gap (eta)

muFactor

@SerializedName(value="mu_factor")
public double muFactor

Increasing factor mu

seed

public long seed

Seed for pseudo random number generator (if applicable)

Constructor Detail

PSVMParametersV3

public PSVMParametersV3()

Public constructor

Method Detail

toString

public java.lang.String toString()

Return the contents of this object as a JSON String.

Overrides:

toString in class ModelParametersSchemaV3