water.bindings.pojos

Class PCAParametersV3

java.lang.Object

water.bindings.pojos.SchemaV3

water.bindings.pojos.ModelParametersSchemaV3

water.bindings.pojos.PCAParametersV3

public class PCAParametersV3
extends ModelParametersSchemaV3

Field Summary

Fields

Modifier and Type	Field and Description
boolean	computeMetrics Whether to compute metrics on the training data
boolean	imputeMissing Whether to impute missing entries with the column mean
int	k Rank of matrix approximation
int	maxIterations Maximum training iterations
PCAImplementation	pcaImpl Specify the implementation to use for computing PCA (via SVD or EVD): MTJ_EVD_DENSEMATRIX - eigenvalue decompositions for dense matrix using MTJ; MTJ_EVD_SYMMMATRIX - eigenvalue decompositions for symmetric matrix using MTJ; MTJ_SVD_DENSEMATRIX - singular-value decompositions for dense matrix using MTJ; JAMA - eigenvalue decompositions for dense matrix using JAMA.
PCAMethod	pcaMethod Specify the algorithm to use for computing the principal components: GramSVD - uses a distributed computation of the Gram matrix, followed by a local SVD; Power - computes the SVD using the power iteration method (experimental); Randomized - uses randomized subspace iteration method; GLRM - fits a generalized low-rank model with L2 loss function and no regularization and solves for the SVD using local matrix algebra (experimental)
long	seed RNG seed for initialization
DataInfoTransformType	transform Transformation of training data
boolean	useAllFactorLevels Whether first factor level is included in each categorical expansion

Fields inherited from class water.bindings.pojos.ModelParametersSchemaV3

categoricalEncoding, checkpoint, customMetricFunc, distribution, exportCheckpointsDir, foldAssignment, foldColumn, 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
PCAParametersV3() 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

transform

public DataInfoTransformType transform

Transformation of training data

pcaMethod

@SerializedName(value="pca_method")
public PCAMethod pcaMethod

Specify the algorithm to use for computing the principal components: GramSVD - uses a distributed computation of the Gram matrix, followed by a local SVD; Power - computes the SVD using the power iteration method (experimental); Randomized - uses randomized subspace iteration method; GLRM - fits a generalized low-rank model with L2 loss function and no regularization and solves for the SVD using local matrix algebra (experimental)

pcaImpl

@SerializedName(value="pca_impl")
public PCAImplementation pcaImpl

Specify the implementation to use for computing PCA (via SVD or EVD): MTJ_EVD_DENSEMATRIX - eigenvalue decompositions for dense matrix using MTJ; MTJ_EVD_SYMMMATRIX - eigenvalue decompositions for symmetric matrix using MTJ; MTJ_SVD_DENSEMATRIX - singular-value decompositions for dense matrix using MTJ; JAMA - eigenvalue decompositions for dense matrix using JAMA. References: JAMA - http://math.nist.gov/javanumerics/jama/; MTJ - https://github.com/fommil/matrix-toolkits-java/

k

public int k

Rank of matrix approximation

maxIterations

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

Maximum training iterations

seed

public long seed

RNG seed for initialization

useAllFactorLevels

@SerializedName(value="use_all_factor_levels")
public boolean useAllFactorLevels

Whether first factor level is included in each categorical expansion

computeMetrics

@SerializedName(value="compute_metrics")
public boolean computeMetrics

Whether to compute metrics on the training data

imputeMissing

@SerializedName(value="impute_missing")
public boolean imputeMissing

Whether to impute missing entries with the column mean

Constructor Detail

PCAParametersV3

public PCAParametersV3()

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