Facemorph.Stats
Class sPLSSVD_DWH

java.lang.Object
  Facemorph.Stats.PLSReducer
      Facemorph.Stats.sPLSSVD_DWH

All Implemented Interfaces:

IniHandler, DataReducer, Regressor, StatisticalModel

public class sPLSSVD_DWH
extends PLSReducer

A version of Le Cao's algorithm modified to be sparse on the patches not on patch

Nested Class Summary

Nested classes/interfaces inherited from interface Facemorph.Stats.DataReducer

DataReducer.DataReducerInformation

Nested classes/interfaces inherited from interface Facemorph.Stats.Regressor

Regressor.RegressorException

Field Summary

Fields inherited from class Facemorph.Stats.PLSReducer

B, c, C, E, epsilon, F, maxComponents, maxIter, meanX, meanY, noComponents, p, P, q, R, stdX, stdY, t, T, targetDependentVariance, targetIndependentVariance, u, U, varX, varY, w, W, X, Y

Constructor Summary

sPLSSVD_DWH()

Method Summary

protected double[]	calcG(double[] vec, int nonZero)
protected double	computeLambda(double[] vec, int noNonZero)
boolean	train(boolean stats) Perform multi-linear regression using the Ordinary Least Squares method.

Methods inherited from class Facemorph.Stats.PLSReducer

apply, build, center, getBasisMatrix, getEpsilon, getInputDimensions, getModelInformation, getModelInformation, getOutputDimensions, getSumSquaredResiduals, getTargetDependentVariance, getTargetIndpendentVariance, initialise, iterate, iterate, main, outputStatistics, outputStatistics, predict, print, read, read, reconstructDependent, reconstructDependent, reconstructIndependent, reconstructIndependent, reduceDependent, reduceDependent, reduceIndependent, reduceIndependent, setDependentData, setDependentData, setEpsilon, setIndependentData, setOutputDimensions, setTargetDependentVariance, setTargetIndependentVariance, setTargetKaiserGuttman, write, write, write

Methods inherited from class java.lang.Object

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

Constructor Detail

sPLSSVD_DWH

public sPLSSVD_DWH()

Method Detail

train

public boolean train(boolean stats)

Description copied from interface: StatisticalModel

Perform multi-linear regression using the Ordinary Least Squares method. Solves y = XB + e using b = inv(X'X)X'y

Specified by:

train in interface StatisticalModel

Overrides:

train in class PLSReducer

Parameters:

stats - calculate values for statistical analysis

Returns:

true if the regression succeeds.

calcG

protected double[] calcG(double[] vec,
                         int nonZero)

computeLambda

protected double computeLambda(double[] vec,
                               int noNonZero)