hex.glrm

Enum GlrmLoss

java.lang.Object

java.lang.Enum<GlrmLoss>

hex.glrm.GlrmLoss

All Implemented Interfaces:

java.io.Serializable, java.lang.Comparable<GlrmLoss>

public enum GlrmLoss
extends java.lang.Enum<GlrmLoss>

Loss function for the GLRM algorithm.

Enum Constant Summary

Enum Constants

Enum Constant and Description
Absolute
Categorical
Hinge
Huber
Logistic
Ordinal
Periodic
Poisson
Quadratic

Method Summary

Methods

Modifier and Type	Method and Description
double	impute(double u) \argmin_a L(u, a): Data imputation for real numeric values
abstract boolean	isForBinary()
abstract boolean	isForCategorical()
abstract boolean	isForNumeric()
double	lgrad(double u, double a) \grad_u L(u,a): Derivative of the numeric loss function with respect to u
double	loss(double u, double a) Loss function for numeric variables
int	mimpute(double[] u) \argmin_a L(u, a): Data imputation for categorical values {0, 1, 2, ...}
double[]	mlgrad(double[] u, int a) \grad_u L(u,a): Gradient of multidimensional loss function with respect to u
double	mloss(double[] u, int a) Loss function for categorical variables
void	setParameters(int p) Initialize additional parameters on the loss function.
static GlrmLoss	valueOf(java.lang.String name) Returns the enum constant of this type with the specified name.
static GlrmLoss[]	values() Returns an array containing the constants of this enum type, in the order they are declared.

Methods inherited from class java.lang.Enum

clone, compareTo, equals, finalize, getDeclaringClass, hashCode, name, ordinal, toString, valueOf

Methods inherited from class java.lang.Object

getClass, notify, notifyAll, wait, wait, wait

Enum Constant Detail

Quadratic

public static final GlrmLoss Quadratic

Absolute

public static final GlrmLoss Absolute

Huber

public static final GlrmLoss Huber

Poisson

public static final GlrmLoss Poisson

Periodic

public static final GlrmLoss Periodic

Logistic

public static final GlrmLoss Logistic

Hinge

public static final GlrmLoss Hinge

Categorical

public static final GlrmLoss Categorical

Ordinal

public static final GlrmLoss Ordinal

Method Detail

values

public static GlrmLoss[] values()

Returns an array containing the constants of this enum type, in the order they are declared. This method may be used to iterate over the constants as follows:

for (GlrmLoss c : GlrmLoss.values())
    System.out.println(c);

Returns:

an array containing the constants of this enum type, in the order they are declared

valueOf

public static GlrmLoss valueOf(java.lang.String name)

Returns the enum constant of this type with the specified name. The string must match exactly an identifier used to declare an enum constant in this type. (Extraneous whitespace characters are not permitted.)

Parameters:

name - the name of the enum constant to be returned.

Returns:

the enum constant with the specified name

Throws:

java.lang.IllegalArgumentException - if this enum type has no constant with the specified name

java.lang.NullPointerException - if the argument is null

isForNumeric

public abstract boolean isForNumeric()

isForCategorical

public abstract boolean isForCategorical()

isForBinary

public abstract boolean isForBinary()

loss

public double loss(double u,
          double a)

Loss function for numeric variables

lgrad

public double lgrad(double u,
           double a)

\grad_u L(u,a): Derivative of the numeric loss function with respect to u

impute

public double impute(double u)

\argmin_a L(u, a): Data imputation for real numeric values

mloss

public double mloss(double[] u,
           int a)

Loss function for categorical variables

mlgrad

public double[] mlgrad(double[] u,
              int a)

\grad_u L(u,a): Gradient of multidimensional loss function with respect to u

mimpute

public int mimpute(double[] u)

\argmin_a L(u, a): Data imputation for categorical values {0, 1, 2, ...}

setParameters

public void setParameters(int p)

Initialize additional parameters on the loss function. Currently used by Periodic class only.