TranRegression2

scalation.modeling.TranRegression2
See theTranRegression2 companion class

The TranRegression2 companion object provides transformation and inverse transformation function based on the parameter λ. It support the family of Box-Cox and Yeo-Johnson Transformations.

Attributes

Companion
class
Graph
Supertypes
class Object
trait Matchable
class Any
Self type

Members list

Value members

Concrete methods

def `λ_=`(`λ_`: Double): Unit
def app_yj(x: MatrixD, y: VectorD, fname: Array[String] = ..., hparam: HyperParameter = ...): TranRegression2

Create a TranRegression2 object that uses a Yeo-Johnson Transformation. To change λ from its default value, call set_lambda first.

Create a TranRegression2 object that uses a Yeo-Johnson Transformation. To change λ from its default value, call set_lambda first.

Value parameters

fname

the feature/variable names (defaults to null)

hparam

the hyper-parameters (defaults to Regression.hp)

x

the data/input matrix

y

the response/output vector

Attributes

def apply(x: MatrixD, y: VectorD, fname: Array[String] = ..., hparam: HyperParameter = ...): TranRegression2

Create a TranRegression2 object that uses a Box-Cox Transformation. To change λ from its default value, call setter first.

Create a TranRegression2 object that uses a Box-Cox Transformation. To change λ from its default value, call setter first.

Value parameters

fname

the feature/variable names (defaults to null)

hparam

the hyper-parameters (defaults to Regression.hp)

x

the data/input matrix

y

the response/output vector

Attributes

def apply(xy: MatrixD, fname: Array[String], hparam: HyperParameter, tran: FunctionS2S, itran: FunctionS2S, bounds: (Double, Double)): TranRegression2

Create a TranRegression2 with automatic rescaling from a combined data matrix.

Create a TranRegression2 with automatic rescaling from a combined data matrix.

Value parameters

bounds

the bounds for rescaling

fname

the feature/variable names

hparam

the hyper-parameters

itran

the inverse transformation function to rescale predictions to original y scale

tran

the transformation function

xy

the combined data/input and response/output matrix

Attributes

def apply(x: MatrixD, y: VectorD, fname: Array[String], hparam: HyperParameter, tran: FunctionS2S, itran: FunctionS2S, bounds: (Double, Double)): TranRegression2

Create a TranRegression2 with automatic rescaling from a data matrix and response vector.

Create a TranRegression2 with automatic rescaling from a data matrix and response vector.

Value parameters

bounds

the bounds for rescaling

fname

the feature/variable names

hparam

the hyper-parameters

itran

the inverse transformation function to rescale predictions to original y scale

tran

the transformation function (defaults to log)

x

the data/input matrix

y

the response/output vector

Attributes

def box_cox(y: Double): Double

Transform y using the Box-Cox transformation.

Transform y using the Box-Cox transformation.

Value parameters

y

the value to be transformed

Attributes

def cox_box(z: Double): Double

Inverse transform z using the Box-Cox transformation.

Inverse transform z using the Box-Cox transformation.

Value parameters

z

the value to be inverse transformed

Attributes

def john_yeo(z: Double): Double

Inverse transform z using the Yeo-Johnson transformation.

Inverse transform z using the Yeo-Johnson transformation.

Value parameters

z

the value to be inverse transformed

Attributes

def yeo_john(y: Double): Double

Transform y using the Yeo-Johnson transformation.

Transform y using the Yeo-Johnson transformation.

Value parameters

y

the value to be transformed

Attributes

inline def λ: Double