SBCK (version 1.0.0)

PPPFunctionLink: PPPFunctionLink

Description

Base class to build link function pre-post processing class. See also the PrePostProcessing documentation

Super class

SBCK::PrePostProcessing -> PPPFunctionLink

Methods

Public methods

• PPPFunctionLink$new()

• PPPFunctionLink$transform()

• PPPFunctionLink$itransform()

• PPPFunctionLink$clone()

Inherited methods

• SBCK::PrePostProcessing$fit()
• SBCK::PrePostProcessing$predict()

---

Method new()

Create a new PPPFunctionLink object.

Usage

PPPFunctionLink$new(transform_, itransform_, cols = NULL, ...)

Arguments

transform_

The transform function

itransform_

The inverse transform function

cols

Columns to apply the link function

...

Others arguments are passed to PrePostProcessing

Returns

A new `PPPFunctionLink` object.

---

Method transform()

Apply the transform.

Usage

PPPFunctionLink$transform(X)

Arguments

X

Data to transform

Returns

Xt a transformed matrix

---

Method itransform()

Apply the inverse transform.

Usage

PPPFunctionLink$itransform(Xt)

Arguments

Xt

Data to transform

Returns

X a transformed matrix

---

Method clone()

The objects of this class are cloneable with this method.

Usage

PPPFunctionLink$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Details

This class is used to define pre/post processing class with a link function and its inverse. See example.

Examples

## Start with data
XY = SBCK::dataset_like_tas_pr(2000)
X0 = XY$X0
X1 = XY$X1
Y0 = XY$Y0

## Define the link function
transform  = function(x) { return(x^3) }
itransform = function(x) { return(x^(1/3)) }

## And the PPP method
ppp = PPPFunctionLink$new( bc_method = CDFt , transform = transform ,
                                             itransform = itransform )

## And now the correction
## Bias correction
ppp$fit(Y0,X0,X1)
Z = ppp$predict(X1,X0)