Abstract input transformation class.
An input transformation can be used within a Surrogate to perform a transformation of the feature variables.
See also
Other Input Transformation:
InputTrafoUnitcube
,
mlr_input_trafos
Active bindings
label
(
character(1)
)
Label for this object.man
(
character(1)
)
String in the format[pkg]::[topic]
pointing to a manual page for this object.packages
(
character()
)
Set of required packages. A warning is signaled if at least one of the packages is not installed, but loaded (not attached) later on-demand viarequireNamespace()
.state
(named
list()
|NULL
)
List of meta information regarding the parameters and their state.search_space
(paradox::ParamSet)
Search space.cols_x
(paradox::ParamSet)
Column ids of feature variables that should be transformed.
Methods
Method new()
Creates a new instance of this R6 class.
Usage
InputTrafo$new(label = NA_character_, man = NA_character_)
Method update()
Learn the transformation based on observed data and update parameters in $state
.
Must be implemented by subclasses.
Arguments
xdt
(
data.table::data.table()
)
Data. One row per observation with at least columns$cols_x
.
Method transform()
Perform the transformation. Must be implemented by subclasses.
Arguments
xdt
(
data.table::data.table()
)
Data. One row per observation with at least columns$cols_x
.
Returns
data.table::data.table()
with the transformation applied to the columns $cols_x
(if applicable) or a subset thereof.