ParamHelpers (version 1.7)

LearnerParam: Create a description object for a parameter of a machine learning algorithm.

Description

This specializes Param by adding a few more attributes, like a default value, whether it refers to a training or a predict function, etc.

Usage

makeNumericLearnerParam(id, lower = -Inf, upper = Inf, allow.inf = FALSE, default, when = "train", requires = NULL, tunable = TRUE)
makeNumericVectorLearnerParam(id, len = as.integer(NA), lower = -Inf, upper = Inf, allow.inf = FALSE, default, when = "train", requires = NULL, tunable = TRUE)
makeIntegerLearnerParam(id, lower = -Inf, upper = Inf, default, when = "train", requires = NULL, tunable = TRUE)
makeIntegerVectorLearnerParam(id, len = as.integer(NA), lower = -Inf, upper = Inf, default, when = "train", requires = NULL, tunable = TRUE)
makeDiscreteLearnerParam(id, values, default, when = "train", requires = NULL, tunable = TRUE)
makeDiscreteVectorLearnerParam(id, len = as.integer(NA), values, default, when = "train", requires = NULL, tunable = TRUE)
makeLogicalLearnerParam(id, default, when = "train", requires = NULL, tunable = TRUE)
makeLogicalVectorLearnerParam(id, len = as.integer(NA), default, when = "train", requires = NULL, tunable = TRUE)
makeUntypedLearnerParam(id, default, when = "train", requires = NULL, tunable = TRUE)
makeFunctionLearnerParam(id, default, when = "train", requires = NULL)

Arguments

id

[character(1)] See Param.

lower

[numeric] See Param.

upper

[numeric] See Param.

allow.inf

[logical(1)] See Param.

default

[any] See Param.

when

[character(1)] Specifies when parameter is used in the learner: “train”, “predict” or “both”. Default is “train”.

requires

[NULL | R expression] See Param.

tunable

[logical(1)] See Param.

len

[integer(1)] See Param.

values

[vector | list] See Param.

Value

[LearnerParam].

Details

The S3 class is a Param which additionally stores these elements:

default [any]

See argument of same name.

has.default [logical(1)]

Was a default value provided?

when [character(1)]

See argument of same name.