Learn R Programming
mlr3fda (version 0.3.0)

mlr_pipeops_fda.wavelets: Discrete Wavelet transform features

Description

This PipeOp extracts discrete wavelet transform coefficients from functional columns. For more details, see wavelets::dwt(), which is called internally.

Arguments

Parameters

The parameters are the parameters inherited from PipeOpTaskPreprocSimple, as well as the following parameters:

  • filter :: character(1) | numeric() | wavelets::wt.filter()
    Specifies which filter should be used. Must be either wavelets::wt.filter() object, an even numeric vector or a string. In case of a string must be one of "d"|"la"|"bl"|"c" followed by an even number for the level of the filter. The level of the filter needs to be smaller or equal then the time-series length. For more information and acceptable filters see help(wt.filter). Defaults to "la8".

  • n.levels :: integer(1)
    An integer specifying the level of the decomposition.

  • boundary :: character(1)
    Boundary to be used. "periodic" assumes circular time series, for "reflection" the series is extended to twice its length. Default is "periodic".

  • fast :: logical(1)
    Should the pyramid algorithm be calculated with an internal C function? Default is TRUE.

Super classes

mlr3pipelines::PipeOp -> mlr3pipelines::PipeOpTaskPreproc -> mlr3pipelines::PipeOpTaskPreprocSimple -> PipeOpFDAWavelets

Methods

Inherited methods

Method new()

Initializes a new instance of this Class.

Usage

PipeOpFDAWavelets$new(id = "fda.wavelets", param_vals = list())

Arguments

id

(character(1))
Identifier of resulting object, default is "fda.wavelets".

param_vals

(named list())
List of hyperparameter settings, overwriting the hyperparameter settings that would otherwise be set during construction. Default list().

Method clone()

The objects of this class are cloneable with this method.

Usage

PipeOpFDAWavelets$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

Run this code
task = tsk("fuel")
po_wavelets = po("fda.wavelets")
task_wavelets = po_wavelets$train(list(task))[[1L]]
task_wavelets$data()

Run the code above in your browser using DataLab