getPreProcessor: getPreProcessor

In MarkusBonsch/mxLSTM: LSTM model for regression

Description

Preprocessing for regression in caret

Usage

getPreProcessor(dat, preProcess, preProcOptions = list(thresh = 0.95, ICAcomp
  = 3, k = 5, freqCut = 95/5, uniqueCut = 10, cutoff = 0.9))

Arguments

dat	data.frame containing the data to be preprocessed.
preProcess	Character vector with preprocessing steps for dat. Can be anything that caret allows (see preProcess) plus c('scaleAgain', 'centerAgain', 'minMax'). scaleAgain and centerAgain are used to rescale data after a PCA or a similar transformation has destroyed the original scaling by caret. minMax transforms the output into [0;1]. minMax is always executed as the last step.
preProcOptions	list of options for the different preProcessing steps from caret.

Value

List with the following items:

• preProcessStep1: preProcessing result for dat, first step (all native caret methods). See preProcess

• preProcessStep2: preProcessing result for dat for scaleAgain, centerAgain Result of caret preProcess with scale and center

• preProcessMinMax: preProcessing result for minMax trafo. Comprises min value, max value and trafo function.

See Also

predictPreProcessor, invertPreProcessor

MarkusBonsch/mxLSTM documentation built on May 28, 2019, 6:40 a.m.