modl.trControl: Control the splitting to train the data

In predtoolsTS: Time Series Prediction Tools

Description

Creates the needed caret::trainControl object to control the training splitting.

Usage

modl.trControl(initialWindow, horizon, fixedWindow, givenSummary = FALSE)

Arguments

initialWindow	An integer. The initial number of consecutive values in each training set sample. Default value: 30.
horizon	An integer. The number of consecutive values in test set sample. Default value: 15.
fixedWindow	A logical: if FALSE, the training set always start at the first sample and the training set size will vary over data splits. Default value: TRUE.
givenSummary	A logical. Indicates if it should be used the customized summaryFunction(?trainControl for more info) modl.sumFunction or not. Default is FALSE; this will use default caret metrics.

Details

We always split using method "timeslice", wich is the better for time series. More information on how this works on http://topepo.github.io/caret/data-splitting.html#data-splitting-for-time-series.

Value

trainControl object

Author(s)

Alberto Vico Moreno

Examples

modl.trControl(initialWindow=30,horizon=15,fixedWindow=TRUE,givenSummary=TRUE)

Example output

$method
[1] "timeslice"

$number
[1] 25

$repeats
[1] NA

$search
[1] "grid"

$p
[1] 0.75

$initialWindow
[1] 30

$horizon
[1] 15

$fixedWindow
[1] TRUE

$skip
[1] 0

$verboseIter
[1] FALSE

$returnData
[1] TRUE

$returnResamp
[1] "final"

$savePredictions
[1] FALSE

$classProbs
[1] FALSE

$summaryFunction
function (data, lev = NULL, model = NULL) 
{
    rmse <- caret::RMSE(data$obs, data$pred)
    mae <- Metrics::mae(data$obs, data$pred)
    mape <- TSPred::MAPE(data$obs, data$pred)
    output <- c(rmse, mae, mape)
    names(output) <- c("RMSE", "MAE", "MAPE")
    return(output)
}
<environment: namespace:predtoolsTS>

$selectionFunction
[1] "best"

$preProcOptions
$preProcOptions$thresh
[1] 0.95

$preProcOptions$ICAcomp
[1] 3

$preProcOptions$k
[1] 5

$preProcOptions$freqCut
[1] 19

$preProcOptions$uniqueCut
[1] 10

$preProcOptions$cutoff
[1] 0.9


$sampling
NULL

$index
NULL

$indexOut
NULL

$indexFinal
NULL

$timingSamps
[1] 0

$predictionBounds
[1] FALSE FALSE

$seeds
[1] NA

$adaptive
$adaptive$min
[1] 5

$adaptive$alpha
[1] 0.05

$adaptive$method
[1] "gls"

$adaptive$complete
[1] TRUE


$trim
[1] FALSE

$allowParallel
[1] TRUE

predtoolsTS documentation built on May 2, 2019, 5:54 a.m.