RemixAutoML (version 0.4.9)

ParallelAutoARIMA: ParallelAutoARIMA

Description

ParallelAutoARIMA for training multiple models at once

Usage

ParallelAutoARIMA(
  Output,
  MetricSelection = "MAE",
  MaxFourierTerms = 1L,
  TrainValidateShare = c(0.5, 0.5),
  MaxNumberModels = 20,
  MaxRunMinutes = 5L,
  MaxRunsWithoutNewWinner = 12,
  NumCores = max(1L, min(4L, parallel::detectCores()))
)

Arguments

Output

The output returned from TimeSeriesDataPrepare()

MetricSelection

Choose from MAE, MSE, and MAPE

MaxFourierTerms

Fourier pairs

TrainValidateShare

c(0.50,0.50)

MaxNumberModels

20

MaxRunMinutes

5

MaxRunsWithoutNewWinner

12

NumCores

Default of max(1L, min(4L, parallel::detectCores())). Up to 4 cores can be utilized.

Value

Time series data sets to pass onto auto modeling functions

See Also

Other Time Series Helper: FinalBuildArfima(), FinalBuildArima(), FinalBuildETS(), FinalBuildNNET(), FinalBuildTBATS(), FinalBuildTSLM(), GenerateParameterGrids(), OptimizeArfima(), OptimizeArima(), OptimizeETS(), OptimizeNNET(), OptimizeTBATS(), OptimizeTSLM(), ParallelAutoArfima(), ParallelAutoETS(), ParallelAutoNNET(), ParallelAutoTBATS(), ParallelAutoTSLM(), PredictArima(), RL_Performance(), Regular_Performance(), StackedTimeSeriesEnsembleForecast(), TimeSeriesDataPrepare(), WideTimeSeriesEnsembleForecast()

Examples

# NOT RUN {
ParallelAutoARIMA(
  MetricSelection = "MAE",
  Output = NULL,
  MaxRunsWithoutNewWinner = 20,
  TrainValidateShare = c(0.50,0.50),
  MaxNumberModels = 5,
  MaxRunMinutes = 5,
  NumCores = max(1L, min(4L, parallel::detectCores())))
# }