Package: forecastHybrid 5.0.19

David Shaub

forecastHybrid: Convenient Functions for Ensemble Time Series Forecasts

Convenient functions for ensemble forecasts in R combining approaches from the 'forecast' package. Forecasts generated from auto.arima(), ets(), thetaf(), nnetar(), stlm(), tbats(), snaive() and arfima() can be combined with equal weights, weights based on in-sample errors (introduced by Bates & Granger (1969) <doi:10.1057/jors.1969.103>), or cross-validated weights. Cross validation for time series data with user-supplied models and forecasting functions is also supported to evaluate model accuracy.

Authors:David Shaub [aut, cre], Peter Ellis [aut]

forecastHybrid_5.0.19.tar.gz
forecastHybrid_5.0.19.zip(r-4.5)forecastHybrid_5.0.19.zip(r-4.4)forecastHybrid_5.0.19.zip(r-4.3)
forecastHybrid_5.0.19.tgz(r-4.4-any)forecastHybrid_5.0.19.tgz(r-4.3-any)
forecastHybrid_5.0.19.tar.gz(r-4.5-noble)forecastHybrid_5.0.19.tar.gz(r-4.4-noble)
forecastHybrid_5.0.19.tgz(r-4.4-emscripten)forecastHybrid_5.0.19.tgz(r-4.3-emscripten)
forecastHybrid.pdf |forecastHybrid.html✨
forecastHybrid/json (API)
NEWS

# Install 'forecastHybrid' in R:
install.packages('forecastHybrid', repos = c('https://ellisp.r-universe.dev', 'https://cloud.r-project.org'))

Peer review:

Bug tracker:https://github.com/ellisp/forecasthybrid/issues

On CRAN:

9.07 score 80 stars 1 packages 121 scripts 3.4k downloads 3 mentions 9 exports 54 dependencies

Last updated 2 years agofrom:53d79a9478. Checks:OK: 5 NOTE: 2. Indexed: yes.

TargetResultDate
Doc / VignettesOKNov 21 2024
R-4.5-winNOTENov 21 2024
R-4.5-linuxNOTENov 21 2024
R-4.4-winOKNov 21 2024
R-4.4-macOKNov 21 2024
R-4.3-winOKNov 21 2024
R-4.3-macOKNov 21 2024

Exports:cvtsextractForecastshybridModelis.hybridModelthetamthiefModeltsCombinetsPartitiontsSubsetWithIndices

Dependencies:clicodetoolscolorspacecurldoParallelfansifarverforeachforecastfracdiffgenericsggplot2gluegtablehtsisobanditeratorsjsonlitelabelinglatticelifecyclelmtestmagrittrMASSMatrixmgcvmunsellnlmennetpillarpkgconfigpurrrquadprogquantmodR6RColorBrewerRcppRcppArmadilloRcppEigenrlangscalesSparseMthieftibbletimeDatetseriesTTRurcautf8vctrsviridisLitewithrxtszoo

Using the "forecastHybrid" package

David Shaub

Rendered fromforecastHybrid.Rmdusingknitr::rmarkdownon Nov 21 2024.

Last update: 2020-03-31
Started: 2016-05-20

Readme and manuals

Help Manual

Help pageTopics
Accuracy measures for cross-validated time seriesaccuracy.cvts
Accuracy measures for hybridModel objectsaccuracy.hybridModel
Validate that CV window parameters are validcheckCVArguments
Helper function to test all the model arguments (e.g. a.args, e.args, etc)checkModelArgs
Helper function to check the that the parallel arguments are validcheckParallelArguments
Cross validation for time seriescvts
Extract cross validated rolling forecastsextractForecasts
Extract Model Fitted Valuesfitted.hybridModel
Hybrid forecastforecast.hybridModel
Forecast using a Theta modelforecast.thetam
Return a forecast model function for a given model charactergetModel
Translate character to model namegetModelName
Hybrid time series modelinghybridModel
Test if the object is a hybridModel objectis.hybridModel
Plot a hybridModel objectplot.hybridModel
Plot components from Theta modelplot.thetam
Plot the fitted values of a hybridModel objectplotFitted
Plot the component models of a hybridModel objectplotModelObjects
Helper function to validate and clean the input time seriesprepareTimeseries
Print information about the hybridModel objectprint.hybridModel
Helper function to remove models that require more dataremoveModels
Extract Model Residualsresiduals.hybridModel
Print a summary of the hybridModel objectsummary.hybridModel
Theta method 'model'thetam
Forecast ensemble using THieFthiefModel
Combine multiple sequential time seriestsCombine
Generate training and test indices for time series cross validationtsPartition
Subset time series with provided indicestsSubsetWithIndices
Helper function used to unpack the fitted model objects from a listunwrapParallelModels