This package creates Time Series Hacks to enhance time series problems, such as forecasting, scenario generation among others. List of methods:
First, I haven't uploaded a stable version to CRAN but you can download from GitHub using devtools, type:
library(devtools)
install_github("tiagomendesdantas/tshacks")
library(tshacks)
method <- baggedClusterETS(gas)
f_method <- forecast(method,h=12)
plot(f_method)
To access the bootstrap versions before the cluster phase:
bootstrap_before_selection <- method$bootstrapped_series_ori
To access the number o clusters selected:
n_clusters <- method$k
To access the bootstrap versions selected after the cluster phase
bootstrap_after_selection <- method$bootstrapped_series
To access the selected model for each selected bootstrapped version
selected_models <- method$models
To access the fitted series and the residuals
fitted_series <- method$fitted
residuals <- method$residuals
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.