Generate new data from a fable model

Source: R/lm.R

Simulates future paths from a dataset using a fitted model. Innovations are sampled by the model's assumed error distribution. If bootstrap is TRUE, innovations will be sampled from the model's residuals. If new_data contains the .innov column, those values will be treated as innovations.

# S3 method for TSLM
generate(x, new_data, specials, bootstrap = FALSE, ...)

Arguments

x

A fitted model.
new_data

A tsibble containing future information used to forecast.
specials

(passed by fabletools::forecast.mdl_df()).
bootstrap

If TRUE, then forecast distributions are computed using simulation with resampled errors.
...

Additional arguments for forecast model methods.

See also

fabletools::generate.mdl_df

Examples

as_tsibble(USAccDeaths) %>%
  model(lm = TSLM(log(value) ~ trend() + season())) %>%
  generate()

#> # A tsibble: 24 x 3 [1M]
#> # Key:       .model [1]
#>    .model    index  .sim
#>    <chr>     <mth> <dbl>
#>  1 lm     1979 Jan 7608.
#>  2 lm     1979 Feb 6856.
#>  3 lm     1979 Mar 7650.
#>  4 lm     1979 Apr 7832.
#>  5 lm     1979 May 8562.
#>  6 lm     1979 Jun 9106.
#>  7 lm     1979 Jul 9912.
#>  8 lm     1979 Aug 9198.
#>  9 lm     1979 Sep 8138.
#> 10 lm     1979 Oct 8520.
#> # … with 14 more rows