Produces forecasts from a trained model.
# S3 method for RW
forecast(
object,
new_data,
specials = NULL,
simulate = FALSE,
bootstrap = FALSE,
times = 5000,
...
)A model for which forecasts are required.
A tsibble containing the time points and exogenous regressors to produce forecasts for.
(passed by fabletools::forecast.mdl_df()).
If TRUE, prediction intervals are produced by simulation rather than using analytic formulae.
If TRUE, then forecast distributions are computed using simulation with resampled errors.
The number of sample paths to use in estimating the forecast distribution when bootstrap = TRUE.
Other arguments passed to methods
A list of forecasts.
as_tsibble(Nile) %>%
model(NAIVE(value)) %>%
forecast()
#> # A fable: 2 x 4 [1Y]
#> # Key: .model [1]
#> .model index value .mean
#> <chr> <dbl> <dist> <dbl>
#> 1 NAIVE(value) 1971 N(740, 27998) 740
#> 2 NAIVE(value) 1972 N(740, 55995) 740
library(tsibbledata)
aus_production %>%
model(snaive = SNAIVE(Beer ~ lag("year"))) %>%
forecast()
#> # A fable: 8 x 4 [1Q]
#> # Key: .model [1]
#> .model Quarter Beer .mean
#> <chr> <qtr> <dist> <dbl>
#> 1 snaive 2010 Q3 N(419, 373) 419
#> 2 snaive 2010 Q4 N(488, 373) 488
#> 3 snaive 2011 Q1 N(414, 373) 414
#> 4 snaive 2011 Q2 N(374, 373) 374
#> 5 snaive 2011 Q3 N(419, 747) 419
#> 6 snaive 2011 Q4 N(488, 747) 488
#> 7 snaive 2012 Q1 N(414, 747) 414
#> 8 snaive 2012 Q2 N(374, 747) 374