Plot forecast error at various levels of aggregation across validation datasets.
# S3 method for validation_error
plot(
x,
type = c("window", "horizon", "global"),
metric = NULL,
facet = NULL,
models = NULL,
horizons = NULL,
windows = NULL,
group_filter = NULL,
...
)An object of class 'validation_error' from return_error().
Select plot type; type = "window" is the default plot.
Select error metric to plot (e.g., "mae"); attributes(x)$error_metrics[1] is the default metric.
Optional. A formula with any combination of horizon, model, or group (for grouped time series).
passed to ggplot2::facet_grid() internally (e.g., horizon ~ model, horizon + model ~ ., ~ horizon + group).
Can be NULL. The default faceting is set internally depending on the plot type.
Optional. A vector of user-defined model names from train_model() to filter results.
Optional. A numeric vector to filter results by horizon.
Optional. A numeric vector to filter results by validation window number.
A string for filtering plot results for grouped time series (e.g., "group_col_1 == 'A'").
Not used.
Forecast error plots of class 'ggplot'.