Several diagnostic plots can be returned to assess the quality of the forecasts based on predictions on the validation datasets.
# S3 method for training_results
plot(x, type = c("prediction", "residual",
"forecast_stability", "forecast_variability"), models = NULL,
horizons = NULL, windows = NULL, valid_indices = NULL,
group_filter = NULL, ...)An object of class 'training_results' from predict.forecast_mode()l.
Plot type. The default plot is "prediction" for validation dataset predictions.
Optional. Filter results by user-defined model name from train_model().
Optional. A numeric vector of model forecast horizons to filter results by horizon-specific model.
Optional. A numeric vector of window numbers to filter results.
Optional. A numeric or date vector to filter results by validation row indices or dates.
Optional. A string for filtering plot results for grouped time series
(e.g., "group_col_1 == 'A'"). The results are passed to dplyr::filter() internally.
Not used.
Diagnostic plots of class 'ggplot'.