Mitchell O'Hara-Wild

Potential interface: ```r bagged_model(, bag_decomposition(, times = 100)) ```

Alternative interface, based on `generate()` to produce simulated data similar to the response: ```r bagged_model(, , ...) ``` Some arguments for `generate()` will need to be passed by `...`. Ref:...

While moving these to fabletools, friendly names should be given to common seasonal periods (say months in years become `yearJan` or similar) for model display output. https://github.com/tidyverts/fable/issues/298

If/when this is done (hopefully, 0.4.0) this should also enable reconciliation of fitted values (#87) and bias adjust fitted values (including multi-step fits).

Added in bca4bcd1a72174ffa75de152b5c46d09ddcc7eef

Re-opening as this needs more work. Temporal aggregations should maintain a flat data structure with new mixed time index class. This new index class should extend the tsibble interval output,...

``` r library(tsibble) library(fabletools) library(dplyr) #> #> Attaching package: 'dplyr' #> The following objects are masked from 'package:stats': #> #> filter, lag #> The following objects are masked from 'package:base':...

Ideally the interface for this would look something like this: ```r tsibble( time = rep(yearquarter("2020 Q1") + 0:3, 2), grp = rep(c("A", "B"), each = 4), index = time, key...

The [{moment}](https://github.com/mitchelloharawild/moment) package (name pending) has been created to represent time vectors with mixed granularity. As such, the named list of aggregation functions is likely more than what is needed....

Sounds reasonable, although `".model"` is assumed in a variety of places (plotting, accuracy, etc.). It will probably need to be stored as an attribute of the `fbl_ts`