fabletools
fabletools copied to clipboard
tidyverts
General fable features useful for extension packages
`aggregate_key()` should store some information about how it was aggregated. @anastasiospanagiotelis
Method not found is not a helpful error when someone tries to `components()` a fable. What about if someone uses `interpolate()` on an ETS? Better errors for `mdl_ts` and `fbl_ts`...
I've prototyped the idea of rolling tsibble https://github.com/tidyverts/tsibble/tree/137/slide-by I like the `collect()` idea, only evaluating when user asks for it. `model()` and `forecast()` may only hold the queries. When `collect()`ing,...
This seems to be unstable for some reason (non-positive-definite covariance), perhaps the `.id` is being used in reconciliation in some way. ```r library(fpp3) tourism_stretch % stretch_tsibble(.init = 16) fits %...
What is the most appropriate plot to show for any model? Galit Shmueli has suggested that the plot should show augment() features, including the fitted values against actual values, along...
MRE: ``` r library(fable) #> Loading required package: fabletools library(future) plan(multiprocess) #> Warning: [ONE-TIME WARNING] Forked processing ('multicore') is disabled #> in future (>= 1.13.0) when running R from RStudio,...
Based on https://stackoverflow.com/q/78388045/144157 ``` r library(fable) library(tsibble) library(dplyr) set.seed(123) # create data aa `x1` #> Warning: 1 error encountered for arima #> [1] subscript out of bounds #> # A...
Good morning, I have been using the excellent fabletools package and I would like to know how to specify a linear combination in a hierarchical time series when using the...
See reprex below. In my real codebase I'm using `furrr`'s `future_map` for other purposes (reading a series of files off disk). ``` library(fable) #> Loading required package: fabletools library(tsibble) #>...
Legend shading is incorrect when h=1. Perhaps related to #400 ``` r library(fable) fit model(NAIVE(value)) fit |> forecast(h = 1) |> autoplot() ```  ``` r fit |> forecast(h =...