feasts
feasts copied to clipboard
Feature Extraction And Statistics for Time Series
Is there a way to make gg_tsdisplay() x axis of the first plot (time series) start on the date of the first sample? In my case the first sample starts...
This package contains both data visualisation tools and features/statistics for time series. These goals can be somewhat conflicting. Feature extraction tends to require highly performant code with minimal dependencies, while...
https://pkg.robjhyndman.com/tsfeatures/reference/nonlinearity.html
I am trying to use gg_season to graph seasonal gun sales with a period of 4 years, to extract seasonal gun sale data aligned with the US Presidential election cycle....
When asking for an STL decomposition, it should always use an STL decomposition. The current behaviour of calling Friedman's SuperSmoother for non-seasonal data is incorrect and can cause confusion and...
Which lag is most appropriate? Old or new? Which gives best ARIMA performance on M3/M4?
This should use the distribution or hilo class from fable. These class definitions should probably be ported to feasts, thoughts @robjhyndman?
These current take values 0:(m-1). It would be much easier to interpret if they took 1:m by changing 0 to m and leaving the others as they are. See https://otexts.com/fpp3/exploring-australian-tourism-data.html...
``` r library(feasts) #> Loading required package: fabletools fpp3::us_gasoline %>% gg_season(Barrels) ```  Created on 2020-05-24 by the [reprex package](https://reprex.tidyverse.org) (v0.3.0)