fable
fable copied to clipboard
tidyverts
Tidy time series forecasting
It would be nice to have a function that takes a model object and returns the latex equations to insert into an Rmarkdown document. This comes up all the time...
I am currently in a scenario where I need to fit multiple models where I just change one of the parameters. ``` library(fpp3) gas % filter(year(Week) % autoplot(Barrels) fit %...
I have a combination model that's running into some problems with `NA`s. The data looks like this (see end of message for actual `dput` format to recreate the exact data...
https://github.com/tidyverts/fable/actions/runs/7721580515 shows that actions/checkout@v2 and r-lib/actions/setup-pandoc@v1 are deprecated. This updates them.
See https://community.rstudio.com/t/problem-with-back-transformation-using-log-in-ets/179368
NNETAR currently normalizes the response variable. This is ok when linout=TRUE, but when linout=FALSE, a logistic activation function is used and the response is assumed to be binary. So it...
Hi, Thanks for the amazing package. In some sectors, it is necessary to perform modeling using three scenarios (baseline, adverse and optimistic). To do this, three `new_data` must be used...
Not absolutely sure this is a bug but can't figure out why the Holt linear trend equations produces different slope values to those given by the components() view of an...
I got a question in the workshop about the fact that you can't do `?drift` and pull up any information on the `drift()` special. I get that this isn't a...
Hello! How can I use `breusch_godfrey()`? I'm using a TSLM model as follows without success. ``` mod % model( LM = TSLM("formula here") ) mod %>% breusch_godfrey() ```
