Use `refit()` or `stream()` to re-fit models with new data

[Aariq]

In #22 I'm working on using auto-ARIMA to select better models for each variable, but it is time consuming. Once the model selection process has happened though, you can use refit() or stream() from the fable package. I'm not sure what the difference between the two is though. Discussed here: https://tidyverts.github.io/tidy-forecasting-principles/methods.html#re-estimation

[Aariq]

This function [refit] is closely linked with stream(). The key difference is that refit() does not condition on earlier data (replacing the dataset entirely), and stream() extends the model fit with the introduction of new future data.