NA omitting

[dajmcdon]

Default na_omit processing should likely remove NAs from y and x at training time, but only x at prediction time. Using default {recipes} steps, one would do something like:

# Baseline AR3
r <- epi_recipe(x) %>% 
  step_epi_ahead(death_rate, ahead = 7) %>%
  step_epi_lag(death_rate, lag = c(0, 7, 14)) %>%
  step_epi_lag(case_rate, lag = c(0, 7, 14)) %>%
  step_naomit(all_predictors()) %>%
  # below, `skip` means we don't do this at predict time
  # we should probably do something useful here to avoid user error
  step_naomit(all_outcomes(), skip = TRUE)

Write a wrapper that adds combines these steps into 1.

[kenmawer]

I will get started on and finish this tomorrow.

[kenmawer]

Completed with PR #79.