printing can be ugly

[dajmcdon]

This example the recipe in the vignette

epipredict/vignettes/preprocessing-and-models.Rmd

Line 323 in 6455828

r <- epi_recipe(jhu) %>%

library(recipes)
library(epipredict)

jhu <- case_death_rate_subset %>%
  dplyr::filter(
    time_value >= "2021-06-04",
    time_value <= "2021-12-31",
    geo_value %in% c("ca", "fl", "tx", "ny", "nj")
  ) %>%
  mutate(geo_value_factor = as.factor(geo_value))

r <- recipe(jhu) %>%
  add_role(time_value, new_role = "predictor") %>%
  step_dummy(geo_value_factor, role = "predictor") %>%
  step_growth_rate(case_rate, role = "none", prefix = "gr_") %>%
  step_epi_lag(starts_with("gr_"), lag = c(0, 7, 14)) %>%
  step_epi_ahead(starts_with("gr_"), ahead = 7, role = "none") %>%
  # note recipes::step_cut() has a bug in it, or we could use that here
  step_mutate(
    response = cut(
      ahead_7_gr_7_rel_change_case_rate,
      breaks = c(-Inf, -0.2, 0.25, Inf) / 7, # division gives weekly not daily
      labels = c("down", "flat", "up")
    ),
    role = "outcome"
  ) %>%
  step_rm(has_role("none"), has_role(NA)) %>%
  step_epi_naomit()

r
#> 
#> ── Epi Recipe ──────────────────────────────────────────────────────────────────
#> 
#> ── Inputs
#> Number of variables by role
#> predictor:       1
#> geo_value:       1
#> time_value:      1
#> undeclared role: 3
#> 
#> ── Operations
#> $terms
#> <list_of<quosure>>
#> 
#> [[1]]
#> <quosure>
#> expr: ^geo_value_factor
#> env:  0x12d1a6128
#> 
#> 
#> $role
#> [1] "predictor"
#> 
#> $trained
#> [1] FALSE
#> 
#> $one_hot
#> [1] FALSE
#> 
#> $preserve
#> [1] FALSE
#> 
#> $naming
#> function (var, lvl, ordinal = FALSE, sep = "_") 
#> {
#>     args <- vctrs::vec_recycle_common(var, lvl)
#>     var <- args[[1]]
#>     lvl <- args[[2]]
#>     if (!ordinal) {
#>         nms <- paste(var, make.names(lvl), sep = sep)
#>     }
#>     else {
#>         nms <- paste0(var, names0(length(lvl), sep))
#>     }
#>     nms
#> }
#> <bytecode: 0x12d048b48>
#> <environment: namespace:recipes>
#> 
#> $levels
#> NULL
#> 
#> $keep_original_cols
#> [1] FALSE
#> 
#> $skip
#> [1] FALSE
#> 
#> $id
#> [1] "dummy_rgGr9"
#> 
#> attr(,"class")
#> [1] "step_dummy" "step"      
#> $role
#> [1] "outcome"
#> 
#> $trained
#> [1] FALSE
#> 
#> $inputs
#> <list_of<quosure>>
#> 
#> $response
#> <quosure>
#> expr: ^cut(ahead_7_gr_7_rel_change_case_rate, breaks = c(-Inf, -0.2, 0.25,
#>           Inf) / 7, labels = c("down", "flat", "up"))
#> env:  0x12d1a63c8
#> 
#> 
#> $skip
#> [1] FALSE
#> 
#> $id
#> [1] "mutate_MVXkG"
#> 
#> attr(,"class")
#> [1] "step_mutate" "step"       
#> $terms
#> <list_of<quosure>>
#> 
#> [[1]]
#> <quosure>
#> expr: ^has_role("none")
#> env:  0x12d1a6470
#> 
#> [[2]]
#> <quosure>
#> expr: ^has_role(NA)
#> env:  0x12d1a6470
#> 
#> 
#> $role
#> [1] NA
#> 
#> $trained
#> [1] FALSE
#> 
#> $removals
#> NULL
#> 
#> $skip
#> [1] FALSE
#> 
#> $id
#> [1] "rm_mV3xQ"
#> 
#> attr(,"class")
#> [1] "step_rm" "step"
#> 1. Calculating growth_rate for: case_rate by rel_change
#> 2. Lagging: starts_with("gr_") by 0, 7, 14
#> 3. Leading: starts_with("gr_") by 7
#> 4. • Removing rows with NA values in: all_predictors()
#> 5. • Removing rows with NA values in: all_outcomes()