bugs seemingly squashed

Author: dajmcdon

R/epi_recipe.R

@@ -113,7 +113,7 @@ epi_recipe.epi_df <-
     )
 
     ## Add types
-    var_info <- dplyr::full_join(get_types(x), var_info, by = "variable")
+    var_info <- dplyr::full_join(recipes:::get_types(x), var_info, by = "variable")
     var_info$source <- "original"
 
     ## arrange to easy order
@@ -371,7 +371,7 @@ prep.epi_recipe <- function(
     dplyr::group_by(variable) %>%
     dplyr::arrange(dplyr::desc(number)) %>%
     dplyr::summarise(
-      type = dplyr::first(type),
+      type = list(dplyr::first(type)),
       role = as.list(unique(unlist(role))),
       source = dplyr::first(source),
       number = dplyr::first(number),

tests/testthat/test-epi_recipe.R

@@ -36,19 +36,21 @@ test_that("epi_recipe formula works", {
   r <- epi_recipe(y ~ x, tib)
   ref_var_info <- tibble::tribble(
     ~ variable, ~ type, ~ role, ~ source,
-    "x", "numeric", "predictor", "original",
-    "y", "numeric", "outcome", "original",
+    "x", c("integer", "numeric"), "predictor", "original",
+    "y", c("integer", "numeric"), "outcome", "original",
     "time_value", "date", "time_value", "original",
-    "geo_value", "nominal", "geo_value", "original"
+    "geo_value", c("string", "unordered", "nominal"), "geo_value", "original"
   )
   expect_identical(r$var_info, ref_var_info)
   expect_equal(nrow(r$template), 1L)
 
   # with an epi_key as a predictor
   r <- epi_recipe(y ~ x + geo_value, tib)
-  ref_var_info <- ref_var_info %>% tibble::add_row(
-    variable = "geo_value", type = "nominal", role = "predictor",
-    source = "original", .after = 1)
+  ref_var_info <- ref_var_info %>%
+    tibble::add_row(
+      variable = "geo_value", type = list(c("string", "unordered", "nominal")),
+      role = "predictor",
+      source = "original", .after = 1)
   expect_identical(r$var_info, ref_var_info)
   expect_equal(nrow(r$template), 1L)
 
@@ -61,11 +63,13 @@ test_that("epi_recipe formula works", {
 
   # with an additional key
   r <- epi_recipe(y ~ x + geo_value, tib)
-  ref_var_info <- ref_var_info %>% tibble::add_row(
-    variable = "z", type = "nominal", role = "key",
-    source = "original")
+  ref_var_info <- ref_var_info %>%
+    tibble::add_row(
+      variable = "z", type = list(c("string", "unordered", "nominal")),
+      role = "key",
+      source = "original")
 
-  #expect_identical(r$var_info, ref_var_info)
+  expect_identical(r$var_info, ref_var_info)
 
 })
 
@@ -81,20 +85,20 @@ test_that("epi_recipe epi_df works", {
   ref_var_info <- tibble::tribble(
     ~ variable, ~ type, ~ role, ~ source,
     "time_value", "date", "time_value", "original",
-    "geo_value", "nominal", "geo_value", "original",
-    "x", "numeric", "raw", "original",
-    "y", "numeric", "raw", "original"
+    "geo_value", c("string", "unordered", "nominal"), "geo_value", "original",
+    "x", c("integer", "numeric"), "raw", "original",
+    "y", c("integer", "numeric"), "raw", "original"
   )
   expect_identical(r$var_info, ref_var_info)
   expect_equal(nrow(r$template), 1L)
 
   r <- epi_recipe(tib, formula = y ~ x)
   ref_var_info <- tibble::tribble(
     ~ variable, ~ type, ~ role, ~ source,
-    "x", "numeric", "predictor", "original",
-    "y", "numeric", "outcome", "original",
+    "x", c("integer", "numeric"), "predictor", "original",
+    "y", c("integer", "numeric"), "outcome", "original",
     "time_value", "date", "time_value", "original",
-    "geo_value", "nominal", "geo_value", "original"
+    "geo_value", c("string", "unordered", "nominal"), "geo_value", "original"
   )
   expect_identical(r$var_info, ref_var_info)
   expect_equal(nrow(r$template), 1L)
@@ -106,7 +110,7 @@ test_that("epi_recipe epi_df works", {
   )
   ref_var_info <- ref_var_info %>%
     tibble::add_row(
-      variable = "time_value", type = "date", role = "funny_business",
+      variable = "time_value", type = list("date"), role = "funny_business",
       source = "original"
     )
   expect_identical(r$var_info, ref_var_info)

vignettes/preprocessing-and-models.Rmd

@@ -549,14 +549,16 @@ Notice the difference in number of rows `b1` and `b2` returns. This is because
 the second version, the one that doesn't use `step_epi_ahead` and `step_epi_lag`,
 has omitted dates compared to the one that used the `epipredict` functions.
 ```{r}
-dates_used_in_training1 <-
- b1 %>% select(- ahead_7_death_rate) %>% na.omit() %>% select(time_value)
-
+dates_used_in_training1 <- b1 %>% 
+  select(- ahead_7_death_rate) %>% 
+  na.omit() %>% 
+  select(time_value)
 dates_used_in_training1
 
-dates_used_in_training2 <- 
-  b2 %>% select(- ahead7death_rate) %>% na.omit() %>% select(time_value)
-
+dates_used_in_training2 <- b2 %>% 
+  select(- ahead7death_rate) %>% 
+  na.omit() %>% 
+  select(time_value)
 dates_used_in_training2
 ```