Re-rendered blog to fix order of NAs in plots

content/blog/2023/forcats-1-0-0/index.Rmd

@@ -14,7 +14,7 @@ photo:
   author: Diego Morales
 
 # one of: "deep-dive", "learn", "package", "programming", "roundup", or "other"
-categories: [package] 
+categories: [package]
 tags: [forcats]
 ---
 
@@ -94,15 +94,15 @@ In the plot below, I've attempted to use `fct_infreq()` to reorder the levels of
 #| fig.alt: >
 #|   The bar chart of hair color, now ordered so that the least
 #|   frequent colours come first and the most frequent colors come last.
-#|   This makes it easy to see that the most common hair color is none 
+#|   This makes it easy to see that the most common hair color is none
 #|   (~35), followed by brown (~18), then black (~12). Surprisingly,
-#|   NAs are at the top of the graph, even though there are ~5 NAs and 
+#|   NAs are at the top of the graph, even though there are ~5 NAs and
 #|   other colors have smaller values.
 library(ggplot2)
 library(dplyr, warn.conflicts = FALSE)
 
-ggplot(starwars, aes(y = fct_rev(fct_infreq(hair_color)))) + 
-  geom_bar() + 
+ggplot(starwars, aes(y = fct_rev(fct_infreq(hair_color)))) +
+  geom_bar() +
   labs(y = "Hair color")
 ```
 
@@ -114,10 +114,10 @@ We can make `fct_infreq()` do what we want by moving the `NA` from the values to
 #| fig-asp: 1
 #| fig-width: 4
 #| fig-alt: >
-#|   The bar chart of hair color, now ordered so that NAs are 
+#|   The bar chart of hair color, now ordered so that NAs are
 #|   ordered where you'd expect: in between white (4) and black (12).
-ggplot(starwars, aes(y = fct_rev(fct_infreq(fct_na_value_to_level(hair_color))))) + 
-  geom_bar() + 
+ggplot(starwars, aes(y = fct_rev(fct_infreq(fct_na_value_to_level(hair_color))))) +
+  geom_bar() +
   labs(y = "Hair color")
 ```
 
@@ -127,15 +127,15 @@ That code is getting a little verbose so lets pull it out into a separate dplyr
 #| fig-asp: 1
 #| fig-width: 4
 #| results: false
-starwars |> 
+starwars |>
   mutate(
-    hair_color = hair_color |> 
-      fct_na_value_to_level() |> 
-      fct_infreq() |> 
+    hair_color = hair_color |>
+      fct_na_value_to_level() |>
+      fct_infreq() |>
       fct_rev()
-  ) |> 
-  ggplot(aes(y = hair_color)) + 
-  geom_bar() + 
+  ) |>
+  ggplot(aes(y = hair_color)) +
+  geom_bar() +
   labs(y = "Hair color")
 ```
 
@@ -148,16 +148,16 @@ I've left the (Other) category as a bar at the end, but if I wanted to I could c
 #| fig-alt: >
 #|   The bar chart of hair color, with NA hair colour now labelled as (Unknown)
 #|   and the low frequency bars lumped into (Other).
-starwars |> 
+starwars |>
   mutate(
-    hair_color = hair_color |> 
-      fct_na_value_to_level("(Unknown)") |> 
-      fct_infreq() |> 
-      fct_lump_min(2, other_level = "(Other)") |> 
-      fct_rev() 
-  ) |> 
-  ggplot(aes(y = hair_color)) + 
-  geom_bar() + 
+    hair_color = hair_color |>
+      fct_na_value_to_level("(Unknown)") |>
+      fct_infreq() |>
+      fct_lump_min(2, other_level = "(Other)") |>
+      fct_rev()
+  ) |>
+  ggplot(aes(y = hair_color)) +
+  geom_bar() +
   labs(y = "Hair color")
 ```
 
@@ -169,17 +169,17 @@ One way to fix that is with `fct_na_level_to_value()`:
 #| fig-alt: >
 #|   The bar chart of hair color, with "unknown" hair colour now lumped in
 #|   with (Unknown) instead of other
-starwars |> 
+starwars |>
   mutate(
-    hair_color = hair_color |> 
-      fct_na_level_to_value("Unknown") |> 
-      fct_na_value_to_level("(Unknown)") |> 
-      fct_infreq() |> 
-      fct_lump_min(2, other_level = "(Other)") |> 
-      fct_rev() 
-  ) |> 
-  ggplot(aes(y = hair_color)) + 
-  geom_bar() + 
+    hair_color = hair_color |>
+      fct_na_level_to_value("Unknown") |>
+      fct_na_value_to_level("(Unknown)") |>
+      fct_infreq() |>
+      fct_lump_min(2, other_level = "(Other)") |>
+      fct_rev()
+  ) |>
+  ggplot(aes(y = hair_color)) +
+  geom_bar() +
   labs(y = "Hair color")
 ```