From 0f956d64db7f2ac2493aab979f9ed76dc58c3524 Mon Sep 17 00:00:00 2001
From: Brent Brewington <brent.brewington@gmail.com>
Date: Thu, 4 May 2017 08:07:34 -0400
Subject: [PATCH] factors.Rmd clarification (#577)

Fixes #576
---
 factors.Rmd | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/factors.Rmd b/factors.Rmd
index ae2e8e1..8db4c0f 100644
--- a/factors.Rmd
+++ b/factors.Rmd
@@ -144,7 +144,7 @@ When working with factors, the two most common operations are changing the order
 It's often useful to change the order of the factor levels in a visualisation. For example, imagine you want to explore the average number of hours spent watching TV per day across religions:
 
 ```{r}
-relig <- gss_cat %>%
+relig_summary <- gss_cat %>%
   group_by(relig) %>%
   summarise(
     age = mean(age, na.rm = TRUE),
@@ -152,7 +152,7 @@ relig <- gss_cat %>%
     n = n()
   )
 
-ggplot(relig, aes(tvhours, relig)) + geom_point()
+ggplot(relig_summary, aes(tvhours, relig)) + geom_point()
 ```
 
 It is difficult to interpret this plot because there's no overall pattern. We can improve it by reordering the levels of `relig` using `fct_reorder()`. `fct_reorder()` takes three arguments:
@@ -163,7 +163,7 @@ It is difficult to interpret this plot because there's no overall pattern. We ca
   `x` for each value of `f`. The default value is `median`.
 
 ```{r}
-ggplot(relig, aes(tvhours, fct_reorder(relig, tvhours))) +
+ggplot(relig_summary, aes(tvhours, fct_reorder(relig, tvhours))) +
   geom_point()
 ```
 
@@ -172,7 +172,7 @@ Reordering religion makes it much easier to see that people in the "Don't know"
 As you start making more complicated transformations, I'd recommend moving them out of `aes()` and into a separate `mutate()` step. For example, you could rewrite the plot above as:
 
 ```{r, eval = FALSE}
-relig %>%
+relig_summary %>%
   mutate(relig = fct_reorder(relig, tvhours)) %>%
   ggplot(aes(tvhours, relig)) +
     geom_point()
@@ -180,7 +180,7 @@ relig %>%
 What if we create a similar plot looking at how average age varies across reported income level?
 
 ```{r}
-rincome <- gss_cat %>%
+rincome_summary <- gss_cat %>%
   group_by(rincome) %>%
   summarise(
     age = mean(age, na.rm = TRUE),
@@ -188,7 +188,7 @@ rincome <- gss_cat %>%
     n = n()
   )
 
-ggplot(rincome, aes(age, fct_reorder(rincome, age))) + geom_point()
+ggplot(rincome_summary, aes(age, fct_reorder(rincome, age))) + geom_point()
 ```
 
 Here, arbitrarily reordering the levels isn't a good idea! That's because `rincome` already has a principled order that we shouldn't mess with. Reserve `fct_reorder()` for factors whose levels are arbitrarily ordered.
@@ -196,7 +196,7 @@ Here, arbitrarily reordering the levels isn't a good idea! That's because `rinco
 However, it does make sense to pull "Not applicable" to the front with the other special levels. You can use `fct_relevel()`. It takes a factor, `f`, and then any number of levels that you want to move to the front of the line.
 
 ```{r}
-ggplot(rincome, aes(age, fct_relevel(rincome, "Not applicable"))) +
+ggplot(rincome_summary, aes(age, fct_relevel(rincome, "Not applicable"))) +
   geom_point()
 ```