Improving the color and labeling
library(ggplot2)
# bar plot, with each bar representing 100%,
# reordered bars, and better labels and colors
library(scales)
ggplot(mpg,
aes(x = factor(class,
levels = c("2seater", "subcompact",
"compact", "midsize", "minivan", "suv", "pickup")), fill = factor(drv,
levels = c("f", "r", "4"),
labels = c("front-wheel", "rear-wheel",
"4-wheel")))) +
geom_bar(position = "fill") +
scale_y_continuous(breaks = seq(0, 1, .2),
label = percent) +
scale_fill_brewer(palette = "Set2") +
labs(y = "Percent",
fill = "Drive Train",
x = "Class",
title = "Automobile Drive by Class") +
theme_minimal()
# create a summary dataset
library(dplyr)
plotdata <- mpg %>%
group_by(class, drv) %>%
summarize(n = n()) %>%
mutate(pct = n/sum(n),
lbl = scales::percent(pct))
## `summarise()` has grouped output by 'class'. You can override using the
## `.groups` argument.
## # A tibble: 12 × 5
## # Groups: class [7]
## class drv n pct lbl
## <chr> <chr> <int> <dbl> <chr>
## 1 2seater r 5 1 100%
## 2 compact 4 12 0.255 26%
## 3 compact f 35 0.745 74%
## 4 midsize 4 3 0.0732 7%
## 5 midsize f 38 0.927 93%
## 6 minivan f 11 1 100%
## 7 pickup 4 33 1 100%
## 8 subcompact 4 4 0.114 11%
## 9 subcompact f 22 0.629 63%
## 10 subcompact r 9 0.257 26%
## 11 suv 4 51 0.823 82%
## 12 suv r 11 0.177 18%
ggplot(plotdata,
aes(x = factor(class,
levels = c("2seater", "subcompact",
"compact", "midsize", "minivan", "suv", "pickup")),y = pct,
fill = factor(drv, levels = c("f", "r", "4"),
labels = c("front-wheel","rear-wheel",
"4-wheel")))) +
geom_bar(stat = "identity",
position = "fill") +
scale_y_continuous(breaks = seq(0, 1, .2),
label = percent) +
geom_text(aes(label = lbl),
size = 3,
position = position_stack(vjust = 0.5)) +
scale_fill_brewer(palette = "Set2") +
labs(y = "Percent",
fill = "Drive Train",
x = "Class",
title = "Automobile Drive by Class") +
theme_minimal()
