ggplot2 : geom_boxplot()

geom_boxplot()

최소값, 최대값, 평균, 4분위수와 이상값을 사각형 모양의 그래프로 출력함.

> mpg
# A tibble: 234 x 11
   manufacturer model      displ  year   cyl trans      drv     cty   hwy fl    class  
   <chr>        <chr>      <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr>  
 1 audi         a4           1.8  1999     4 auto(l5)   f        18    29 p     compact
 2 audi         a4           1.8  1999     4 manual(m5) f        21    29 p     compact
 3 audi         a4           2    2008     4 manual(m6) f        20    31 p     compact
 4 audi         a4           2    2008     4 auto(av)   f        21    30 p     compact
 5 audi         a4           2.8  1999     6 auto(l5)   f        16    26 p     compact
 6 audi         a4           2.8  1999     6 manual(m5) f        18    26 p     compact
 7 audi         a4           3.1  2008     6 auto(av)   f        18    27 p     compact
 8 audi         a4 quattro   1.8  1999     4 manual(m5) 4        18    26 p     compact
 9 audi         a4 quattro   1.8  1999     4 auto(l5)   4        16    25 p     compact
10 audi         a4 quattro   2    2008     4 manual(m6) 4        20    28 p     compact
# ... with 224 more rows

p <- ggplot(mpg, aes(class, hwy))
p + geom_boxplot()
p + geom_boxplot() + coord_flip()

p + geom_boxplot(notch = TRUE)
p + geom_boxplot(varwidth = TRUE)
p + geom_boxplot(fill = "white", colour = "#3366FF")

# By default, outlier points match the colour of the box. Use
# outlier.colour to override
p + geom_boxplot(outlier.colour = "red", outlier.shape = 1)

# Remove outliers when overlaying boxplot with original data points
p + geom_boxplot(outlier.shape = NA) + geom_jitter(width = 0.2)

> diamonds
# A tibble: 53,940 x 10
   carat cut       color clarity depth table price     x     y     z
   <dbl> <ord>     <ord> <ord>   <dbl> <dbl> <int> <dbl> <dbl> <dbl>
 1 0.23  Ideal     E     SI2      61.5    55   326  3.95  3.98  2.43
 2 0.21  Premium   E     SI1      59.8    61   326  3.89  3.84  2.31
 3 0.23  Good      E     VS1      56.9    65   327  4.05  4.07  2.31
 4 0.290 Premium   I     VS2      62.4    58   334  4.2   4.23  2.63
 5 0.31  Good      J     SI2      63.3    58   335  4.34  4.35  2.75
 6 0.24  Very Good J     VVS2     62.8    57   336  3.94  3.96  2.48
 7 0.24  Very Good I     VVS1     62.3    57   336  3.95  3.98  2.47
 8 0.26  Very Good H     SI1      61.9    55   337  4.07  4.11  2.53
 9 0.22  Fair      E     VS2      65.1    61   337  3.87  3.78  2.49
10 0.23  Very Good H     VS1      59.4    61   338  4     4.05  2.39
# ... with 53,930 more rows
# You can also use boxplots with continuous x, as long as you supply
# a grouping variable. cut_width is particularly useful
ggplot(diamonds, aes(carat, price)) +
  geom_boxplot()
ggplot(diamonds, aes(carat, price)) +
  geom_boxplot(aes(group = cut_width(carat, 0.25)))

# Adjust the transparency of outliers using outlier.alpha
ggplot(diamonds, aes(carat, price)) +
  geom_boxplot(aes(group = cut_width(carat, 0.25)), outlier.alpha = 0.1)

# It's possible to draw a boxplot with your own computations if you
# use stat = "identity":
y <- rnorm(100)
df <- data.frame(
  x = 1,
  y0 = min(y),
  y25 = quantile(y, 0.25),
  y50 = median(y),
  y75 = quantile(y, 0.75),
  y100 = max(y)
)
ggplot(df, aes(x)) +
  geom_boxplot(
    aes(ymin = y0, lower = y25, middle = y50, upper = y75, ymax = y100),
    stat = "identity"
  )