Data Visualization: Box Plots

viz_box.R

# basic plot
boxplot(mtcars$mpg)

# horizontal box plot
boxplot(mtcars$mpg, horizontal = TRUE)

# color
boxplot(mtcars$mpg, col = 'blue')

# border color
boxplot(mtcars$mpg, border = 'red')

# range
boxplot(mtcars$mpg, range = 0)
boxplot(mtcars$mpg, range = 1)

# outline
boxplot(mtcars$mpg, range = 1, outline = FALSE)
boxplot(mtcars$mpg, range = 1, outline = TRUE)

# varwidth
boxplot(mtcars$mpg, varwidth = TRUE, range = 1)
boxplot(mtcars$mpg, varwidth = FALSE, range = 1)

# bivariate plot
# using formula
boxplot(mtcars$mpg ~ mtcars$cyl)

# using data
mpg_split <- split(mtcars$mpg, mtcars$cyl)
mpg_4 <- mpg_split$`4`
mpg_6 <- mpg_split$`6`
mpg_8 <- mpg_split$`8`
boxplot(mpg_4, mpg_6, mpg_8)

# color
boxplot(mtcars$mpg ~ mtcars$cyl, col = 'blue')

# compare medians
hsb <- read.table('https://stats.idre.ucla.edu/wp-content/uploads/2016/02/hsb2-2.csv', header=T, sep=",")
boxplot(hsb$read ~ hsb$female, notch = TRUE, 
        col = c('red', 'blue'))

# putting it all together
boxplot(mtcars$mpg ~ mtcars$cyl, range = 1, outline = TRUE, 
        horizontal = TRUE, col = c('red', 'blue', 'yellow'),
        main = 'Miles Per Gallon by Cylinders', 
        ylab = 'Number of Cylinders', xlab = 'Miles Per Gallon',
        names = c('Four', 'Six', 'Eight'))