Plots of mtcars data with ggplot2

Load the mtcars data

data(mtcars, package="datasets")
str(mtcars)

## 'data.frame':    32 obs. of  11 variables:
##  $ mpg : num  21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
##  $ cyl : num  6 6 4 6 8 6 8 4 4 6 ...
##  $ disp: num  160 160 108 258 360 ...
##  $ hp  : num  110 110 93 110 175 105 245 62 95 123 ...
##  $ drat: num  3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
##  $ wt  : num  2.62 2.88 2.32 3.21 3.44 ...
##  $ qsec: num  16.5 17 18.6 19.4 17 ...
##  $ vs  : num  0 0 1 1 0 1 0 1 1 1 ...
##  $ am  : num  1 1 1 0 0 0 0 0 0 0 ...
##  $ gear: num  4 4 4 3 3 3 3 4 4 4 ...
##  $ carb: num  4 4 1 1 2 1 4 2 2 4 ...

Plot with base graphics

This doesn’t quite come out right because it is hard to coordinate the choices for point symbols and colors in the plot with those in the legend

mtcars$cyl <- as.factor(mtcars$cyl)
plot(mpg ~ hp , data=mtcars, 
    col=cyl, pch=c(4,6,8)[mtcars$cyl], cex=1.2)
legend("topright", legend=levels(mtcars$cyl),
                   pch = c(4,6,8),
                   col=levels(mtcars$cyl))

Plots with ggplot2

Basic plot: mpg vs. hp

Specify aesthetic mappings for x=hp and y=mpg to setup the coordinates, then add points with geom_point()

library(ggplot2)
ggplot(mtcars, aes(x=hp, y=mpg)) +
  geom_point(size=3)

Distinguish cars by number of cylinders

Use color and shape as additional aesthetics. To do this, make cyl a factor

library(dplyr)
mtcars <- mtcars |>
  mutate(cyl = as.factor(cyl))

ggplot(mtcars, aes(x=hp, y=mpg, 
                   color=cyl, 
                   shape=cyl)) +
    geom_point(size=3)

Add separate regression lines

ggplot(mtcars, aes(x=hp, y=mpg, color=cyl, shape=cyl)) +
    geom_point(size=3) +
    geom_smooth(method="lm", aes(fill=cyl)) 

Add overall smooth

ggplot(mtcars, aes(x=hp, y=mpg)) +
    geom_point(size=3, aes(color=cyl, shape=cyl)) +
    geom_smooth(method="loess", color="black", se=FALSE, lwd = 2) +
    geom_smooth(method="lm", aes(color=cyl, fill=cyl)) 

Change the theme

last_plot() + theme_bw()

Faceting

plt <-
ggplot(mtcars, aes(x=hp, y=mpg, color=cyl, shape=cyl)) +
    geom_point(size=3) +
    geom_smooth(method="lm", aes(fill=cyl)) 

plt + facet_wrap(~cyl)

Labeling points, change theme,

plt2 <- ggplot(mtcars, aes(x=wt, y=mpg)) +
  geom_point(color = 'red', size=2) +
  geom_smooth(method="loess") +
  labs(y="Miles per gallon", x="Weight (1000 lbs.)") +
  theme_classic(base_size = 16)
plt2 + geom_text(aes(label = rownames(mtcars)))

library(ggrepel)
plt2 + geom_text_repel(aes(label = rownames(mtcars)))

Only label points with large residuals

mod <- loess( mpg ~ wt, data=mtcars)
resids <- residuals(mod)
mtcars$label <- ifelse(abs(resids) > 2.5, rownames(mtcars), "")

plt2 + 
    geom_text_repel(aes(label = mtcars$label))