Rescale the data is a big part of the data scientist job. In rare occasion data comes in a nice bell shape. One solution to make your data less sensitive to outliers is to rescale them.
ggplot(mtcars, aes(x = log(mpg), y = log(drat))) +
geom_point(aes(color = factor(gear)))
- You transform the x and y variables in log() directly inside the aes() mapping.
Note that any other transformation can be applied such as standardization or normalization.