Boxplots

Lets look at some boxplots

data("ToothGrowth")

Lets change the dose to a factor, and look at the top of the dataframe

ToothGrowth$dose <- as.factor(ToothGrowth$dose)

head(ToothGrowth,4)

##    len supp dose
## 1  4.2   VC  0.5
## 2 11.5   VC  0.5
## 3  7.3   VC  0.5
## 4  5.8   VC  0.5

Lets load ggplot

library(ggplot2)

Lets set the theme for our plots to classic

theme_set(
  theme_bw()+
    theme(legend.position = "top")
)

Lets start with a very basic boxplot with dose vs length

tg <- ggplot(ToothGrowth,aes(x=dose,y=len))
tg+geom_boxplot()

Now lets look at a boxplot with points for the mean

tg +geom_boxplot(notch = TRUE,fill="lightgrey")+
  stat_summary(fun.y=mean,geom="point",shape=18,size=2.5,color="indianred")

## Warning: The `fun.y` argument of `stat_summary()` is deprecated as of ggplot2 3.3.0.
## ℹ Please use the `fun` argument instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

We can also change the scale number of variables included, and their order

tg + geom_boxplot()+
  scale_x_discrete(limits=c("0.5","2"))

## Warning: Removed 20 rows containing missing values (`stat_boxplot()`).

Let put our x axis in descending order

tg + geom_boxplot()+
  scale_x_discrete(limits=c("2","1","0.5"))

We can also change boxplot colors by groups

tg+geom_boxplot(aes(color =dose))+
  scale_color_manual(values=c("indianred","blue1","green2"))

What if we want to display our data subset data subset by oj vs vitamin c?

tg2 <- tg + geom_boxplot(aes(fill=supp),position=position_dodge(0.9))+
  scale_fill_manual(values = c("#999999","#E69F00"))
tg2

We can also arrange this as two plots with facet_wrap

tg2+facet_wrap(~supp)