Data

Data derived from ToothGrowth data sets are used. ToothGrowth describes the effect of Vitamin C on Tooth growth in Guinea pigs.

df <- data.frame(dose=c("D0.5", "D1", "D2"),
                len=c(4.2, 10, 29.5))
head(df)

##   dose  len
## 1 D0.5  4.2
## 2   D1 10.0
## 3   D2 29.5

• len : Tooth length
• dose : Dose in milligrams (0.5, 1, 2)

Create barplots

library(ggplot2)
# Basic barplot
p<-ggplot(data=df, aes(x=dose, y=len)) +
  geom_bar(stat="identity")
p
   
# Horizontal bar plot
p + coord_flip()

Change the width and the color of bars :

# Change the width of bars
ggplot(data=df, aes(x=dose, y=len)) +
  geom_bar(stat="identity", width=0.5)
# Change colors
ggplot(data=df, aes(x=dose, y=len)) +
  geom_bar(stat="identity", color="blue", fill="white")
# Minimal theme + blue fill color
p<-ggplot(data=df, aes(x=dose, y=len)) +
  geom_bar(stat="identity", fill="steelblue")+
  theme_minimal()
p

Choose which items to display :

p + scale_x_discrete(limits=c("D0.5", "D2"))

Bar plot with labels

# Outside bars
ggplot(data=df, aes(x=dose, y=len)) +
  geom_bar(stat="identity", fill="steelblue")+
  geom_text(aes(label=len), vjust=-0.3, size=3.5)+
  theme_minimal()
# Inside bars
ggplot(data=df, aes(x=dose, y=len)) +
  geom_bar(stat="identity", fill="steelblue")+
  geom_text(aes(label=len), vjust=1.6, color="white", size=3.5)+
  theme_minimal()

Barplot of counts

In the R code above, we used the argument stat = “identity” to make barplots. Note that, the default value of the argument stat is “bin”. In this case, the height of the bar represents the count of cases in each category.

To make a barplot of counts, we will use the mtcars data sets :

head(mtcars)

##                    mpg cyl disp  hp drat    wt  qsec vs am gear carb
## Mazda RX4         21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
## Mazda RX4 Wag     21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
## Datsun 710        22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
## Hornet 4 Drive    21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
## Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2
## Valiant           18.1   6  225 105 2.76 3.460 20.22  1  0    3    1

# Don't map a variable to y
ggplot(mtcars, aes(x=factor(cyl)))+
  geom_bar(stat="bin", width=0.7, fill="steelblue")+
  theme_minimal()

Change outline colors

Barplot outline colors can be automatically controlled by the levels of the variable dose :

# Change barplot line colors by groups
p<-ggplot(df, aes(x=dose, y=len, color=dose)) +
  geom_bar(stat="identity", fill="white")
p

It is also possible to change manually barplot line colors using the functions :

• scale_color_manual() : to use custom colors
• scale_color_brewer() : to use color palettes from RColorBrewer package
• scale_color_grey() : to use grey color palettes

# Use custom color palettes
p+scale_color_manual(values=c("#999999", "#E69F00", "#56B4E9"))
# Use brewer color palettes
p+scale_color_brewer(palette="Dark2")
# Use grey scale
p + scale_color_grey() + theme_classic()

Read more on ggplot2 colors here : ggplot2 colors

Change fill colors

In the R code below, barplot fill colors are automatically controlled by the levels of dose :

# Change barplot fill colors by groups
p<-ggplot(df, aes(x=dose, y=len, fill=dose)) +
  geom_bar(stat="identity")+theme_minimal()
p

It is also possible to change manually barplot fill colors using the functions :

• scale_fill_manual() : to use custom colors
• scale_fill_brewer() : to use color palettes from RColorBrewer package
• scale_fill_grey() : to use grey color palettes

# Use custom color palettes
p+scale_fill_manual(values=c("#999999", "#E69F00", "#56B4E9"))
# use brewer color palettes
p+scale_fill_brewer(palette="Dark2")
# Use grey scale
p + scale_fill_grey()

Use black outline color :

ggplot(df, aes(x=dose, y=len, fill=dose))+
geom_bar(stat="identity", color="black")+
scale_fill_manual(values=c("#999999", "#E69F00", "#56B4E9"))+
  theme_minimal()

Read more on ggplot2 colors here : ggplot2 colors

Data

Data derived from ToothGrowth data sets are used. ToothGrowth describes the effect of Vitamin C on tooth growth in Guinea pigs. Three dose levels of Vitamin C (0.5, 1, and 2 mg) with each of two delivery methods [orange juice (OJ) or ascorbic acid (VC)] are used :

df2 <- data.frame(supp=rep(c("VC", "OJ"), each=3),
                dose=rep(c("D0.5", "D1", "D2"),2),
                len=c(6.8, 15, 33, 4.2, 10, 29.5))
head(df2)

##   supp dose  len
## 1   VC D0.5  6.8
## 2   VC   D1 15.0
## 3   VC   D2 33.0
## 4   OJ D0.5  4.2
## 5   OJ   D1 10.0
## 6   OJ   D2 29.5

• len : Tooth length
• dose : Dose in milligrams (0.5, 1, 2)
• supp : Supplement type (VC or OJ)

Create barplots

A stacked barplot is created by default. You can use the function position_dodge() to change this. The barplot fill color is controlled by the levels of dose :

# Stacked barplot with multiple groups
ggplot(data=df2, aes(x=dose, y=len, fill=supp)) +
  geom_bar(stat="identity")
# Use position=position_dodge()
ggplot(data=df2, aes(x=dose, y=len, fill=supp)) +
geom_bar(stat="identity", position=position_dodge())

Change the color manually :

# Change the colors manually
p <- ggplot(data=df2, aes(x=dose, y=len, fill=supp)) +
geom_bar(stat="identity", color="black", position=position_dodge())+
  theme_minimal()
# Use custom colors
p + scale_fill_manual(values=c('#999999','#E69F00'))
# Use brewer color palettes
p + scale_fill_brewer(palette="Blues")

Add labels

Add labels to a dodged barplot :

ggplot(data=df2, aes(x=dose, y=len, fill=supp)) +
  geom_bar(stat="identity", position=position_dodge())+
  geom_text(aes(label=len), vjust=1.6, color="white",
            position = position_dodge(0.9), size=3.5)+
  scale_fill_brewer(palette="Paired")+
  theme_minimal()

Add labels to a stacked barplot : 3 steps are required

1. Sort the data by dose and supp : the package plyr is used
2. Calculate the cumulative sum of the variable len for each dose
3. Create the plot

library(plyr)
# Sort by dose and supp
df_sorted <- arrange(df2, dose, supp) 
head(df_sorted)

##   supp dose  len
## 1   OJ D0.5  4.2
## 2   VC D0.5  6.8
## 3   OJ   D1 10.0
## 4   VC   D1 15.0
## 5   OJ   D2 29.5
## 6   VC   D2 33.0

# Calculate the cumulative sum of len for each dose
df_cumsum <- ddply(df_sorted, "dose",
                   transform, label_ypos=cumsum(len))
head(df_cumsum)

##   supp dose  len label_ypos
## 1   OJ D0.5  4.2        4.2
## 2   VC D0.5  6.8       11.0
## 3   OJ   D1 10.0       10.0
## 4   VC   D1 15.0       25.0
## 5   OJ   D2 29.5       29.5
## 6   VC   D2 33.0       62.5

# Create the barplot
ggplot(data=df_cumsum, aes(x=dose, y=len, fill=supp)) +
  geom_bar(stat="identity")+
  geom_text(aes(y=label_ypos, label=len), vjust=1.6, 
            color="white", size=3.5)+
  scale_fill_brewer(palette="Paired")+
  theme_minimal()

If you want to place the labels at the middle of bars, you have to modify the cumulative sum as follow :

df_cumsum <- ddply(df_sorted, "dose",
                   transform, 
                   label_ypos=cumsum(len) - 0.5*len)
# Create the barplot
ggplot(data=df_cumsum, aes(x=dose, y=len, fill=supp)) +
  geom_bar(stat="identity")+
  geom_text(aes(y=label_ypos, label=len), vjust=1.6, 
            color="white", size=3.5)+
  scale_fill_brewer(palette="Paired")+
  theme_minimal()