Scatter plots with text annotations

We start by creating a simple scatter plot using a subset of the mtcars data set containing 15 rows.

1. Prepare some data:

# Take a subset of 15 random points
set.seed(1234)
ss <- sample(1:32, 15)
df <- mtcars[ss, ]

2. Create a scatter plot:

p <- ggplot(df, aes(wt, mpg)) +
  geom_point(color = 'red') +
  theme_classic(base_size = 10)

3. Add text labels:

# Add text annotations using ggplot2::geom_text
p + geom_text(aes(label = rownames(df)),
              size = 3.5)

# Use ggrepel::geom_text_repel
require("ggrepel")
set.seed(42)
p + geom_text_repel(aes(label = rownames(df)),
                    size = 3.5) 

# Use ggrepel::geom_label_repel and 
# Change color by groups
set.seed(42)
p + geom_label_repel(aes(label = rownames(df),
                    fill = factor(cyl)), color = 'white',
                    size = 3.5) +
   theme(legend.position = "bottom")

Volcano plot

genes <- read.table("https://gist.githubusercontent.com/stephenturner/806e31fce55a8b7175af/raw/1a507c4c3f9f1baaa3a69187223ff3d3050628d4/results.txt", header = TRUE)
genes$Significant <- ifelse(genes$padj < 0.05, "FDR < 0.05", "Not Sig")
ggplot(genes, aes(x = log2FoldChange, y = -log10(pvalue))) +
  geom_point(aes(color = Significant)) +
  scale_color_manual(values = c("red", "grey")) +
  theme_bw(base_size = 12) + theme(legend.position = "bottom") +
  geom_text_repel(
    data = subset(genes, padj < 0.05),
    aes(label = Gene),
    size = 5,
    box.padding = unit(0.35, "lines"),
    point.padding = unit(0.3, "lines")
  )

source

Calculate the mean of each group :

library(plyr)
mu <- ddply(df, "sex", summarise, grp.mean=mean(weight))
head(mu)

##   sex grp.mean
## 1   F    54.70
## 2   M    65.36

Change line colors

Density plot line colors can be automatically controlled by the levels of sex :

# Change density plot line colors by groups
ggplot(df, aes(x=weight, color=sex)) +
  geom_density()
# Add mean lines
p<-ggplot(df, aes(x=weight, color=sex)) +
  geom_density()+
  geom_vline(data=mu, aes(xintercept=grp.mean, color=sex),
             linetype="dashed")
p

It is also possible to change manually density plot 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

Density plot fill colors can be automatically controlled by the levels of sex :

# Change density plot fill colors by groups
ggplot(df, aes(x=weight, fill=sex)) +
  geom_density()
# Use semi-transparent fill
p<-ggplot(df, aes(x=weight, fill=sex)) +
  geom_density(alpha=0.4)
p
# Add mean lines
p+geom_vline(data=mu, aes(xintercept=grp.mean, color=sex),
             linetype="dashed")

It is also possible to change manually density plot 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() + theme_classic()

Read more on ggplot2 colors here : ggplot2 colors

Scatter plots

The R code below creates basic scatter plots using the argument geom = “point”. It’s also possible to combine different geoms (e.g.: geom = c(“point”, “smooth”)).

# Basic scatter plot
qplot(x = mpg, y = wt, data = df, geom = "point")
# Scatter plot with smoothed line
qplot(mpg, wt, data = df, 
      geom = c("point", "smooth"))

The following R code will change the color and the shape of points by groups. The column cyl will be used as grouping variable. In other words, the color and the shape of points will be changed by the levels of cyl.

qplot(mpg, wt, data = df, colour = cyl, shape = cyl)

Box plot, violin plot and dot plot

The R code below generates some data containing the weights by sex (M for male; F for female):

set.seed(1234)
wdata = data.frame(
        sex = factor(rep(c("F", "M"), each=200)),
        weight = c(rnorm(200, 55), rnorm(200, 58)))
head(wdata)

##   sex   weight
## 1   F 53.79293
## 2   F 55.27743
## 3   F 56.08444
## 4   F 52.65430
## 5   F 55.42912
## 6   F 55.50606

# Basic box plot from data frame
qplot(sex, weight, data = wdata, 
      geom= "boxplot", fill = sex)
# Violin plot
qplot(sex, weight, data = wdata, geom = "violin")
# Dot plot
qplot(sex, weight, data = wdata, geom = "dotplot",
      stackdir = "center", binaxis = "y", dotsize = 0.5)

Histogram and density plots

The histogram and density plots are used to display the distribution of data.

# Histogram  plot
# Change histogram fill color by group (sex)
qplot(weight, data = wdata, geom = "histogram",
      fill = sex)
# Density plot
# Change density plot line color by group (sex)
# change line type
qplot(weight, data = wdata, geom = "density",
    color = sex, linetype = sex)

One variable: Continuous

We’ll use weight data (wdata), generated in the previous sections.

head(wdata)

##   sex   weight
## 1   F 53.79293
## 2   F 55.27743
## 3   F 56.08444
## 4   F 52.65430
## 5   F 55.42912
## 6   F 55.50606

The following R code computes the mean value by sex:

library(plyr)
mu <- ddply(wdata, "sex", summarise, grp.mean=mean(weight))
head(mu)

##   sex grp.mean
## 1   F 54.94224
## 2   M 58.07325

We start by creating a plot, named a, that we’ll finish in the next section by adding a layer.

a <- ggplot(wdata, aes(x = weight))

# Basic plot
a + geom_area(stat = "bin")
# change fill colors by sex
a + geom_area(aes(fill = sex), stat ="bin", alpha=0.6) +
  theme_classic()

a + geom_area(aes(y = ..density..), stat ="bin")

a + stat_bin(geom = "area")

# Basic plot
a + geom_density()
# change line colors by sex
a + geom_density(aes(color = sex)) 
# Change fill color by sex
# Use semi-transparent fill: alpha = 0.4
a + geom_density(aes(fill = sex), alpha=0.4)
   
# Add mean line and Change color manually
a + geom_density(aes(color = sex)) +
  geom_vline(data=mu, aes(xintercept=grp.mean, color=sex),
             linetype="dashed") +
  scale_color_manual(values=c("#999999", "#E69F00"))

a + stat_density()

# Basic plot
a + geom_dotplot()
# change fill and color by sex
a + geom_dotplot(aes(fill = sex)) 
# Change fill color manually 
a + geom_dotplot(aes(fill = sex)) +
  scale_fill_manual(values=c("#999999", "#E69F00"))

# Basic plot
a + geom_freqpoly() 
# change y axis to density value
# and change theme
a + geom_freqpoly(aes(y = ..density..)) +
  theme_minimal()
# change color and linetype by sex
a + geom_freqpoly(aes(color = sex, linetype = sex)) +
  theme_minimal()

# Basic plot
a + geom_histogram()
# change line colors by sex
a + geom_histogram(aes(color = sex), fill = "white",
                   position = "dodge") 

a + geom_histogram(aes(y = ..density..))

a + stat_bin(geom = "histogram")

a + stat_ecdf()

ggplot(mtcars, aes(sample=mpg)) + stat_qq()

One variable: Discrete

The function geom_bar() can be used to visualize one discrete variable. In this case, the count of each level is plotted. We’ll use the mpg data set [in ggplot2 package]. The R code is as follow:

data(mpg)
b <- ggplot(mpg, aes(fl))
# Basic plot
b + geom_bar()
# Change fill color
b + geom_bar(fill = "steelblue", color ="steelblue") +
  theme_minimal()

To customize the plot, the following arguments can be used: alpha, color, fill, linetype and size. Learn more here: ggplot2 bar plot.

• Key function: geom_bar()
• Alternative function: stat_count()

b + stat_count()

Two variables: Continuous X, Continuous Y

We’ll use the mtcars data set. The variable cyl is used as grouping variable.

data(mtcars)
mtcars$cyl <- as.factor(mtcars$cyl)
head(mtcars[, c("wt", "mpg", "cyl")])

##                      wt  mpg cyl
## Mazda RX4         2.620 21.0   6
## Mazda RX4 Wag     2.875 21.0   6
## Datsun 710        2.320 22.8   4
## Hornet 4 Drive    3.215 21.4   6
## Hornet Sportabout 3.440 18.7   8
## Valiant           3.460 18.1   6

We start by creating a plot, named b, that we’ll finish in the next section by adding a layer.

b <- ggplot(mtcars, aes(x = wt, y = mpg))

# Basic plot
b + geom_point()
   
# change the color and the point 
# by the levels of cyl variable
b + geom_point(aes(color = cyl, shape = cyl)) 
# Change color manually
b + geom_point(aes(color = cyl, shape = cyl)) +
  scale_color_manual(values = c("#999999", "#E69F00", "#56B4E9"))+
  theme_minimal()

# Regression line only
b + geom_smooth(method = lm)
  
# Point + regression line
# Remove the confidence interval 
b + geom_point() + 
  geom_smooth(method = lm, se = FALSE)
# loess method: local regression fitting
b + geom_point() + geom_smooth()
# Change color and shape by groups (cyl)
b + geom_point(aes(color=cyl, shape=cyl)) + 
  geom_smooth(aes(color=cyl, shape=cyl), 
              method=lm, se=FALSE, fullrange=TRUE)

b + stat_smooth(method = "lm")

ggplot(mpg, aes(cty, hwy)) +
  geom_point() + geom_quantile() +
  theme_minimal()

ggplot(mpg, aes(cty, hwy)) +
  geom_point() + stat_quantile(quantiles = c(0.25, 0.5, 0.75))

# Add marginal rugs using faithful data
ggplot(faithful, aes(x=eruptions, y=waiting)) +
  geom_point() + geom_rug()

p <- ggplot(mpg, aes(displ, hwy))
# Default scatter plot
p + geom_point()
# Use jitter to reduce overplotting
p + geom_jitter(
    position = position_jitter(width = 0.5, height = 0.5))

b + geom_text(aes(label = rownames(mtcars)))

Two variables: Continuous bivariate distribution

We start by using the diamonds data set [in ggplot2].

data(diamonds)
head(diamonds[, c("carat", "price")])

##   carat price
## 1  0.23   326
## 2  0.21   326
## 3  0.23   327
## 4  0.29   334
## 5  0.31   335
## 6  0.24   336

We start by creating a plot, named c, that we’ll finish in the next section by adding a layer.

c <- ggplot(diamonds, aes(carat, price))

# Default plot 
c + geom_bin2d()
# Change the number of bins
c + geom_bin2d(bins = 15)

c + stat_bin_2d()
c + stat_summary_2d(aes(z = depth))

install.packages("hexbin")

require(hexbin)
# Default plot 
c + geom_hex()
# Change the number of bins
c + geom_hex(bins = 10)

c + stat_bin_hex()
c + stat_summary_hex(aes(z = depth))

# Scatter plot 
sp <- ggplot(faithful, aes(x=eruptions, y=waiting)) 

# Default plot
sp + geom_density_2d()
# Add points
sp + geom_point() + geom_density_2d()
# Use stat_density_2d with geom = "polygon"
sp + geom_point() + 
  stat_density_2d(aes(fill = ..level..), geom="polygon")

sp + stat_density_2d()

Two variables: Continuous function

In this section, we’ll see how to connect observations by line. The economics data set [in ggplot2] is used.

data(economics)
head(economics)

##         date   pce    pop psavert uempmed unemploy
## 1 1967-07-01 507.4 198712    12.5     4.5     2944
## 2 1967-08-01 510.5 198911    12.5     4.7     2945
## 3 1967-09-01 516.3 199113    11.7     4.6     2958
## 4 1967-10-01 512.9 199311    12.5     4.9     3143
## 5 1967-11-01 518.1 199498    12.5     4.7     3066
## 6 1967-12-01 525.8 199657    12.1     4.8     3018

We start by creating a plot, named d, that we’ll finish in the next section by adding a layer.

d <- ggplot(economics, aes(x = date, y = unemploy))

# Area plot
d + geom_area()
# Line plot: connecting observations, ordered by x
d + geom_line()
# Connecting observations by stairs
# a subset of economics data set is used
set.seed(1234)
ss <- economics[sample(1:nrow(economics), 20), ]
ggplot(ss, aes(x = date, y = unemploy)) + 
  geom_step()

To customize the plot, the following arguments can be used: alpha, color, linetype, size and fill (for geom_area only). Learn more here: ggplot2 line plot.

• Key functions: geom_area(), geom_line(), geom_step()

Two variables: Discrete X, Continuous Y

The ToothGrowth data set we’ll be used to plot the continuous variable len (for tooth length) by the discrete variable dose. The following R code converts the variable dose from a numeric to a discrete factor variable.

data("ToothGrowth")
ToothGrowth$dose <- as.factor(ToothGrowth$dose)
head(ToothGrowth)

##    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
## 5  6.4   VC  0.5
## 6 10.0   VC  0.5

We start by creating a plot, named e, that we’ll finish in the next section by adding a layer.

e <- ggplot(ToothGrowth, aes(x = dose, y = len))

# Default plot
e + geom_boxplot()
# Notched box plot
e + geom_boxplot(notch = TRUE)
# Color by group (dose)
e + geom_boxplot(aes(color = dose))
# Change fill color by group (dose)
e + geom_boxplot(aes(fill = dose))

# Box plot with multiple groups
ggplot(ToothGrowth, aes(x=dose, y=len, fill=supp)) +
  geom_boxplot()

e + stat_boxplot(coeff = 1.5)

# Default plot
e + geom_violin(trim = FALSE)
# violin plot with mean points (+/- SD)
e + geom_violin(trim = FALSE) + 
  stat_summary(fun.data="mean_sdl",  fun.args = list(mult=1), 
               geom="pointrange", color = "red")
# Combine with box plot
e + geom_violin(trim = FALSE) + 
  geom_boxplot(width = 0.2)
# Color by group (dose) 
e + geom_violin(aes(color = dose), trim = FALSE)

e + stat_ydensity(trim = FALSE)

# Default plot
e + geom_dotplot(binaxis = "y", stackdir = "center")
# Dot plot with mean points (+/- SD)
e + geom_dotplot(binaxis = "y", stackdir = "center") + 
  stat_summary(fun.data="mean_sdl",  fun.args = list(mult=1), 
               geom="pointrange", color = "red")

# Combine with box plot
e + geom_boxplot() + 
  geom_dotplot(binaxis = "y", stackdir = "center") 
# Add violin plot
e + geom_violin(trim = FALSE) +
  geom_dotplot(binaxis='y', stackdir='center')
  
# Color and fill by group (dose) 
e + geom_dotplot(aes(color = dose, fill = dose), 
                 binaxis = "y", stackdir = "center")

# Default plot
e + geom_jitter(position=position_jitter(0.2))
# Strip charts with mean points (+/- SD)
e + geom_jitter(position=position_jitter(0.2)) + 
  stat_summary(fun.data="mean_sdl",  fun.args = list(mult=1), 
               geom="pointrange", color = "red")

# Combine with box plot
e + geom_jitter(position=position_jitter(0.2)) + 
  geom_dotplot(binaxis = "y", stackdir = "center") 
# Add violin plot
e + geom_violin(trim = FALSE) +
  geom_jitter(position=position_jitter(0.2))
  
# Change color and shape by group (dose) 
e +  geom_jitter(aes(color = dose, shape = dose),
                 position=position_jitter(0.2))

df <- 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(df)

##   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

# Change line types by groups (supp)
ggplot(df, aes(x=dose, y=len, group=supp)) +
  geom_line(aes(linetype=supp))+
  geom_point()
# Change line types, point shapes and colors
ggplot(df, aes(x=dose, y=len, group=supp)) +
  geom_line(aes(linetype=supp, color = supp))+
  geom_point(aes(shape=supp, color = supp))

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

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

f <- ggplot(df, aes(x = dose, y = len))

# Basic bar plot
f + geom_bar(stat = "identity")
# Change fill color and add labels
f + geom_bar(stat="identity", fill="steelblue")+
  geom_text(aes(label=len), vjust=-0.3, size=3.5)+
  theme_minimal()
# Change bar plot line colors by groups
f + geom_bar(aes(color = dose),
             stat="identity", fill="white")
# Change bar plot fill colors by groups
f + geom_bar(aes(fill = dose), stat="identity")

g <- ggplot(data=df2, aes(x=dose, y=len, fill=supp)) 
# Stacked bar plot
g + geom_bar(stat = "identity")
# Use position=position_dodge()
g + geom_bar(stat="identity", position=position_dodge())

g + stat_identity(geom = "bar")
g + stat_identity(geom = "bar", position = "dodge")

Two variables: Discrete X, Discrete Y

The diamonds data set [in ggplot2] we’ll be used to plot the discrete variable color (for diamond colors) by the discrete variable cut (for diamond cut types). The plot is created using the function geom_jitter().

ggplot(diamonds, aes(cut, color)) +
  geom_jitter(aes(color = cut), size = 0.5)

To customize the plot, the following arguments can be used: alpha, color, fill, shape and size.

• Key function: geom_jitter()

Two variables: Visualizing error

The ToothGrowth data set we’ll be used. We start by creating a data set named df which holds ToothGrowth data.

# ToothGrowth data set
df <- ToothGrowth
df$dose <- as.factor(df$dose)
head(df)

##    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
## 5  6.4   VC  0.5
## 6 10.0   VC  0.5

The helper function below (data_summary()) will be used to calculate the mean and the standard deviation (used as error), for the variable of interest, in each group. The plyr package is required.

# Calculate the mean and the SD in each group
#+++++++++++++++++++++++++
# data : a data frame
# varname : the name of the variable to be summariezed
# grps : column names to be used as grouping variables
data_summary <- function(data, varname, grps){
  require(plyr)
  summary_func <- function(x, col){
    c(mean = mean(x[[col]], na.rm=TRUE),
      sd = sd(x[[col]], na.rm=TRUE))
  }
  data_sum<-ddply(data, grps, .fun=summary_func, varname)
  data_sum <- rename(data_sum, c("mean" = varname))
 return(data_sum)
}

Using the function data_summary(), the following R code creates a data set named df2 which holds the mean and the SD of tooth length (len) by groups (dose).

df2 <- data_summary(df, varname="len", grps= "dose")
# Convert dose to a factor variable
df2$dose=as.factor(df2$dose)
head(df2)

##   dose    len       sd
## 1  0.5 10.605 4.499763
## 2    1 19.735 4.415436
## 3    2 26.100 3.774150

We start by creating a plot, named f, that we’ll finish in the next section by adding a layer.

f <- ggplot(df2, aes(x = dose, y = len, 
                     ymin = len-sd, ymax = len+sd))

# Default plot
f + geom_crossbar()
# color by groups
f + geom_crossbar(aes(color = dose))
# Change color manually
f + geom_crossbar(aes(color = dose)) + 
  scale_color_manual(values = c("#999999", "#E69F00", "#56B4E9"))+
  theme_minimal()
# fill by groups and change color manually
f + geom_crossbar(aes(fill = dose)) + 
  scale_fill_manual(values = c("#999999", "#E69F00", "#56B4E9"))+
  theme_minimal()

df3 <- data_summary(df, varname="len", grps= c("supp", "dose"))
head(df3)

##   supp dose   len       sd
## 1   OJ  0.5 13.23 4.459709
## 2   OJ    1 22.70 3.910953
## 3   OJ    2 26.06 2.655058
## 4   VC  0.5  7.98 2.746634
## 5   VC    1 16.77 2.515309
## 6   VC    2 26.14 4.797731

f <- ggplot(df3, aes(x = dose, y = len, 
                     ymin = len-sd, ymax = len+sd))
# Default plot
f + geom_crossbar(aes(color = supp))
# Use position_dodge() to avoid overlap
f + geom_crossbar(aes(color = supp), 
                  position = position_dodge(1))

f <- ggplot(df, aes(x = dose, y = len, color = supp)) 
# Use geom_crossbar()
f + stat_summary(fun.data="mean_sdl", fun.args = list(mult=1), 
                 geom="crossbar", width = 0.6, 
                 position = position_dodge(0.8))

f <- ggplot(df2, aes(x = dose, y = len, 
                     ymin = len-sd, ymax = len+sd))

# Error bars colored by groups
f + geom_errorbar(aes(color = dose), width = 0.2)
# Combine with line plot
f + geom_line(aes(group = 1)) + 
  geom_errorbar(width = 0.2)
# Combine with bar plot, color by groups
f + geom_bar(aes(color = dose), stat = "identity", fill ="white") + 
  geom_errorbar(aes(color = dose), width = 0.2)

f <- ggplot(df3, aes(x = dose, y = len, 
                     ymin = len-sd, ymax = len+sd))
# Default plot
f + geom_bar(aes(fill = supp), stat = "identity",
             position = "dodge") + 
  geom_errorbar(aes(color = supp),  position = "dodge")

df2 <- data_summary(ToothGrowth, varname="len", grps = "dose")
head(df2)

##   dose    len       sd
## 1  0.5 10.605 4.499763
## 2    1 19.735 4.415436
## 3    2 26.100 3.774150

f <- ggplot(df2, aes(x = len, y = dose ,
                     xmin=len-sd, xmax=len+sd))

f <- ggplot(df2, aes(x = dose, y = len,
                     ymin=len-sd, ymax=len+sd))
# Line range
f + geom_linerange()
# Point range
f + geom_pointrange()

g <- ggplot(df, aes(x=dose, y=len)) + 
  geom_dotplot(binaxis='y', stackdir='center')

# use geom_crossbar()
g + stat_summary(fun.data="mean_sdl", fun.args = list(mult=1), 
                 geom="crossbar", width=0.5)
# Use geom_errorbar()
g + stat_summary(fun.data=mean_sdl, fun.args = list(mult=1), 
        geom="errorbar", color="red", width=0.2) +
  stat_summary(fun.y=mean, geom="point", color="red")
   
# Use geom_pointrange()
g + stat_summary(fun.data=mean_sdl, fun.args = list(mult=1), 
                 geom="pointrange", color="red")

Two variables: Maps

The function geom_map() can be used to create a map with ggplot2. The R package map is required. It contains geographical information useful for drawing easily maps in ggplot2.

Install map package (if you don’t have it):

install.packages("map")

In the following R code, we’ll create USA map and USArrests crime data to shade each region.

# Prepare the data
crimes <- data.frame(state = tolower(rownames(USArrests)), 
                     USArrests)
library(reshape2) # for melt
crimesm <- melt(crimes, id = 1)
# Get map data
require(maps) 
map_data <- map_data("state")
# Plot the map with Murder data
ggplot(crimes, aes(map_id = state)) + 
  geom_map(aes(fill = Murder), map = map_data) + 
  expand_limits(x = map_data$long, y = map_data$lat)

To customize the plot, the following arguments can be used: alpha, color, fill, linetype and size. Learn more here: ggplot2 map.

Key function: geom_map()

Three variables

The mtcars data set we’ll be used. We first compute a correlation matrix, which will be visualized using specific ggplot2 functions.

Prepare the data:

df <- mtcars[, c(1,3,4,5,6,7)]
# Correlation matrix
cormat <- round(cor(df),2)
# Melt the correlation matrix
require(reshape2)
cormat <- melt(cormat)
head(cormat)

##   Var1 Var2 value
## 1  mpg  mpg  1.00
## 2 disp  mpg -0.85
## 3   hp  mpg -0.78
## 4 drat  mpg  0.68
## 5   wt  mpg -0.87
## 6 qsec  mpg  0.42

We start by creating a plot, named g, that we’ll finish in the next section by adding a layer.

g <- ggplot(cormat, aes(x = Var1, y = Var2))

We’ll use the function geom_tile() to visualize a correlation matrix.

Compute and visualize correlation matrix:

# 1. Compute correlation
cormat <- round(cor(df),2)
# 2. Reorder the correlation matrix by 
# Hierarchical clustering
hc <- hclust(as.dist(1-cormat)/2)
cormat.ord <- cormat[hc$order, hc$order]
# 3. Get the upper triangle
cormat.ord[lower.tri(cormat.ord)]<- NA
# 4. Melt the correlation matrix
require(reshape2)
melted_cormat <- melt(cormat.ord, na.rm = TRUE)
# Create the heatmap
ggplot(melted_cormat, aes(Var2, Var1, fill = value))+
  geom_tile(color = "white")+
  scale_fill_gradient2(low = "blue", high = "red", mid = "white", 
   midpoint = 0, limit = c(-1,1), space = "Lab",
   name="Pearson\nCorrelation") + # Change gradient color
  theme_minimal()+ # minimal theme
 theme(axis.text.x = element_text(angle = 45, vjust = 1, 
                                  size = 12, hjust = 1))+
 coord_fixed()

To customize the plot, the following arguments can be used: alpha, color, fill, linetype and size. Learn more here: ggplot2 correlation matrix heatmap.

• Key functions: geom_tile(), geom_raster()

Other types of graphs

• Pie chart: (click to read more)

• Survival curves: (click to read more)

Graphical primitives: polygon, path, ribbon, segment, rectangle

This section describes how to add graphical elements to a plot. The functions below we’ll be used:

1. The R code below draws France map using geom_polygon():

require(maps)
france = map_data('world', region = 'France')
ggplot(france, aes(x = long, y = lat, group = group)) +
  geom_polygon(fill = 'white', colour = 'black')

To customize the plot, the following arguments can be used: alpha, color, fill, linetype and size.

2. The following R code uses econimics data [in ggplot2] and produces path, ribbon and rectangles.

h <- ggplot(economics, aes(date, unemploy))
# Path
h + geom_path()
# Ribbon
h + geom_ribbon(aes(ymin = unemploy-900, ymax = unemploy+900),
                fill = "steelblue") +
  geom_path(size = 0.8)
# Rectangle
h + geom_rect(aes(xmin = as.Date('1980-01-01'), ymin = -Inf, 
                 xmax = as.Date('1985-01-01'), ymax = Inf),
             fill = "steelblue") +
  geom_path(size = 0.8) 

To customize the plot, the following arguments can be used: alpha, color, fill (for ribbon only), linetype and size.

3. Add line segments between points (x1, y1) and (x2, y2):

# Create a scatter plot
i <- ggplot(mtcars, aes(wt, mpg)) + geom_point()
# Add segment
i + geom_segment(aes(x = 2, y = 15, xend = 3, yend = 15))
# Add arrow
require(grid)
i + geom_segment(aes(x = 5, y = 30, xend = 3.5, yend = 25),
                  arrow = arrow(length = unit(0.5, "cm")))

To customize the plot, the following arguments can be used: alpha, color, linetype and size. Learn more here: ggplot2 add line segment.

4. Add curves between points (x1, y1) and (x2, y2):

i + geom_curve(aes(x = 2, y = 15, xend = 3, yend = 15))

• Key functions: geom_path(), geom_ribbon(), geom_rect(), geom_segment()

Main title, axis labels and legend title

We start by creating a box plot using the data set ToothGrowth:

# Convert the variable dose from numeric to factor variable
ToothGrowth$dose <- as.factor(ToothGrowth$dose)
p <- ggplot(ToothGrowth, aes(x=dose, y=len)) + geom_boxplot()

The function below can be used for changing titles and labels:

The function labs() can be also used to change the legend title.

1. Change main title and axis labels

# Default plot
print(p)
# Change title and axis labels
p <- p +labs(title="Plot of length \n by dose",
        x ="Dose (mg)", y = "Teeth length")
p

Note that, \n is used to split long title into multiple lines.

2. Change the appearance of labels:

To change the appearance(color, size and face ) of labels, the functions theme() and element_text() can be used.

The function element_blank() hides the labels.

# Change the appearance of labels
p + theme(
plot.title = element_text(color="red", size=14, face="bold.italic"),
axis.title.x = element_text(color="blue", size=14, face="bold"),
axis.title.y = element_text(color="#993333", size=14, face="bold")
)
# Hide labels
p + theme(plot.title = element_blank(), 
          axis.title.x = element_blank(),
          axis.title.y = element_blank())

3. Change legend titles: Scale functions (fill, color, size, shape, …) are used to update legend titles.

# Default plot
p <- ggplot(ToothGrowth, aes(x=dose, y=len, fill=dose))+
  geom_boxplot()
p
# Modify legend titles
p + labs(fill = "Dose (mg)")

Learn more here: ggplot2 title: main, axis and legend titles.

Legend position and appearance

1. Create a box plot

# Convert the variable dose from numeric to factor variable
ToothGrowth$dose <- as.factor(ToothGrowth$dose)
p <- ggplot(ToothGrowth, aes(x=dose, y=len, fill=dose))+
  geom_boxplot()

2. Change legend position and appearance

# Change legend position: "left","top", "right", "bottom", "none"
p + theme(legend.position="top")
# Remove legends
p + theme(legend.position = "none")
# Change the appearance of legend title and labels
p + theme(legend.title = element_text(colour="blue"),
          legend.text = element_text(colour="red"))
# Change legend box background color
p + theme(legend.background = element_rect(fill="lightblue"))

3. Customize legends using scale functions
   • Change the order of legend items: scale_x_discrete()
   • Set legend title and labels: scale_fill_discrete()

# Change the order of legend items
p + scale_x_discrete(limits=c("2", "0.5", "1"))
# Set legend title and labels
p + scale_fill_discrete(name = "Dose", labels = c("A", "B", "C"))

Learn more here: ggplot2 legend position and appearance.

Change colors automatically and manually

ToothGrowth and mtcars data sets are used in the examples below.

# Convert dose and cyl columns from numeric to factor variables
ToothGrowth$dose <- as.factor(ToothGrowth$dose)
mtcars$cyl <- as.factor(mtcars$cyl)

We start by creating some plots which will be finished hereafter:

# Box plot
bp <- ggplot(ToothGrowth, aes(x=dose, y=len))
# Scatter plot
sp <- ggplot(mtcars, aes(x=wt, y=mpg))

1. Draw plots: change fill and outline colors

# box plot
bp + geom_boxplot(fill='steelblue', color="red")
# scatter plot
sp + geom_point(color='darkblue')

2. Change color by groups using the levels of dose variable

# Box plot
bp <- bp + geom_boxplot(aes(fill = dose))
bp
# Scatter plot
sp <- sp + geom_point(aes(color = cyl))
sp

3. Change colors manually:

• scale_fill_manual() for box plot, bar plot, violin plot, etc
• scale_color_manual() for lines and points

# Box plot
bp + scale_fill_manual(values=c("#999999", "#E69F00", "#56B4E9"))
# Scatter plot
sp + scale_color_manual(values=c("#999999", "#E69F00", "#56B4E9"))

4. Use RColorBrewer palettes: (Read more about RColorBrewer: color in R)

• scale_fill_brewer() for box plot, bar plot, violin plot, etc
• scale_color_brewer() for lines and points

# Box plot
bp + scale_fill_brewer(palette="Dark2")
# Scatter plot
sp + scale_color_brewer(palette="Dark2")

Available color palettes in the RColorBrewer package:

RColorBrewer palettes

5. Use gray colors:

• scale_fill_grey() for box plot, bar plot, violin plot, etc
• scale_colour_grey() for points, lines, etc

# Box plot
bp + scale_fill_grey() + theme_classic()
# Scatter plot
sp + scale_color_grey() + theme_classic()

6. Gradient or continuous colors:

Plots can be colored according to the values of a continuous variable using the functions :

• scale_color_gradient(), scale_fill_gradient() for sequential gradients between two colors
• scale_color_gradient2(), scale_fill_gradient2() for diverging gradients
• scale_color_gradientn(), scale_fill_gradientn() for gradient between n colors

Gradient colors for scatter plots: The graphs are colored using the qsec continuous variable :

# Color by qsec values
sp2<-ggplot(mtcars, aes(x=wt, y=mpg)) +
  geom_point(aes(color = qsec))
sp2
# Change the low and high colors
# Sequential color scheme
sp2+scale_color_gradient(low="blue", high="red")
# Diverging color scheme
mid<-mean(mtcars$qsec)
sp2+scale_color_gradient2(midpoint=mid, low="blue", mid="white",
                          high="red", space = "Lab" )

Learn more here: ggplot2 colors.

Point shapes, colors and size

The different points shapes commonly used in R are shown in the image below:

mtcars data is used in the following examples.

# Convert cyl as factor variable
mtcars$cyl <- as.factor(mtcars$cyl)

Create a scatter plot and change point shapes, colors and size:

# Basic scatter plot
ggplot(mtcars, aes(x=wt, y=mpg)) +
  geom_point(shape = 18, color = "steelblue", size = 4)
# Change point shapes and colors by groups
ggplot(mtcars, aes(x=wt, y=mpg)) +
  geom_point(aes(shape = cyl, color = cyl))

It’s also possible to manually change the appearance of points:

• scale_shape_manual() : to change point shapes
• scale_color_manual() : to change point colors
• scale_size_manual() : to change the size of points

# Change colors and shapes manually
ggplot(mtcars, aes(x=wt, y=mpg, group=cyl)) +
  geom_point(aes(shape=cyl, color=cyl), size=2)+
  scale_shape_manual(values=c(3, 16, 17))+
  scale_color_manual(values=c('#999999','#E69F00', '#56B4E9'))+
  theme(legend.position="top")

Learn more here: ggplot2 point shapes, colors and size.

Add text annotations to a graph

There are three important functions for adding texts to a plot:

• geom_text(): Textual annotations
• annotate(): Textual annotations
• annotation_custom(): Static annotations that are the same in every panel. These annotations are not affected by the plot scales.

A subset of mtcars data is used:

set.seed(1234)
df <- mtcars[sample(1:nrow(mtcars), 10), ]
df$cyl <- as.factor(df$cyl)

Scatter plots with textual annotations:

# Scatter plot
sp <- ggplot(df, aes(x=wt, y=mpg))+ geom_point() 
# Add text, change colors by groups
sp + geom_text(aes(label = rownames(df), color = cyl),
               size = 3, vjust = -1)
# Add text at a particular coordinate
sp + geom_text(x = 3, y = 30, label = "Scatter plot",
              color="red")

Learn more here: ggplot2 text: Add text annotations to a graph.

Line types

The different line types available in R software are : “blank”, “solid”, “dashed”, “dotted”, “dotdash”, “longdash”, “twodash”.

Note that, line types can be also specified using numbers : 0, 1, 2, 3, 4, 5, 6. 0 is for “blank”, 1 is for “solid”, 2 is for “dashed”, ….

A graph of the different line types is shown below :

1. Basic line plot

# Create some data
df <- data.frame(time=c("breakfeast", "Lunch", "Dinner"),
                bill=c(10, 30, 15))
head(df)

##         time bill
## 1 breakfeast   10
## 2      Lunch   30
## 3     Dinner   15

# Basic line plot with points
# Change the line type
ggplot(data=df, aes(x=time, y=bill, group=1)) +
  geom_line(linetype = "dashed")+
  geom_point()

2. Line plots with multiple groups

# Create some data
df2 <- data.frame(sex = rep(c("Female", "Male"), each=3),
                  time=c("breakfeast", "Lunch", "Dinner"),
                  bill=c(10, 30, 15, 13, 40, 17) )
head(df2)

##      sex       time bill
## 1 Female breakfeast   10
## 2 Female      Lunch   30
## 3 Female     Dinner   15
## 4   Male breakfeast   13
## 5   Male      Lunch   40
## 6   Male     Dinner   17

# Line plot with multiple groups
# Change line types and colors by groups (sex)
ggplot(df2, aes(x=time, y=bill, group=sex)) +
  geom_line(aes(linetype = sex, color = sex))+
  geom_point(aes(color=sex))+
  theme(legend.position="top")

The functions below can be used to change the appearance of line types manually:

• scale_linetype_manual() : to change line types
• scale_color_manual() : to change line colors
• scale_size_manual() : to change the size of lines

# Change line types, colors and sizes
ggplot(df2, aes(x=time, y=bill, group=sex)) +
  geom_line(aes(linetype=sex, color=sex, size=sex))+
  geom_point()+
  scale_linetype_manual(values=c("twodash", "dotted"))+
  scale_color_manual(values=c('#999999','#E69F00'))+
  scale_size_manual(values=c(1, 1.5))+
  theme(legend.position="top")

Learn more here: ggplot2 line types.

Themes and background colors

ToothGrowth data is used :

# Convert the column dose from numeric to factor variable
ToothGrowth$dose <- as.factor(ToothGrowth$dose)

1. Create a box plot

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

2. Change plot themes

Several functions are available in ggplot2 package for changing quickly the theme of plots :

• theme_gray(): gray background color and white grid lines
• theme_bw() : white background and gray grid lines

p + theme_gray(base_size = 14)
p + theme_bw()

ggplot2 background color, theme_gray and theme_bw, R programming

• theme_linedraw : black lines around the plot
• theme_light : light gray lines and axis (more attention towards the data)

p + theme_linedraw()
p + theme_light()

ggplot2 background color, theme_linedraw and theme_light, R programming

• theme_minimal: no background annotations
• theme_classic : theme with axis lines and no grid lines

p + theme_minimal()
p + theme_classic()

ggplot2 background color, theme_minimal and theme_classic, R programming

Learn more here: ggplot2 themes and background colors.

Axis limits: Minimum and Maximum values

Create a plot:

p <- ggplot(cars, aes(x = speed, y = dist)) + geom_point()

Different functions are available for setting axis limits:

# Default plot
print(p)
# Change axis limits using coord_cartesian()
p + coord_cartesian(xlim =c(5, 20), ylim = c(0, 50))
# Use xlim() and ylim()
p + xlim(5, 20) + ylim(0, 50)
# Expand limits
p + expand_limits(x = c(5, 50), y = c(0, 150))

Learn more here: ggplot2 axis limits.

Note that, date axis limits can be set using the functions scale_x_date() and scale_y_date(). Read more here: ggplot2 date axis.

Axis transformations: log and sqrt scales

1. Create a scatter plot:

p <- ggplot(cars, aes(x = speed, y = dist)) + geom_point()

2. ggplot2 functions for continuous axis transformations:

3. The R code below uses the function scale_xx_continuous() to transform axis scales:

# Default scatter plot
print(p)
# Log transformation using scale_xx()
# possible values for trans : 'log2', 'log10','sqrt'
p + scale_x_continuous(trans='log2') +
  scale_y_continuous(trans='log2')
# Format axis tick mark labels
require(scales)
p + scale_y_continuous(trans = log2_trans(),
    breaks = trans_breaks("log2", function(x) 2^x),
    labels = trans_format("log2", math_format(2^.x)))
# Reverse coordinates
p + scale_y_reverse() 

Learn more here: ggplot2 axis limits.

Axis ticks: customize tick marks and labels, reorder and select items

1. Functions for changing the style of axis tick mark labels:

2. Create a box plot:

p <- ggplot(ToothGrowth, aes(x=dose, y=len)) + geom_boxplot()
# print(p)

3. Change the style and the orientation angle of axis tick labels

# Change the style of axis tick labels
# face can be "plain", "italic", "bold" or "bold.italic"
p + theme(axis.text.x = element_text(face="bold", color="#993333", 
                           size=14, angle=45),
          axis.text.y = element_text(face="bold", color="blue", 
                           size=14, angle=45))
# Remove axis ticks and tick mark labels
p + theme(
  axis.text.x = element_blank(), # Remove x axis tick labels
  axis.text.y = element_blank(), # Remove y axis tick labels
  axis.ticks = element_blank()) # Remove ticks

4. Customize continuous and discrete axes:

• Discrete axes
  • scale_x_discrete(name, breaks, labels, limits): for X axis
  • scale_y_discrete(name, breaks, labels, limits): for y axis
• Continuous axes
  • scale_x_continuous(name, breaks, labels, limits, trans): for X axis
  • scale_y_continuous(name, breaks, labels, limits, trans): for y axis

Briefly, the meaning of the arguments are as follow:

scale_xx() functions can be used to change the following x or y axis parameters :

• axis titles
• axis limits (data range to display)
• choose where tick marks appear
• manually label tick marks

4.1. Discrete axes:

# Change x axis label and the order of items
p + scale_x_discrete(name ="Dose (mg)", 
                    limits=c("2","1","0.5"))
# Change tick mark labels
p + scale_x_discrete(breaks=c("0.5","1","2"),
        labels=c("Dose 0.5", "Dose 1", "Dose 2"))
# Choose which items to display
p + scale_x_discrete(limits=c("0.5", "2"))

4.2. Continuous axes:

# Default scatter plot
# +++++++++++++++++
sp <- ggplot(cars, aes(x = speed, y = dist)) + geom_point()
sp
# Customize the plot
#+++++++++++++++++++++
# 1. Change x and y axis labels, and limits
sp <- sp + scale_x_continuous(name="Speed of cars", limits=c(0, 30)) +
  scale_y_continuous(name="Stopping distance", limits=c(0, 150))
# 2. Set tick marks on y axis: a tick mark is shown on every 50
sp + scale_y_continuous(breaks=seq(0, 150, 50))
# Format the labels
# +++++++++++++++++
require(scales)
sp + scale_y_continuous(labels = percent) # labels as percents

Learn more here: ggplot2 Axis ticks: tick marks and labels.

Add straight lines to a plot: horizontal, vertical and regression lines

The R function below can be used :

• geom_hline(yintercept, linetype, color, size): for horizontal lines
• geom_vline(xintercept, linetype, color, size): for vertical lines
• geom_abline(intercept, slope, linetype, color, size): for regression lines
• geom_segment() to add segments

1. Create a simple scatter plot

# Simple scatter plot
sp <- ggplot(data=mtcars, aes(x=wt, y=mpg)) + geom_point()

2. Add straight lines

# Add horizontal line at y = 2O; change line type and color
sp + geom_hline(yintercept=20, linetype="dashed", color = "red")
# Add vertical line at x = 3; change line type, color and size
sp + geom_vline(xintercept = 3, color = "blue", size=1.5)
# Add regression line
sp + geom_abline(intercept = 37, slope = -5, color="blue")+
  ggtitle("y = -5X + 37")
# Add horizontal line segment
sp + geom_segment(aes(x = 2, y = 15, xend = 3, yend = 15))

Learn more here: ggplot2 add straight lines to a plot.

Rotate a plot: flip and reverse

• coord_flip(): Create horizontal plots
• scale_x_reverse(), scale_y_reverse(): Reverse the axes

set.seed(1234)
# Basic histogram
hp <- qplot(x=rnorm(200), geom="histogram")
hp
# Horizontal histogram
hp + coord_flip()
# Y axis reversed
hp + scale_y_reverse()

Learn more here: ggplot2 rotate a graph.

Faceting: split a plot into a matrix of panels

Facets divide a plot into subplots based on the values of one or more categorical variables.

There are two main functions for faceting :

• facet_grid()
• facet_wrap()

Create a box plot filled by groups:

p <- ggplot(ToothGrowth, aes(x=dose, y=len, group=dose)) + 
  geom_boxplot(aes(fill=dose))
p

The following functions can be used for facets:

1. Facet with one discrete variable: Split by the levels of the group “supp”

# Split in vertical direction
p + facet_grid(supp ~ .)
# Split in horizontal direction
p + facet_grid(. ~ supp)

2. Facet with two discrete variables: Split by the levels of the groups “dose” and “supp”

# Facet by two variables: dose and supp.
# Rows are dose and columns are supp
p + facet_grid(dose ~ supp)
# Facet by two variables: reverse the order of the 2 variables
# Rows are supp and columns are dose
p + facet_grid(supp ~ dose)

By default, all the panels have the same scales (scales=“fixed”). They can be made independent, by setting scales to free, free_x, or free_y.

p + facet_grid(dose ~ supp, scales='free')

Learn more here: ggplot2 facet : split a plot into a matrix of panels.

Position adjustements

Position adjustments determine how to arrange geoms. The argument position is used to adjust geom positions:

p <- ggplot(mpg, aes(fl, fill = drv))
# Arrange elements side by side
p + geom_bar(position = "dodge")
# Stack objects on top of one another, 
# and normalize to have equal height
p + geom_bar(position = "fill")

# Stack elements on top of one another
p + geom_bar(position = "stack")
# Add random noise to X and Y position 
# of each element to avoid overplotting
ggplot(mpg, aes(cty, hwy)) + 
  geom_point(position = "jitter")

Note that, each of these position adjustments can be done using a function with manual width and height argument.

• position_dodge(width, height)
• position_fill(width, height)
• position_stack(width, height)
• position_jitter(width, height)

p + geom_bar(position = position_dodge(width = 1))

Learn more here: ggplot2 bar plots.

Coordinate systems

p <- ggplot(mpg, aes(fl)) + geom_bar()

The coordinate systems in ggplot2 are:

1. Arguments for coord_cartesian(), coord_fixed() and coord_flip()
   • xlim: limits for the x axis
   • ylim: limits for the y axis
   • ratio: aspect ratio, expressed as y/x
   • …: Other arguments passed onto coord_cartesian
2. Arguments for coord_polar()
   • theta: variable to map angle to (x or y)
   • start: offset of starting point from 12 o’clock in radians
   • direction: 1, clockwise; -1, anticlockwise
3. Arguments for coord_trans()
   • x, y: transformers for x and y axes
   • limx, limy: limits for x and y axes.

p + coord_cartesian(ylim = c(0, 200))
p + coord_fixed(ratio = 1/50)
p + coord_flip()

p + coord_polar(theta = "x", direction = 1)
p + coord_trans(y = "sqrt")

Books

• ggplot2: The Elements for Elegant Data Visualization in R

• Cookbook for R

Blog posts

• Build a plot layer by layer

Cheat Sheets

• Data Visualization with ggplot2, RStudio cheat sheet
• Beautiful plotting in R: A ggplot2 cheatsheet

Change the colors of the plot panel background and the grid lines

1. The functions theme() and element_rect() are used for changing the plot panel background color :

p + theme(panel.background = element_rect(fill, colour, size, 
                                          linetype, color))

2. The appearance of grid lines can be changed using the function element_line() as follow :

# change major and minor grid lines
p + theme(
  panel.grid.major = element_line(colour, size, linetype,
                                   lineend, color),
  panel.grid.minor = element_line(colour, size, linetype,
                                   lineend, color)
  )

The R code below illustrates how to modify the appearance of the plot panel background and grid lines :

# Change the colors of plot panel background to lightblue
# and the color of grid lines to white
p + theme(
  panel.background = element_rect(fill = "lightblue",
                                colour = "lightblue",
                                size = 0.5, linetype = "solid"),
  panel.grid.major = element_line(size = 0.5, linetype = 'solid',
                                colour = "white"), 
  panel.grid.minor = element_line(size = 0.25, linetype = 'solid',
                                colour = "white")
  )

ggplot2 background color, grid lines, R programming

Remove plot panel borders and grid lines

It is possible to hide plot panel borders and grid lines with the function element_blank() as follow :

# Remove panel borders and grid lines
p + theme(panel.border = element_blank(),
          panel.grid.major = element_blank(),
          panel.grid.minor = element_blank())
# Hide panel borders and grid lines
# But change axis line
p + theme(panel.border = element_blank(),
          panel.grid.major = element_blank(),
          panel.grid.minor = element_blank(),
          axis.line = element_line(size = 0.5, linetype = "solid",
                                   colour = "black"))

ggplot2 background color, remove plot panel border, remove grid lines, R programming

Change the plot background color (not the panel)

p + theme(plot.background = element_rect(fill = "darkblue"))

ggplot2 background color, R programming

theme_tufte : a minimalist theme

# scatter plot
ggplot(mtcars, aes(wt, mpg)) +
  geom_point() + geom_rangeframe() + 
  theme_tufte()

ggplot2 theme_tufte, R statistical software

theme_economist : theme based on the plots in the economist magazine

p <- ggplot(iris, aes(Sepal.Length, Sepal.Width, colour = Species))+
  geom_point()
# Use economist color scales
p + theme_economist() + 
  scale_color_economist()+
  ggtitle("Iris data sets")

ggplot2 theme_economist, R statistical software

Note that, the function scale_fill_economist() are also available.

theme_stata: theme based on Stata graph schemes.

p + theme_stata() + scale_color_stata() +
  ggtitle("Iris data")

ggplot2 theme_stata, R statistical software

The stata theme color scales can be used as follow :

scale_fill_stata(scheme = "s2color", ...)
scale_color_stata(scheme = "s2color", ...)

The allowed values for the argument scheme are one of “s2color”, “s1rcolor”, “s1color”, or “mono”.

theme_wsj: theme based on plots in the Wall Street Journal

p + theme_wsj()+ scale_colour_wsj("colors6")+
  ggtitle("Iris data")

ggplot2 theme_wsj, R statistical software

The Wall Street Journal color and fill scales are :

scale_color_wsj(palette = "colors6", ...)
scale_fill_wsj(palette = "colors6", ...)

The color palette to use can be one of “rgby”, “red_green”, “black_green”, “dem_rep”, “colors6”.

theme_calc : theme based on LibreOffice Calc

These themes are based on the defaults in Google Docs and LibreOffice Calc, respectively.

p + theme_calc()+ scale_colour_calc()+
  ggtitle("Iris data")

ggplot2 theme_calc, R statistical software

theme_hc : theme based on Highcharts JS

p + theme_hc()+ scale_colour_hc()

ggplot2 theme_hc, R statistical software

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 line plots with points

library(ggplot2)
# Basic line plot with points
ggplot(data=df, aes(x=dose, y=len, group=1)) +
  geom_line()+
  geom_point()
# Change the line type
ggplot(data=df, aes(x=dose, y=len, group=1)) +
  geom_line(linetype = "dashed")+
  geom_point()
# Change the color
ggplot(data=df, aes(x=dose, y=len, group=1)) +
  geom_line(color="red")+
  geom_point()

Read more on line types : ggplot2 line types

You can add an arrow to the line using the grid package :

library(grid)
# Add an arrow
ggplot(data=df, aes(x=dose, y=len, group=1)) +
  geom_line(arrow = arrow())+
  geom_point()
# Add a closed arrow to the end of the line
myarrow=arrow(angle = 15, ends = "both", type = "closed")
ggplot(data=df, aes(x=dose, y=len, group=1)) +
  geom_line(arrow=myarrow)+
  geom_point()

Observations can be also connected using the functions geom_step() or geom_path() :

ggplot(data=df, aes(x=dose, y=len, group=1)) +
  geom_step()+
  geom_point()
ggplot(data=df, aes(x=dose, y=len, group=1)) +
  geom_path()+
  geom_point()

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 line plots

In the graphs below, line types, colors and sizes are the same for the two groups :

# Line plot with multiple groups
ggplot(data=df2, aes(x=dose, y=len, group=supp)) +
  geom_line()+
  geom_point()
# Change line types
ggplot(data=df2, aes(x=dose, y=len, group=supp)) +
  geom_line(linetype="dashed", color="blue", size=1.2)+
  geom_point(color="red", size=3)

Change line types by groups

In the graphs below, line types and point shapes are controlled automatically by the levels of the variable supp :

# Change line types by groups (supp)
ggplot(df2, aes(x=dose, y=len, group=supp)) +
  geom_line(aes(linetype=supp))+
  geom_point()
# Change line types and point shapes
ggplot(df2, aes(x=dose, y=len, group=supp)) +
  geom_line(aes(linetype=supp))+
  geom_point(aes(shape=supp))

It is also possible to change manually the line types using the function scale_linetype_manual().

# Set line types manually
ggplot(df2, aes(x=dose, y=len, group=supp)) +
  geom_line(aes(linetype=supp))+
  geom_point()+
  scale_linetype_manual(values=c("twodash", "dotted"))

You can read more on line types here : ggplot2 line types

If you want to change also point shapes, read this article : ggplot2 point shapes

Change line colors by groups

Line colors are controlled automatically by the levels of the variable supp :

p<-ggplot(df2, aes(x=dose, y=len, group=supp)) +
  geom_line(aes(color=supp))+
  geom_point(aes(color=supp))
p

It is also possible to change manually 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 the point shapes, colors and sizes automatically

In the R code below, point shapes, colors and sizes are controlled automatically by the variable cyl :

library(ggplot2)
# Scatter plot with multiple groups
# shape depends on cyl
ggplot(df, aes(x=wt, y=mpg, group=cyl)) +
  geom_point(aes(shape=cyl))
# Change point shapes and colors
ggplot(df, aes(x=wt, y=mpg, group=cyl)) +
  geom_point(aes(shape=cyl, color=cyl))
# change point shapes,  colors and sizes
ggplot(df, aes(x=wt, y=mpg, group=cyl)) +
  geom_point(aes(shape=cyl, color=cyl, size=cyl))

Change point shapes, colors and sizes manually :

The functions below can be used :

• scale_shape_manual() : to change point shapes
• scale_color_manual() : to change point colors
• scale_size_manual() : to change the size of points

# Change colors and shapes manually
ggplot(df, aes(x=wt, y=mpg, group=cyl)) +
  geom_point(aes(shape=cyl, color=cyl), size=2)+
  scale_shape_manual(values=c(3, 16, 17))+
  scale_color_manual(values=c('#999999','#E69F00', '#56B4E9'))+
  theme(legend.position="top")
# Change the point size manually
ggplot(df, aes(x=wt, y=mpg, group=cyl)) +
  geom_point(aes(shape=cyl, color=cyl, size=cyl))+
  scale_shape_manual(values=c(3, 16, 17))+
  scale_color_manual(values=c('#999999','#E69F00', '#56B4E9'))+
  scale_size_manual(values=c(2,3,4))+
  theme(legend.position="top")

Generate some data

df <- data.frame(time=c("breakfeast", "Lunch", "Dinner"),
                bill=c(10, 30, 15))
head(df)

##         time bill
## 1 breakfeast   10
## 2      Lunch   30
## 3     Dinner   15

Create line plots and change line types

The argument linetype is used to change the line type :

library(ggplot2)
# Basic line plot with points
ggplot(data=df, aes(x=time, y=bill, group=1)) +
  geom_line()+
  geom_point()
# Change the line type
ggplot(data=df, aes(x=time, y=bill, group=1)) +
  geom_line(linetype = "dashed")+
  geom_point()

Create some data

df2 <- data.frame(sex = rep(c("Female", "Male"), each=3),
                  time=c("breakfeast", "Lunch", "Dinner"),
                  bill=c(10, 30, 15, 13, 40, 17) )
head(df2)

##      sex       time bill
## 1 Female breakfeast   10
## 2 Female      Lunch   30
## 3 Female     Dinner   15
## 4   Male breakfeast   13
## 5   Male      Lunch   40
## 6   Male     Dinner   17

Change globally the appearance of lines

In the graphs below, line types, colors and sizes are the same for the two groups :

library(ggplot2)
# Line plot with multiple groups
ggplot(data=df2, aes(x=time, y=bill, group=sex)) +
  geom_line()+
  geom_point()
# Change line types
ggplot(data=df2, aes(x=time, y=bill, group=sex)) +
  geom_line(linetype="dashed")+
  geom_point()
# Change line colors and sizes
ggplot(data=df2, aes(x=time, y=bill, group=sex)) +
  geom_line(linetype="dotted", color="red", size=2)+
  geom_point(color="blue", size=3)

Change automatically the line types by groups

In the graphs below, line types, colors and sizes are changed automatically by the levels of the variable sex :

# Change line types by groups (sex)
ggplot(df2, aes(x=time, y=bill, group=sex)) +
  geom_line(aes(linetype=sex))+
  geom_point()+
  theme(legend.position="top")
# Change line types + colors
ggplot(df2, aes(x=time, y=bill, group=sex)) +
  geom_line(aes(linetype=sex, color=sex))+
  geom_point(aes(color=sex))+
  theme(legend.position="top")

Change manually the appearance of lines

The functions below can be used :

• scale_linetype_manual() : to change line types
• scale_color_manual() : to change line colors
• scale_size_manual() : to change the size of lines

# Set line types manually
ggplot(df2, aes(x=time, y=bill, group=sex)) +
  geom_line(aes(linetype=sex))+
  geom_point()+
  scale_linetype_manual(values=c("twodash", "dotted"))+
  theme(legend.position="top")
# Change line colors and sizes
ggplot(df2, aes(x=time, y=bill, group=sex)) +
  geom_line(aes(linetype=sex, color=sex, size=sex))+
  geom_point()+
  scale_linetype_manual(values=c("twodash", "dotted"))+
  scale_color_manual(values=c('#999999','#E69F00'))+
  scale_size_manual(values=c(1, 1.5))+
  theme(legend.position="top")

Use xlim() and ylim() functions

To change the range of a continuous axis, the functions xlim() and ylim() can be used as follow :

# x axis limits
sp + xlim(min, max)
# y axis limits
sp + ylim(min, max)

min and max are the minimum and the maximum values of each axis.

# Box plot : change y axis range
bp + ylim(0,50)
# scatter plots : change x and y limits
sp + xlim(5, 40)+ylim(0, 150)

Use expand_limts() function

# set the intercept of x and y axis at (0,0)
sp + expand_limits(x=0, y=0)
# change the axis limits
sp + expand_limits(x=c(0,30), y=c(0, 150))

Use scale_xx() functions

It is also possible to use the functions scale_x_continuous() and scale_y_continuous() to change x and y axis limits, respectively.

The simplified formats of the functions are :

scale_x_continuous(name, breaks, labels, limits, trans)
scale_y_continuous(name, breaks, labels, limits, trans)

The functions scale_x_continuous() and scale_y_continuous() can be used as follow :

# Change x and y axis labels, and limits
sp + scale_x_continuous(name="Speed of cars", limits=c(0, 30)) +
  scale_y_continuous(name="Stopping distance", limits=c(0, 150))

Log and sqrt transformations

Built in functions for axis transformations are :

• scale_x_log10(), scale_y_log10() : for log10 transformation
• scale_x_sqrt(), scale_y_sqrt() : for sqrt transformation
• scale_x_reverse(), scale_y_reverse() : to reverse coordinates
• coord_trans(x =“log10”, y=“log10”) : possible values for x and y are “log2”, “log10”, “sqrt”, …
• scale_x_continuous(trans=‘log2’), scale_y_continuous(trans=‘log2’) : another allowed value for the argument trans is ‘log10’

These functions can be used as follow :

# Default scatter plot
sp <- ggplot(cars, aes(x = speed, y = dist)) + geom_point()
sp
# Log transformation using scale_xx()
# possible values for trans : 'log2', 'log10','sqrt'
sp + scale_x_continuous(trans='log2') +
  scale_y_continuous(trans='log2')
# Sqrt transformation
sp + scale_y_sqrt()
# Reverse coordinates
sp + scale_y_reverse() 

The function coord_trans() can be used also for the axis transformation

# Possible values for x and y : "log2", "log10", "sqrt", ...
sp + coord_trans(x="log2", y="log2")

Format axis tick mark labels

Axis tick marks can be set to show exponents. The scales package is required to access break formatting functions.

# Log2 scaling of the y axis (with visually-equal spacing)
library(scales)
sp + scale_y_continuous(trans = log2_trans())
# show exponents
sp + scale_y_continuous(trans = log2_trans(),
    breaks = trans_breaks("log2", function(x) 2^x),
    labels = trans_format("log2", math_format(2^.x)))

Note that many transformation functions are available using the scales package : log10_trans(), sqrt_trans(), etc. Use help(trans_new) for a full list.

Format axis tick mark labels :

library(scales)
# Percent
sp + scale_y_continuous(labels = percent)
# dollar
sp + scale_y_continuous(labels = dollar)
# scientific
sp + scale_y_continuous(labels = scientific)

Display log tick marks

It is possible to add log tick marks using the function annotation_logticks().

Note that, these tick marks make sense only for base 10

The Animals data sets, from the package MASS, are used :

library(MASS)
head(Animals)

##                     body brain
## Mountain beaver     1.35   8.1
## Cow               465.00 423.0
## Grey wolf          36.33 119.5
## Goat               27.66 115.0
## Guinea pig          1.04   5.5
## Dipliodocus     11700.00  50.0

The function annotation_logticks() can be used as follow :

library(MASS) # to access Animals data sets
library(scales) # to access break formatting functions
# x and y axis are transformed and formatted
p2 <- ggplot(Animals, aes(x = body, y = brain)) + geom_point() +
     scale_x_log10(breaks = trans_breaks("log10", function(x) 10^x),
              labels = trans_format("log10", math_format(10^.x))) +
     scale_y_log10(breaks = trans_breaks("log10", function(x) 10^x),
              labels = trans_format("log10", math_format(10^.x))) +
     theme_bw()
# log-log plot without log tick marks
p2
# Show log tick marks
p2 + annotation_logticks()  

Note that, default log ticks are on bottom and left.

To specify the sides of the log ticks :

# Log ticks on left and right
p2 + annotation_logticks(sides="lr")
# All sides
p2+annotation_logticks(sides="trbl")

Allowed values for the argument sides are :

• t : for top
• r : for right
• b : for bottom
• l : for left
• the combination of t, r, b and l

Example of data

Create some time serie data

df <- data.frame(
  date = seq(Sys.Date(), len=100, by="1 day")[sample(100, 50)],
  price = runif(50)
)
df <- df[order(df$date), ]
head(df)

##          date      price
## 33 2016-09-21 0.07245190
## 3  2016-09-23 0.51772443
## 23 2016-09-25 0.05758921
## 43 2016-09-26 0.99389551
## 45 2016-09-27 0.94858770
## 29 2016-09-28 0.82420890

Plot with dates

# Plot with date
dp <- ggplot(data=df, aes(x=date, y=price)) + geom_line()
dp

Format axis tick mark labels

Load the package scales to access break formatting functions.

library(scales)
# Format : month/day
dp + scale_x_date(labels = date_format("%m/%d")) +
  theme(axis.text.x = element_text(angle=45))
# Format : Week
dp + scale_x_date(labels = date_format("%W"))
# Months only
dp + scale_x_date(breaks = date_breaks("months"),
  labels = date_format("%b"))

Note that, since ggplot2 v2.0.0, date and datetime scales now have date_breaks, date_minor_breaks and date_labels arguments so that you never need to use the long scales::date_breaks() or scales::date_format().

Date axis limits

US economic time series data sets (from ggplot2 package) are used :

head(economics)

##         date   pce    pop psavert uempmed unemploy
## 1 1967-07-01 507.4 198712    12.5     4.5     2944
## 2 1967-08-01 510.5 198911    12.5     4.7     2945
## 3 1967-09-01 516.3 199113    11.7     4.6     2958
## 4 1967-10-01 512.9 199311    12.5     4.9     3143
## 5 1967-11-01 518.1 199498    12.5     4.7     3066
## 6 1967-12-01 525.8 199657    12.1     4.8     3018

Create the plot of psavert by date :

• date : Month of data collection
• psavert : personal savings rate

# Plot with dates
dp <- ggplot(data=economics, aes(x=date, y=psavert)) + geom_line()
dp
# Axis limits c(min, max)
min <- as.Date("2002-1-1")
max <- max(economics$date)
dp+ scale_x_date(limits = c(min, max))

Add regression lines

The functions below can be used to add regression lines to a scatter plot :

• geom_smooth() and stat_smooth()
• geom_abline()

geom_abline() has been already described at this link : ggplot2 add straight lines to a plot.

Only the function geom_smooth() is covered in this section.

A simplified format is :

geom_smooth(method="auto", se=TRUE, fullrange=FALSE, level=0.95)

# Add the regression line
ggplot(mtcars, aes(x=wt, y=mpg)) + 
  geom_point()+
  geom_smooth(method=lm)
# Remove the confidence interval
ggplot(mtcars, aes(x=wt, y=mpg)) + 
  geom_point()+
  geom_smooth(method=lm, se=FALSE)
# Loess method
ggplot(mtcars, aes(x=wt, y=mpg)) + 
  geom_point()+
  geom_smooth()

Change the appearance of points and lines

This section describes how to change :

• the color and the shape of points
• the line type and color of the regression line
• the fill color of the confidence interval

# Change the point colors and shapes
# Change the line type and color
ggplot(mtcars, aes(x=wt, y=mpg)) + 
  geom_point(shape=18, color="blue")+
  geom_smooth(method=lm, se=FALSE, linetype="dashed",
             color="darkred")
# Change the confidence interval fill color
ggplot(mtcars, aes(x=wt, y=mpg)) + 
  geom_point(shape=18, color="blue")+
  geom_smooth(method=lm,  linetype="dashed",
             color="darkred", fill="blue")

Note that a transparent color is used, by default, for the confidence band. This can be changed by using the argument alpha : geom_smooth(fill=“blue”, alpha=1)

Read more on point shapes : ggplot2 point shapes

Read more on line types : ggplot2 line types

Change the point color/shape/size automatically

In the R code below, point shapes, colors and sizes are controlled by the levels of the factor variable cyl :

# Change point shapes by the levels of cyl
ggplot(mtcars, aes(x=wt, y=mpg, shape=cyl)) +
  geom_point()
# Change point shapes and colors
ggplot(mtcars, aes(x=wt, y=mpg, shape=cyl, color=cyl)) +
  geom_point()
# Change point shapes, colors and sizes
ggplot(mtcars, aes(x=wt, y=mpg, shape=cyl, color=cyl, size=cyl)) +
  geom_point()

Add regression lines

Regression lines can be added as follow :

# Add regression lines
ggplot(mtcars, aes(x=wt, y=mpg, color=cyl, shape=cyl)) +
  geom_point() + 
  geom_smooth(method=lm)
# Remove confidence intervals
# Extend the regression lines
ggplot(mtcars, aes(x=wt, y=mpg, color=cyl, shape=cyl)) +
  geom_point() + 
  geom_smooth(method=lm, se=FALSE, fullrange=TRUE)

Note that, you can also change the line type of the regression lines by using the aesthetic linetype = cyl.

The fill color of confidence bands can be changed as follow :

ggplot(mtcars, aes(x=wt, y=mpg, color=cyl, shape=cyl)) +
  geom_point() + 
  geom_smooth(method=lm, aes(fill=cyl))

Change the point color/shape/size manually

The functions below are used :

• scale_shape_manual() for point shapes
• scale_color_manual() for point colors
• scale_size_manual() for point sizes

# Change point shapes and colors manually
ggplot(mtcars, aes(x=wt, y=mpg, color=cyl, shape=cyl)) +
  geom_point() + 
  geom_smooth(method=lm, se=FALSE, fullrange=TRUE)+
  scale_shape_manual(values=c(3, 16, 17))+ 
  scale_color_manual(values=c('#999999','#E69F00', '#56B4E9'))+
  theme(legend.position="top")
  
# Change the point sizes manually
ggplot(mtcars, aes(x=wt, y=mpg, color=cyl, shape=cyl))+
  geom_point(aes(size=cyl)) + 
  geom_smooth(method=lm, se=FALSE, fullrange=TRUE)+
  scale_shape_manual(values=c(3, 16, 17))+ 
  scale_color_manual(values=c('#999999','#E69F00', '#56B4E9'))+
  scale_size_manual(values=c(2,3,4))+
  theme(legend.position="top")

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

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

p <- ggplot(mtcars, aes(x=wt, y=mpg, color=cyl, shape=cyl)) +
  geom_point() + 
  geom_smooth(method=lm, se=FALSE, fullrange=TRUE)+
  theme_classic()
# Use brewer color palettes
p+scale_color_brewer(palette="Dark2")
# Use grey scale
p + scale_color_grey()

Read more on ggplot2 colors here : ggplot2 colors