Bar Charts in R

Using R to make Bar Charts

In this demonstration, we’ll need to load the openintro and lattice packages. Use the require command to do this first.

require(openintro)
require(lattice)

Let’s look at the cars data. The command below will show you the first 10 rows.

cars[1:10,]

##       type price mpgCity driveTrain passengers weight
## 1    small  15.9      25      front          5   2705
## 2  midsize  33.9      18      front          5   3560
## 3  midsize  37.7      19      front          6   3405
## 4  midsize  30.0      22       rear          4   3640
## 5  midsize  15.7      22      front          6   2880
## 6    large  20.8      19      front          6   3470
## 7    large  23.7      16       rear          6   4105
## 8  midsize  26.3      19      front          5   3495
## 9    large  34.7      16      front          6   3620
## 10 midsize  40.1      16      front          5   3935

It appears that we have two qualitative variables in the data set, type and driveTrain. Notice the spelling/punctuation on each variable. You’ll need to copy this exactly in your commands.

We can use the barchart() command in the lattice package to make a simple frequency barchart for the variable type. If you just want a quick glimpse at the variable, this will usually do the trick.

barchart(cars$type)

If you want to dress the chart up for presentation, you can use some additional arguments to the barchart command as shown below. Notice that there is a comma separating each argument, and parentheses enclosing all the arguments.

barchart(cars$type, #This specifies the dataset and the variable
         horizontal = FALSE, #Turn the bars so they are vertical
         main = "Cars in 1993", #Give your chart a title
         xlab = "Type of Car", #Label the x axis
         ylab = "Frequency", #Label the y axis 
         col = "darkgreen") #change the color of the bars

If you want to make either a relative frequency bar chart or a class percentage bar chart, I recommend you use the barplot() command instead of barchart(). The arguments are called slightly differently for barplot(), but it allows you to modify how the frequencies are reported.

To make a relative frequency bar chart, use the command below.

barplot(table(cars$type)/nrow(cars), #divide the frequency counts by the total
        main = "Cars in 1993", #Give your chart a title
        xlab = "Type of Car", #Label the x axis
        ylab = "Relative Frequency", #Label the y axis 
        col = "darkgreen")

To make a percentage bar chart, use the command below.

barplot(table(cars$type)/nrow(cars)*100, #convert relative frequencies to percentages
        main = "Cars in 1993", #Give your chart a title
        xlab = "Type of Car", #Label the x axis
        ylab = "Percentage", #Label the y axis 
        col = "darkgreen")

As an exercise, modify the code on this page to create a bar chart for the variable driveTrain. You should be able to do this by replacing type with driveTrain wherever you see it in the code above and by modifying the x-axis label with the xlab argument.

Bar Charts in R

Camille Fairbourn

Using R to make Bar Charts