Session 1 exercises
Last modified: 10 May 2019
These exercises require you to generate plots of various kinds. This document shows both the plots that you should obtain and the solutions.
Not everything was necessarily covered during the teaching session, you may need to use R help pages, the Cheat Sheets, or search the web to figure out the answers.
Part I – geoms and aesthetics
These first few exercises will run through some of the simple principles of creating a ggplot2 object, assigning aesthetics mappings and geoms.
- Read in the cleaned patients dataset,
patient-data-cleaned.txt, into a new object calledpatients.
library(tidyverse)
patients <- read_tsv("data/patient-data-cleaned.txt")
patients## # A tibble: 100 x 15
## ID Name Sex Smokes Height Weight Birth State Grade Died
## <chr> <chr> <chr> <chr> <dbl> <dbl> <date> <chr> <dbl> <lgl>
## 1 AC/A… Mich… Male Non-S… 183. 76.6 1972-02-06 Geor… 2 FALSE
## 2 AC/A… Derek Male Non-S… 179. 80.4 1972-06-15 Colo… 2 FALSE
## 3 AC/A… Todd Male Non-S… 169. 75.5 1972-07-09 New … 2 FALSE
## 4 AC/A… Rona… Male Non-S… 176. 94.5 1972-08-17 Colo… 1 FALSE
## 5 AC/A… Chri… Fema… Non-S… 164. 71.8 1973-06-12 Geor… 2 TRUE
## 6 AC/A… Dana Fema… Smoker 158. 69.9 1973-07-01 Indi… 2 FALSE
## 7 AC/A… Erin Fema… Non-S… 162. 68.8 1972-03-26 New … 1 FALSE
## 8 AC/A… Rach… Fema… Non-S… 166. 70.4 1973-05-11 Colo… 1 FALSE
## 9 AC/A… Rona… Male Non-S… 181. 76.9 1971-12-31 Geor… 1 FALSE
## 10 AC/A… Bryan Male Non-S… 167. 79.1 1973-07-19 New … 2 FALSE
## # … with 90 more rows, and 5 more variables: Count <dbl>,
## # Date.Entered.Study <date>, Age <dbl>, BMI <dbl>, Overweight <lgl>Scatterplots
- Generate a scatter plot of BMI versus Weight using the patient dataset .
ggplot(data = patients, mapping = aes(x = BMI, y = Weight)) +
geom_point()
- Extending the plot from exercise 2, add a colour scale to the scatterplot based on the Height variable.
ggplot(data = patients, mapping = aes(x = BMI, y = Weight, colour = Height)) +
geom_point()
- Using an additional geom, add an extra layer of a fit line to the solution from exercise 3.
ggplot(data = patients, mapping = aes(x = BMI, y = Weight, colour = Height)) +
geom_point() +
geom_smooth()
- Does the fit in question 5 look good? Look at the help page for
geom_smoothand adjust the method to fit a straight line without standard error bounds.
ggplot(data = patients, mapping = aes(x = BMI, y = Weight, colour = Height)) +
geom_point() +
geom_smooth(method = "lm", se = FALSE)
Boxplots and Violin plots
- Generate a boxplot of BMIs comparing smokers and non-smokers.
ggplot(data = patients, mapping = aes(x = Smokes, y = BMI)) +
geom_boxplot()
- Following from the boxplot comparing smokers and non-smokers in exercise 6, colour boxplot edges by Sex.
ggplot(data = patients, mapping = aes(x = Smokes, y = BMI, colour = Sex)) +
geom_boxplot()
- Produce a similar boxplot of BMIs but this time group data by Sex and colour the interior of the box (not the outline) by Age.
Note: Having loaded the data using read_tsv, the Age column has been set to dbl (short for double, a numeric vector type) as it only contains numbers. This makes it a continuous variable. In order to split the boxplot by age and colour each one according to Age, it is necessary to change age to be a categorical variable. We can do this by changing the Age column into a different vector type: a factor.
patients$Age <- factor(patients$Age)
ggplot(data = patients, mapping = aes(x = Sex, y = BMI, fill = Age)) +
geom_boxplot()
- Regenerate the solution to exercise 8 but this time using a violin plot.
ggplot(data = patients, mapping = aes(x = Sex, y = BMI, fill = Age)) +
geom_violin()
Histogram and Density plots
- Generate a histogram of BMIs with each bar coloured blue, choosing a suitable bin width.
ggplot(data = patients, mapping = aes(x = BMI)) +
geom_histogram(fill = "blue", binwidth = 0.5)
- Instead of a histogram, generate a density plot of BMI
ggplot(data = patients, mapping = aes(x = BMI)) +
geom_density()
- Generate density plots of BMIs coloured by Sex.
Hint: alpha can be used to control transparency.
ggplot(data = patients, mapping = aes(x = BMI)) +
geom_density(aes(fill = Sex), alpha = 0.5)
Line plots - time series data
Time series data is often represented using line graphs. Here we will look at the data in the diabetes.txt file.
- Read in the cleaned patients dataset,
diabetes.txt, into a new object calleddiabetes. There are lots of patients in this study, let’s just look at a few of them - subset the table to only keep patients with ID’s AC/AH/001, AC/AH/017, and AC/AH/020.
diabetes <- read_tsv("data/diabetes.txt")
diabetes <- diabetes[diabetes$ID%in%c("AC/AH/001", "AC/AH/017", "AC/AH/020"),]
diabetes## # A tibble: 45 x 4
## ID Date Glucose BP
## <chr> <date> <dbl> <dbl>
## 1 AC/AH/001 2011-03-07 100 98
## 2 AC/AH/001 2011-03-14 110 89
## 3 AC/AH/001 2011-03-24 94 88
## 4 AC/AH/001 2011-03-31 111 92
## 5 AC/AH/001 2011-04-03 94 83
## 6 AC/AH/001 2011-05-21 110 93
## 7 AC/AH/001 2011-06-24 105 79
## 8 AC/AH/001 2011-07-11 88 86
## 9 AC/AH/001 2011-07-11 101 92
## 10 AC/AH/001 2011-07-13 112 88
## # … with 35 more rowsAlternative methods for filtering:
Using subset and three conditions checks with | for OR
diabetes_subset <- subset(diabetes, diabetes$ID=="AC/AH/001" |diabetes$ID=="AC/AH/017" |diabetes$ID=="AC/AH/020")Using grepl, a regular expression (regex) and square brackets
to_match_pts <- c("AC/AH/001|AC/AH/017|AC/AH/020")
diabetes <- diabetes[grepl(to_match_pts, diabetes$ID ),]Using filter from dplyr - we’ll cover this later in the course
diabetes_subset <- filter(diabetes, ID == "AC/AH/001" | ID == "AC/AH/017" | ID == "AC/AH/020")- Create a line plot that allows us to examine the change in Glucose levels for each patient by Date.
ggplot(diabetes, aes(x=Date, y=Glucose, group=ID)) +
geom_line(aes(colour=ID))
- Add points to the plot from 14 to make the measurement time-points clearer. Instead of a dot change the shape to a hollow circle and colour the interior of the point.
ggplot(diabetes, aes(x=Date, y=Glucose, group=ID)) +
geom_line(aes(colour=ID)) +
geom_point(aes(fill=ID), shape=21)