Exercises using dplyr and ggplot2 packages

The packages are read into the markdown

library(ggplot2)
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

The data used for the exercises is from the theophylline pharmacokinetic study

theoph = read.csv("theoph.csv")

The subject IDs are converted into a factor

theoph$Subject = factor(theoph$Subject)

Exercises

Use select() to make a new data frame containing only the subject ID, the Time and conc variables.

theoph_sel = theoph %>%
  select(Subject, Time, conc)
head(theoph_sel)
##   Subject Time  conc
## 1       1 0.00  0.74
## 2       1 0.25  2.84
## 3       1 0.57  6.57
## 4       1 1.12 10.50
## 5       1 2.02  9.66
## 6       1 3.82  8.58

Use a combination of select() and distinct() to make a new data frame containing a single row for each subject with the subject ID, their weight and the dose

theoph_dis = theoph %>%
  select(Subject, Wt, Dose) %>%
  distinct(Subject, Wt, Dose)
theoph_dis
##    Subject   Wt Dose
## 1        1 79.6 4.02
## 2        2 72.4 4.40
## 3        3 70.5 4.53
## 4        4 72.7 4.40
## 5        5 54.6 5.86
## 6        6 80.0 4.00
## 7        7 64.6 4.95
## 8        8 70.5 4.53
## 9        9 86.4 3.10
## 10      10 58.2 5.50
## 11      11 65.0 4.92
## 12      12 60.5 5.30

Use filter() to make a new data frame containing only the first subject

theoph_sub1 = theoph %>%
  filter(Subject == 1)
theoph_sub1
##    Subject   Wt Dose  Time  conc
## 1        1 79.6 4.02  0.00  0.74
## 2        1 79.6 4.02  0.25  2.84
## 3        1 79.6 4.02  0.57  6.57
## 4        1 79.6 4.02  1.12 10.50
## 5        1 79.6 4.02  2.02  9.66
## 6        1 79.6 4.02  3.82  8.58
## 7        1 79.6 4.02  5.10  8.36
## 8        1 79.6 4.02  7.03  7.47
## 9        1 79.6 4.02  9.05  6.89
## 10       1 79.6 4.02 12.12  5.94
## 11       1 79.6 4.02 24.37  3.28

Use filter() to make a new data frame containing only the first four subjects

theoph_sub14 = theoph %>%
  filter(Subject %in% c(1, 2, 3, 4))
theoph_sub14
##    Subject   Wt Dose  Time  conc
## 1        1 79.6 4.02  0.00  0.74
## 2        1 79.6 4.02  0.25  2.84
## 3        1 79.6 4.02  0.57  6.57
## 4        1 79.6 4.02  1.12 10.50
## 5        1 79.6 4.02  2.02  9.66
## 6        1 79.6 4.02  3.82  8.58
## 7        1 79.6 4.02  5.10  8.36
## 8        1 79.6 4.02  7.03  7.47
## 9        1 79.6 4.02  9.05  6.89
## 10       1 79.6 4.02 12.12  5.94
## 11       1 79.6 4.02 24.37  3.28
## 12       2 72.4 4.40  0.00  0.00
## 13       2 72.4 4.40  0.27  1.72
## 14       2 72.4 4.40  0.52  7.91
## 15       2 72.4 4.40  1.00  8.31
## 16       2 72.4 4.40  1.92  8.33
## 17       2 72.4 4.40  3.50  6.85
## 18       2 72.4 4.40  5.02  6.08
## 19       2 72.4 4.40  7.03  5.40
## 20       2 72.4 4.40  9.00  4.55
## 21       2 72.4 4.40 12.00  3.01
## 22       2 72.4 4.40 24.30  0.90
## 23       3 70.5 4.53  0.00  0.00
## 24       3 70.5 4.53  0.27  4.40
## 25       3 70.5 4.53  0.58  6.90
## 26       3 70.5 4.53  1.02  8.20
## 27       3 70.5 4.53  2.02  7.80
## 28       3 70.5 4.53  3.62  7.50
## 29       3 70.5 4.53  5.08  6.20
## 30       3 70.5 4.53  7.07  5.30
## 31       3 70.5 4.53  9.00  4.90
## 32       3 70.5 4.53 12.15  3.70
## 33       3 70.5 4.53 24.17  1.05
## 34       4 72.7 4.40  0.00  0.00
## 35       4 72.7 4.40  0.35  1.89
## 36       4 72.7 4.40  0.60  4.60
## 37       4 72.7 4.40  1.07  8.60
## 38       4 72.7 4.40  2.13  8.38
## 39       4 72.7 4.40  3.50  7.54
## 40       4 72.7 4.40  5.02  6.88
## 41       4 72.7 4.40  7.02  5.78
## 42       4 72.7 4.40  9.02  5.33
## 43       4 72.7 4.40 11.98  4.19
## 44       4 72.7 4.40 24.65  1.15

Use group_by() to calculate the average concentration per subject (across all times)

theoph_conc = theoph %>%
  group_by(Subject) %>%
  summarize(avgconc = mean(conc))
theoph_conc
## # A tibble: 12 × 2
##    Subject avgconc
##    <fct>     <dbl>
##  1 1          6.44
##  2 2          4.82
##  3 3          5.09
##  4 4          4.94
##  5 5          5.78
##  6 6          3.53
##  7 7          3.91
##  8 8          4.27
##  9 9          4.89
## 10 10         5.93
## 11 11         4.51
## 12 12         5.41

Use filter() to make a new data frame containing only the first subject and pipe this to ggplot() to make a line plot with time on the x-axis and conc on the y-axis

theoph_plot1 = theoph %>%
  filter(Subject == 1) %>%
  ggplot(aes(x=Time, y=conc)) + geom_line()
theoph_plot1

Use select() to extract just the Subject, Time, and conc variables and pipe this to ggplot() to make a line plot with time on the x-axis, conc on the y-axis, and the lines colored by subject

theoph_plot2 = theoph %>%
  select(Subject, Time, conc) %>%
  ggplot(aes(x=Time, y=conc, col=Subject)) + geom_line()
theoph_plot2

Use select() to extract just the Subject, Time, and conc variables and pipe this to ggplot() to make a line plot with time on the x-axis, conc on the y-axis, and faceted by the subject ID

theoph_plot3 = theoph %>%
  select(Subject, Time, conc) %>%
  ggplot(aes(x=Time, y=conc)) + geom_line() + facet_wrap(~Subject)
theoph_plot3