Download the data and read it into R. Before starting the exercise,
convert the subject ID (Subject) to a factor:
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
theoph <- read.csv("theoph.csv")
theoph$Subject = factor(theoph$Subject)
str(theoph)
## 'data.frame': 132 obs. of 5 variables:
## $ Subject: Factor w/ 12 levels "1","2","3","4",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ Wt : num 79.6 79.6 79.6 79.6 79.6 79.6 79.6 79.6 79.6 79.6 ...
## $ Dose : num 4.02 4.02 4.02 4.02 4.02 4.02 4.02 4.02 4.02 4.02 ...
## $ Time : num 0 0.25 0.57 1.12 2.02 ...
## $ conc : num 0.74 2.84 6.57 10.5 9.66 8.58 8.36 7.47 6.89 5.94 ...
head(theoph)
## 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
Using select() make a new data frame containing only the subject ID,
the Time and conc variables
library(dplyr)
theoph <- read.csv("theoph.csv")
theoph$Subject = factor(theoph$Subject)
theoph_timeandconc <- select(theoph, Subject, Time, conc)
head(theoph_timeandconc)
## 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
Using a combination of select() and distinct() make a new data frame
containing a single row for each subject with the subject ID, their
weight and the dose
library(dplyr)
theoph <- read.csv("theoph.csv")
theoph$Subject = factor(theoph$Subject)
theoph2 <- select(theoph, Subject, Dose, Wt)
theoph2 %>%
distinct(Subject, Dose, Wt) %>%
head()
## Subject Dose Wt
## 1 1 4.02 79.6
## 2 2 4.40 72.4
## 3 3 4.53 70.5
## 4 4 4.40 72.7
## 5 5 5.86 54.6
## 6 6 4.00 80.0
Using filter() make a new data frame containing only the first
subject
library(dplyr)
theoph <- read.csv("theoph.csv")
theoph$Subject = factor(theoph$Subject)
filter(theoph, Subject == 1)
## 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
Using filter() make a new data frame containing only the first four
subjects
library(dplyr)
theoph <- read.csv("theoph.csv")
theoph$Subject = factor(theoph$Subject)
filter(theoph, Subject == 1:4)
## Subject Wt Dose Time conc
## 1 1 79.6 4.02 0.00 0.74
## 2 1 79.6 4.02 2.02 9.66
## 3 1 79.6 4.02 9.05 6.89
## 4 2 72.4 4.40 0.52 7.91
## 5 2 72.4 4.40 5.02 6.08
## 6 2 72.4 4.40 24.30 0.90
## 7 3 70.5 4.53 0.00 0.00
## 8 3 70.5 4.53 2.02 7.80
## 9 3 70.5 4.53 9.00 4.90
## 10 4 72.7 4.40 0.60 4.60
## 11 4 72.7 4.40 5.02 6.88
## 12 4 72.7 4.40 24.65 1.15
Using group_by(), calculate the average concentration per subject
(across all times)
theoph %>%
group_by(Subject) %>%
summarise(conc = mean(conc))
## # A tibble: 12 × 2
## Subject conc
## <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
Using filter() 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
library(ggplot2)
library(dplyr)
theoph <- read.csv("theoph.csv")
theoph$Subject = factor(theoph$Subject)
theoph %>%
filter(Subject == 1) %>%
ggplot(aes(x=Time, y=conc)) + geom_line() + ggtitle("Subject 1 treatment")
Using 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
library(dplyr)
theoph <- read.csv("theoph.csv")
theoph$Subject = factor(theoph$Subject)
theoph %>%
select(Subject, Time, conc) %>%
ggplot(aes(x=Time, y=conc, col=Subject)) + geom_line() + ggtitle("Subject treatment over time")
Using 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
library(dplyr)
theoph <- read.csv("theoph.csv")
theoph$Subject = factor(theoph$Subject)
theoph %>%
select(Subject, Time, conc) %>%
ggplot(aes(x=Time, y=conc)) + geom_line() + ggtitle("Subject treatment over time") + facet_wrap(~ Subject)
