Load in data
theoph = read.csv("theoph.csv")
library(dplyr) ## Load in dplyr library for exercise
## Warning: package 'dplyr' was built under R version 4.0.5
##
## 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
library(ggplot2) ## Load in ggplot2 for exercise
## Warning: package 'ggplot2' was built under R version 4.0.5
theoph$Subject = factor(theoph$Subject) ## Create subject variable for exercise
Task 1, create new data frame using select of subject ID, Time, and conc values:
theoph_select = select(theoph, Subject, Time, conc)
theoph_select
## 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
## 7 1 5.10 8.36
## 8 1 7.03 7.47
## 9 1 9.05 6.89
## 10 1 12.12 5.94
## 11 1 24.37 3.28
## 12 2 0.00 0.00
## 13 2 0.27 1.72
## 14 2 0.52 7.91
## 15 2 1.00 8.31
## 16 2 1.92 8.33
## 17 2 3.50 6.85
## 18 2 5.02 6.08
## 19 2 7.03 5.40
## 20 2 9.00 4.55
## 21 2 12.00 3.01
## 22 2 24.30 0.90
## 23 3 0.00 0.00
## 24 3 0.27 4.40
## 25 3 0.58 6.90
## 26 3 1.02 8.20
## 27 3 2.02 7.80
## 28 3 3.62 7.50
## 29 3 5.08 6.20
## 30 3 7.07 5.30
## 31 3 9.00 4.90
## 32 3 12.15 3.70
## 33 3 24.17 1.05
## 34 4 0.00 0.00
## 35 4 0.35 1.89
## 36 4 0.60 4.60
## 37 4 1.07 8.60
## 38 4 2.13 8.38
## 39 4 3.50 7.54
## 40 4 5.02 6.88
## 41 4 7.02 5.78
## 42 4 9.02 5.33
## 43 4 11.98 4.19
## 44 4 24.65 1.15
## 45 5 0.00 0.00
## 46 5 0.30 2.02
## 47 5 0.52 5.63
## 48 5 1.00 11.40
## 49 5 2.02 9.33
## 50 5 3.50 8.74
## 51 5 5.02 7.56
## 52 5 7.02 7.09
## 53 5 9.10 5.90
## 54 5 12.00 4.37
## 55 5 24.35 1.57
## 56 6 0.00 0.00
## 57 6 0.27 1.29
## 58 6 0.58 3.08
## 59 6 1.15 6.44
## 60 6 2.03 6.32
## 61 6 3.57 5.53
## 62 6 5.00 4.94
## 63 6 7.00 4.02
## 64 6 9.22 3.46
## 65 6 12.10 2.78
## 66 6 23.85 0.92
## 67 7 0.00 0.15
## 68 7 0.25 0.85
## 69 7 0.50 2.35
## 70 7 1.02 5.02
## 71 7 2.02 6.58
## 72 7 3.48 7.09
## 73 7 5.00 6.66
## 74 7 6.98 5.25
## 75 7 9.00 4.39
## 76 7 12.05 3.53
## 77 7 24.22 1.15
## 78 8 0.00 0.00
## 79 8 0.25 3.05
## 80 8 0.52 3.05
## 81 8 0.98 7.31
## 82 8 2.02 7.56
## 83 8 3.53 6.59
## 84 8 5.05 5.88
## 85 8 7.15 4.73
## 86 8 9.07 4.57
## 87 8 12.10 3.00
## 88 8 24.12 1.25
## 89 9 0.00 0.00
## 90 9 0.30 7.37
## 91 9 0.63 9.03
## 92 9 1.05 7.14
## 93 9 2.02 6.33
## 94 9 3.53 5.66
## 95 9 5.02 5.67
## 96 9 7.17 4.24
## 97 9 8.80 4.11
## 98 9 11.60 3.16
## 99 9 24.43 1.12
## 100 10 0.00 0.24
## 101 10 0.37 2.89
## 102 10 0.77 5.22
## 103 10 1.02 6.41
## 104 10 2.05 7.83
## 105 10 3.55 10.21
## 106 10 5.05 9.18
## 107 10 7.08 8.02
## 108 10 9.38 7.14
## 109 10 12.10 5.68
## 110 10 23.70 2.42
## 111 11 0.00 0.00
## 112 11 0.25 4.86
## 113 11 0.50 7.24
## 114 11 0.98 8.00
## 115 11 1.98 6.81
## 116 11 3.60 5.87
## 117 11 5.02 5.22
## 118 11 7.03 4.45
## 119 11 9.03 3.62
## 120 11 12.12 2.69
## 121 11 24.08 0.86
## 122 12 0.00 0.00
## 123 12 0.25 1.25
## 124 12 0.50 3.96
## 125 12 1.00 7.82
## 126 12 2.00 9.72
## 127 12 3.52 9.75
## 128 12 5.07 8.57
## 129 12 7.07 6.59
## 130 12 9.03 6.11
## 131 12 12.05 4.57
## 132 12 24.15 1.17
Task 2, create data frame using select() and distinct() of subject ID and their individual Weight and Dose:
sub_wt_dose = theoph %>%
distinct(Subject, Wt, Dose)
sub_wt_dose
## 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
Task 3, using filter() create a data frame of only the first subject:
sub1 = filter(theoph, Subject == 1)
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
Task 4, using filter() create a data frame of subject 1 to 4:
sub_1_4 = filter(theoph, Subject == 1:4)
sub_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
Task 5, using groupby() calculate the average concentration per subject:
avgconc = theoph %>%
group_by(Subject) %>%
summarise(avgConc = mean(conc))
avgconc
## # A tibble: 12 x 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
Task 6, 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:
sub1_gg = theoph %>%
filter(Subject == 1) %>%
ggplot(aes(x = Time, y = conc)) + geom_line() + ggtitle(" Subject 1 concentration over time")
sub1_gg
Task 6, 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:
subs_gg = theoph %>%
select(Subject, Time, conc) %>%
ggplot(aes(x = Time, y = conc)) + geom_line(aes(color = Subject)) +
ggtitle(" Subject concentration over time")
subs_gg
Task 8, 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:
subs_gg_facet = theoph %>%
select(Subject, Time, conc) %>%
ggplot(aes(x = Time, y = conc)) + facet_wrap(~ Subject) + geom_line(color = "red") +
ggtitle(" Subject concentration over time")
subs_gg_facet
