generated from ITSLeeds/RpackageTemplate
/
upset.R
177 lines (172 loc) · 6.33 KB
/
upset.R
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
#' Create 'who-hit-who' visualisations
#'
#' @param crash_summary crashes dataset with vehicles and casuatlties variables
#' @param family font family
#' @param casualty_type The casualty types to plot
#' @export
#' @examples
#' crash_summary = tc_join_stats19_for_upset(crashes_wf, casualties_wf, vehicles_wf)
#' names(crash_summary)
#' summary(crash_summary)
#' tc_upset(crash_summary)
#' tc_upset(crash_summary, casualty_type = c("Car", "Pedestrian", "Bicycle"))
#' # create plot with 'Other' category
#' table(casualties_wf$casualty_type)
#' casualties_wf2 = dplyr::mutate(
#' casualties_wf,
#' casualty_type_simple = dplyr::case_when(
#' casualty_type == "Car occupant" ~ "Car",
#' casualty_type == "Pedestrian" ~ "Pedestrian",
#' casualty_type == "Cyclist" ~ "Cyclist",
#' TRUE ~ "Other"
#' )
#' )
#' table(casualties_wf2$casualty_type_simple)
#' table(vehicles_wf$vehicle_type)
#' vehicles_wf2 = dplyr::mutate(
#' vehicles_wf,
#' vehicle_type_simple = dplyr::case_when(
#' vehicle_type == "Car" ~ "Car",
#' vehicle_type == "Bicycle" ~ "Pedal cycle",
#' TRUE ~ "Other"
#' )
#' )
#' crash_summary = tc_join_stats19_for_upset(crashes_wf, casualties_wf2, vehicles_wf2)
#' tc_upset(crash_summary, casualty_type = c("Car", "Pedestrian", "Bicycle", "Other"))
tc_upset = function(crash_summary,
casualty_type = c(
"Car",
"Pedestrian",
"Van",
"Bicycle",
"Motorcycle",
"Bus",
"HGV",
"Taxi"
),
family = "") {
# code resulting in upset plot
# For the UpSet plot we do not differentiate number of vehicles involved in single crash.
# As this is a set visualization we don't want to double count crashes.
if (!requireNamespace("ComplexUpset", quietly = TRUE)) {
stop("Install the ComplexUpset package")
}
ComplexUpset::upset(
crash_summary,
casualty_type,
# split out as separate function?
annotations = list("KSI" = list(
aes = ggplot2::aes(x = intersection, fill = accident_severity),
geom = list(
ggplot2::geom_bar(stat = 'count', position = 'fill'),
ggplot2::scale_y_continuous(labels = scales::percent_format()),
ggplot2::scale_fill_manual(
values = c(
"Slight" = "#fee0d2",
"Serious" = "#fc9272",
"Fatal" = "#de2d26"
)
)
)
)),
base_annotations = list(
'Intersection size' = ComplexUpset::intersection_size(
text = ggplot2::element_text(size = 3)
)
),
name = "Combinations of casualty types",
width_ratio = 0.1,
min_size = 50,
themes = ComplexUpset::upset_modify_themes(
list(
'KSI' = ggplot2::theme(
text = ggplot2::element_text(family = family),
axis.text.x = ggplot2::element_blank()
),
'Intersection size' = ggplot2::theme(text = ggplot2::element_text(family = family)),
'intersections_matrix' = ggplot2::theme(text = ggplot2::element_text(family = family)),
'overall_sizes' = ggplot2::theme(
axis.text.x = ggplot2::element_blank(),
text = ggplot2::element_text(family = family)
)
)
)
)
}
# original code -----------------------------------------------------------
# casualties_lookup_2 = c(
# "otorcyc" = "Motorcyclist",
# "7.5" = "HGV",
# "Goods" = "HGV",
# "Car occupant" = "Car",
# "Van" = "Van",
# "coach" = "Bus",
# "Minibus" = "Minibus",
# "Taxi" = "Taxi",
# "Agri" = "Other",
# "Missing" = "Other",
# "Mobility" = "Other",
# "Tram" = "Other",
# "Horse" = "Other",
# "Other" = "Other",
# "issing" = "Other"
# )
#
# # Recode casualty types and vehicle types.
# casualties_all$casualty_type_simple <- tc_recode_casualties(casualties_all$casualty_type, pattern_match = casualties_lookup_2)
# vehicles_all$vehicle_type_simple <- tc_recode_vehicle_type(vehicles_all$vehicle_type)
# casualties_all <- casualties_all %>%
# mutate(
# casualty_type_simple=case_when(
# casualty_type_simple=="Cyclist" ~ "Bicycle",
# casualty_type_simple=="Motorcyclist" ~ "Motorcycle",
# TRUE ~ casualty_type_simple
# )
# )
#
# # Join casualties to crashes using accident index
# family = "Avenir Book"
# crash_cas <- inner_join(
# vehicles_all %>% select(accident_index, vehicle_type_simple),
# casualties_all %>% select(accident_index, casualty_type_simple), by="accident_index") %>%
# inner_join(crashes_all %>% select(accident_index, accident_severity), by = "accident_index")
#
# crash_cas <- crash_cas %>% pivot_longer(-c(accident_index, accident_severity), names_to="cas_veh", values_to="type")
# # For the UpSet plot we do not differentiate number of vehicles involved in single crash.
# # As this is a set visualization we don't want to double count crashes.
# crash_summary <- crash_cas %>% select(accident_index, type) %>% unique %>% mutate(is_present=TRUE) %>%
# pivot_wider(id=accident_index, names_from=type, values_from=is_present, values_fill=list(is_present=FALSE) )
# casualty_type <- colnames(crash_summary[2:11])
# crash_summary <- crash_summary %>% inner_join(crash_cas %>% select(accident_index, accident_severity) %>% unique)
#
# # Plot
# plot <- upset(
# crash_summary,
# casualty_type,
# annotations=list(
# "KSI"=list(
# aes=aes(x=intersection, fill=accident_severity),
# geom=list(
# geom_bar(stat='count', position='fill'),
# scale_y_continuous(labels=scales::percent_format()),
# scale_fill_manual(values=c(
# "Slight"="#fee0d2", "Serious"="#fc9272", "Fatal"="#de2d26"
# ))
# )
# )
# ),
# base_annotations=list('Intersection size'=intersection_size(text=element_text(size=3))),
# name="Combinations of casualty types",
# width_ratio=0.1,
# min_size=50,
# themes=upset_modify_themes(
# list(
# 'KSI'=theme(text=element_text(family = family), axis.text.x=element_blank()),
# 'Intersection size'=theme(text=element_text(family = family)),
# 'intersections_matrix'=theme(text=element_text(family = family)),
# 'overall_sizes'=theme(axis.text.x=element_blank(), text=element_text(family = family))
# )
# )
# )
#
# ggsave("./figures/upset_stats19.png", plot=plot, width=12, height=9, dpi=600)