-
Notifications
You must be signed in to change notification settings - Fork 0
/
prep.R
216 lines (182 loc) · 7.91 KB
/
prep.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
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
library(readr)
library(tidyverse)
setwd(here::here())
#This chunk needs to be replaced by references to SQL tables.
#Importing data
d1 <- read_csv("XXXdatapath.csv")
d2 <- read_csv("XXXdatapath.csv")
d3 <- read_csv("XXXdatapath.csv")
currency_lookup_18 <- read_csv("XXXdatapath.csv")
e1 <- read_csv("XXXdatapath.csv")
e2 <- read_csv("XXXdatapath.csv")
e3 <- read_csv("XXXdatapath.csv")
b1 <- read_csv("XXXdatapath.csv")
schools <- read_csv("XXXdatapath.csv")
d <- d1 %>%
rbind(.,d2) %>%
rbind(.,d3) %>%
separate(., BSCI01c, into = c("Curr", "Curr_full"), sep = "-")
schools <- schools %>%
select(UNITID=unitid, country, class_Control, old_region = class_Region, accred = class_Accreditation, name=unitname, membertype, groupname) %>%
mutate(
country = gsub("United States", "the United States", x=country),
country = gsub("Czech Republic", "the Czech Republic", x=country),
country = gsub("Netherlands", "the Netherlands", x=country),
country = gsub("United Arab Emirates", "the United Arab Emirates", x=country),
country = gsub("United Kingdom", "the United Kingdom", x=country)
) %>%
separate(., old_region, into = c("Mega_region", "Sub_region"), sep = ":") %>%
na.omit()
schools_short <- schools %>%
select(UNITID, country, Mega_region, Sub_region)
data <- e1 %>%
rbind(.,e2) %>%
rbind(.,e3) %>%
inner_join(.,d) %>%
left_join(., currency_lookup_18) %>%
mutate(BSCU02=BSCU02*con_rate) %>%
separate(., class_region, into = c("Mega_region", "Sub_region"), sep = ":")
b1 <- merge(b1, schools_short, by.x = "unitid", by.y="UNITID")
e1 <- merge(e1, schools_short, by.x = "unitID", by.y="UNITID")
data <- merge(data, schools_short, by.x = "unitID", by.y="UNITID", all.x=TRUE)%>%
mutate(Sub_region=Sub_region.x) %>%
mutate(Mega_region=Mega_region.x)
#controlled sample vector - schools that participated in past three surveys
controlled <- data %>%
group_by(unitID) %>%
summarise(n=n()) %>%
filter(n>=3) %>%
select(unitID) %>%
as.matrix()
#tables for trend data - split by countries/regions to identify if <6 schools participated
country_table <- data %>%
filter(unitID %in% controlled) %>%
group_by(cycleID, country) %>%
summarise(n=n()) %>%
as.data.frame()
sub_table <- data %>%
filter(unitID %in% controlled) %>%
group_by(cycleID, Sub_region) %>%
summarise(n=n())%>%
as.data.frame()
mega_table <- data %>%
filter(unitID %in% controlled) %>%
group_by(cycleID, Mega_region) %>%
summarise(n=n())%>%
as.data.frame()
country_table_control <- data %>%
filter(unitID %in% controlled) %>%
group_by(cycleID, country, class_Control) %>%
summarise(n=n()) %>%
as.data.frame()
sub_table_control <- data %>%
filter(unitID %in% controlled) %>%
group_by(cycleID, Sub_region, class_Control) %>%
summarise(n=n())%>%
as.data.frame()
mega_table_control <- data %>%
filter(unitID %in% controlled) %>%
group_by(cycleID, Mega_region, class_Control) %>%
summarise(n=n())%>%
as.data.frame()
country_table_accredited <- data %>%
filter(unitID %in% controlled & class_Accreditation!="Not Accredited") %>%
group_by(cycleID, country) %>%
summarise(n=n()) %>%
as.data.frame()
sub_table_accredited <- data %>%
filter(unitID %in% controlled & class_Accreditation!="Not Accredited") %>%
group_by(cycleID, Sub_region) %>%
summarise(n=n())%>%
as.data.frame()
mega_table_accredited <- data %>%
filter(unitID %in% controlled & class_Accreditation!="Not Accredited") %>%
group_by(cycleID, Mega_region) %>%
summarise(n=n())%>%
as.data.frame()
country_table_accredited_control <- data %>%
filter(unitID %in% controlled & class_Accreditation!="Not Accredited") %>%
group_by(cycleID, country, class_Control) %>%
summarise(n=n()) %>%
as.data.frame()
sub_table_accredited_control <- data %>%
filter(unitID %in% controlled & class_Accreditation!="Not Accredited") %>%
group_by(cycleID, Sub_region, class_Control) %>%
summarise(n=n())%>%
as.data.frame()
mega_table_accredited_control <- data %>%
filter(unitID %in% controlled & class_Accreditation!="Not Accredited") %>%
group_by(cycleID, Mega_region, class_Control) %>%
summarise(n=n())%>%
as.data.frame()
all_accredited_control <- data %>%
filter(unitID %in% controlled & class_Accreditation!="Not Accredited") %>%
group_by(cycleID, class_Control) %>%
summarise(n=n())%>%
as.data.frame()
all_accredited <- data %>%
filter(unitID %in% controlled & class_Accreditation!="Not Accredited") %>%
group_by(cycleID) %>%
summarise(n=n())%>%
as.data.frame()
theme_corporate <- function() {
font <- "Arial"
ggplot2::theme(
#Text format:
#This sets the font, size, type and color of text for the plot's title
plot.title = ggplot2::element_text(family=font,
size=20,
face="bold",
color="#006E62",
hjust = 0),
#This sets the font, size, type and color of text for the plots's subtitle, as well as setting a margin between the title and the subtitle
plot.subtitle = ggplot2::element_text(family=font,
size=16,
color = "#006E62",
margin=ggplot2::margin(9,0,9,0)),
plot.caption = ggplot2::element_text(family=font,
size=10,
color = "#55565A",
hjust = 0),
plot.margin = unit(c(1, 0, 1, 1), "lines"),
#Legend format
#This sets the position and alignment of the legend, removes a title and backround for it and sets the requirements for any text within the legend. The legend may often need some more manual tweaking when it comes to its exact position based on the plot coordinates.
legend.position = "top",
legend.text.align = 0,
legend.background = ggplot2::element_blank(),
legend.title = ggplot2::element_blank(),
legend.key = ggplot2::element_blank(),
legend.text = ggplot2::element_text(family=font,
size=12,
color="#55565A"),
#Axis format
#This sets the text font, size and color for the axis test, as well as setting the margins and removes lines and ticks. In some cases, axis lines and axis ticks are things we would want to have in the plot.
axis.title.x = ggplot2::element_blank(),
#axis.title.y = ggplot2::element_blank(),
axis.text = ggplot2::element_text(family=font,
size=12,
color="#55565A"),
axis.text.x = ggplot2::element_text(margin=ggplot2::margin(5, b = 10)),
axis.ticks = ggplot2::element_blank(),
axis.line = ggplot2::element_blank(),
#Grid lines
#This removes all minor gridlines and adds major y gridlines. In many cases you will want to change this to remove y gridlines and add x gridlines.
panel.grid.minor = ggplot2::element_blank(),
panel.grid.major.y = ggplot2::element_line(color="#DBD9D6"),
panel.grid.major.x = ggplot2::element_blank(),
#Blank background
#This sets the panel background as blank, removing the standard grey ggplot background colour from the plot
panel.background = ggplot2::element_blank(),
# Panel Border
#Strip background (#This sets the panel background for facet-wrapped plots to white, removing the standard grey ggplot background color and sets the title size of the facet-wrap title to font size 16)
strip.background = ggplot2::element_rect(fill="white"),
strip.text = ggplot2::element_text(size = 16, hjust = 0)
)
}
corporate_colors <- c("#800080",
"#800080",
"#800080",
"#800080",
"#800080",
"#800080",
"#800080")