In analyticsresearchlab/thestats: R Package for Exploring Turkish Higher Education Statistics
Packages
# Packages must be installed
packages <- c("thestats", "dplyr", "ggplot2", "sp", "mapproj", "networkD3",
"tidyr", "data.table", "circlize", "RColorBrewer")
# Install packages not yet installed
installed_packages <- packages %in% rownames(installed.packages())
if (any(installed_packages == FALSE)) {
install.packages(packages[!installed_packages])
}
# Packages loading
invisible(lapply(packages, library, character.only = TRUE))
The plot of number of placed students in state universities map by cities (Fig.7A)
data <- list_score(region_names = "all",
city_names = "all",
university_names = "all",
department_names = "all",
var_ids = c("X11", "X12", "X13"),
lang = "en")
id <- numeric(dim(data)[1])
for(i in 1:dim(data)[1]){id[i] <- which(grepl(data$id[i], regions_cities_en$id))}
data_reg_city <- cbind(data, region = regions_cities_en$region[id], city = regions_cities_en$city[id])
data_subset <- data_reg_city %>%
mutate(X11 = replace(X11, X11 == "---", NA)) %>%
replace(is.na(.), 0) %>%
select(X11, X12, X13) %>%
mutate_if(is.character, as.numeric)
data_sub_loc <- cbind(data_reg_city[,-c(8:10)], data_subset)
city_stat <- data_sub_loc %>%
filter(type == "State") %>%
mutate(total = X11 + X12 + X13) %>%
select(city, total, year) %>%
group_by(city, year) %>%
summarise(mean_t = sum(total))
TUR <- readRDS("gadm36_TUR_1_sp.rds") # The RDS file must be downloaded from https://gadm.org/download_country_v3.html.
TUR@data$NAME_1 <- gsub("K. Maras", "Kahramanmaras",TUR@data$NAME_1)
TUR@data$NAME_1 <- gsub("Kinkkale","Kirikkale",TUR@data$NAME_1)
TUR@data$NAME_1 <- gsub("Zinguldak", "Zonguldak", TUR@data$NAME_1)
TUR@data$NAME_1 <- gsub("Adıyaman", "Adiyaman", TUR@data$NAME_1)
city_stat$city <- rep(TUR@data$NAME_1, each = 3)
tur_for <- fortify(TUR)
colnames(city_stat) <- c("city", "year", "total")
id_and_cities<- tibble(id = rownames(TUR@data), city = TUR@data$NAME_1) %>%
left_join(city_stat, by = "city")
map1 <- left_join(tur_for, id_and_cities, by = "id")
fig7A <- ggplot(map1) +
geom_polygon(aes(x = long, y = lat, group = group, fill = total), color = "grey") +
coord_map() +
theme_void() +
scale_fill_distiller(name = "Number of the\nplaced students\n",
palette = "Reds",
direction = 1,
limits = c(0, 100000)) +
facet_grid(rows = vars(year)) +
theme() +
guides(fill = guide_colourbar(barwidth = 0.5, barheight = 15))
fig7A
The plot of number of placed students map by cities (Fig.7B)
data2 <- list_score(region_names = "all",
city_names = "all",
university_names = "all",
department_names = "all",
var_ids = c("X11", "X12", "X13"),
lang = "en")
id2 <- numeric(dim(data2)[1])
for(i in 1:dim(data2)[1]){id2[i] <- which(grepl(data2$id[i], regions_cities_en$id)) }
data2_reg_city <- cbind(data2, region = regions_cities_en$region[id2],
city = regions_cities_en$city[id2])
data2_subset <- data2_reg_city %>%
mutate(X11 = replace(X11, X11 == "---", NA)) %>%
replace(is.na(.), 0) %>%
select(X11, X12, X13) %>%
mutate_if(is.character, as.numeric)
data2_sub_loc <- cbind(data2_reg_city[,-c(8:10)], data2_subset)
city_stat2 <- data2_sub_loc %>%
mutate(total = X11 + X12 + X13) %>%
select(city, total, year) %>%
group_by(city, year) %>%
summarise(mean_t = sum(total))
city_stat2$city <- rep(TUR@data$NAME_1, each = 3)
colnames(city_stat2) <- c("city", "year", "total")
id_and_cities2<- tibble(id = rownames(TUR@data), city = TUR@data$NAME_1) %>%
left_join(city_stat2, by = "city")
map2 <- left_join(tur_for, id_and_cities2, by = "id")
fig7B <- ggplot(map2) +
geom_polygon(aes(x = long, y = lat, group = group, fill = total), color = "grey") +
coord_map() +
theme_void() +
scale_fill_distiller(name = "Number of the\nplaced students\n",
palette = "Reds",
direction = 1,
limits = c(0, 100000)) +
facet_grid(rows = vars(year)) +
theme() +
guides(fill = guide_colourbar(barwidth = 0.5, barheight = 15))
fig7B
Combining of the Fig.7A and Fig.7B
legend <- get_legend(
# create some space to the left of the legend
fig7R + theme(legend.box.margin = margin(0, 0, 0, 12))
)
prow <- plot_grid(fig7A + theme(legend.position="none"),
fig7B + theme(legend.position="none"),
align = "h",
labels = "AUTO")
fig7 <- plot_grid(prow, legend, rel_widths = c(3, .4))
fig7
The plot in the Figure 8
data <- list_score(region_names = "all", city_names = "all", university_names = "all",
department_names = "all", var_ids = paste("X", seq(32, 112), sep = ""), lang = "en")
data_2020 <- data %>% filter(year == "2020")
id <- numeric(dim(data_2020)[1])
for(i in 1:dim(data_2020)[1]){
id[i] <- which(grepl(data_2020$id[i], regions_cities_en$id))}
data_2020_reg_city <- cbind(data_2020, region = regions_cities_en$region[id])
city <- c("Adana", "Adiyaman", "Afyon", "Agri", "Amasya", "Ankara", "Antalya", "Artvin",
"Aydin", "Balikesir", "Bilecik", "Bingol", "Bitlis", "Bolu","Burdur",
"Bursa", "Canakkale", "Cankiri", "Corum", "Denizli", "Diyarbakir", "Edirne",
"Elazig","Erzincan", "Erzurum", "Eskisehir","Gaziantep", "Giresun",
"Gumushane", "Hakkari", "Hatay", "Isparta", "Mersin", "Istanbul", "Izmir",
"Kars", "Kastamonu", "Kayseri", "Kirklareli", "Kirsehir", "Kocaeli", "Konya",
"Kutahya", "Malatya", "Manisa", "Kahramanmaras", "Mardin", "Mugla", "Mus",
"Nevsehir", "Nigde", "Ordu", "Rize", "Sakarya", "Samsun", "Siirt", "Sinop", "Sivas",
"Tekirdag", "Tokat", "Trabzon", "Tunceli", "Sanliurfa", "Usak", "Van", "Yozgat",
"Zonguldak", "Aksaray", "Bayburt", "Karaman", "Kirikkale", "Batman", "Sirnak",
"Bartin", "Ardahan", "Igdir", "Yalova", "Karabuk", "Kilis", "Osmaniye", "Duzce")
colnames(data_2020_reg_city)[8:88] <- city
data_flow <- aggregate(.~region, data = data_2020_reg_city[,8:89], FUN = sum)
connect <- data_flow %>% pivot_longer(!region, names_to = "from", values_to = "count")
region <- c("Mediterranean", "Southeastern Anatolia", "Agean", "Eastern Anatolia", "Black Sea",
"Central Anatolia", "Mediterranean", "Black Sea", "Agean", "Marmara", "Marmara",
"Eastern Anatolia", "Eastern Anatolia", "Black Sea", "Mediterranean", "Marmara",
"Marmara", "Central Anatolia", "Black Sea", "Agean", "Southeastern Anatolia",
"Marmara", "Eastern Anatolia", "Eastern Anatolia", "Eastern Anatolia",
"Central Anatolia",
"Southeastern Anatolia", "Black Sea", "Black Sea", "Eastern Anatolia",
"Mediterranean", "Mediterranean", "Mediterranean", "Marmara", "Agean",
"Eastern Anatolia", "Black Sea", "Central Anatolia", "Marmara", "Central Anatolia",
"Marmara", "Central Anatolia", "Agean", "Eastern Anatolia", "Agean",
"Mediterranean", "Southeastern Anatolia", "Agean", "Eastern Anatolia",
"Central Anatolia", "Central Anatolia", "Black Sea", "Black Sea",
"Marmara", "Black Sea", "Southeastern Anatolia", "Black Sea", "Central Anatolia",
"Marmara", "Black Sea", "Black Sea", "Eastern Anatolia", "Southeastern Anatolia",
"Agean", "Eastern Anatolia", "Central Anatolia", "Black Sea", "Central Anatolia",
"Black Sea", "Central Anatolia", "Central Anatolia", "Southeastern Anatolia",
"Southeastern Anatolia", "Black Sea", "Eastern Anatolia", "Eastern Anatolia",
"Marmara", "Black Sea", "Southeastern Anatolia", "Mediterranean", "Black Sea")
connect$from <- rep(region, 7)
connect_dt <- data.table(connect)
connect_dt <- connect_dt[,list(total = sum(count)), by = c('region', 'from')]
links <- data.frame(connect_dt)
colnames(links) <- c("target", "source", "value")
nodes <- data.frame(name = c(as.character(links$source), as.character(links$target)) %>% unique())
links$IDsource <- match(links$target, nodes$name)-1
links$IDtarget <- match(links$source, nodes$name)-1
lin <- data.frame(from = links$source, to = links$target, value = links$value)
mycolor <- brewer.pal(7, "Paired")
pdf(file="circlize.pdf", width=8, height=5, pointsize=8)
chordDiagram(lin, directional = 1, direction.type = c("diffHeight", "arrows"), link.arr.type = "big.arrow", grid.col = mycolor)
title("Migration of Freshman students by region in Turkey in 2020")
legend("right", pch = 15, legend = unique(lin$from), col = mycolor, bty = "n", cex = 1, pt.cex = 3, border = "black")
dev.off()
analyticsresearchlab/thestats documentation built on July 1, 2023, 2:20 a.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Packages
# Packages must be installed packages <- c("thestats", "dplyr", "ggplot2", "sp", "mapproj", "networkD3", "tidyr", "data.table", "circlize", "RColorBrewer") # Install packages not yet installed installed_packages <- packages %in% rownames(installed.packages()) if (any(installed_packages == FALSE)) { install.packages(packages[!installed_packages]) } # Packages loading invisible(lapply(packages, library, character.only = TRUE))
The plot of number of placed students in state universities map by cities (Fig.7A)
data <- list_score(region_names = "all", city_names = "all", university_names = "all", department_names = "all", var_ids = c("X11", "X12", "X13"), lang = "en") id <- numeric(dim(data)[1]) for(i in 1:dim(data)[1]){id[i] <- which(grepl(data$id[i], regions_cities_en$id))} data_reg_city <- cbind(data, region = regions_cities_en$region[id], city = regions_cities_en$city[id]) data_subset <- data_reg_city %>% mutate(X11 = replace(X11, X11 == "---", NA)) %>% replace(is.na(.), 0) %>% select(X11, X12, X13) %>% mutate_if(is.character, as.numeric) data_sub_loc <- cbind(data_reg_city[,-c(8:10)], data_subset) city_stat <- data_sub_loc %>% filter(type == "State") %>% mutate(total = X11 + X12 + X13) %>% select(city, total, year) %>% group_by(city, year) %>% summarise(mean_t = sum(total)) TUR <- readRDS("gadm36_TUR_1_sp.rds") # The RDS file must be downloaded from https://gadm.org/download_country_v3.html. TUR@data$NAME_1 <- gsub("K. Maras", "Kahramanmaras",TUR@data$NAME_1) TUR@data$NAME_1 <- gsub("Kinkkale","Kirikkale",TUR@data$NAME_1) TUR@data$NAME_1 <- gsub("Zinguldak", "Zonguldak", TUR@data$NAME_1) TUR@data$NAME_1 <- gsub("Adıyaman", "Adiyaman", TUR@data$NAME_1) city_stat$city <- rep(TUR@data$NAME_1, each = 3) tur_for <- fortify(TUR) colnames(city_stat) <- c("city", "year", "total") id_and_cities<- tibble(id = rownames(TUR@data), city = TUR@data$NAME_1) %>% left_join(city_stat, by = "city") map1 <- left_join(tur_for, id_and_cities, by = "id") fig7A <- ggplot(map1) + geom_polygon(aes(x = long, y = lat, group = group, fill = total), color = "grey") + coord_map() + theme_void() + scale_fill_distiller(name = "Number of the\nplaced students\n", palette = "Reds", direction = 1, limits = c(0, 100000)) + facet_grid(rows = vars(year)) + theme() + guides(fill = guide_colourbar(barwidth = 0.5, barheight = 15)) fig7A
The plot of number of placed students map by cities (Fig.7B)
data2 <- list_score(region_names = "all", city_names = "all", university_names = "all", department_names = "all", var_ids = c("X11", "X12", "X13"), lang = "en") id2 <- numeric(dim(data2)[1]) for(i in 1:dim(data2)[1]){id2[i] <- which(grepl(data2$id[i], regions_cities_en$id)) } data2_reg_city <- cbind(data2, region = regions_cities_en$region[id2], city = regions_cities_en$city[id2]) data2_subset <- data2_reg_city %>% mutate(X11 = replace(X11, X11 == "---", NA)) %>% replace(is.na(.), 0) %>% select(X11, X12, X13) %>% mutate_if(is.character, as.numeric) data2_sub_loc <- cbind(data2_reg_city[,-c(8:10)], data2_subset) city_stat2 <- data2_sub_loc %>% mutate(total = X11 + X12 + X13) %>% select(city, total, year) %>% group_by(city, year) %>% summarise(mean_t = sum(total)) city_stat2$city <- rep(TUR@data$NAME_1, each = 3) colnames(city_stat2) <- c("city", "year", "total") id_and_cities2<- tibble(id = rownames(TUR@data), city = TUR@data$NAME_1) %>% left_join(city_stat2, by = "city") map2 <- left_join(tur_for, id_and_cities2, by = "id") fig7B <- ggplot(map2) + geom_polygon(aes(x = long, y = lat, group = group, fill = total), color = "grey") + coord_map() + theme_void() + scale_fill_distiller(name = "Number of the\nplaced students\n", palette = "Reds", direction = 1, limits = c(0, 100000)) + facet_grid(rows = vars(year)) + theme() + guides(fill = guide_colourbar(barwidth = 0.5, barheight = 15)) fig7B
Combining of the Fig.7A and Fig.7B
legend <- get_legend( # create some space to the left of the legend fig7R + theme(legend.box.margin = margin(0, 0, 0, 12)) ) prow <- plot_grid(fig7A + theme(legend.position="none"), fig7B + theme(legend.position="none"), align = "h", labels = "AUTO") fig7 <- plot_grid(prow, legend, rel_widths = c(3, .4)) fig7
The plot in the Figure 8
data <- list_score(region_names = "all", city_names = "all", university_names = "all", department_names = "all", var_ids = paste("X", seq(32, 112), sep = ""), lang = "en") data_2020 <- data %>% filter(year == "2020") id <- numeric(dim(data_2020)[1]) for(i in 1:dim(data_2020)[1]){ id[i] <- which(grepl(data_2020$id[i], regions_cities_en$id))} data_2020_reg_city <- cbind(data_2020, region = regions_cities_en$region[id]) city <- c("Adana", "Adiyaman", "Afyon", "Agri", "Amasya", "Ankara", "Antalya", "Artvin", "Aydin", "Balikesir", "Bilecik", "Bingol", "Bitlis", "Bolu","Burdur", "Bursa", "Canakkale", "Cankiri", "Corum", "Denizli", "Diyarbakir", "Edirne", "Elazig","Erzincan", "Erzurum", "Eskisehir","Gaziantep", "Giresun", "Gumushane", "Hakkari", "Hatay", "Isparta", "Mersin", "Istanbul", "Izmir", "Kars", "Kastamonu", "Kayseri", "Kirklareli", "Kirsehir", "Kocaeli", "Konya", "Kutahya", "Malatya", "Manisa", "Kahramanmaras", "Mardin", "Mugla", "Mus", "Nevsehir", "Nigde", "Ordu", "Rize", "Sakarya", "Samsun", "Siirt", "Sinop", "Sivas", "Tekirdag", "Tokat", "Trabzon", "Tunceli", "Sanliurfa", "Usak", "Van", "Yozgat", "Zonguldak", "Aksaray", "Bayburt", "Karaman", "Kirikkale", "Batman", "Sirnak", "Bartin", "Ardahan", "Igdir", "Yalova", "Karabuk", "Kilis", "Osmaniye", "Duzce") colnames(data_2020_reg_city)[8:88] <- city data_flow <- aggregate(.~region, data = data_2020_reg_city[,8:89], FUN = sum) connect <- data_flow %>% pivot_longer(!region, names_to = "from", values_to = "count") region <- c("Mediterranean", "Southeastern Anatolia", "Agean", "Eastern Anatolia", "Black Sea", "Central Anatolia", "Mediterranean", "Black Sea", "Agean", "Marmara", "Marmara", "Eastern Anatolia", "Eastern Anatolia", "Black Sea", "Mediterranean", "Marmara", "Marmara", "Central Anatolia", "Black Sea", "Agean", "Southeastern Anatolia", "Marmara", "Eastern Anatolia", "Eastern Anatolia", "Eastern Anatolia", "Central Anatolia", "Southeastern Anatolia", "Black Sea", "Black Sea", "Eastern Anatolia", "Mediterranean", "Mediterranean", "Mediterranean", "Marmara", "Agean", "Eastern Anatolia", "Black Sea", "Central Anatolia", "Marmara", "Central Anatolia", "Marmara", "Central Anatolia", "Agean", "Eastern Anatolia", "Agean", "Mediterranean", "Southeastern Anatolia", "Agean", "Eastern Anatolia", "Central Anatolia", "Central Anatolia", "Black Sea", "Black Sea", "Marmara", "Black Sea", "Southeastern Anatolia", "Black Sea", "Central Anatolia", "Marmara", "Black Sea", "Black Sea", "Eastern Anatolia", "Southeastern Anatolia", "Agean", "Eastern Anatolia", "Central Anatolia", "Black Sea", "Central Anatolia", "Black Sea", "Central Anatolia", "Central Anatolia", "Southeastern Anatolia", "Southeastern Anatolia", "Black Sea", "Eastern Anatolia", "Eastern Anatolia", "Marmara", "Black Sea", "Southeastern Anatolia", "Mediterranean", "Black Sea") connect$from <- rep(region, 7) connect_dt <- data.table(connect) connect_dt <- connect_dt[,list(total = sum(count)), by = c('region', 'from')] links <- data.frame(connect_dt) colnames(links) <- c("target", "source", "value") nodes <- data.frame(name = c(as.character(links$source), as.character(links$target)) %>% unique()) links$IDsource <- match(links$target, nodes$name)-1 links$IDtarget <- match(links$source, nodes$name)-1 lin <- data.frame(from = links$source, to = links$target, value = links$value) mycolor <- brewer.pal(7, "Paired") pdf(file="circlize.pdf", width=8, height=5, pointsize=8) chordDiagram(lin, directional = 1, direction.type = c("diffHeight", "arrows"), link.arr.type = "big.arrow", grid.col = mycolor) title("Migration of Freshman students by region in Turkey in 2020") legend("right", pch = 15, legend = unique(lin$from), col = mycolor, bty = "n", cex = 1, pt.cex = 3, border = "black") dev.off()
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.