YOK Foreign Students Data Starter Code for Tidyverse (dplyr + ggplot2) and Quarto

foreign_students_report_starter_code.qmd

---
title: "Yabancı Öğrenci Raporu (Örnek)"
author: "MEF MGMT 553 2022-2023 Bahar Dönemi"
format: pptx
editor: visual
execute: 
  echo: false
  message: false
  warning: false
---

```{r,echo=FALSE,message=FALSE,warning=FALSE}

## Hazırlık: tidyverse paketini yükle, excel dosyalarını yükle, dataframei düzenle
library(tidyverse)
raw_df <- readxl::read_excel("/Users/rocket/Downloads/mef_mgmt_quarto/foreign_students_by_nationality_2021_2022.xlsx")

raw_df <- raw_df %>% rename(univ_name=1,univ_type=2,city_name=3,country=4,male=5,female=6,total=7)
the_df <- raw_df %>% mutate(across(c(male,female,total),as.numeric))

```


```{r}
## Örnek grafik: En fazla yabancı öğrenci sağlayan 10 ülkeyi listele

## veriyi hazırla
df1 <- the_df %>% 
  filter(complete.cases(.)) %>% #Eksik (NA) değerleri olmayan satırları getir 
  group_by(country) %>% # Ülkelere göre grupla
  summarise(total=sum(total)) %>%  # Toplam öğrenci sayısını hesapla
  arrange(desc(total)) # Büyükten küçüğe sırala

ggplot(
  df1 %>% slice(1:10),
  aes(
    x=reorder(country,-total),
    y=total
  )
) + 
geom_bar(stat="identity") + 
theme_minimal() + 
theme(axis.text.x = element_text(angle=60,hjust=1)) + 
labs(
  title="En Fazla Yabancı Öğrencinin Geldiği Ülkeler", 
  subtitle="Kaynak: 2021-2022 YÖK Verileri",
  y="Öğrenci Sayısı",
  x=""
 )
```

```{r}
## Fonksiyon hazırla
generate_country_plot <- function(the_df,the_country){
country_df<- the_df %>% 
  filter(complete.cases(.) & country==the_country[1]) %>% arrange(desc(total)) %>%
  select(univ_name,male,female,total,univ_type) %>% pivot_longer(.,-c(univ_name,univ_type,total)) %>% arrange(desc(total))

# ggplot(country_df,aes(x=univ_name,y=))
country_plot <- ggplot(country_df %>% slice(1:20),aes(x=reorder(univ_name,total),y=value,fill=name)) + geom_bar(stat="identity",position="stack") + coord_flip() + theme_minimal() + labs(title = paste0(the_country),subtitle="Ülkeden gelen öğrencilerin en fazla yerleştiği 10 üniversite.",y="",x="Öğrenci Sayısı",fill="") + theme(legend.position = "top")
return(country_plot)
  
}
```



```{r,output='asis'}

for (i in 1:10){
the_country <- df1 %>% select(country) %>% slice(i) %>% unlist()
total_students <- df1 %>% filter(complete.cases(.) & country==the_country[1]) %>% select(total) %>% unlist()
cat(paste0("## ",the_country),"\n\n")
cat(paste0("Öğrenci sayısı: ", total_students,"\n\n"))
# generate_country_plot(the_df,the_country)
knitr::knit_print(generate_country_plot(the_df,the_country))
cat("\n\n")
}
```

foreign_students_report_starter_code_2.qmd

---
title: "Yabancı Öğrenci Raporu (Üniversiteler)"
author: "MEF MGMT 553 2022-2023 Bahar Dönemi"
format: html
editor: visual
execute: 
  echo: false
  message: false
  warning: false
---

```{r,echo=FALSE,message=FALSE,warning=FALSE}

## Hazırlık: tidyverse paketini yükle, excel dosyalarını yükle, dataframei düzenle
library(tidyverse)
raw_df <- readxl::read_excel("foreign_students_by_nationality_2021_2022.xlsx")

raw_df <- raw_df %>% rename(univ_name=1,univ_type=2,city_name=3,country=4,male=5,female=6,total=7)
the_df <- raw_df %>% mutate(across(c(male,female,total),as.numeric))
n_results = 20
```


```{r}
## Örnek grafik: En fazla yabancı öğrenci sağlayan 10 ülkeyi listele

## veriyi hazırla
df1 <- the_df %>% filter(univ_type=="VAKIF") %>% 
  filter(complete.cases(.)) %>% #Eksik (NA) değerleri olmayan satırları getir 
  group_by(univ_name,univ_type) %>% # Ülkelere göre grupla
  summarise(total=sum(total)) %>%  # Toplam öğrenci sayısını hesapla
  arrange(desc(total)) %>% ungroup() %>% ungroup() # Büyükten küçüğe sırala

ggplot(
  df1 %>% slice(1:n_results),
  aes(
    x=reorder(univ_name,total),
    y=total,
    fill=univ_type
  )
) + 
geom_bar(stat="identity") + 
theme_minimal() + 
theme(axis.text.x = element_text(angle=60,hjust=1)) + 
labs(
  title="En Fazla Yabancı Öğrencinin Bulunduğu Üniversiteler", 
  subtitle="Kaynak: 2021-2022 YÖK Verileri",
  y="Öğrenci Sayısı",
  x=""
 ) + coord_flip()
```

```{r}
## Fonksiyon hazırla
generate_university_plot <- function(the_df,the_university){
university_df<- the_df %>% 
  filter(complete.cases(.) & univ_name==the_university[1]) %>% arrange(desc(total)) %>% mutate(male=male/sum(total),female=female/sum(total)) %>%
  select(country,male,female,total) %>% pivot_longer(.,-c(country,total)) %>% arrange(desc(total))

# ggplot(country_df,aes(x=univ_name,y=))
university_plot <- ggplot(university_df %>% slice(1:20),aes(x=reorder(country,total),y=value,fill=name)) + geom_bar(stat="identity",position="stack") + coord_flip() + theme_minimal() + labs(title = paste0(the_university),subtitle="Üniversiteye gelen öğrencilerin en fazla geldikleri 10 ülke.",y="Öğrenci Yüzdesi",x="",fill="") + theme(legend.position = "top") + scale_y_continuous(labels=scales::percent)
return(university_plot)
  
}
```



```{r,output='asis',eval=TRUE}

for (i in 1:n_results){
the_university <- df1 %>% filter(univ_type=="VAKIF") %>% select(univ_name) %>% slice(i) %>% unlist()
# the_country <- df1 %>% select(country) %>% slice(i) %>% unlist()
total_students <- df1 %>% filter(complete.cases(.) & univ_name==the_university[1]) %>% select(total) %>% unlist()
cat(paste0("## ",the_university),"\n\n")
cat(paste0("Öğrenci sayısı: ", total_students,"\n\n"))
# generate_country_plot(the_df,the_country)
knitr::knit_print(generate_university_plot(the_df,the_university))
cat("\n\n")
}
```

foreign_students_starter_code.R

#install.packages("tidyverse","readxl")
library(tidyverse)

#https://github.com/berkorbay/datasets/raw/master/foreign_students/foreign_students_by_nationality_2021_2022.xlsx
raw_df <- readxl::read_excel("foreign_students_by_nationality_2021_2022.xlsx")

raw_df <- raw_df %>% rename(univ_name=1,univ_type=2,city_name=3,country=4,male=5,female=6,total=7)
the_df <- raw_df %>% mutate(across(c(male,female,total),as.numeric))

the_df %>% 
  filter(complete.cases(.)) %>% 
  group_by(country) %>% 
  summarise(total=sum(total)) %>% 
  arrange(desc(total))