Korea_Population Practice

Data Clearning

Data- 데이터 공공 포털 다운로드

setwd("C:/Users/Administrator/Desktop/BIG DATA")

data<-read.csv("popul_korea.csv")


data %>% 
  select("시점", "한국인인구", "한국인남자", "한국인여자") %>% 
  filter("시점" > 1963) -> df_one

names(df_one) <- c("Year", "Total", "Male", "Female")


as.numeric(as.character(df_one$Total)) -> df_one$Total
as.numeric(as.character(df_one$Male)) -> df_one$Male
as.numeric(as.character(df_one$Female)) -> df_one$Female

df_one %>% 
  mutate(Male_2 = Male/10000,
         Female_2 = Female/10000,
         Percent_total = round(Total/sum(Total) *100,1),
         Percent_total = paste0(Percent_total, "%"),
         Percent_male = round(Male/Total *100,2),
         Percent_Female = round(Female/Total *100,2)) -> df_two

#my_colors <- c("#770A1F", "#EC1D27", "#F56F52", "#F9B297")
#my_colors <- c("#014d64", "#01a2d9")


my_font <- "Roboto Condensed"

View(df_two)


df_two %>% 
  mutate(Stage = case_when(df_two$Year <  1980 ~ "Stage 1", 
                           df_two$Year >= 1980 & df_two$Year < 2000 ~ "Stage 2",
                           TRUE ~ "Stage 3")) %>% 
  mutate(Stage = as.character(Stage)) -> Stage_label



#c("#fff5f0", "#fcbba1", "#fc9272", "#fb6a4a")
#("#f15b40", "#eca221", "#00526d", "#b0c6d2")
    

ggplot(df_two) +  
  geom_rect(aes(xmin = 1960, xmax = 1980, ymin =70, ymax= Inf, fill= "Stage 1"), 
            fill= "#fff5f0", alpha = 0.9, show.legend = FALSE)+
  geom_rect(aes(xmin= 1980, xmax= 2000, ymin=70, ymax=Inf, fill= "Stage 2"), 
            fill= "#b0c6d2", alpha = 0.3,show.legend = FALSE)+
  geom_rect(aes(xmin= 2000, xmax= 2014, ymin=70, ymax=Inf, fill= "Stage 3"), 
            fill= "grey90", alpha= 0.5,show.legend = FALSE)+
  geom_line(aes(Year, Male_2), col = "#014d64", size= 1.2)+
  geom_line(aes(Year, Female_2), col = "#770A1F",size= 1.2)+
  annotate("text", x = 1970, y= 101, label = "Stage 1", color = 'Black', size=4.5)+
  annotate("text", x = 1990, y= 101, label = "Stage 2", color = 'Black',  size=4.5)+
  annotate("text", x = 2006, y= 101, label = "Stage 3", color = 'Black',  size=4.5)+
  
  annotate("curve", curvature =0, x = 1964, xend = 2012, 
           y = seq(70,100,10), yend= seq(70,100,10), 
           color ="grey80", size= 0.5)+
  theme_fivethirtyeight()+
  theme(panel.grid = element_blank())+
  theme(legend.key.width = unit(0.9, "cm")) + 
  theme(legend.key.height = unit(0.0, "cm")) +
  annotate("text", x = 2013, y = 78, label= "Male", color = "#014d64")+
  annotate("text", x = 2013, y = 75, label= "Female", color = "#770A1F" )+
  labs(y = "Number of population (in Million)",
       x= "Year", 
       title = "The Number of population from 1970 to 2012", 
       subtitle = "Male Population is over Female population", 
       caption = "Data Source : 공공데이터포털")+
  theme(text = element_text(family = my_font, size = 12, color = "gray30"))+ 
  theme(plot.caption = element_text(size = 10, color = "grey40", family = my_font, 
                                    face = "bold"))+ 
  theme(plot.title = element_text(size= 15, face= "bold"))+
  theme(plot.subtitle = element_text(color = "gray30", size = 10, family = my_font))