Data Collection and Cleaning

link <- "https://en.wikipedia.org/wiki/2020_coronavirus_pandemic_in_South_Korea"

link %>% 
  read_html() %>% 
  html_nodes(xpath = '//*[@id="mw-content-text"]/div/table[4]') %>% 
  html_table() %>% 
  .[[1]] -> df_corona

names(df_corona) <-names(df_corona) %>% str_replace_all(" ","")

## Converting data 

df_corona %>% 
  mutate(Date= dmy(Date)) ->df_corona


df_corona %>%  
  group_by(Date) %>% 
  count() %>% 
  ungroup() %>% 
  mutate(Total = cumsum(n)) ->byDate

Corona Map of South Korea

# Specific Date 

Gyeonggi_do <- c("Asan", "Bucheon", "Goyang", "Guri", "Incheon", "Pyeongtaek", "Siheung","Suwon")
Jeollabuk_do <- c("Gunsan")
Jeollanam_do <- c("Gwangju","Naju")
Seoul <- c("Seoul")

df_corona %>% 
  group_by(Placeofstay) %>% 
  count() %>% 
  mutate(Province =Placeofstay) %>% 
  mutate(Province = case_when(Province %in% Gyeonggi_do ~ "16",
                              Province %in% Jeollabuk_do ~ "5",
                              Province %in% Jeollanam_do ~ "6",
                              Province %in% Seoul ~ "8",
                              TRUE ~ "0")) -> coronaNow



library(raster)
Korea <- getData("GADM", country = "KOR", level = 1)



# 위치 정보 가공 
Korea_df <- Korea %>% 
  fortify(Province = "NAME_1") %>% 
  mutate(Province = stri_trans_general(id, "Latin-ASCII"))

# 데이터 병함 
bb <- full_join(coronaNow, Korea_df, by="Province" )



my_font <- "Ubuntu Condensed"

ggplot()+
  geom_polygon(data=bb, aes(long, lat, group=group, fill=n), color="grey20")+
  scale_fill_viridis()+
  theme(panel.grid = element_blank()) + 
  theme(axis.title = element_blank()) + 
  theme(axis.text = element_blank()) +
  labs(x = NULL, y = NULL, 
       title = "Corona Virus in South Korea(Feb - Mar, 2020)", 
       caption = "Data Source: Wikipeia") + 
  theme(plot.title = element_text(size = 15, family = my_font, color = "gray20", face="bold")) +  
  theme(plot.caption = element_text(family = my_font, size = 10, colour = "grey30", face = "italic")) + 
  theme(legend.text = element_text(size = 10, color = "grey10", family = my_font)) + 
  theme_gray() -> g1

g1

Corona EDA of South Korea

df_corona %>% 
  group_by(`VisitedWuhan?`) %>% 
  rename(Wuhan = `VisitedWuhan?`) %>% 
  count() %>% 
  ungroup() -> from_wuhan

kable(from_wuhan)

from_wuhan %>% 
  ggplot(aes(Wuhan, n))+
  geom_bar(stat= "identity",fill="#F89441FF", col="black")+
  theme_economist()+
  labs(x = NULL, y = "Answers", 
       title = "Have you been to Wuhan?")+
  theme(plot.title = element_text(size = 12, family = my_font, color = "gray20", face="bold")) ->g2

g2

df_corona %>% 
  group_by(Nationality) %>% 
  count() %>% 
  ungroup() -> national

kable(national)

national %>% 
  ggplot(aes(Nationality , n))+
  geom_bar(stat= "identity",fill="#F89441FF", col="black")+
  theme_economist()+
  labs(x = NULL, y = "Answers", 
       title = "What is your Nationality?")+
  theme(plot.title = element_text(size = 12, family = my_font, color = "gray20", face="bold")) ->g3

g3

Question_1) All chinese are from Wuhan?

df_corona %>% 
  group_by(Nationality,`VisitedWuhan?` ) %>% 
  rename(Wuhan = `VisitedWuhan?`) %>% 
  summarise(count=n()) %>% 
  mutate(pct =count/sum(count),
         lbl = scales :: percent(pct)) -> china_wuhan

kable(china_wuhan)

ggplot(china_wuhan, aes(x=Nationality, y= pct, fill=Wuhan))+
  geom_bar(stat = "identity", position = "fill", col="black")+
  geom_text(aes(label=lbl),
            size = 3,position = position_stack(vjust = 0.5))+
  scale_fill_manual(values=c("#999999", "#E69F00"))+
  theme_economist()+
  labs(x = NULL, y = "Percent", 
       title = "Rate of Wuhan Visitor by Nationality?")+
  theme(plot.title = element_text(size = 12, family = my_font, color = "gray20", face="bold")) -> g4


g4

df_corona %>% 
  group_by(Gender, Placeofstay) %>% 
  summarise(count=n()) %>% 
  mutate(pct =count/sum(count),
         lbl = scales :: percent(pct)) -> gender_stay

kable(gender_stay)

ggplot(gender_stay, aes(reorder(Placeofstay, pct) , y=pct, fill=Gender))+
  geom_col(col="black")+
  coord_flip()+
  theme_economist()+
  scale_fill_manual(values=c("#999999", "#E69F00"))+
   labs(x = "Percent", y = "Province", 
       title = "Provinces town rate by gender", 
       subtitle = "Data from Feb to Mar in 2020", 
       caption = "Data Source: Wikipeida") + 
  theme(plot.title = element_text(family = my_font, size = 15, colour = "grey10")) + 
  theme(plot.subtitle = element_text(family = my_font, size = 10, colour = "grey20")) + 
  theme(plot.caption = element_text(family = my_font, size = 10, colour = "grey30", face = "italic")) + 
  theme(legend.text = element_text(size = 10, color = "grey10", family = my_font))  -> g5

g5

df_corona %>% 
  group_by(Date) %>% 
  count() %>% 
  ungroup() %>% 
  mutate(Total = cumsum(n)) -> plot
  
  
highchart() %>% 
  hc_add_series(data = plot$Total,name= "The Number of Confirmed Cases", 
                showInLegend= FALSE, type="line") %>%   
  hc_yAxis(gridLineWidth = 0.6)%>% 
    hc_xAxis(categories = plot$Date) %>% 
  hc_title(text = "Accumulative Coronavirus Cases Confirmed", style = list(color = "grey20", useHTML = TRUE)) %>% 
  hc_chart(backgroundColor = "White")

df_corona %>% 
  group_by(Date) %>% 
  mutate(encount = sum(Contactsofcase)) %>% 
  filter(!duplicated(Date)) %>% 
  na.omit() ->Encounter_bydate

Encounter_bydate$Date <- as.factor(Encounter_bydate$Date)
  

highchart() %>% 
  hc_add_series(Encounter_bydate, hcaes(x= Date, y=encount), type="line") %>% 
  hc_tooltip(borderWidth = 1.5, 
             pointFormat = paste("Encounters: <b>{point.y}</b>")) %>% 
  hc_xAxis(categories = Encounter_bydate$Date, 
             labels = list(step = 1),
             min = 0, max = 12,
             scrollbar = list(enabled = TRUE)) %>% 
  hc_title(text = "The Encounter number by dates") %>% 
  hc_subtitle(text = "Jan to Feb in 2020") %>% 
  hc_yAxis(title = list(text = "Numbers")) 

View(df_corona)

df_corona %>% 
  group_by(Date, Gender) %>% 
  count() %>% 
  ungroup() -> bygender

datatable(bygender)

bygender$Date <- as.factor(bygender$Date)


sex_color <- c("#EE6AA7", "#87CEEB")

highchart() %>% 
  hc_add_series(bygender, hcaes(x= Date, y=n, group=Gender), type="line",
                color=sex_color) %>% 
  hc_tooltip(crosshairs = TRUE, borderWidth = 1.5, headerFormat = "",
              pointFormat = paste("Year: <b>{point.Date}</b> <br>",
                                  "Gender: <b>{point.Gender}</b><br>",
                                  "Cases: <b>{point.n}</b>")) %>% 
  hc_xAxis(categories = bygender$Date) %>% 
  hc_title(text = "Corona confirmed cases by Gender") %>% 
    hc_subtitle(text = "Jan to Feb in 2020") %>%
    hc_xAxis(title = list(text = "Date")) %>%
    hc_yAxis(title = list(text = "The number of cases"),
             allowDecimals = FALSE,
             plotLines = list(list(color = "black", width = 1, dashStyle = "Dash", 
                    value = mean(bygender$n)))) 

#summary(df_corona$Age)
#Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
#   20.0    33.5    42.5    45.0    55.0    82.0 

df_corona$Age_group <- ifelse(df_corona$Age >= 20 & df_corona$Age <= 40, 'Young Aged',
                              ifelse(df_corona$Age >= 40 & df_corona$Age <= 60, "Middle Aged",
                                     ifelse(df_corona$Age >= 60 & df_corona$Age <= 70, "Old Aged", "Very Old")))

df_corona %>% 
  group_by(Date, Age_group) %>% 
  count() %>% 
  ungroup() -> by_age

by_age

## # A tibble: 23 x 3
##    Date       Age_group       n
##    <date>     <chr>       <int>
##  1 2020-01-20 Young Aged      1
##  2 2020-01-24 Middle Aged     1
##  3 2020-01-26 Middle Aged     1
##  4 2020-01-27 Middle Aged     1
##  5 2020-01-30 Middle Aged     1
##  6 2020-01-30 Young Aged      2
##  7 2020-01-31 Middle Aged     1
##  8 2020-01-31 Old Aged        1
##  9 2020-01-31 Young Aged      2
## 10 2020-02-01 Middle Aged     1
## # ... with 13 more rows

by_age$Date <- as.factor(by_age$Date)
by_age$Age_group <- as.factor(by_age$Age_group)

age_color <- rev(plasma(4)) 

highchart() %>% 
  hc_add_series(by_age, hcaes(x= Date, y=n, group=Age_group), type="line", color=age_color) %>%  
  hc_tooltip(crosshairs = TRUE, borderWidth = 1.5, 
              pointFormat = paste("Date: <b>{point.x: %Y-%m-%d}</b> <br>",
                                  "Gender: <b>{point.Age_group}</b><br>",
                                  "Cases: <b>{point.y}</b>")) %>% 
  hc_title(text="Corona confirmed cases by Age Groups") %>% 
  hc_subtitle(text = "Jan to Feb in 2020") %>%
  hc_xAxis(title = list(text = "Date")) %>%
  hc_yAxis(title = list(text = "The number of cases")) %>% 
  hc_xAxis(categories = c("2020-01-20", "2020-01-24",
                          "2020-01-26", "2020-01-27",
                          "2020-01-30", "2020-01-31",
                          "2020-02-01", "2020-02-02",
                          "2020-02-04", "2020-02-06",
                          "2020-02-09", "2020-02-10",
                          "2020-02-16"))

지역/ 연령별 마주친 사람들 count

df_corona %>% 
  group_by(Placeofstay,Contactsofcase ,Age_group) %>%
  filter(!duplicated(Placeofstay)) %>% 
  mutate(total = sum(Contactsofcase)) %>% 
  ungroup() %>% 
  na.omit()-> national_contact

datatable(national_contact)

highchart() %>% 
  hc_add_series(national_contact, hcaes(x=factor(Placeofstay), y=total,
                                        color=Age_group),type="bar", showInLegend = TRUE) %>% 
  hc_tooltip(borderWidth = 1.5, 
             pointFormat = paste("Total Encounter: <b>{point.y}</b>",
                                  "Age_Group: <b>{point.Age_group}</b><br>",
                                  "Encounters: <b>{point.y}</b>")) %>% 
  hc_plotOptions(column = list(stacking = "normal", borderWidth = 0.5)) %>% 
  hc_xAxis(categories = national_contact$Placeofstay, 
             labels = list(step = 1),
             min = 0, max = 11,
             scrollbar = list(enabled = TRUE)) %>% 
  hc_title(text = "The Encounter number by region and age_groups") %>% 
  hc_subtitle(text = "Jan to Feb in 2020") %>% 
  hc_yAxis(title = list(text = "Numbers"))