General View about the COVID pandemic till 31 July 2020

R for Data Visualization

Coronavirus Dataset

Coronavirus Dataset is provided by RamiKrispin, updated till 31 July 2020

library(coronavirus)
#update_dataset()
#covid19_df <- refresh_coronavirus_jhu()
#head(covid19_df)
#glimpse(covid19_df)
data("coronavirus")
head(coronavirus)

##         date province     country      lat     long      type cases
## 1 2020-01-22          Afghanistan 33.93911 67.70995 confirmed     0
## 2 2020-01-23          Afghanistan 33.93911 67.70995 confirmed     0
## 3 2020-01-24          Afghanistan 33.93911 67.70995 confirmed     0
## 4 2020-01-25          Afghanistan 33.93911 67.70995 confirmed     0
## 5 2020-01-26          Afghanistan 33.93911 67.70995 confirmed     0
## 6 2020-01-27          Afghanistan 33.93911 67.70995 confirmed     0

Top 20 country

Summary of the total confrimed cases by country (top 20):

library(dplyr)
summary_df <- coronavirus %>% 
  filter(type == "confirmed") %>%
  group_by(country) %>%
  summarise(total_cases = sum(cases)) %>%
  arrange(-total_cases)

Update new cases

Summary of new cases during the past 24 hours by country and type (as of 2020-07-31):

library(tidyr)

coronavirus %>% 
  filter(date == max(date)) %>%
  select(country, type, cases) %>%
  group_by(country, type) %>%
  summarise(total_cases = sum(cases)) %>%
  pivot_wider(names_from = type,
              values_from = total_cases) %>%
  arrange(-confirmed)

## # A tibble: 188 x 4
## # Groups:   country [188]
##    country      confirmed death recovered
##    <chr>            <int> <int>     <int>
##  1 US               67023  1259     24005
##  2 India            61242   793     39026
##  3 Brazil           52383  1212     52047
##  4 South Africa     11014   193     16570
##  5 Colombia          9488   295      5692
##  6 Mexico            8458   688      7015
##  7 Peru              6809   205         0
##  8 Argentina         5929   102      3184
##  9 Russia            5468   161      8735
## 10 Iraq              3346    70      1888
## # ... with 178 more rows

Total cases

Plotting the total cases by type worldwide:

library(plotly)

coronavirus %>% 
  group_by(type, date) %>%
  summarise(total_cases = sum(cases)) %>%
  pivot_wider(names_from = type, values_from = total_cases) %>%
  arrange(date) %>%
  mutate(active = confirmed - death - recovered) %>%
  mutate(active_total = cumsum(active),
                recovered_total = cumsum(recovered),
                death_total = cumsum(death)) %>%
  plot_ly(x = ~ date,
                  y = ~ active_total,
                  name = 'Active', 
                  fillcolor = '#1f77b4',
                  type = 'scatter',
                  mode = 'none', 
                  stackgroup = 'one') %>%
  add_trace(y = ~ death_total, 
             name = "Death",
             fillcolor = '#E41317') %>%
  add_trace(y = ~recovered_total, 
            name = 'Recovered', 
            fillcolor = 'forestgreen') %>%
  layout(title = "Distribution of Covid19 Cases Worldwide",
         legend = list(x = 0.1, y = 0.9),
         yaxis = list(title = "Number of Cases"),
         xaxis = list(title = "Source: Johns Hopkins University Center for Systems Science and Engineering"))

## The treemap {.tabset}

Plot the confirmed cases distribution by country with treemap plot:

conf_df <- coronavirus %>% 
  filter(type == "confirmed") %>%
  group_by(country) %>%
  summarise(total_cases = sum(cases)) %>%
  arrange(-total_cases) %>%
  mutate(parents = "Confirmed") %>%
  ungroup() 
  
  plot_ly(data = conf_df,
          type= "treemap",
          values = ~total_cases,
          labels= ~ country,
          parents=  ~parents,
          domain = list(column=0),
          name = "Confirmed",
          textinfo="label+value+percent parent")