Plotting coronavirus cases in R

Introduction

We want to show the evolution of the coronavirus cases using R creating static and interactive plots.

Plots

Interactive (linear scale)

Interactive (log scale)

Solution

We use the data repository created by Johns Hopkins University Center for Systems Science and Engineering (JHU CSSE). There are three time-series: confirmed, deaths and recovered cases. First we will prepare the data and then plot the time-series using ggplot2 for the static version and plotly to add interactivity. The data source includes cases across the world, but in our example we will subset the time-series for Germany, France, Italy, Spain, and the United Kingdom.

# Libraries
library(magrittr)
library(lubridate) 
library(tidyverse)
library(plotly)
library(scales)

# Importing data
confirmed <- read_csv("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Confirmed.csv")
deaths <- read_csv("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Deaths.csv")
recovered <- read_csv("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_19-covid-Recovered.csv")

# Data preparation
AppendMe <- function(dfNames) {
  do.call(rbind, lapply(dfNames, function(x) {
    cbind(get(x), source = x)
  }))
}
df <- AppendMe(c("confirmed", "deaths", "recovered"))
data <- df %>%
  rename(province = `Province/State`, country = `Country/Region`) %>% 
  pivot_longer(
    -c(province, country, Lat, Long, source),
    names_to = "date",
    values_to = "count"
  ) %>% 
mutate(date = mdy(date)) 

# Plot linear scale
p <- data %>%
  filter(country %in% c("Germany", "France", "Italy",  "Spain", "United Kingdom")) %>% 
  group_by(country, date, source) %>%
  summarise(n = sum(count)) %>%
  ggplot(aes(date, n, colour = country)) +
  geom_line(linetype = 2) +
  geom_point(size = 1) +
  facet_wrap( ~  source  , scales = "free", nrow = 3) +
  theme_bw()+
  labs(title = "Cumulative Covid-19 cases (linear scale)")+
  ylab("")+
  scale_x_date(date_labels = "%b %d")+
  scale_y_continuous(labels = comma)
p # Static
ggplotly(p) # Interactive

# Plot log scale
p <- data %>%
  filter(country %in% c("Germany", "France", "Italy",  "Spain", "United Kingdom")) %>% 
  group_by(country, date, source) %>%
  summarise(n = sum(count)) %>%
  ggplot(aes(date, n, colour = country)) +
  geom_line(linetype = 2) +
  geom_point(size = 1) +
  facet_wrap( ~  source, scales = "free",  nrow = 3) +
  theme_bw()+
  labs(title = "Cumulative Covid-19 cases (log scale)")+
  ylab("")+
  scale_x_date(date_labels = "%b %d")+
  scale_y_log10(breaks = c(1, 10, 100, 10000))
  p 
ggplotly(p) 

To highlight a series while hovering over it, we use the function highlightfrom the plotly package.

p <- data %>%
  filter(country %in% c("Germany", "France", "Italy",  "Spain", "United Kingdom")) %>% 
  group_by(country, date, source) %>%
  summarise(cases = sum(count)) %>%
  highlight_key(~ country ) %>% 
  ggplot(aes(date, cases, colour = country)) +
  geom_line(linetype = 2)+
  geom_point(size = 1) +
  facet_wrap(~  source  , scales = "free", nrow = 3)+
  theme_bw()+
  labs(title = "Cumulative Covid-19 cases (linear scale)")+
  ylab("")+
  scale_x_date(date_labels = "%b %d")+
  scale_y_continuous(labels = comma)
ggplotly(p, tooltip = c("country", "date", "cases")) %>% 
highlight(on = "plotly_hover")

Plot here. Screenshot below.

References

• csse_covid_19_time_series
• Novel Coronavirus (COVID-19) Cases Data
• Covid-19 Shiny Dashboard