Tidy Data: Why We Should Invest On It and How to Do it

import.r

library(readr)
confirmed <- read_csv("https://raw.githubusercontent.com/CSSEGISandData/COVID-19/master/csse_covid_19_data/csse_covid_19_time_series/time_series_covid19_confirmed_global.csv")
head(confirmed)

plot.r

x <- as.Date(colnames(confirmed)[5:length(colnames(confirmed))], format="%m/%d/%y")
y <- confirmed[confirmed$`Country/Region` == "Indonesia", 5:length(colnames(confirmed))]
plot(x, y)

plot_tidy.r

library(dplyr)
library(ggplot2)
asean <- c("Indonesia", "Singapore", "Vietnam", "Malaysia", "Thailand")
confirmed_tidy %>%
  filter(country %in% asean) %>%
  ggplot(aes(x=date, y=total, color=country)) +
  geom_line(size=1.5) +
  ggtitle("COVID-19 Cases", subtitle = "Indonesia, Malaysia, Singapore, Thailand, Vietnam")

tidy.r

library(tidyr)
confirmed_tidy <- confirmed %>%
  pivot_longer(5:(length(colnames(confirmed))), names_to = "date", values_to = "total")
colnames(confirmed_tidy) <- c("province", "country", "lat", "long", "date", "total")
confirmed_tidy$date <- as.Date(confirmed_tidy$date, format="%m/%d/%y")
confirmed_tidy