🧪 Objective

Analyze global COVID-19 cases and deaths using real-world data from Our World in Data.

📦 Load Required Packages

library(readr)
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(tidyr)
## Warning: package 'tidyr' was built under R version 4.3.3
library(lubridate)
## Warning: package 'lubridate' was built under R version 4.3.3
## 
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

📂 Load the Data

covid <- read_csv("D:/R Programming/data/owid-covid-data.csv")
## Rows: 429435 Columns: 67
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr   (4): iso_code, continent, location, tests_units
## dbl  (62): total_cases, new_cases, new_cases_smoothed, total_deaths, new_dea...
## date  (1): date
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

This dataset has over 429,000 rows and 67 columns, including cases, deaths, dates, locations, and more.

🔍 Select and Clean Relevant Columns

covid_clean <- covid %>%
  select(location, continent, date, total_cases, total_deaths) %>%
  filter(!is.na(continent), !is.na(total_cases))

📅 Find the Most Recent Date

latest_date <- max(covid_clean$date)
latest_date
## [1] "2024-08-04"

📊 Summarise Cases and Deaths by Continent (Latest Date)

covid_latest <- covid_clean %>%
  filter(date == latest_date) %>%
  group_by(continent) %>%
  summarise(
    total_cases = sum(total_cases, na.rm = TRUE),
    total_deaths = sum(total_deaths, na.rm = TRUE)
  )
covid_latest
## # A tibble: 6 × 3
##   continent     total_cases total_deaths
##   <chr>               <dbl>        <dbl>
## 1 Africa           13145380       259117
## 2 Asia            301499099      1637249
## 3 Europe          252916868      2102483
## 4 North America   124492666      1671178
## 5 Oceania          15003352        32918
## 6 South America    68809418      1354187

🔁 Reshape Data to Long Format (Tidy)

covid_tidy <- covid_latest %>%
  pivot_longer(cols = c(total_cases, total_deaths),
               names_to = "metric",
               values_to = "count")
covid_tidy
## # A tibble: 12 × 3
##    continent     metric           count
##    <chr>         <chr>            <dbl>
##  1 Africa        total_cases   13145380
##  2 Africa        total_deaths    259117
##  3 Asia          total_cases  301499099
##  4 Asia          total_deaths   1637249
##  5 Europe        total_cases  252916868
##  6 Europe        total_deaths   2102483
##  7 North America total_cases  124492666
##  8 North America total_deaths   1671178
##  9 Oceania       total_cases   15003352
## 10 Oceania       total_deaths     32918
## 11 South America total_cases   68809418
## 12 South America total_deaths   1354187

✏️ Questions Answered

1. Which continent had the most total cases?

Asia

2. What’s the total number of deaths globally?

sum(covid_latest$total_deaths, na.rm = TRUE)
## [1] 7057132

3. Why reshape to long format?

Long format is preferred for plotting grouped metrics and works better with ggplot2, facet_wrap, and tidyverse tools.