Data Exploration: Two years of COVID

A data exploration project of the COVID-19 dataset using tools like SQL and Tableau.

Daniel Querales

Project overview

  • This is a Data Exploration Project of the COVID-19 dataset (from 2020 to 2021).
  • I explore the values of total cases, total deaths & people fully vaccinated.
  • The project was made for educational purpose and his values can be easily compared with Google Coronavirus (COVID-19) dashboard.
  • The tools used are SQL Server and Tableau Public.
  • All the files can be downloaded from my GitHub Repository.

Objectives

The goal is to build a report that shows summarized information about the deaths, cases and vaccinations corresponding to the period of 2020-2021 to understand how the pandemic is currently developing in the world.

Data transformation and data preparation

Importing data

All the data was taken from the Our World in Data COVID-19 dataset. It was obtained as a .csv, imported to a SQL server, then expose to specific queries to extract the information wanted. At last, the results were imported to Tableau Public and represented using a dashboard.

Asking the Questions

a) How many total cases exists? What are the total of deaths?

SELECT MAX(total_cases) AS TotalCases,  MAX(total_deaths) AS TotalDeaths, (MAX(total_deaths)/MAX(total_cases)*100) AS DeathPercentage 
FROM clean_owid_covid;

b) How many people are fully vaccinated?

SELECT MAX(population) AS WorldPopulation, MAX(people_fully_vaccinated) AS PeopleFullyVaccinated, 
    MAX(people_fully_vaccinated)/MAX(population)*100 AS VaccinationPercentage
FROM clean_owid_covid;

c) How many new cases we had per date? 

SELECT date, MAX(new_cases) AS NewCases 
FROM clean_owid_covid 
GROUP BY date 
ORDER BY date;

d) Which are the countries with most deaths? 

SELECT location, MAX(total_deaths) AS TotalDeaths FROM clean_owid_covid
WHERE continent IS NOT NULL
GROUP BY location
ORDER BY TotalDeaths DESC
LIMIT 5;

e) How fast the vaccination goes? 

SELECT location, MAX(people_fully_vaccinated) AS PeopleFullyVaccinated,
    MAX(people_fully_vaccinated)/MAX(population)*100 AS PercentagePeopleFullyVaccinated
FROM clean_owid_covid
WHERE continent IS NOT NULL
GROUP BY location
ORDER BY PeopleFullyVaccinated DESC;

Results

Conclusions

  • Only 1.8% percent of the total cases resulted in deaths.
  • By the start of 2022, half of the world population are fully vaccinated.
  • US is the country with the most deaths with 824K.
  • At the end of 2021, we had a spike in new cases to 1.9 M in a single day.
  • China has the most population fully vaccinated, with 83.6%.