LA1 - COVID-19 Data Visualization Presentation

Data Visualization | 22ISA465 | Semester 4

Stephen George & Battini Jeevan Kumar

USN

1NT24IS227 & 1NT24IS057

Introduction

Dataset: Our World in Data — COVID-19

  • 262 countries | Jan 2020 to Dec 2025
  • Key columns: new_cases_smoothed, new_deaths_smoothed, total_cases, total_deaths

Four Visualizations:

  1. Line plot — cases & deaths over time (India)
  2. Faceted plots — multi-country comparison
  3. Scatter plot — cases vs deaths
  4. Area plot — cumulative cases

Load and Prepare Data

  • Dataset loaded from CSV file
  • Missing values removed
  • Required columns selected
  • Countries filtered for analysis

Visualization 1: Line Plot — India

Cases and deaths over time using 7-day smoothed values

Insight: Line Plot

  • Wave 1 (2020): Small increase
  • Wave 2 (Apr–May 2021): Highest spike
  • Wave 3 (Jan 2022): High cases, fewer deaths
  • Deaths occur after cases

Visualization 2: Faceted Plots

One panel per country using facet_wrap()

Insight: Faceted Plots

  • USA: highest cases
  • Brazil: long wave
  • India: Sharp spike
  • UK & Germany: Omicron Wave
  • South Africa: Short early waves — Omicron origin

Visualization 3: Scatter Plot

Total cases vs total deaths — log scale, colored by continent

Insight: Scatter Plot

  • Strong positive correlation between cases and deaths
  • Countries above the line: higher case fatality rate
  • Countries below the line: better healthcare outcomes
  • African countries cluster low — likely under-reporting

Visualization 4: Area Plot

Cumulative cases stacked across 6 countries

Insight: Area Plot

  • USA and India dominate cumulative case counts
  • Growth is step-like — surges during waves, flat between them
  • Most burden accumulated during Delta and Omicron waves
  • Post-2022 plateau = end of mass testing, not end of pandemic

Summary

Visualization Key Finding
Line plot (India) 3 waves; Delta deadliest; deaths lag cases
Faceted plots Each country had a unique trajectory
Scatter plot Strong case-death correlation; outliers matter
Area plot Burden concentrated in USA & India

Conclusion

  • COVID-19 impact was impact was different across countries across countries
  • Visualizations reveal patterns invisible in raw tables
  • Delta = highest mortality | Omicron = high cases, lower CFR
  • Vaccination and healthcare capacity explain cross-country scatter

References