COVID-19 Data Analysis Final Year Project with Source Code

Project Features in this Final Year Project

• COVID-19 dataset loading from local CSV
• Province/state-level data processing
• Country-day aggregation
• Country-level latest snapshot creation
• Global daily series generation
• Exploratory data analysis
• Statistical summary printing
• Missing-value rate analysis
• WHO region distribution analysis
• Country-wise confirmed case ranking
• COVID-19 deaths analysis
• Recovered vs deaths comparison
• Global daily new confirmed case trend
• 7-day rolling average calculation
• Cumulative confirmed case trend analysis
• Data visualization using Matplotlib and Seaborn
• 12 PNG chart exports
• Machine learning regression model training
• Linear Regression model
• Random Forest Regression model
• Holdout train-test split
• R² score evaluation
• MAE evaluation
• RMSE evaluation
• Random Forest feature importance listing
• Jupyter Notebook support
• Standalone Python script support
• Inline notebook chart display
• Exported figures folder support

Data Analytics / EDA Features in this Final Year Project

• Raw dataset row count
• Country-day aggregate row count
• Date range identification
• Number of distinct countries/regions
• Column data type inspection
• Sample row display
• Numeric summary statistics
• Missing-value analysis
• WHO region distribution
• Top countries by confirmed cases
• Province/state level to country-day aggregation
• Latest country snapshot generation
• Global daily total calculation
• Daily new confirmed case calculation
• Rolling mean calculation
• Country-level cross-sectional analytics

Visualization Features in this Final Year Project

The project generates 12 chart images in the figures/ folder:

1. Top 15 countries by confirmed cases
2. Top 12 countries by total deaths
3. Pie chart of confirmed case share among top 8 countries
4. Scatter plot of confirmed cases vs deaths
5. Hexbin density chart of confirmed cases vs deaths
6. Histogram of log-transformed confirmed case distribution
7. Box plot of deaths by WHO region
8. Violin plot of confirmed cases by WHO region
9. Correlation heatmap of numeric latest snapshot columns
10. Global daily new confirmed cases with 7-day rolling mean
11. Cumulative confirmed cases for selected large countries
12. Grouped bar chart of recovered vs deaths for top 10 countries by confirmed cases

Machine Learning Features in this Final Year Project

• Predicts reported COVID-19 deaths
• Uses latest country-level snapshot
• Uses only rows where confirmed cases are greater than zero
• Input features:
  • Confirmed cases
  • Latitude
  • Longitude
  • WHO region
• Linear Regression model
• Random Forest Regression model
• One-hot encoding for WHO region
• Scaled numeric features for Linear Regression
• Numeric passthrough for Random Forest pipeline
• 75% training and 25% testing split
• R² score calculation
• Mean Absolute Error calculation
• Root Mean Squared Error calculation
• Random Forest feature importance output
• Avoids using Recovered and Active as input features to prevent artificially perfect correlations

Dataset Details in this Final Year Project

Dataset file:
data/data.csv

Date range:
2020-01-22 to 2020-07-27

Important columns:

• Province/State
• Country/Region
• Lat
• Long
• Date
• Confirmed
• Deaths
• Recovered
• Active
• WHO Region

Used column names after processing:

• Province_State
• Country_Region
• WHO_Region

Files / Modules Included in this Final Year Project

• covid19_data_analysis_project.py — main script for EDA, visualization, and ML
• covid_project_loader.py — notebook bootstrap loader
• covid19_analysis.ipynb — Jupyter Notebook workflow
• requirements.txt — Python dependency list
• README.md — project documentation
• data/data.csv — required COVID-19 dataset
• figures/ — generated PNG chart output folder

Output Files

The project exports chart images into:

figures/

Generated figures include:

• Top countries by confirmed cases
• Top countries by deaths
• Confirmed case share pie chart
• Confirmed vs deaths scatter plot
• Confirmed vs deaths hexbin plot
• Confirmed case histogram
• WHO region deaths box plot
• WHO region confirmed cases violin plot
• Correlation heatmap
• Global daily new confirmed trend chart
• Cumulative confirmed cases chart
• Recovered vs deaths grouped bar chart

Option 1: Run as command-line script

1. Open project folder:

   cd "Covid 19 data analysis"

2. Create virtual environment:

   python -m venv .venv

3. Activate virtual environment on Windows:

   .\.venv\Scripts\Activate.ps1

4. Activate virtual environment on macOS/Linux:

   source .venv/bin/activate

5. Install dependencies:

   pip install -r requirements.txt

6. Ensure dataset exists:

   data/data.csv

7. Run the analysis:

   python covid19_data_analysis_project.py

8. Check generated charts:

   figures/

Option 2: Run in Jupyter Notebook

1. Complete virtual environment and dependency installation.

2. Register environment as Jupyter kernel:

   python -m ipykernel install --user --name=covid19-analysis --display-name="Python (covid19-analysis)"

3. Start Jupyter Notebook:

   jupyter notebook

4. Open:

   covid19_analysis.ipynb

5. Select the project kernel.
6. Run all cells from top to bottom.
7. View EDA, charts, and ML results inline.

This project has no login credentials because it is not a web application.

Credential note:
No admin panel, user login, password, or database authentication is included. The project runs locally as a Python data analysis script or Jupyter Notebook.