An analysis of UK road accident statistics from the RAS91 dataset covering 2015-2024.
It analyzes UK road accident statistics from the RAS91 dataset covering 2015-2024. It provides:
- Analysis of road casualties by various demographics
- Trends and patterns in road accidents over time
- Breakdown by road user type, severity, age, sex, and geographical regions
- Statistical insights and visualizations of accident data
- Automated extraction from RAS91 ODS files to CSV format
- Multiple datasets: Numbers, Age/Sex, Severity, Monthly, Local Authority, and Regional data
- Data cleaning and preprocessing for analysis
- Structured data organization for easy access
- Year-over-year trend analysis (2015-2024)
- Demographic breakdown by age groups and sex
- Severity classification (Killed, KSI, All casualties)
- Road user type analysis (Pedestrians, Cyclists, Motorists, etc.)
- Geographical analysis by local authorities and regions
- Time series plots of accident trends
- Demographic distribution charts
- Severity comparison visualizations
- Geographical heat maps and regional comparisons
- Interactive plots using Matplotlib and Seaborn
- Numbers: 32 rows, 12 columns - Overall casualty statistics
- Age/Sex: 384 rows, 14 columns - Demographic breakdown
- Local Authority: 852 rows, 14 columns - Geographical analysis
- Monthly: 440 rows, 15 columns - Temporal trends
- Severity: 176 rows, 13 columns - Accident severity classification
- Regional: 48 rows, 13 columns - Regional comparisons
Use the package manager pip to install required libraries:
# Prerequisites
python3 -m venv .venv
source .venv/bin/activate
pip install pandas numpy matplotlib seaborn scikit-learn openpyxl odfpy jupyter
It requires the RAS91 ODS file from the UK Department for Transport to run the analysis.
- File:
ras91.ods
(placed in the data/ folder) - Source: Reported road casualties Great Britain, provisional results: 2024
- The script automatically extracts and processes the data into CSV format
Click the Run
button to run the individual cell of the Jupyter Notebook.
This project is licensed under the Modified MIT License.
(c) 2025 Finbarrs Oketunji. All Rights Reserved.