Road Accidents Analysis (2022)

This project analyzes road accident data for the year 2022. It examines various aspects of road accidents, including casualty distribution, severity, vehicle types involved, and geographic patterns. The analysis provides insights into factors contributing to road accidents and helps in understanding trends for better road safety measures.

Dataset

The dataset used for this analysis consists of road accident statistics for the year 2022. It includes information such as casualty class, severity, vehicle types, pedestrian movement, and geographic locations.

Analysis

The code analyzes different aspects of road accidents using Python and various libraries such as Pandas, Matplotlib, Seaborn, and Folium. Here's a summary of the analyses performed:

1. Passenger Distribution Analysis: Analyzes the proportion of casualties who were passengers in cars or buses/coaches.

2. Home Area Distribution Analysis: Examines the distribution of casualties based on home area types.

3. Vehicle Type Distribution Analysis: Explores the distribution of casualties by the type of vehicles involved in accidents.

4. IMD Decile and Casualty Severity Analysis: Investigates the distribution of casualty severity across different IMD deciles.

5. Pedestrian Location and Movement Analysis: Analyzes the distribution of pedestrian location and movement during accidents.

6. LOSA Analysis: Analyzes the distribution of casualties across different Lower Layer Super Output Areas (LOSA) by casualty class.

Machine Learning Predictive Model

In addition to descriptive analysis, this project also includes the development of machine learning predictive models to forecast casualty severity based on various features. The following algorithms are used for model building:

• Principal Component Analysis (PCA)
• Random Forest
• Logistic Regression
• Support Vector Machine (SVM)

The predictive models aim to provide insights into the factors contributing to casualty severity and assist in implementing targeted interventions for accident prevention.

How to Use

1. Clone the repository: git clone https://github.com/Arshiagosh/Road-Accidents-2022.git
2. Install the required dependencies: pip install -r requirements.txt
3. Run the Jupyter notebook road_accidents_analysis.ipynb to view the code and perform the analysis.

Author

• Arshia Goshtasbi
• GitHub: @Arshiagosh

Feel free to explore the code and analysis, and any contributions or feedback are welcome!