An individual project for the Machine Learning and Parallel Computing module. It focuses on concepts in machine learning, machine learning models and algorithms, hyperparameter tuning, and introduction to parallel computing through Python.

Data is by Sobhan Moosavi on Kaggle. Please download the dataset first and place it in the root folder.

Abstract

This study aims to create an accurate and effective prediction model for predicting severity in road traffic accidents. The severity is categorized based on the length of traffic is closed, and has a value range from 1 to 4. The study will also conduct experiments to find the most suitable model and sampling techniques required. Random forest that has its parameters tuned with an equal distributed target variable is found to be the best, with an accuracy of 65.9%.

Project Pipeline

To Run

1. Clone the repository.

git clone https://github.com/your-username/your-repo.git
cd your-repo

2. Download the dataset and place it in the root folder. The dataset file name must be US_Accidents_March23.csv.

3. Set up a virtual environment

python -m venv venv
# Activate the virtual environment
# On Windows:
venv\Scripts\activate
# On macOS/Linux:
source venv/bin/activate

4. Install dependencies

pip install -r requirements.txt

5. Open Jupyter Notebook on a supported application.

6. Run the file using the virtual environment.