This is my first project in Exploratory Data Analysis (EDA), where I analyze real-world traffic accident data to uncover trends, patterns, and insights that can potentially inform better road safety and urban planning decisions.

To perform a detailed EDA on traffic accident data to understand:

• Common causes and types of accidents
• Temporal patterns (days, months, hours)
• Geographic hotspots of accidents
• Influence of weather, lighting, and road conditions
• Vehicle types and casualty distributions

• Python 🐍
• Pandas – data manipulation
• NumPy – numerical computations
• Matplotlib & Seaborn – data visualization
• Jupyter Notebook – interactive analysis

The dataset used includes multiple features related to traffic accidents such as:

• Date and time
• Weather conditions
• Road type
• Number of casualties
• Vehicle types involved
• Injury occured and corresponding cause.

🗂️ Dataset Source: A kaggle Dataset.

• 🚦 Accidents are more frequent during peak hours and weekends.
• 🌧️ Weather conditions such as rain or fog significantly increase risk.
• 🛣️ Certain road types (like intersections) have a higher accident density.
• 🚗 Two-wheelers and four-wheelers are most commonly involved.

• Apply predictive models to forecast accident probabilities
• Cluster accident-prone zones geographically
• Integrate external datasets (e.g., population density, traffic volume)

Thanks to "Yury Kashnitsky" for his very well curated notebook.

This project is licensed under the MIT License.

• GitHub: @Yeeyash
• LinkedIn: Yash Ghansham Thakare