Student Performance Analysis: End-to-End ML with AWS & Azure Deployment

This project builds and deploys a machine learning model to predict student performance in math, reading, and writing using demographic and educational factors. It showcases an end-to-end machine learning pipeline, including data preprocessing, model training, and deployment on both AWS and Azure cloud platforms.

Project Goals

• Develop predictive models for student scores.
• Explore feature relationships and identify factors influencing performance.
• Deploy trained models as scalable web services on AWS and Azure.
• Demonstrate a complete ML lifecycle from data to deployment.

Dataset

The dataset contains student information, including:

• Gender
• Race/Ethnicity
• Parental Level of Education
• Lunch Type
• Test Preparation Course
• Math Score
• Reading Score
• Writing Score

Project Structure

Getting Started

1. Clone the repository: https://github.com/PiusSunday/student-performance-analysis
2. Navigate to the project directory: cd student-performance-analysis
3. Create a virtual environment (recommended): conda create -n student-performance-analysis-venv -y
4. Activate the virtual environment:
   • macOS/Linux: conda activate student-performance-analysis-venv
5. Install dependencies: pip install -r requirements.txt
6. Explore the data and train the model using the Jupyter notebooks in the notebooks directory.
7. Follow the instructions in the aws/ and azure/ directories to deploy the model on your chosen cloud platform.

Dependencies

• pandas
• numpy
• scikit-learn
• matplotlib
• seaborn
• Flask/FastAPI (for API deployment)

Deployment

• AWS: coming soon...

• Azure: coming soon...

Contributing

Contributions are welcome! Please feel free to submit pull requests or open issues.

License

MIT License