Student Performance MLOps

An end-to-end Machine Learning and MLOps project for analyzing and predicting student performance using academic and demographic data.
This repository covers the life cycle of a typical ML project — from data exploration and model training to deployment and CI/CD automation.

📌 This project was built for learning and experimentation in MLOps.

---

🧠 Project Overview

Student performance prediction is an application of predictive modeling where academic scores are forecast based on features like gender, ethnicity, parental education, lunch type, and test preparation completion.:contentReference[oaicite:1]{index=1}

This project integrates:

• Exploratory Data Analysis (EDA)
• Data preprocessing and feature engineering
• Model training and evaluation
• Model deployment via a REST API
• Containerization and CI/CD automation
• Serving predictions to users

---

📁 Repository Structure

Student_Performance_MLOps/
├── notebook/                # Notebooks with training, EDA, modeling
├── src/                     # Source code (model utils, pipelines)
├── templates/               # UI templates (if web UI exists)
├── app.py                   # Web application entrypoint
├── requirements.txt         # Python dependencies
├── setup.py                 # Project packaging
├── ReadMe.md
└── .gitignore

---

🛠 Setup & Installation

1. Clone the repo.

   git clone https://github.com/abrarshahh/Student_Performance_MLOps.git
   cd Student_Performance_MLOps
   

2. Create and activate a virtual environment

   python3 -m venv venv
   source venv/bin/activate
   

3. Install dependencies

   pip install -r requirements.txt
   

---

🚀 Usage

Run the application locally

1. Start the app:

   python app.py
   

2. Visit the local dev server (default port may vary) to interact with the prediction UI.

Model Training & Evaluation

• Use the notebook in notebook/ to explore the dataset
• Train models and evaluate performance
• Save the final model for deployment

---

📌 Architecture Summary

1. Notebook for EDA & modeling — explore the dataset and train candidate models.

2. Source code for inference — load and serve models via app.py.

3. Web interface / REST API — interactively predict student performance.

---

🛠 Tools & Tech Stack

• Python 3.x

• Flask for REST API

• MLOps

• Jupyter Notebooks

• Pandas, Scikit-Learn, and visualization libraries