Skip to content

README.md

Latest commit

 

History

History
149 lines (101 loc) · 2.87 KB

README.md

File metadata and controls

149 lines (101 loc) · 2.87 KB
Raw

🎓 Student Performance Predictor

An interactive Machine Learning web application that predicts student marks based on study hours using Linear Regression.

This project demonstrates a complete ML workflow — from dataset upload to prediction, evaluation, and visualization inside a user-friendly web interface.

🌐 Live Demo

👉 Run the application here:
https://student-performance-predictor-tcxlodkvordbwnkbtn5gth.streamlit.app/

📌 Project Description

The Student Performance Predictor allows users to upload their own dataset and instantly train a machine learning model.

It dynamically learns the relationship between study hours and marks, evaluates model accuracy using regression metrics, and generates real-time predictions with graphical visualization.

This project focuses on converting theoretical Machine Learning concepts into a practical and usable real-world application.

🚀 Features

  • Upload custom CSV dataset
  • Select feature & target columns
  • Automatic model training
  • Predict marks using study hours slider
  • Model performance metrics (R² Score & MAE)
  • Regression visualization graph
  • Download trained model (.pkl)

🧠 Machine Learning Concepts Used

  • Linear Regression
  • Model Training & Prediction
  • Performance Evaluation (R² Score, MAE)
  • Regression Visualization
  • Model Serialization using Pickle

⚙️ Tech Stack

  • Python
  • Pandas
  • NumPy
  • Scikit-learn
  • Matplotlib
  • Streamlit

📊 Application Workflow

  1. Upload dataset (Study Hours vs Marks)
  2. Choose feature and target column
  3. Model trains automatically
  4. Enter study hours
  5. Get predicted marks
  6. View regression graph
  7. Download trained model

📁 Project Structure

student-performance-predictor/
│── app.py
│── requirements.txt
│── README.md

▶️ Run Locally

Clone the repository:

git clone https://github.com/YOUR_USERNAME/student-performance-predictor.git
cd student-performance-predictor

Install dependencies:

pip install -r requirements.txt

Run the application:

streamlit run app.py

📦 Requirements

streamlit
pandas
numpy
matplotlib
scikit-learn

📈 Example Dataset Format

Study Hours Marks
2 25
4 45
6 70
8 88

💡 Learning Outcomes

  • Practical understanding of regression models
  • Evaluating model performance using R² & MAE
  • Building interactive ML web applications
  • Handling real user input datasets
  • Converting ML logic into a usable product

👨‍💻 Author

Thota Hari Krishna
AI & Data Science Student
Aspiring Machine Learning Engineer

📫 Open to internships and entry-level opportunities in AI / ML / Data Science

⭐ Support

If you like this project, consider giving it a star ⭐ on GitHub.