🎓 Student Score Predictor

A beginner-friendly Machine Learning project built with Python, Scikit-learn, and Streamlit that predicts a student's exam score based on study habits and academic performance.

The model uses Linear Regression to estimate the final score using the following inputs:

• 📚 Hours Studied
• ✅ Attendance Percentage
• 📝 Previous Exam Score
• 😴 Sleep Hours

This project demonstrates the complete machine learning workflow, from data preparation and model training to prediction, visualization, and a simple web interface.

---

🚀 Features

• Predicts student exam scores using Linear Regression
• Input validation to prevent invalid values
• Model evaluation using R² Score and Mean Squared Error (MSE)
• Scatter plot comparing actual vs. predicted scores
• Saves the trained model using Joblib
• Command-line prediction using argparse
• Interactive web application built with Streamlit
• Clean and beginner-friendly project structure

---

🛠 Technologies Used

• Python 3
• Pandas
• Scikit-learn
• Matplotlib
• Joblib
• Streamlit
• VS Code
• Git & GitHub

---

📂 Project Structure

student-score-predictor/
│
├── data/
│   └── student_scores.csv
├── train.py
├── predict.py
├── app.py
├── student_model.pkl
├── actual_vs_predicted.png
├── requirements.txt
├── README.md
└── .gitignore

---

⚙️ Installation

Clone the repository:

git clone https://github.com/Hasu0507/student-score-predictor.git

Go to the project directory:

cd student-score-predictor

Install dependencies:

pip install -r requirements.txt

---

▶️ Running the Project

Train the model

python train.py

Predict from the command line

python predict.py --hours 6 --attendance 85 --previous 75 --sleep 7

Run the Streamlit web app

streamlit run app.py

---

📊 Example Output

Command-line

Predicted Score: 79.21

Training

R² Score: 0.98
Mean Squared Error: 2.10
Model saved successfully.

---

📈 Machine Learning Workflow

1. Load the dataset.
2. Preprocess the data.
3. Split into training and testing datasets.
4. Train a Linear Regression model.
5. Evaluate model performance.
6. Save the trained model.
7. Predict new student scores.
8. Visualize model predictions.
9. Deploy a simple web interface with Streamlit.

---

👨‍💻 Author

Sreekamali J

GitHub: https://github.com/hasu0507