Study Hours Score Predictor

A simple machine learning web app built with Streamlit that predicts a student's exam score based on the number of hours they studied — powered by Linear Regression.

---

Demo

Enter the number of hours you studied (0–9), hit Submit, and the model will predict your exam score.

---

How It Works

1. Loads a CSV dataset (Hours_and_Scores.csv) containing study hours and corresponding exam scores.
2. Trains a Linear Regression model on 75% of the data.
3. Uses the trained model to predict a score from user input.
4. Clamps the output between 0 and 100 to keep it realistic.

---

Project Structure

project/
│
├── data/
│   └── Hours_and_Scores.csv   # Dataset with Hours and Scores columns
│
├── app.py                     # Main Streamlit application
└── README.md

---

Requirements

Install the dependencies with:

pip install pandas numpy streamlit plotly scikit-learn

Or if you have a requirements.txt:

pip install -r requirements.txt

requirements.txt

pandas
numpy
streamlit
plotly
scikit-learn

---

Running the App

streamlit run app.py

Then open your browser at http://localhost:8501.

---

Dataset

The dataset (Hours_and_Scores.csv) should have the following structure:

Hours	Scores
2.5	21
5.1	47
3.2	27
...	...

• Hours — Number of hours studied
• Scores — Exam score achieved (0–100)

The dataset contains 25 samples and is split 75/25 for training and testing.

---

Model Details

Property	Value
Algorithm	Linear Regression
Library	scikit-learn
Train/Test Split	75% / 25%
Feature Scaling	Not applied*
Input Range	0 – 9 hours
Output Range	0 – 100 (clamped)

*Feature scaling (StandardScaler) is not needed for Linear Regression and has been intentionally left out.

---

Built With

• Streamlit — Web UI framework
• scikit-learn — Machine learning
• pandas — Data handling
• NumPy — Numerical operations
• Plotly — Visualization (imported for future use)

---

Notes

• The model is retrained every time the app starts (no model persistence).
• Since train_test_split uses a random seed by default, results may vary slightly between runs. Add random_state=42 for reproducibility:

  X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)

---

🙋 Author

NFlux