An advanced Machine Learning web application built using Streamlit that compares multiple regression models and identifies the best-performing model based on R² score.
This project allows users to:
- Upload any dataset (CSV format)
- Select the target variable dynamically
- Train multiple regression models
- Compare their performance
- Automatically identify the best model
- Linear Regression
- Polynomial Regression (Degree = 4)
- Random Forest Regression
- Decision Tree Regression
- Support Vector Regression (SVR with scaling)
- 📂 Upload your own dataset
- ⚙️ Dynamic target column selection
- 📉 Adjustable train-test split
- 🤖 Multiple model training
- 📊 Performance comparison using R² score
- 🏆 Best model detection
- 📈 Interactive bar chart visualization
- 🎨 Modern UI with custom styling
- Python
- Streamlit
- Pandas
- NumPy
- Scikit-learn
- Matplotlib
Regression-Model-Selection/ │ ├── app.py ├── dataset.csv ├── requirements.txt └── README.md
- Clone the repository:
git clone https://github.com/selvan-01/regression-model-selection.git cd regression-model-selection
- Install dependencies:
pip install -r requirements.txt
- Run the application:
streamlit run app.py
- Upload your dataset (CSV)
- Select the target column
- Click "Train & Compare Models"
- View model performance
- Identify the best regression model automatically
R² Score (Coefficient of Determination) is used to evaluate model performance.
- Add more ML models (XGBoost, Gradient Boosting)
- Hyperparameter tuning
- Download predictions feature
- Model saving/loading
- Deployment on cloud platforms
S. Senthamil Selvan AI | Data Science
Portfolio: https://senthamill.vercel.app/
LinkedIn: Senthamil45-linkdin profile
If you like this project, give it a ⭐ on GitHub and share it!