Interactive Streamlit app benchmarking SVM, Logistic Regression, and Perceptron across 3 real-world Kaggle datasets — spanning binary classification (fruit, pumpkin) and multi-class classification (9 fish species) — with Grid Search hyperparameter tuning and real-time algorithm/dataset selection.
🔗 Live Demo:Try it here
| Dataset | Task | Best Accuracy / CV Score |
|---|---|---|
| Fruit | Binary classification | 96.5% test accuracy |
| Fish | Multi-class (9 species) | 94.0% CV score |
| Pumpkin | Binary classification | 89.0% CV score |
- Extensive Grid Search hyperparameter tuning per algorithm-dataset pair (kernel, C, gamma, solver, regularization)
- Users can select any algorithm/dataset combination and instantly view classification results
App/ # Streamlit application + saved models
SVM/ # SVM training notebooks per dataset
Logistic Regression/ # Logistic Regression training notebooks per dataset
Perceptron/ # Perceptron training notebooks per dataset
Python · Scikit-learn · Streamlit
cd App
pip install -r requirements.txt
streamlit run app.py