This project focuses on applying machine learning classification to wine recognition data. The process includes exploratory data analysis (EDA), data visualization, and correlation analysis to gain insights into the dataset. Afterward, we perform a spot-check of various classification models to determine their effectiveness. We assess the classification models' performance using confusion matrices to evaluate their accuracy and error rates. To further enhance our results, we apply Optuna, an automatic hyperparameter optimization framework, and cross-validation to fine-tune and optimize the model parameters. Finally, we draw conclusions based on the results obtained through our extensive analysis.
- K-Nearest Neighbors (KNN)
- Decision Tree (CART)
- Naive Bayes (NB)
- Support Vector Classifier (SVC)
- AdaBoost (AB)
- Gradient Boosting Machine (GBM)
- Random Forest (RF)
- Extra Trees (ET)