NhanPhamThanh-IT/Random-Forest-Wine-Quality-Prediction

The project implements classification on imbalanced wine quality data using scikit-learn's Random Forest with GridSearchCV hyperparameter optimization and cross-validation techniques. It provides a complete ML workflow with data preprocessing, feature scaling options, and model persistence capabilities alongside comprehensive EDA visualizations (correlation heatmaps, distribution plots, confusion matrices, ROC curves) using Matplotlib and Seaborn. Built entirely in Jupyter notebooks with reproducible code examples, supporting both interactive exploration and command-line batch processing for predictions on new datasets.

No commits in the last 6 months.