user@devops:~$ cat README.md
KNN — Wine Quality Classification
# Description
Classification project with K-Nearest Neighbors to predict red wine quality (good vs normal) using the UCI Wine Quality dataset. Learn to transform a regression problem into binary classification, scale features with StandardScaler (critical for KNN), find the optimal K by testing from 1 to 50 neighbors, and evaluate with confusion matrix, precision, recall, and F1-score. Includes decision boundary visualization with PCA.
# Key features
$ Binary classification: good wine (quality >= 7) vs normal
$ Feature scaling with StandardScaler for KNN
$ Hyperparameter K optimization: from 1 to 50 neighbors
$ Confusion matrix: True Positives, False Positives
$ Metrics: precision, recall, F1-score, accuracy
$ Decision boundary visualization with PCA 2D
# Gallery
# Technologies used
