Wine_Quality_Clustering_(Unsupervised_Macine_Learning) BY ---> Feysel Mifta

[feysel2003]

Project: Wine Quality Clustering (Unsupervised Learning)

1. Introduction

In this project, we will explore a dataset containing chemical properties of red and white wines. Unlike supervised learning, we do not have a specific target to predict. Instead, our goal is Clustering.

We will use K-Means and Hierarchical Clustering to find natural groupings (clusters) within the wine data. This helps us understand if wines group themselves by type (Red vs. White) or by quality levels based purely on their chemical makeup.

Workflow:

1. Data Cleaning: Handling missing values and duplicates.
2. EDA: Visualizing the data distribution.
3. Preprocessing: Encoding text and scaling features (crucial for clustering).
4. K-Means Clustering: Grouping wines using centroids.
5. Hierarchical Clustering: Grouping wines using a tree structure (Dendrogram).