Wine Clustering Using Unsupervised Machine Learning

Developed an unsupervised machine learning project to cluster wine samples based on their chemical properties. The project included data preprocessing, exploratory data analysis (EDA), feature scaling, dimensionality reduction using PCA, and K-Means clustering to identify hidden patterns within the dataset.

Key Features

Performed Exploratory Data Analysis (EDA) to understand the dataset.

Standardized features using StandardScaler.

Applied Principal Component Analysis (PCA) for dimensionality reduction.

Used the Elbow Method to determine the optimal number of clusters.

Built and evaluated a K-Means clustering model using the Silhouette Score.

Visualized clustering results using Matplotlib and Seaborn.

Tools & Technologies

Python

Pandas

NumPy

Scikit-learn

Matplotlib

Seaborn

YData Profiling

Outcome

Successfully grouped wine samples into meaningful clusters, demonstrating practical experience in data preprocessing, unsupervised machine learning, and data visualization.