Cluster Analysis on IRIS Data Using Partitional Clustering Algorithms

Conducting cluster analysis on the IRIS dataset using partitional clustering algorithms. The IRIS dataset consists of measurements from three independent species of iris flowers, totaling 150 samples with 50 samples per category across 3 distinct classes. Each sample contains 4 feature dimensions representing sepal and petal measurements. The clustering analysis employs algorithms such as K-Means, which operates by initializing centroids and iteratively assigning data points to the nearest centroid while updating centroid positions. This process helps reveal underlying patterns and relationships between different categories, demonstrating how species separate in the 4-dimensional feature space. Cluster analysis facilitates the discovery of hidden data structures and natural groupings, providing foundational insights for further research and applications. Implementation typically involves data preprocessing, feature scaling, algorithm parameter tuning (e.g., determining optimal K values using elbow method), and validation through silhouette scores or cluster purity metrics to assess separation quality between iris species.