Cluster Analysis-Partitioning Clustering Analysis of Vehicles Data

R Language Codes for Data Analysis & Machine Learning Projects

we will conduct a k-means clustering analysis (Partitioning Clustering) on a vehicle dataset consisting of 846 samples and 20 attributes. The dataset also includes one output variable (class) with four distinct classes (a double decker bus, Chevrolet van, Saab and an Opel Manta). The aim of the analysis is to assess different clustering results under the initial conditions and determine the preferable choice of k (number of clusters). Moreover, we will perform methodologies for reducing dimensionality in this problem and perform pre-processing tasks to prepare our dataset, including scaling and outlier removal. This code will cover the following objectives in detail:

1. Dimensionality Reduction Methodologies
2. Pre-processing Tasks: Scaling and Outliers Removal
3. Determining the Number of Cluster Centers via Automated Tools
4. K-means Analysis for K=2,3, and 4
5. Evaluation of Clustering Outputs: BSS, BSS/TSS, and WSS Indices