Red Wine Analysis-Clustering/PCA

1. Pre-processing 2.Define the number of cluster centers by showing all necessary steps/methods via manual & automated tools
2. K-means analysis for each k attempt
3. Evaluation of the produced outputs against the 12th column
4. Define the final “winner” cluster case and provide a brief explanation of evaluation indices
5. Apply a PCA for this white wine dataset. Create a new dataset with those PCs with a cumulative score > 96%, as attributes.
6. Apply kmeans on this new “PCA-based” dataset
7. Discuss the performance for this “PCA-based” dataset through the calculation of WSS, BSS, and BSS/TSS indices and compare them against the ones produced from the previous “winner” model utilizing all attributes.