Add error handling, Change in clusters

[Cheshta17]

Fix issues #22

Changes proposed

Visualization of Clusters: Add a visualization of the clusters using dimensionality reduction techniques like PCA or t-SNE.

Optimal Number of Clusters: Implement a method to automatically determine the optimal number of clusters (e.g., elbow method, silhouette score).

Recommendation System: Develop a recommendation system within each cluster to suggest similar products to users.

Error Handling: Add error handling for file loading and data preprocessing steps.

Model Persistence: Save the trained models and vectorizers for future use without retraining.