You could take a look at some traditional stat anslyses, like Cluster Analysis, and for a visual representation,  try Multidimensional Scaling. These would save you a lot of time. There is no reason to reinvent the wheel, but Big Data seems intent upon ignoring the vast historical knowkedge regarding statistics,  psychometrics, and Measurement Theory. Believe me- if you have a question on how to proceed with an analysis, multivariate statistics is likely to have several accaeptable answers.…