This example uses PCA for dimension reduction; that is, it determines the principal components that capture most of the variance of the explanatory variables. The principal components are mutually orthogonal because the eigenvectors that span them are orthogonal.
The example uses the PCA_Map and PCA_Reduce functions to output a table of eigenvectors with their component ranks and standard deviations and then uses SQL statements to derive the principal components of the top three eigenvectors.