Computing k-means clustering in MADlib

gistfile1.sql

SELECT data.*, (madlib.closest_column(centroids, points)).column_id as cluster_id
FROM public.iris_data as data,
     (SELECT centroids
      FROM madlib.kmeanspp('iris_data', 'points', 
                           <Parameters.K>,
                           <Parameters.distance function>,
                           <Parameters.aggregation method>,
                           <Parameters.max number of iterations>, 
                           <Parameters.min frac reassigned >)) as centroids
ORDER BY data.pid