(ns code.learners.kmeans.k_means_model 
  (:use (code.utils utils folds)) 
  (:use (incanter core)))

(def CLUSTERS [])

(defn Membership [centroids one dist]
  (let [distances (loop [cent centroids results (transient [])]
		    (if (empty? cent)
                      (persistent! results)
		      (recur (rest cent)
                             (conj! results 
				    (vector (first cent) 
					    (dist (first cent) 
						  one))))))
	closest-centroid (first (first (sort-by second distances)))]
    [one closest-centroid]))

(defn MakeClusters [centroids dataset dist]
  (let [members (loop [data dataset results (transient [])]
                  (if (empty? data)
                    (persistent! results)
                    (recur (rest data)
                           (conj! results 
                                  (Membership centroids 
                                              (first data) 
                                              dist)))))]
    (loop [cent centroids results (transient [])]
      (if (empty? cent)
	(apply vector (remove #(= nil %) (persistent! results)))
	(recur (rest cent)
	       (conj! results 
		      (matrix (map first 
				   (apply vector 
					  (filter #(= (first cent) 
						      (second %)) 
						  members))))))))))

(defn k-means [centroids dataset dist]
  (loop [C centroids]
    (let [clusters (MakeClusters centroids dataset dist)
	  new-centroids (map centroid clusters)]  
      (if (= new-centroids C) 
        clusters
        (recur new-centroids)))))      

(defn k-means-model [k D dist]
  (let [clusters (k-means (take k D) D dist)]
    clusters))