Multi-level Grouping and Computations

group.clj

(ns pas.tree
    (:use [clojure.pprint :only [pprint]]))

(def reg-cntry-list
  {"America" ["USA" "Canada" "Mexico" "Venezuala" "Brazil" "Argentina" "Cuba"]
   "Asia" ["India" "Pakistan" "Singapore" "China" "Japan" "Sri Lanka" "Malaysia"]
   "Europe" ["UK" "Germany" "France" "Italy" "Belgium" "Turkey" "Finland"]
   "Middle East" ["Saudi Arabia" "Bahrain" "UAE" "Kuwait" "Yemen" "Qatar" "Iraq"]
   "Africa" ["Libya" "Tanzania" "South Africa" "Kenya" "Ethiopia" "Morocco" "Zimbabwe"]})


(def sec-ind-list 
  {"Basic Materials" ["Apparel" "Auto Part" "Building" "Packaged"]
   "Consumer Goods" ["Beveragess" "Cigarettes" "Drugs" "Newspapers"]
   "Financial" ["Life Insurance" "Banking" "Investment" "Funds"]
   "Healthcare" ["Home care" "Hospitals" "Plans" "Medical"]
   "Industrial" ["Chemicals" "Cleaning" "Machine" "Lumber"]
   "Services" ["Advertising" "Broadcasting" "Education" "Publishing"]
   "Technology" ["Biotechnology" "Computers" "Data Storage" "Electronics"]
   "Utilities" ["Farm Products" "Electric" "Gas" "Oil"]})

(defn get-rec []
  (let 
    [r (rand-nth (keys reg-cntry-list))
     s (rand-nth (keys sec-ind-list))]

    {:sec_id (rand-int 1000) 
     :attr1  r
     :attr2  (rand-nth (reg-cntry-list r))
     :attr3  s
     :attr4  (rand-nth (sec-ind-list s))
     :mv  (rand 1000000)
    }))

;generate 50 random records
(def data (take 50 (repeatedly get-rec)))

(defn sum-by [data attrs]
  (let [aggregated (group-by (apply juxt attrs) data)]
    (zipmap (keys aggregated) (map #(reduce + (map :mv %)) (vals aggregated)))))

;(println (sum-by data [:attr1 :attr2]))

; tree-grouping

(def data (take 50 (repeatedly get-rec)))

(defn mlg [attrs data]
    (if (empty? attrs)
        [ (reduce + (map :mv data)) {:children data}]
    	(let [parts (group-by (first attrs) data)
    	      subtrees (map (fn [[value data]] 
    	                    [value (mlg (rest attrs) (map #(dissoc % (first attrs)) data))])
    	                  parts)]
    	    (reduce (fn [[sum tree] [value [sumsubtree subtree]]]
    	                [(+ sum sumsubtree)
    	                 (update-in tree [:children] conj (assoc subtree 
    	                                                    :path [(first attrs) value]
    	                                                    :mv sumsubtree))]
    	            )
    	            [ 0.0  { :children [] }]
    	            subtrees))))
			     
(comment
    (def mydata (take 10 (repeatedly get-rec)))
    (mlg [] mydata)
    (mlg [:attr1] mydata)
    (mlg [:attr1 :attr2] mydata)
    (mlg [:attr1 :attr2 :attr3 :attr4 :attr5] mydata)
    (mlg [:attr1 :attr2 :attr3 :attr4 :attr5] data)
)