Multi-level Grouping and Computations

group.clj

(ns pas.tree
  (:use [incanter core io charts datasets]))

(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]))

(defn is-prog [ns]
  (cond (apply = (map - (rest ns) ns)) "AP"
        (apply = (map / (rest ns) ns)) "GP"
        :else "Neither"))

(def ds (to-dataset data))

(def cats ((comp seq sort set) (map :attr1 data)))

(defn cnt [k v data] (count (filter #(= (k %) v) data)))

(def cnts (map #(cnt :attr1 % data) cats))
(view (to-dataset data))
(view (line-chart cats cnts))