naive-bayes(clojure)

naive-bayes.clj

;; 訓練データ
(def text_classified_p '(["good" "bad" "good" "good"]
                            ["exciting" "exciting"]
                            ["good" "good" "exciting" "boring"]))
(def text_classified_n '(["bad" "boring" "boring" "boring"]
                           ["bad" "good" "bad"]
                           ["bad" "bad" "boring" "exciting"]))

;;多変数ベルヌーイモデル 
(defn train [features]
  (reduce (fn [model f] (assoc model f (get model f 1))) {} features))
(defn count-wordset [training-data]
  (apply merge-with + (map train training-data)))
(defn mBm-MLestimate [documents datasets]
  (* (/ (count datasets) (count (concat text_classified_p text_classified_n)))
     (apply * (map #(/ % (count datasets))
                   (vals (select-keys (count-wordset datasets) documents))))
     (apply * (map #(- 1 (/ % (count datasets)) )
                   (vals (apply dissoc (count-wordset datasets) documents))))))

(defn classify [d]
  (sorted-map
   :positive (mBm-MLestimate d text_classified_p)
   :negative (mBm-MLestimate d text_classified_n)))

;; 多項モデル
(defn train [features]
    (reduce (fn [model f] (assoc model f (inc (get model f 0)))) {} features))
(defn count-wordset [training-data]
  (apply merge-with + (map train training-data)))
(defn mm-MLestimate [documents datasets]
  (* (/ (count datasets) (count (concat text_classified_p text_classified_n)))
     (apply * (map #(/ % (count (reduce concat datasets)))
                   (map #(get (count-wordset datasets) %) documents)))))

(defn classify [d]
  (sorted-map-by >
                 (mm-MLestimate d text_classified_p) :positive
                 (mm-MLestimate d text_classified_n) :negative))

;; 実行例
(classify ["good" "good" "bad" "boring"])