markov-usrnames.clj

(ns markov-usrnames)

(require '[clojure.string :as str])

(def file (slurp "/usr/share/dict/words" :encoding "ASCII"))
(def words (str/split-lines file))

(defn generate-markov-nodes
  [words]
  (->>
    words
    (map str/lower-case)
    (str/join \space)
    (partition 2 1)
    (reduce
      (fn [acc [l next-l]] (update-in acc [l next-l] (fnil inc 0)))
      {}
    )
  )
)

(defn wrand
  "given a vector of slice sizes, returns the index of a slice given a                                                                                                                                      
  random spin of a roulette wheel with compartments proportional to                                                                                                                                         
  slices."
  [slices]
  (let [total (reduce + slices)
        r (rand total)]
    (loop [i 0 sum 0]
      (if (< r (+ (slices i) sum))
        i
        (recur (inc i) (+ (slices i) sum))
      )
    )
  )
)

(defn generate-usrname [nodes]
  (loop [node (nodes \space)
         acc []]
    (let [probabilities (vec (vals node))
          index (wrand probabilities)
          letter (nth (keys node) index)
          next-node (nodes letter)]
      (if (= 5 (count acc))
        (clojure.string/join acc)
        (if (= letter \space)
          (recur node acc)
          (recur next-node (conj acc letter))
        )
      )
    )
  )
)

(def nodes (generate-markov-nodes words))

(->>
  (repeatedly (partial generate-usrname nodes))
  distinct
  (take 10000)
  (str/join "\n")
  (spit "markov-usrnames.txt")
)