Created
January 24, 2015 15:26
-
-
Save woxtu/2873895837b22f04275b to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| (ns markov | |
| (:require [cljs.nodejs :as nodejs] | |
| [clojure.string :refer [join replace]])) | |
| (def kuromoji (nodejs/require "kuromoji")) | |
| (defn wakachi [tokenizer sentence] | |
| (->> (js->clj (.tokenize tokenizer sentence) :keywordize-keys true) | |
| (map :surface_form))) | |
| (defn n-gramize [order tokens] | |
| (let [tokens (vec (concat tokens (repeat (dec order) nil)))] | |
| (->> (range (- (count tokens) (dec order))) | |
| (map #(subvec tokens % (+ % order)))))) | |
| (defn markov-chain [grams & {:keys [start] | |
| :or {start (first (rand-nth grams))}}] | |
| (loop [node start, result [start]] | |
| (if (nil? (last result)) | |
| result | |
| (let [gram (rand-nth (filter #(= (first %) node) grams))] | |
| (recur (last gram) (concat result (drop 1 gram))))))) | |
| (defn -main [& args] | |
| (if-let [[sentence _] args] | |
| (-> kuromoji | |
| (.builder #js {:dicPath "./node_modules/kuromoji/dist/dict/"}) | |
| (.build (fn [error tokenizer] | |
| (let [tokens (wakachi tokenizer sentence)] | |
| (println (->> tokens (n-gramize 3) markov-chain join)))))))) | |
| (nodejs/enable-util-print!) | |
| (set! *main-cli-fn* -main) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment