ticket-sentiment.clj

ticket-sentiment.clj

(ns ticket-sentiment.core
  (:require [clojure.data.csv :as csv]
            [clojure.java.io :as io]
            [clojure.pprint :refer [pprint]]
            [damionjunk.nlp.cmu-ark :as ark]
            [damionjunk.nlp.stanford :as nlp]))

(defn mean [coll]
  (let [sum (apply + coll)
        count (count coll)]
    (if (pos? count)
      (/ sum count)
      0)))

(defn median [coll]
  (let [sorted (sort coll)
        cnt (count sorted)
        halfway (quot cnt 2)]
    (if (odd? cnt)
      (nth sorted halfway)
      (let [bottom (dec halfway)
            bottom-val (nth sorted bottom)
            top-val (nth sorted halfway)]
        (mean [bottom-val top-val])))))

(defn -main [& _]
  (with-open [writer (io/writer "scored-output.csv")
              reader (io/reader
                       (io/resource
                         "sql_runner_dr6tdfnkpwfxzh_2020-01-08_19-17-24.csv"))]
    (csv/write-csv writer
      (cons ["ID" "SENTIMENT" "FROM-MEMBER"]
        (for [[id dt text email] (csv/read-csv reader)]
          (let [sentence-sentiments (map :sentiment (nlp/sentiment-maps text))
                total-sentiment (apply max
                                  [(double (mean sentence-sentiments))
                                   (double (median sentence-sentiments))])
                from-member? (and email
                                  (not
                                    (re-find #"@starcity.com$" email)))
                row-out [id total-sentiment from-member?]]
            (prn row-out)
            row-out))))))