fraud-detection-data.clj

(ns fraud-detection.core
  (:require [clojure.java.io :as io]
           [clojure.string :as string]
           [clojure.data.csv :as csv]
           [clojure.core.matrix :as mat]
           [clojure.core.matrix.stats :as matstats]
           [cortex.nn.layers :as layers]
           [cortex.nn.network :as network]
           [cortex.nn.execute :as execute]
           [cortex.optimize.adadelta :as adadelta]
           [cortex.optimize.adam :as adam]
           [cortex.metrics :as metrics]
           [cortex.util :as util]
           [cortex.experiment.util :as experiment-util]
           [cortex.experiment.train :as experiment-train]))

(def orig-data-file "resources/creditcard.csv")
(def log-file "training.log")
(def network-file "trained-network.nippy")

;; Read input csv and create a vector of maps {:data [...] :label [..]}, 
;; where each map represents one training instance in the data
(defonce create-dataset
  (memoize
    (fn []
      (let [credit-data (with-open [infile (io/reader orig-data-file)]
                          (rest (doall (csv/read-csv infile))))
            data (mapv #(mapv read-string %) (map #(drop 1 %) (map drop-last credit-data))) ; drop label and time
            labels (mapv #(util/idx->one-hot (read-string %) 2) (map last credit-data))
            dataset (mapv (fn [d l] {:data d :label l}) data labels)]
        dataset))))