feature_loader.rb

class FeatureLoader
  attr_accessor :train_data
  attr_accessor :test_data

  def initialize(path)
    self.load_data(path)
  end

  def load_data(path)
    data = load_file(path).shuffle
    feature_space(data)

    self.train_data = feature_vectors(data[0..(data.length*0.8).floor])
    self.test_data = feature_vectors(data[(data.length*0.8).floor..data.length])
  end

  def load_simple_features
    train_data = [["r",[1,1]],
                   ["r",[2,3]],
                   ["r",[3,1]],
                   ["g",[15,17]],
                   ["g",[20,17]],
                   ["g",[16,16]],
                   ["b",[1,15]],
                   ["b",[5,15]],
                   ["b",[7,20]],
                 ].shuffle
    test_data = [["r",[3,3]],
                  ["g",[15,19]],
                  ["b",[1,21]],
                 ]
  end

  def load_file(path)
    File.open(path, "r").map{ |line|
      remove_stop_words(line)
    }.map { |x|
      x.split(' ')
    }.map { |x|
      [x[0], x[1..x.length]]
    }
  end

  def feature_space(data = nil)
    raise 'no data' unless data || @feature_space
    @feature_space ||= _feature_space(data)
  end

  def _feature_space(data)
    data.map {|x| x[1]}.flatten.uniq.sort_by { |x| x.downcase }
  end

  def feature_vectors(data)
    data.map { |x| feature_vector(x) }
  end

  def feature_vector(review)
    review_text = review[1]
    array = empty_feature_array

    for word in review_text
      if feature_space.include? word
        array[feature_space.index word] = array[feature_space.index word] + 1
      end
    end
    [review[0], array]
  end

  def empty_feature_array
    Array.new(feature_space.length, 0)
  end

  def stop_words
    ["a", "about", "above", "across", "after", "afterwards", "again",
    "against", "all", "almost", "alone", "along", "already", "also", "although",
    "always", "am", "among", "amongst", "amoungst", "amount", "an", "and",
    "another", "any", "anyhow", "anyone", "anything", "anyway", "anywhere", "are",
    "around", "as", "at", "back", "be", "became", "because", "become", "becomes",
    "becoming", "been", "before", "beforehand", "behind", "being", "below",
    "beside", "besides", "between", "beyond", "bill", "both", "bottom", "but",
    "by", "call", "can", "cannot", "cant", "co", "computer", "con", "could",
    "couldnt", "cry", "de", "describe", "detail", "do", "done", "down", "due",
    "during", "each", "eg", "eight", "either", "eleven", "else", "elsewhere",
    "empty", "enough", "etc", "even", "ever", "every", "everyone", "everything",
    "everywhere", "except", "few", "fifteen", "fify", "fill", "find", "fire",
    "first", "five", "for", "former", "formerly", "forty", "found", "four",
    "from", "front", "full", "further", "get", "give", "go", "had", "has",
    "hasnt", "have", "he", "hence", "her", "here", "hereafter", "hereby",
    "herein", "hereupon", "hers", "herself", "him", "himself", "his", "how",
    "however", "hundred", "i", "ie", "if", "in", "inc", "indeed", "interest",
    "into", "is", "it", "its", "itself", "keep", "last", "latter", "latterly",
    "least", "less", "ltd", "made", "many", "may", "me", "meanwhile", "might",
    "mill", "mine", "more", "moreover", "most", "mostly", "move", "much", "must",
    "my", "myself", "name", "namely", "neither", "never", "nevertheless", "next",
    "nine", "no", "nobody", "none", "noone", "nor", "not", "nothing", "now",
    "nowhere", "of", "off", "often", "on", "once", "one", "only", "onto", "or",
    "other", "others", "otherwise", "our", "ours", "ourselves", "out", "over",
    "own", "part", "per", "perhaps", "please", "put", "rather", "re", "same",
    "see", "seem", "seemed", "seeming", "seems", "serious", "several", "she",
    "should", "show", "side", "since", "sincere", "six", "sixty", "so", "some",
    "somehow", "someone", "something", "sometime", "sometimes", "somewhere",
    "still", "such", "system", "take", "ten", "than", "that", "the", "their",
    "them", "themselves", "then", "thence", "there", "thereafter", "thereby",
    "therefore", "therein", "thereupon", "these", "they", "thick", "thin",
    "third", "this", "those", "though", "three", "through", "throughout", "thru",
    "thus", "to", "together", "too", "top", "toward", "towards", "twelve",
    "twenty", "two", "un", "under", "until", "up", "upon", "us", "very", "via",
    "was", "we", "well", "were", "what", "whatever", "when", "whence", "whenever",
    "where", "whereafter", "whereas", "whereby", "wherein", "whereupon",
    "wherever", "whether", "which", "while", "whither", "who", "whoever", "whole",
    "whom", "whose", "why", "will", "with", "within", "without", "would", "yet",
    "you", "your", "yours", "yourself", "yourselves"]
  end

  def punctuation
    ["!", '"', "£", "$", "%", "^", "&", "*", "(", ")", "-", ".", ",", "'"]
  end

  def remove_stop_words(review)
    review_text = review.split(" ").map{ |x| x.split("__") }

    review_text.delete_if { |x|
      stop = false
      x.each { |y|
        if stop_words.include?(y) || punctuation.include?(y)
          stop = true
        end
      }
      stop
    }

    review_text.map { |x| x.join("__") }.join(" ")
  end
end