ruby - 如何重构我的词频方法？

Question

这是我的方法 word_frequency。

def frequencies(text)
      words = text.split
      the_frequencies = Hash.new(0)
      words.each do |word|
        the_frequencies[word] += 1
      end
      return the_frequencies
    end

    def most_common_words(file_name, stop_words_file_name, number_of_word)
      # TODO: return hash of occurences of number_of_word most frequent words
      opened_file_string = File.open(file_name.to_s).read.downcase.strip.split.join(" ").gsub(/[^a-zA-Z \'$]/, "").gsub(/'s/, "").split
      opened_stop_file_string = File.open(stop_words_file_name.to_s).read.downcase.strip.split.join(" ").gsub(/[^a-zA-Z \']/, "").gsub(/'s/, "").split
      # declarar variables de file_name stop words.
      filtered_array = opened_file_string.reject { |n| opened_stop_file_string.include? n }
      the_frequencies = Hash.new(0)
      filtered_array.each do |word|
        the_frequencies[word] += 1
      end
      store = the_frequencies.sort_by { |_key, value| value }.reverse[0..number_of_word - 1].to_h
      store
    end

效果很好，但我认为我可以做得更好。 Rubocop 说我的台词太长了，我同意，但这是我最好的。有人可以解释我如何才能做得更好吗？

Answer 1

如果只是分解大的部分就好了。 most_common_words 似乎仍然很微妙，你可以解释你正在尝试做什么，看看在那里还能做什么。

您还可以使用频率，并查看方法参数中的模式，OOP 方法更适合这里。

def join_file(file_name)
  File.open(file_name).read.downcase.strip.split.join(' ')
end

def frequencies(text)
  text.split.each_with_object(Hash.new(0)) { |word, hash| hash[word] += 1 }
end

def opened_file_string(file_name)
  join_file(file_name).gsub(/[^a-zA-Z \'$]/, '').gsub(/'s/, '').split
end

def opened_stop_file_string(file_name)
  @opened_stop_file_string ||= join_file(file_name).gsub(/[^a-zA-Z \']/, '').gsub(/'s/, '').split
end

def in_stop_file_string?(file_name, word)
  opened_stop_file_string(file_name).include?(word)
end

def filtered_array(file_name, stop_words_file_name)
  opened_file_string(file_name).reject do |word|
    in_stop_file_string?(stop_words_file_name, word)
  end
end

def frequencies_in_filtered_array(file_name, stop_words_file_name)
  frequencies(filtered_array(file_name, stop_words_file_name)).sort_by { |_, value| value }
end

def most_common_words(file_name, stop_words_file_name, number_of_word)
  frequencies_in_filtered_array(file_name.to_s, stop_words_file_name.to_s).reverse[0...number_of_word].to_h
end