enumerable_to_spark_histogram.rb

Enumerable.class_eval do
  def dump_spark_histogram
    element_count_pairs = self.group_by { |x| x }.to_a.map { |el, els| [el, els.size] }
    element_count_pairs = element_count_pairs.sort_by(&:first)

    max_el_len = element_count_pairs.map(&:first).map(&:to_s).map(&:size).max

    element_count_pairs.each do |el, count|
      puts("%#{max_el_len}s: #{('=' * count)}" % el)
    end
  end
end

array = ['a', 'b', 'c', 'd', 'a', 'a', 'c', 'dd', 'eee', 'eee', 'ffff', 'a']
array.dump_spark_histogram
# outputs
#    a: ====
#    b: =
#    c: ==
#    d: =
#   dd: =
#  eee: ==
# ffff: =