fetch elements that occurred multiple times in Ruby Array

big_array_duplicates_bench.rb

require 'benchmark'
require 'faker'

ary = []

100.times do
  ary << Faker::Name.name
end

n = 100_000

Benchmark.bmbm(20) do |r|
  r.report('Using group_by.select') do
    n.times do
      ary
        .group_by{ |e| e }
        .select { |k, v| v.size > 1 }
        .map(&:first)
    end
  end

  r.report('Using sort.chunk.select') do
    n.times do
      ary
        .sort
        .chunk{ |e| e }
        .select { |e, chunk| chunk.size > 1 }
        .map(&:first)
    end
  end

  r.report('Using count select') do
    n.times do
      ary.select{ |e| ary.count(e) > 1 }.uniq
    end
  end
end

# running or ruby 2.2.2
#
# Rehearsal -----------------------------------------------------------
# Using group_by.select     5.350000   0.000000   5.350000 (  5.356332)
# Using sort.chunk.select   7.640000   0.000000   7.640000 (  7.641986)
# Using count select       45.320000   0.030000  45.350000 ( 45.320775)
# ------------------------------------------------- total: 58.340000sec
# 
#                               user     system      total        real
# Using group_by.select     5.460000   0.000000   5.460000 (  5.457235)
# Using sort.chunk.select   7.670000   0.000000   7.670000 (  7.664146)
# Using count select       45.490000   0.030000  45.520000 ( 45.488224)

small_array_duplicates_bench.rb

require 'benchmark'

ary = ["A", "B", "C", "B", "A", "D", "E", "F", "G", "H"]

n = 100_000

Benchmark.bmbm(20) do |r|
  r.report('Using group_by.select') do
    n.times do
      ary
        .group_by{ |e| e }
        .select { |k, v| v.size > 1 }
        .map(&:first)
    end
  end

  r.report('Using sort.chunk.select') do
    n.times do
      ary
        .sort
        .chunk{ |e| e }
        .select { |e, chunk| chunk.size > 1 }
        .map(&:first)
    end
  end

  r.report('Using count select') do
    n.times do
      ary.select{ |e| ary.count(e) > 1 }.uniq
    end
  end
end


# on Ruby 2.1.2
#
# Rehearsal -----------------------------------------------------------
# Using group_by.select     0.720000   0.000000   0.720000 (  0.717274)
# Using sort.chunk.select   1.510000   0.000000   1.510000 (  1.506170)
# Using count select        0.730000   0.000000   0.730000 (  0.737882)
# -------------------------------------------------- total: 2.960000sec
#
#                              user     system      total        real
# Using group_by.select     0.790000   0.000000   0.790000 (  0.790971)
# Using sort.chunk.select   1.500000   0.000000   1.500000 (  1.498845)
# Using count select        0.720000   0.000000   0.720000 (  0.725994)


# on Ruby 2.2.2
#
# Using group_by.select     0.640000   0.010000   0.650000 (  0.645127)
# Using sort.chunk.select   1.370000   0.000000   1.370000 (  1.365221)
# Using count select        0.730000   0.000000   0.730000 (  0.735518)
#-------------------------------------------------- total: 2.750000sec
#
#                              user     system      total        real
# Using group_by.select     0.710000   0.000000   0.710000 (  0.710802)
# Using sort.chunk.select   1.380000   0.000000   1.380000 (  1.385528)
# Using count select        0.720000   0.000000   0.720000 (  0.710731)

Thank you for sharing this