benchmark-44097717.rb

# benchmark for http://stackoverflow.com/q/44097717/229044

require 'set'
require 'benchmark'

def make_data(size = 25_000)
  t = Time.now
  size.downto(0).map do |i|
    {
      'timestamp-value' => (t - i * 60).to_s[0..15],
      'value' => i
    }
  end
end

X_DATA = make_data.freeze
Y_DATA = make_data.freeze

N = 100
def values_for_regression(x_data, y_data)
  x_timestamps = timestamps_for(x_data)
  y_timestamps = timestamps_for(y_data)

  # Get final timestamps as the intersection of the two
  timestamps = x_timestamps.intersection(y_timestamps)

  x_values = values_for(x_data, timestamps)
  y_values = values_for(y_data, timestamps)

  [x_values, y_values]
end

def timestamps_for(data)
  Set.new data.reject { |row| row['value'].nil? }.map { |row| row['timestamp-value'] }
end

def values_for(data, timestamps)
  data.select { |row| timestamps.include?(row['timestamp-value']) }.map { |row| row['value'] }
end

def my_values_for_regression(x_data, y_data)
  x_values = []
  y_values = []

  y_map = y_data.each_with_object({}) { |data, hash| hash[data['timestamp-value']] = data['value'] }

  x_data.each do |data|
    next unless x_value = data['value']
    next unless y_value = y_map[data['timestamp-value']]
    x_values << x_value
    y_values << y_value
  end

  [x_values, y_values]
end

yours = values_for_regression(X_DATA, Y_DATA)
mine = my_values_for_regression(X_DATA, Y_DATA)
unless yours[0] == mine[0] && yours[1] == mine[1]
  raise("Output doesn't match!")
end

Benchmark.bm(10) do |bm|
  bm.report 'yours' do
    N.times { values_for_regression(X_DATA, Y_DATA) }
  end
  bm.report 'mine' do
    N.times { my_values_for_regression(X_DATA, Y_DATA) }
  end
end