sapor 0.1b1

data/lib/sapor/dichotomies.rb

@@ -0,0 +1,98 @@
+# encoding: utf-8
+#
+# Statistical Analysis of Polling Results (SAPoR)
+# Copyright (C) 2014 Filip van Laenen <f.a.vanlaenen@ieee.org>
+#
+# This file is part of SAPoR.
+#
+# SAPoR is free software: you can redistribute it and/or modify it under the
+# terms of the GNU General Public License as published by the Free Software
+# Foundation, either version 3 of the License, or (at your option) any later
+# version.
+#
+# SAPoR is distributed in the hope that it will be useful, but WITHOUT ANY
+# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
+# A PARTICULAR PURPOSE.  See the GNU General Public License for more details.
+#
+# You can find a copy of the GNU General Public License in /doc/gpl.txt
+#
+
+module Sapor
+  #
+  # Represents a set of dichotomies.
+  #
+  class Dichotomies
+    include NumberFormatter
+
+    def initialize(results, population_size, threshold = nil)
+      sample_size = results.values.inject(:+)
+      @dichotomy_hash = {}
+      results.each_pair do |choice, number|
+        @dichotomy_hash[choice] = Dichotomy.new(number, sample_size,
+                                                population_size)
+      end
+      @threshold = threshold
+    end
+
+    def refine
+      @dichotomy_hash.values.each(&:refine)
+    end
+
+    def error_estimate
+      @dichotomy_hash.values.map(&:error_estimate).max
+    end
+
+    def confidence_interval_values(choice, level)
+      @dichotomy_hash[choice].confidence_interval_values(level)
+    end
+
+    def report
+      choice_lengths = @dichotomy_hash.keys.map(&:length)
+      choice_lengths << 6
+      max_choice_width = choice_lengths.max
+      sorted_choices = sort_choices_by_label_and_mpv
+      lines = sorted_choices.map do |choice|
+        create_report_line(choice, @dichotomy_hash[choice], max_choice_width)
+      end
+      "Most probable fractions and 95% confidence intervals:\n" +
+        'Choice'.ljust(max_choice_width) + '    MPF      CI(95%)' +
+        (@threshold.nil? ? '' : '     P(≥' + (100 * @threshold).to_i.to_s +
+         '%)') +
+        "\n" + lines.join("\n")
+    end
+
+    def progress_report
+      size = @dichotomy_hash.values.first.values.size
+      "Number of data points: #{with_thousands_separator(size)}."
+    end
+
+    private
+
+    def compare_choices_by_label_and_mpv(a, b)
+      if a == OTHER
+        1
+      elsif b == OTHER
+        -1
+      else
+        mpv_a = @dichotomy_hash[a].most_probable_value
+        mpv_b = @dichotomy_hash[b].most_probable_value
+        mpv_a == mpv_b ? a <=> b : mpv_b <=> mpv_a
+      end
+    end
+
+    def sort_choices_by_label_and_mpv
+      @dichotomy_hash.keys.sort do |a, b|
+        compare_choices_by_label_and_mpv(a, b)
+      end
+    end
+
+    def create_report_line(choice, dichotomy, max_choice_width)
+      choice.ljust(max_choice_width) + '  ' + \
+        six_char_percentage(dichotomy.most_probable_fraction) + '  ' + \
+        six_char_percentage(dichotomy.confidence_interval.first) + '–' + \
+        six_char_percentage(dichotomy.confidence_interval.last) +
+        (@threshold.nil? ? '' : '  ' +
+         six_char_percentage(dichotomy.threshold_probability(@threshold)))
+    end
+  end
+end

data/lib/sapor/dichotomy.rb

@@ -0,0 +1,138 @@
+# encoding: utf-8
+#
+# Statistical Analysis of Polling Results (SAPoR)
+# Copyright (C) 2014 Filip van Laenen <f.a.vanlaenen@ieee.org>
+#
+# This file is part of SAPoR.
+#
+# SAPoR is free software: you can redistribute it and/or modify it under the
+# terms of the GNU General Public License as published by the Free Software
+# Foundation, either version 3 of the License, or (at your option) any later
+# version.
+#
+# SAPoR is distributed in the hope that it will be useful, but WITHOUT ANY
+# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
+# A PARTICULAR PURPOSE.  See the GNU General Public License for more details.
+#
+# You can find a copy of the GNU General Public License in /doc/gpl.txt
+#
+
+module Sapor
+  #
+  # Represents a dichotomy.
+  #
+  class Dichotomy
+    def initialize(number, sample_size, population_size)
+      @number = number
+      @sample_size = sample_size
+      @population_size = population_size
+      @distribution = CombinationsDistribution.new
+      middle = @population_size / 2
+      @distribution[middle] = combinations_for(middle)
+    end
+
+    def combinations(value)
+      @distribution[value]
+    end
+
+    def confidence_interval(level = 0.95)
+      value_confidence_interval(level).map { |x| x.to_f / @population_size }
+    end
+
+    def confidence_interval_values(level = 0.95)
+      @distribution.confidence_interval_values(level)
+    end
+
+    def error_estimate
+      estimate_error
+    end
+
+    def most_probable_fraction
+      most_probable_value.to_f / @population_size
+    end
+
+    def most_probable_value
+      @distribution.most_probable_value
+    end
+
+    def refine
+      new_values = find_refinement_values
+      new_values.each do |value|
+        @distribution[value] = combinations_for(value)
+      end
+    end
+
+    def threshold_probability(threshold)
+      @distribution.threshold_probability(threshold, @population_size)
+    end
+
+    def value_confidence_interval(level = 0.95)
+      @distribution.confidence_interval(level, @population_size)
+    end
+
+    def values
+      @distribution.values
+    end
+
+    private
+
+    def combinations_for(value)
+      dual_value = @population_size - value
+      dual_number = @sample_size - @number
+      if value < @number || dual_value < dual_number
+        0.to_lf
+      else
+        BinomialsCache.binomial(value, @number) * \
+          BinomialsCache.binomial(dual_value, dual_number)
+      end
+    end
+
+    def find_refinement_value_at_bottom
+      bottom = values.min
+      if bottom == 0
+        []
+      else
+        [(bottom.to_f / 3).round]
+      end
+    end
+
+    def find_refinement_values_between(low, high)
+      new_low = ((2 * low + high).to_f / 3).round
+      new_high = ((2 * high + low).to_f / 3).round
+      refinement_values = []
+      refinement_values << new_high unless new_high == high
+      refinement_values << new_low unless new_low == new_high || new_low == low
+      refinement_values
+    end
+
+    def find_refinement_values_in_between
+      sorted_values = values.sort
+      refinement_values = (0..(@distribution.size - 2)).to_a.map do |i|
+        find_refinement_values_between(sorted_values[i], sorted_values[i + 1])
+      end
+      refinement_values.flatten
+    end
+
+    def find_refinement_value_at_top
+      top = values.max
+      if top == @population_size
+        []
+      else
+        [((2.to_f * @population_size + top) / 3).round]
+      end
+    end
+
+    def find_refinement_values
+      find_refinement_value_at_bottom + find_refinement_values_in_between +
+        find_refinement_value_at_top
+    end
+
+    def estimate_error
+      if @distribution.size == @population_size + 1
+        0
+      else
+        1.to_f / @distribution.size
+      end
+    end
+  end
+end

data/lib/sapor/first_past_the_post.rb

@@ -0,0 +1,78 @@
+# encoding: utf-8
+#
+# Statistical Analysis of Polling Results (SAPoR)
+# Copyright (C) 2014 Filip van Laenen <f.a.vanlaenen@ieee.org>
+#
+# This file is part of SAPoR.
+#
+# SAPoR is free software: you can redistribute it and/or modify it under the
+# terms of the GNU General Public License as published by the Free Software
+# Foundation, either version 3 of the License, or (at your option) any later
+# version.
+#
+# SAPoR is distributed in the hope that it will be useful, but WITHOUT ANY
+# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
+# A PARTICULAR PURPOSE.  See the GNU General Public License for more details.
+#
+# You can find a copy of the GNU General Public License in /doc/gpl.txt
+#
+
+module Sapor
+  #
+  # Class representing an electoral system based on the First-Past-The-Post
+  # system.
+  #
+  class FirstPastThePost
+    def initialize(last_election_result, last_detailed_election_result)
+      @last_election_result = last_election_result
+      @last_detailed_election_result = last_detailed_election_result
+    end
+
+    def project(simulation)
+      multiplicators = calculate_multiplicators(simulation)
+      result = create_empty_result(simulation)
+      @last_detailed_election_result.each_value do |local_last_result|
+        winner = local_winner(local_last_result, multiplicators)
+        result[winner] += 1
+      end
+      result
+    end
+
+    private
+
+    def calculate_multiplicators(simulation)
+      simulation_sum = simulation.values.inject(:+)
+      last_election_sum = @last_election_result.values.inject(:+)
+      multiplicators = {}
+      simulation.each_key do |choice|
+        new_fraction = simulation[choice].to_f / simulation_sum
+        last_fraction = @last_election_result[choice].to_f / last_election_sum
+        multiplicators[choice] = new_fraction / last_fraction
+      end
+      multiplicators
+    end
+
+    def create_empty_result(simulation)
+      result = {}
+      simulation.each_key do |choice|
+        result[choice] = 0
+      end
+      result[OTHER] = 0
+      result
+    end
+
+    def local_winner(local_last_result, multiplicators)
+      new_local_result = {}
+      local_last_result.each_pair do |choice, votes|
+        if multiplicators.key?(choice)
+          new_local_result[choice] = votes * multiplicators[choice]
+        else
+          new_local_result[choice] = votes
+        end
+      end
+      max_votes = new_local_result.values.max
+      winner = new_local_result.select { |_k, v| v.equal?(max_votes) }.keys.first
+      multiplicators.key?(winner) ? winner : OTHER
+    end
+  end
+end

data/lib/sapor/leveled_proportional.rb

@@ -0,0 +1,64 @@
+# encoding: utf-8
+#
+# Statistical Analysis of Polling Results (SAPoR)
+# Copyright (C) 2014 Filip van Laenen <f.a.vanlaenen@ieee.org>
+#
+# This file is part of SAPoR.
+#
+# SAPoR is free software: you can redistribute it and/or modify it under the
+# terms of the GNU General Public License as published by the Free Software
+# Foundation, either version 3 of the License, or (at your option) any later
+# version.
+#
+# SAPoR is distributed in the hope that it will be useful, but WITHOUT ANY
+# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
+# A PARTICULAR PURPOSE.  See the GNU General Public License for more details.
+#
+# You can find a copy of the GNU General Public License in /doc/gpl.txt
+#
+
+module Sapor
+  #
+  # Class representing a proportional electoral system with a second round of
+  # leveling seats.
+  #
+  class LeveledProportional
+    def initialize(last_election_result, last_detailed_election_result,
+                   seat_distribution, leveling_seats, leveling_threshold,
+                   denominators_class)
+      @proportional = Proportional.new(last_election_result,
+                                       last_detailed_election_result,
+                                       seat_distribution, denominators_class)
+      @leveling_seats = leveling_seats
+      @leveling_threshold = leveling_threshold
+      @denominators_class = denominators_class
+    end
+
+    def project(simulation)
+      result = @proportional.project(simulation)
+      threshold = @leveling_threshold * simulation.values.inject(:+)
+      quotients = []
+      simulation.each_pair do |choice, votes|
+        next if votes < threshold
+        denominators(result[choice]).each do |d|
+          quotients << [choice, votes.to_f / d]
+        end
+      end
+      seats = quotients.sort { |a, b| b.last <=> a.last }.map(&:first).slice(0, @leveling_seats)
+      seats.each do |seat|
+        if result.key?(seat)
+          result[seat] += 1
+        else
+          result[seat] = 1
+        end
+      end
+      result
+    end
+
+    private
+
+    def denominators(seats)
+      @denominators_class.get(seats + @leveling_seats).reverse_each.take(@leveling_seats)
+    end
+  end
+end

data/lib/sapor/log4r_logger.rb

@@ -0,0 +1,49 @@
+# encoding: utf-8
+#
+# Statistical Analysis of Polling Results (SAPoR)
+# Copyright (C) 2014 Filip van Laenen <f.a.vanlaenen@ieee.org>
+#
+# This file is part of SAPoR.
+#
+# SAPoR is free software: you can redistribute it and/or modify it under the
+# terms of the GNU General Public License as published by the Free Software
+# Foundation, either version 3 of the License, or (at your option) any later
+# version.
+#
+# SAPoR is distributed in the hope that it will be useful, but WITHOUT ANY
+# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
+# A PARTICULAR PURPOSE.  See the GNU General Public License for more details.
+#
+# You can find a copy of the GNU General Public License in /doc/gpl.txt
+#
+
+module Sapor
+  #
+  # Builder to create Log4rLoggers.
+  #
+  class Log4rLoggerBuilder
+    def create_logger
+      Log4rLogger.new
+    end
+  end
+
+  require 'rubygems'
+  require 'log4r'
+  #
+  # Logger using Log4r.
+  #
+  class Log4rLogger
+    def initialize
+      @logger = Log4r::Logger.new 'stdout'
+      stdout_outputter = Log4r::Outputter.stdout
+      @logger.outputters = stdout_outputter
+      stdout_format = Log4r::PatternFormatter.new(pattern: '%d %l: %m')
+      stdout_outputter.formatter = stdout_format
+      @logger.level = Log4r::INFO
+    end
+
+    def info(message)
+      @logger.info(message)
+    end
+  end
+end

data/lib/sapor/log_facade.rb

@@ -0,0 +1,40 @@
+# encoding: utf-8
+#
+# Statistical Analysis of Polling Results (SAPoR)
+# Copyright (C) 2014 Filip van Laenen <f.a.vanlaenen@ieee.org>
+#
+# This file is part of SAPoR.
+#
+# SAPoR is free software: you can redistribute it and/or modify it under the
+# terms of the GNU General Public License as published by the Free Software
+# Foundation, either version 3 of the License, or (at your option) any later
+# version.
+#
+# SAPoR is distributed in the hope that it will be useful, but WITHOUT ANY
+# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
+# A PARTICULAR PURPOSE.  See the GNU General Public License for more details.
+#
+# You can find a copy of the GNU General Public License in /doc/gpl.txt
+#
+
+module Sapor
+  #
+  # A facade for logging.
+  #
+  class LogFacade
+    @logger_builder = nil
+
+    class << self
+      attr_writer :logger_builder
+    end
+
+    def self.builder
+      @logger_builder = Log4rLoggerBuilder.new if @logger_builder.nil?
+      @logger_builder
+    end
+
+    def self.create_logger
+      builder.create_logger
+    end
+  end
+end