more_math 1.8.0 → 1.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: bcc2d84dad36dba3b74a49a1de06431135c220cb4b027251c30fb828a8078bb0
-  data.tar.gz: 075dcb1e3dbdd99870de43f04ae5d5481c8e02fa712fd70dab95c214e0d39da7
+  metadata.gz: bd844028040726f15a03d4260e794d2b6dd47edf0ddac071be3fc2d3e1742be5
+  data.tar.gz: 9fc2b5f24a5ffd586cfcd7f700dcb85510f799a8f1af356289233316d6f91966
 SHA512:
-  metadata.gz: 5a354f264cca954a2f5bb1633131117c533e02375b55281c5a070e60ab64439d9e6a50cf8a6b654004f5d0d565e2cd6179927b6987a8beb118093a70c66a4ee2
-  data.tar.gz: 00ed6ef336035013ac18608cdcc1b52c4eb11947cc71f9d9bd5dce1c330be91d3669efb4b613930c0d9b74e227c02eef7d0aa501663c883b1f215bfecad6d00d
+  metadata.gz: ddd7116481e881af48ab5cd854f4ff6def832c30e491767bae3835f17bd2f12ba19d171c9b765d3ef41b1f50b33e6a5fa9ca73a7c6c9817379da13b0aa63e509
+  data.tar.gz: 0346e146c89234d85eb9ab38a69598f2dc879ea3335c23cddc36cc29ddfaf1cb0cd3e44fb7bc17a4634c3cfbb37a4ff2d0916d04f630b42dd1a7de7b2d8da341

data/CHANGES.md

@@ -1,5 +1,16 @@
 # Changes
 
+## 2026-01-16 v1.9.0
+
+- Added support for array inputs in entropy calculation methods by checking
+  `text.respond_to?(:chars)` and using raw arrays when appropriate
+- Added `MoreMath::Entropy.entropy_ratio_minimum` method to provide
+  conservative lower bound accounting for sampling error
+- Updated `entropy_ratio` method to use `text.size` instead of
+  `text.each_char.size` for consistency
+- Added comprehensive tests for new minimum entropy
+  ratio methods
+
 ## 2026-01-15 v1.8.0
 
 - Added tests for `entropy_ratio` and `lambert_w` method inclusion/extension

data/lib/more_math/entropy.rb

@@ -37,7 +37,12 @@ module MoreMath
     # @param text [String] The input text to calculate entropy for
     # @return [Float] The Shannon entropy in bits
     def entropy(text)
-      chars = text.chars
+      chars = nil
+      if text.respond_to?(:chars)
+        chars = text.chars
+      else
+        chars = text
+      end
       size  = chars.size
 
       chars.each_with_object(Hash.new(0.0)) { |c, h| h[c] += 1 }.
@@ -64,7 +69,6 @@ module MoreMath
       -1.0 * size * frequency * Math.log2(frequency)
     end
 
-
     # Calculates the normalized entropy ratio of a text string.
     #
     # The ratio is calculated as actual entropy divided by ideal entropy,
@@ -86,13 +90,44 @@ module MoreMath
     #
     # @param text [String] The input text to calculate entropy ratio for
     # @param size [Integer] The size of the character set to normalize against.
-    #   Defaults to the total length of the text (`text.each_char.size`), which
+    #   Defaults to the total length of the text (`text.size`), which
     #   normalizes the entropy relative to the text's own character space.
     #   This allows comparison of texts with different lengths on the same scale.
     # @return [Float] Normalized entropy ratio between 0 and 1
-    def entropy_ratio(text, size: text.each_char.size)
+    def entropy_ratio(text, size: text.size)
       size <= 1 and return 0.0
       entropy(text) / entropy_ideal(size)
     end
+
+    # Calculates the minimum entropy ratio with confidence interval adjustment
+    #
+    # This method computes a adjusted entropy ratio that accounts for
+    # statistical uncertainty by incorporating the standard error and a
+    # confidence level.
+    #
+    # @param text [String] The input text to calculate entropy ratio for
+    # @param size [Integer] The size of the character set to normalize against
+    # @param alpha [Float] The significance level for the confidence interval (default: 0.05)
+    # @return [Float] The adjusted entropy ratio within the confidence interval
+    # @raise [ArgumentError] When alphabet size is less than 2
+    # @raise [ArgumentError] When text is empty
+    def entropy_ratio_minimum(text, size: text.size, alpha: 0.05)
+      raise ArgumentError, 'alphabet size must be ≥ 2' if size < 2
+      raise ArgumentError, 'text must not be empty'    if text.empty?
+
+      n = text.size
+      k = size
+
+      ratio = MoreMath::Functions.entropy_ratio(text, size: k)
+
+      logk = Math.log2(k)
+      diff = logk - 1.0 / Math.log(2)
+      var  = (diff ** 2) / (logk ** 2) * (1.0 - 1.0 / k) / n
+      se   = Math.sqrt(var)          # standard error
+
+      z = STD_NORMAL_DISTRIBUTION.inverse_probability(1.0 - alpha / 2.0)
+
+      (ratio - z * se).clamp(0, 1)
+    end
   end
 end

data/lib/more_math/version.rb

@@ -1,6 +1,6 @@
 module MoreMath
   # MoreMath version
-  VERSION         = '1.8.0'
+  VERSION         = '1.9.0'
   VERSION_ARRAY   = VERSION.split('.').map(&:to_i) # :nodoc:
   VERSION_MAJOR   = VERSION_ARRAY[0] # :nodoc:
   VERSION_MINOR   = VERSION_ARRAY[1] # :nodoc:

data/more_math.gemspec

@@ -1,9 +1,9 @@
 # -*- encoding: utf-8 -*-
-# stub: more_math 1.8.0 ruby lib
+# stub: more_math 1.9.0 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "more_math".freeze
-  s.version = "1.8.0".freeze
+  s.version = "1.9.0".freeze
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0".freeze) if s.respond_to? :required_rubygems_version=
   s.require_paths = ["lib".freeze]
@@ -12,14 +12,14 @@ Gem::Specification.new do |s|
   s.description = "Library that provides more mathematical functions/algorithms than standard Ruby.".freeze
   s.email = "flori@ping.de".freeze
   s.extra_rdoc_files = ["README.md".freeze, "lib/more_math.rb".freeze, "lib/more_math/cantor_pairing_function.rb".freeze, "lib/more_math/constants/functions_constants.rb".freeze, "lib/more_math/continued_fraction.rb".freeze, "lib/more_math/distributions.rb".freeze, "lib/more_math/entropy.rb".freeze, "lib/more_math/exceptions.rb".freeze, "lib/more_math/functions.rb".freeze, "lib/more_math/histogram.rb".freeze, "lib/more_math/lambert.rb".freeze, "lib/more_math/linear_regression.rb".freeze, "lib/more_math/newton_bisection.rb".freeze, "lib/more_math/numberify_string_function.rb".freeze, "lib/more_math/permutation.rb".freeze, "lib/more_math/ranking_common.rb".freeze, "lib/more_math/sequence.rb".freeze, "lib/more_math/sequence/moving_average.rb".freeze, "lib/more_math/sequence/refinement.rb".freeze, "lib/more_math/string_numeral.rb".freeze, "lib/more_math/subset.rb".freeze, "lib/more_math/version.rb".freeze]
-  s.files = ["CHANGES.md".freeze, "Gemfile".freeze, "LICENSE".freeze, "README.md".freeze, "Rakefile".freeze, "lib/more_math.rb".freeze, "lib/more_math/cantor_pairing_function.rb".freeze, "lib/more_math/constants/functions_constants.rb".freeze, "lib/more_math/continued_fraction.rb".freeze, "lib/more_math/distributions.rb".freeze, "lib/more_math/entropy.rb".freeze, "lib/more_math/exceptions.rb".freeze, "lib/more_math/functions.rb".freeze, "lib/more_math/histogram.rb".freeze, "lib/more_math/lambert.rb".freeze, "lib/more_math/linear_regression.rb".freeze, "lib/more_math/newton_bisection.rb".freeze, "lib/more_math/numberify_string_function.rb".freeze, "lib/more_math/permutation.rb".freeze, "lib/more_math/ranking_common.rb".freeze, "lib/more_math/sequence.rb".freeze, "lib/more_math/sequence/moving_average.rb".freeze, "lib/more_math/sequence/refinement.rb".freeze, "lib/more_math/string_numeral.rb".freeze, "lib/more_math/subset.rb".freeze, "lib/more_math/version.rb".freeze, "more_math.gemspec".freeze, "tests/cantor_pairing_function_test.rb".freeze, "tests/continued_fraction_test.rb".freeze, "tests/distribution_test.rb".freeze, "tests/entropy_test.rb".freeze, "tests/functions_test.rb".freeze, "tests/histogram_test.rb".freeze, "tests/lambert_test.rb".freeze, "tests/newton_bisection_test.rb".freeze, "tests/numberify_string_function_test.rb".freeze, "tests/permutation_test.rb".freeze, "tests/sequence/refinement_test.rb".freeze, "tests/sequence_moving_average_test.rb".freeze, "tests/sequence_test.rb".freeze, "tests/string_numeral_test.rb".freeze, "tests/subset_test.rb".freeze, "tests/test_helper.rb".freeze]
+  s.files = ["CHANGES.md".freeze, "Gemfile".freeze, "LICENSE".freeze, "README.md".freeze, "Rakefile".freeze, "lib/more_math.rb".freeze, "lib/more_math/cantor_pairing_function.rb".freeze, "lib/more_math/constants/functions_constants.rb".freeze, "lib/more_math/continued_fraction.rb".freeze, "lib/more_math/distributions.rb".freeze, "lib/more_math/entropy.rb".freeze, "lib/more_math/exceptions.rb".freeze, "lib/more_math/functions.rb".freeze, "lib/more_math/histogram.rb".freeze, "lib/more_math/lambert.rb".freeze, "lib/more_math/linear_regression.rb".freeze, "lib/more_math/newton_bisection.rb".freeze, "lib/more_math/numberify_string_function.rb".freeze, "lib/more_math/permutation.rb".freeze, "lib/more_math/ranking_common.rb".freeze, "lib/more_math/sequence.rb".freeze, "lib/more_math/sequence/moving_average.rb".freeze, "lib/more_math/sequence/refinement.rb".freeze, "lib/more_math/string_numeral.rb".freeze, "lib/more_math/subset.rb".freeze, "lib/more_math/version.rb".freeze, "more_math.gemspec".freeze, "tests/cantor_pairing_function_test.rb".freeze, "tests/continued_fraction_test.rb".freeze, "tests/distribution_test.rb".freeze, "tests/entropy_test.rb".freeze, "tests/functions_test.rb".freeze, "tests/histogram_test.rb".freeze, "tests/lambert_test.rb".freeze, "tests/newton_bisection_test.rb".freeze, "tests/numberify_string_function_test.rb".freeze, "tests/permutation_test.rb".freeze, "tests/sequence_moving_average_test.rb".freeze, "tests/sequence_refinement_test.rb".freeze, "tests/sequence_test.rb".freeze, "tests/string_numeral_test.rb".freeze, "tests/subset_test.rb".freeze, "tests/test_helper.rb".freeze]
   s.homepage = "https://github.com/flori/more_math".freeze
   s.licenses = ["MIT".freeze]
   s.rdoc_options = ["--title".freeze, "MoreMath -- More Math in Ruby".freeze, "--main".freeze, "README.md".freeze]
   s.required_ruby_version = Gem::Requirement.new(">= 2.0".freeze)
   s.rubygems_version = "4.0.3".freeze
   s.summary = "Library that provides more mathematics.".freeze
-  s.test_files = ["tests/cantor_pairing_function_test.rb".freeze, "tests/continued_fraction_test.rb".freeze, "tests/distribution_test.rb".freeze, "tests/entropy_test.rb".freeze, "tests/functions_test.rb".freeze, "tests/histogram_test.rb".freeze, "tests/lambert_test.rb".freeze, "tests/newton_bisection_test.rb".freeze, "tests/numberify_string_function_test.rb".freeze, "tests/permutation_test.rb".freeze, "tests/sequence/refinement_test.rb".freeze, "tests/sequence_moving_average_test.rb".freeze, "tests/sequence_test.rb".freeze, "tests/string_numeral_test.rb".freeze, "tests/subset_test.rb".freeze, "tests/test_helper.rb".freeze]
+  s.test_files = ["tests/cantor_pairing_function_test.rb".freeze, "tests/continued_fraction_test.rb".freeze, "tests/distribution_test.rb".freeze, "tests/entropy_test.rb".freeze, "tests/functions_test.rb".freeze, "tests/histogram_test.rb".freeze, "tests/lambert_test.rb".freeze, "tests/newton_bisection_test.rb".freeze, "tests/numberify_string_function_test.rb".freeze, "tests/permutation_test.rb".freeze, "tests/sequence_moving_average_test.rb".freeze, "tests/sequence_refinement_test.rb".freeze, "tests/sequence_test.rb".freeze, "tests/string_numeral_test.rb".freeze, "tests/subset_test.rb".freeze, "tests/test_helper.rb".freeze]
 
   s.specification_version = 4
 

data/tests/entropy_test.rb

@@ -1,6 +1,7 @@
 #!/usr/bin/env ruby
 
 require 'test_helper'
+require 'tins'
 
 class EntropyTest < Test::Unit::TestCase
   include MoreMath::Functions
@@ -11,14 +12,16 @@ class EntropyTest < Test::Unit::TestCase
     @string = 'Lorem ipsum dolor sit amet, consectetur adipiscing elit'
     @high   = 'The quick brown fox jumps over the lazy dog'
     @random = "\xAC-\x8A\xF5\xA8\xF7\\\e\xB5\x8CI\x06\xA7"
+    @hi     = "こんにちは世界"
   end
 
   def test_entropy
     assert_equal 0, entropy(@empty)
     assert_equal 0, entropy(@low)
-    assert_in_delta 3.9514, entropy(@string), 1E-3
-    assert_in_delta 4.4319, entropy(@high), 1E-3
+    assert_in_delta 3.951, entropy(@string), 1E-3
+    assert_in_delta 4.431, entropy(@high), 1E-3
     assert_in_delta 3.700, entropy(@random), 1E-3
+    assert_in_delta 2.807, entropy(@hi), 1E-3
   end
 
   def test_entropy_ideal
@@ -26,18 +29,42 @@ class EntropyTest < Test::Unit::TestCase
     assert_equal 0, entropy_ideal(0)
     assert_equal 0, entropy_ideal(0.5)
     assert_equal 0, entropy_ideal(1)
-    assert_in_delta 1, entropy_ideal(2), 1E-3
+    assert_in_delta 1,     entropy_ideal(2), 1E-3
     assert_in_delta 1.584, entropy_ideal(3), 1E-3
-    assert_in_delta 3, entropy_ideal(8), 1E-3
+    assert_in_delta 3,     entropy_ideal(8), 1E-3
     assert_in_delta 3.321, entropy_ideal(10), 1E-3
-    assert_in_delta 4, entropy_ideal(16), 1E-3
+    assert_in_delta 4,     entropy_ideal(16), 1E-3
   end
 
   def test_entropy_ratio
-    assert_equal 0, entropy_ratio(@empty)
-    assert_equal 0, entropy_ratio(@low)
-    assert_in_delta 0.6834, entropy_ratio(@string), 1E-3
-    assert_in_delta 0.8167, entropy_ratio(@high), 1E-3
-    assert_in_delta 1.0, entropy_ratio(@random), 1E-3
+    assert_equal 0,        entropy_ratio(@empty)
+    assert_equal 0,        entropy_ratio(@low, size: 128)
+    assert_in_delta 0.564, entropy_ratio(@string, size: 128), 1E-3
+    assert_in_delta 0.633, entropy_ratio(@high, size: 128), 1E-3
+    assert_in_delta 1.0,   entropy_ratio(@random), 1E-3
+    assert_in_delta 0.462, entropy_ratio(@random, size: 256), 1E-3
+    assert_in_delta 0.253, entropy_ratio(@hi, size: 2_136), 1E-3
+  end
+
+  def test_entropy_ratio_minimum_basic
+    # A fairly long random token over a 16‑symbol alphabet
+    token = Tins::Token.new(length: 128, alphabet: Tins::Token::BASE16_LOWERCASE_ALPHABET)
+
+    limit = entropy_ratio_minimum(token, size: 16)
+
+    # Bounds must be ≧ 0
+    assert_operator limit, :>=, 0.0
+
+    # The observed ratio should be ≧ limit
+    ratio = entropy_ratio(token, size: 16)
+    assert_operator ratio, :>=, limit
+  end
+
+  def test_entropy_ratio_minimum_small
+    # Very short string – the interval will stay below 1.0
+    str = 'a'          # alphabet size 2 (binary)
+    limit = entropy_ratio_minimum(str, size: 2)
+
+    assert_equal 0.0, limit
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: more_math
 version: !ruby/object:Gem::Version
-  version: 1.8.0
+  version: 1.9.0
 platform: ruby
 authors:
 - Florian Frank
@@ -201,8 +201,8 @@ files:
 - tests/newton_bisection_test.rb
 - tests/numberify_string_function_test.rb
 - tests/permutation_test.rb
-- tests/sequence/refinement_test.rb
 - tests/sequence_moving_average_test.rb
+- tests/sequence_refinement_test.rb
 - tests/sequence_test.rb
 - tests/string_numeral_test.rb
 - tests/subset_test.rb
@@ -243,8 +243,8 @@ test_files:
 - tests/newton_bisection_test.rb
 - tests/numberify_string_function_test.rb
 - tests/permutation_test.rb
-- tests/sequence/refinement_test.rb
 - tests/sequence_moving_average_test.rb
+- tests/sequence_refinement_test.rb
 - tests/sequence_test.rb
 - tests/string_numeral_test.rb
 - tests/subset_test.rb