wikipedia-vandalism_detection 0.1.0-java

Sign up to get free protection for your applications and to get access to all the features.
Files changed (245) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +19 -0
  3. data/.rspec +2 -0
  4. data/.rubocop.yml +35 -0
  5. data/.travis.yml +6 -0
  6. data/Gemfile +4 -0
  7. data/LICENSE.txt +4 -0
  8. data/README.md +288 -0
  9. data/Rakefile +11 -0
  10. data/config/wikipedia-vandalism-detection.yml.example +103 -0
  11. data/lib/java/SMOTE.jar +0 -0
  12. data/lib/java/balancedRandomForest.jar +0 -0
  13. data/lib/java/diffutils-1.3.0.jar +0 -0
  14. data/lib/java/oneClassClassifier.jar +0 -0
  15. data/lib/java/realAdaBoost.jar +0 -0
  16. data/lib/java/swc-engine-1.1.0-jar-with-dependencies.jar +0 -0
  17. data/lib/java/sweble-wikitext-extractor.jar +0 -0
  18. data/lib/weka/classifiers/meta/one_class_classifier.rb +21 -0
  19. data/lib/weka/classifiers/meta/real_ada_boost.rb +15 -0
  20. data/lib/weka/classifiers/trees/balanced_random_forest.rb +16 -0
  21. data/lib/weka/filters/supervised/instance/smote.rb +15 -0
  22. data/lib/wikipedia/vandalism_detection/algorithms/kullback_leibler_divergence.rb +103 -0
  23. data/lib/wikipedia/vandalism_detection/algorithms.rb +12 -0
  24. data/lib/wikipedia/vandalism_detection/classifier.rb +202 -0
  25. data/lib/wikipedia/vandalism_detection/configuration.rb +350 -0
  26. data/lib/wikipedia/vandalism_detection/diff.rb +36 -0
  27. data/lib/wikipedia/vandalism_detection/edit.rb +81 -0
  28. data/lib/wikipedia/vandalism_detection/evaluator.rb +640 -0
  29. data/lib/wikipedia/vandalism_detection/exceptions.rb +47 -0
  30. data/lib/wikipedia/vandalism_detection/feature_calculator.rb +94 -0
  31. data/lib/wikipedia/vandalism_detection/features/all_wordlists_frequency.rb +22 -0
  32. data/lib/wikipedia/vandalism_detection/features/all_wordlists_impact.rb +21 -0
  33. data/lib/wikipedia/vandalism_detection/features/anonymity.rb +17 -0
  34. data/lib/wikipedia/vandalism_detection/features/anonymity_previous.rb +32 -0
  35. data/lib/wikipedia/vandalism_detection/features/article_size.rb +17 -0
  36. data/lib/wikipedia/vandalism_detection/features/bad_frequency.rb +21 -0
  37. data/lib/wikipedia/vandalism_detection/features/bad_impact.rb +20 -0
  38. data/lib/wikipedia/vandalism_detection/features/base.rb +61 -0
  39. data/lib/wikipedia/vandalism_detection/features/biased_frequency.rb +21 -0
  40. data/lib/wikipedia/vandalism_detection/features/biased_impact.rb +21 -0
  41. data/lib/wikipedia/vandalism_detection/features/blanking.rb +26 -0
  42. data/lib/wikipedia/vandalism_detection/features/character_diversity.rb +23 -0
  43. data/lib/wikipedia/vandalism_detection/features/character_sequence.rb +19 -0
  44. data/lib/wikipedia/vandalism_detection/features/comment_bad_frequency.rb +21 -0
  45. data/lib/wikipedia/vandalism_detection/features/comment_biased_frequency.rb +21 -0
  46. data/lib/wikipedia/vandalism_detection/features/comment_length.rb +16 -0
  47. data/lib/wikipedia/vandalism_detection/features/comment_markup_frequency.rb +30 -0
  48. data/lib/wikipedia/vandalism_detection/features/comment_pronoun_frequency.rb +21 -0
  49. data/lib/wikipedia/vandalism_detection/features/comment_sex_frequency.rb +21 -0
  50. data/lib/wikipedia/vandalism_detection/features/comment_vulgarism_frequency.rb +21 -0
  51. data/lib/wikipedia/vandalism_detection/features/compressibility.rb +31 -0
  52. data/lib/wikipedia/vandalism_detection/features/contains_base.rb +16 -0
  53. data/lib/wikipedia/vandalism_detection/features/copyedit.rb +17 -0
  54. data/lib/wikipedia/vandalism_detection/features/digit_ratio.rb +23 -0
  55. data/lib/wikipedia/vandalism_detection/features/edits_per_user.rb +72 -0
  56. data/lib/wikipedia/vandalism_detection/features/emoticons_frequency.rb +27 -0
  57. data/lib/wikipedia/vandalism_detection/features/emoticons_impact.rb +29 -0
  58. data/lib/wikipedia/vandalism_detection/features/frequency_base.rb +18 -0
  59. data/lib/wikipedia/vandalism_detection/features/impact_base.rb +25 -0
  60. data/lib/wikipedia/vandalism_detection/features/inserted_character_distribution.rb +23 -0
  61. data/lib/wikipedia/vandalism_detection/features/inserted_external_links.rb +19 -0
  62. data/lib/wikipedia/vandalism_detection/features/inserted_internal_links.rb +18 -0
  63. data/lib/wikipedia/vandalism_detection/features/inserted_size.rb +19 -0
  64. data/lib/wikipedia/vandalism_detection/features/inserted_words.rb +17 -0
  65. data/lib/wikipedia/vandalism_detection/features/longest_word.rb +21 -0
  66. data/lib/wikipedia/vandalism_detection/features/markup_frequency.rb +29 -0
  67. data/lib/wikipedia/vandalism_detection/features/markup_impact.rb +30 -0
  68. data/lib/wikipedia/vandalism_detection/features/non_alphanumeric_ratio.rb +23 -0
  69. data/lib/wikipedia/vandalism_detection/features/personal_life.rb +17 -0
  70. data/lib/wikipedia/vandalism_detection/features/pronoun_frequency.rb +21 -0
  71. data/lib/wikipedia/vandalism_detection/features/pronoun_impact.rb +20 -0
  72. data/lib/wikipedia/vandalism_detection/features/removed_all_wordlists_frequency.rb +22 -0
  73. data/lib/wikipedia/vandalism_detection/features/removed_bad_frequency.rb +21 -0
  74. data/lib/wikipedia/vandalism_detection/features/removed_biased_frequency.rb +21 -0
  75. data/lib/wikipedia/vandalism_detection/features/removed_character_distribution.rb +23 -0
  76. data/lib/wikipedia/vandalism_detection/features/removed_emoticons_frequency.rb +28 -0
  77. data/lib/wikipedia/vandalism_detection/features/removed_markup_frequency.rb +30 -0
  78. data/lib/wikipedia/vandalism_detection/features/removed_pronoun_frequency.rb +21 -0
  79. data/lib/wikipedia/vandalism_detection/features/removed_sex_frequency.rb +21 -0
  80. data/lib/wikipedia/vandalism_detection/features/removed_size.rb +19 -0
  81. data/lib/wikipedia/vandalism_detection/features/removed_vulgarism_frequency.rb +21 -0
  82. data/lib/wikipedia/vandalism_detection/features/removed_words.rb +17 -0
  83. data/lib/wikipedia/vandalism_detection/features/replacement_similarity.rb +20 -0
  84. data/lib/wikipedia/vandalism_detection/features/reverted.rb +16 -0
  85. data/lib/wikipedia/vandalism_detection/features/revisions_character_distribution.rb +25 -0
  86. data/lib/wikipedia/vandalism_detection/features/same_editor.rb +32 -0
  87. data/lib/wikipedia/vandalism_detection/features/sex_frequency.rb +21 -0
  88. data/lib/wikipedia/vandalism_detection/features/sex_impact.rb +20 -0
  89. data/lib/wikipedia/vandalism_detection/features/size_increment.rb +20 -0
  90. data/lib/wikipedia/vandalism_detection/features/size_ratio.rb +28 -0
  91. data/lib/wikipedia/vandalism_detection/features/term_frequency.rb +31 -0
  92. data/lib/wikipedia/vandalism_detection/features/time_interval.rb +38 -0
  93. data/lib/wikipedia/vandalism_detection/features/time_of_day.rb +21 -0
  94. data/lib/wikipedia/vandalism_detection/features/upper_case_ratio.rb +23 -0
  95. data/lib/wikipedia/vandalism_detection/features/upper_case_words_ratio.rb +33 -0
  96. data/lib/wikipedia/vandalism_detection/features/upper_to_lower_case_ratio.rb +23 -0
  97. data/lib/wikipedia/vandalism_detection/features/vulgarism_frequency.rb +21 -0
  98. data/lib/wikipedia/vandalism_detection/features/vulgarism_impact.rb +21 -0
  99. data/lib/wikipedia/vandalism_detection/features/weekday.rb +19 -0
  100. data/lib/wikipedia/vandalism_detection/features/words_increment.rb +20 -0
  101. data/lib/wikipedia/vandalism_detection/features.rb +66 -0
  102. data/lib/wikipedia/vandalism_detection/instances.rb +121 -0
  103. data/lib/wikipedia/vandalism_detection/page.rb +101 -0
  104. data/lib/wikipedia/vandalism_detection/page_parser.rb +63 -0
  105. data/lib/wikipedia/vandalism_detection/revision.rb +75 -0
  106. data/lib/wikipedia/vandalism_detection/revision_parser.rb +67 -0
  107. data/lib/wikipedia/vandalism_detection/test_dataset.rb +374 -0
  108. data/lib/wikipedia/vandalism_detection/text.rb +23 -0
  109. data/lib/wikipedia/vandalism_detection/training_dataset.rb +282 -0
  110. data/lib/wikipedia/vandalism_detection/version.rb +5 -0
  111. data/lib/wikipedia/vandalism_detection/wikitext_extractor.rb +80 -0
  112. data/lib/wikipedia/vandalism_detection/word_lists/bad.rb +11 -0
  113. data/lib/wikipedia/vandalism_detection/word_lists/biased.rb +20 -0
  114. data/lib/wikipedia/vandalism_detection/word_lists/emoticons.rb +26 -0
  115. data/lib/wikipedia/vandalism_detection/word_lists/markup.rb +19 -0
  116. data/lib/wikipedia/vandalism_detection/word_lists/pronouns.rb +11 -0
  117. data/lib/wikipedia/vandalism_detection/word_lists/sex.rb +10 -0
  118. data/lib/wikipedia/vandalism_detection/word_lists/vulgarism.rb +96 -0
  119. data/lib/wikipedia/vandalism_detection/word_lists.rb +17 -0
  120. data/lib/wikipedia/vandalism_detection.rb +29 -0
  121. data/lib/wikipedia.rb +41 -0
  122. data/spec/factories/edit.rb +19 -0
  123. data/spec/factories/page.rb +12 -0
  124. data/spec/factories/revision.rb +51 -0
  125. data/spec/resources/config/wikipedia-vandalism-detection.yml +35 -0
  126. data/spec/resources/corpora/test/edits.csv +8 -0
  127. data/spec/resources/corpora/test/ground-truth.txt +3 -0
  128. data/spec/resources/corpora/test/revisions/part-1/326471754.txt +199 -0
  129. data/spec/resources/corpora/test/revisions/part-1/326873205.txt +137 -0
  130. data/spec/resources/corpora/test/revisions/part-1/328774035.txt +162 -0
  131. data/spec/resources/corpora/test/revisions/part-2/307084144.txt +137 -0
  132. data/spec/resources/corpora/test/revisions/part-2/326978767.txt +199 -0
  133. data/spec/resources/corpora/test/revisions/part-2/328774110.txt +162 -0
  134. data/spec/resources/corpora/training/annotations.csv +7 -0
  135. data/spec/resources/corpora/training/edits.csv +7 -0
  136. data/spec/resources/corpora/training/revisions/part-1/326471754.txt +199 -0
  137. data/spec/resources/corpora/training/revisions/part-1/326873205.txt +137 -0
  138. data/spec/resources/corpora/training/revisions/part-1/328774035.txt +162 -0
  139. data/spec/resources/corpora/training/revisions/part-2/307084144.txt +137 -0
  140. data/spec/resources/corpora/training/revisions/part-2/326978767.txt +199 -0
  141. data/spec/resources/corpora/training/revisions/part-2/328774110.txt +162 -0
  142. data/spec/resources/page_with_redirects.xml +85 -0
  143. data/spec/resources/redirect_page.xml +59 -0
  144. data/spec/resources/revision_simplified.xml +13 -0
  145. data/spec/resources/sample_revision.txt +137 -0
  146. data/spec/resources/sample_revision_clean_text.txt +1 -0
  147. data/spec/resources/sample_revision_plain_text.txt +183 -0
  148. data/spec/resources/vandalism_on_wikipedia.xml +234 -0
  149. data/spec/resources/vandalism_on_wikipedia_simplified.xml +119 -0
  150. data/spec/resources/wikipedia_tokens.txt +30 -0
  151. data/spec/spec_helper.rb +38 -0
  152. data/spec/support/macros/file_reading.rb +6 -0
  153. data/spec/support/macros/test_configuration.rb +81 -0
  154. data/spec/vandalism_detection/algorithms/kullback_leibler_divergence_spec.rb +34 -0
  155. data/spec/vandalism_detection/classifier_spec.rb +330 -0
  156. data/spec/vandalism_detection/configuration_spec.rb +601 -0
  157. data/spec/vandalism_detection/diff_spec.rb +40 -0
  158. data/spec/vandalism_detection/edit_spec.rb +122 -0
  159. data/spec/vandalism_detection/evaluator_spec.rb +711 -0
  160. data/spec/vandalism_detection/feature_calculator_spec.rb +135 -0
  161. data/spec/vandalism_detection/features/all_wordlists_frequency_spec.rb +30 -0
  162. data/spec/vandalism_detection/features/all_wordlists_impact_spec.rb +52 -0
  163. data/spec/vandalism_detection/features/anonymity_previous_spec.rb +67 -0
  164. data/spec/vandalism_detection/features/anonymity_spec.rb +17 -0
  165. data/spec/vandalism_detection/features/article_size_spec.rb +29 -0
  166. data/spec/vandalism_detection/features/bad_frequency_spec.rb +30 -0
  167. data/spec/vandalism_detection/features/bad_impact_spec.rb +53 -0
  168. data/spec/vandalism_detection/features/base_spec.rb +41 -0
  169. data/spec/vandalism_detection/features/biased_frequency_spec.rb +30 -0
  170. data/spec/vandalism_detection/features/biased_impact_spec.rb +52 -0
  171. data/spec/vandalism_detection/features/blanking_spec.rb +35 -0
  172. data/spec/vandalism_detection/features/character_diversity_spec.rb +30 -0
  173. data/spec/vandalism_detection/features/character_sequence_spec.rb +31 -0
  174. data/spec/vandalism_detection/features/comment_bad_frequency_spec.rb +28 -0
  175. data/spec/vandalism_detection/features/comment_biased_frequency_spec.rb +28 -0
  176. data/spec/vandalism_detection/features/comment_length_spec.rb +21 -0
  177. data/spec/vandalism_detection/features/comment_markup_frequency_spec.rb +28 -0
  178. data/spec/vandalism_detection/features/comment_pronoun_frequency_spec.rb +28 -0
  179. data/spec/vandalism_detection/features/comment_sex_frequency_spec.rb +28 -0
  180. data/spec/vandalism_detection/features/comment_vulgarism_frequency_spec.rb +28 -0
  181. data/spec/vandalism_detection/features/compressibility_spec.rb +38 -0
  182. data/spec/vandalism_detection/features/contains_base_spec.rb +27 -0
  183. data/spec/vandalism_detection/features/copyedit_spec.rb +30 -0
  184. data/spec/vandalism_detection/features/digit_ratio_spec.rb +30 -0
  185. data/spec/vandalism_detection/features/edits_per_user_spec.rb +51 -0
  186. data/spec/vandalism_detection/features/emoticons_frequency_spec.rb +30 -0
  187. data/spec/vandalism_detection/features/emoticons_impact_spec.rb +45 -0
  188. data/spec/vandalism_detection/features/frequency_base_spec.rb +20 -0
  189. data/spec/vandalism_detection/features/impact_base_spec.rb +36 -0
  190. data/spec/vandalism_detection/features/inserted_character_distribution_spec.rb +40 -0
  191. data/spec/vandalism_detection/features/inserted_external_links_spec.rb +29 -0
  192. data/spec/vandalism_detection/features/inserted_internal_links_spec.rb +29 -0
  193. data/spec/vandalism_detection/features/inserted_size_spec.rb +29 -0
  194. data/spec/vandalism_detection/features/inserted_words_spec.rb +29 -0
  195. data/spec/vandalism_detection/features/longest_word_spec.rb +29 -0
  196. data/spec/vandalism_detection/features/markup_frequency_spec.rb +31 -0
  197. data/spec/vandalism_detection/features/markup_impact_spec.rb +53 -0
  198. data/spec/vandalism_detection/features/non_alphanumeric_ratio_spec.rb +30 -0
  199. data/spec/vandalism_detection/features/personal_life_spec.rb +22 -0
  200. data/spec/vandalism_detection/features/pronoun_frequency_spec.rb +30 -0
  201. data/spec/vandalism_detection/features/pronoun_impact_spec.rb +53 -0
  202. data/spec/vandalism_detection/features/removed_all_wordlists_frequency_spec.rb +30 -0
  203. data/spec/vandalism_detection/features/removed_bad_frequency_spec.rb +30 -0
  204. data/spec/vandalism_detection/features/removed_biased_frequency_spec.rb +30 -0
  205. data/spec/vandalism_detection/features/removed_character_distribution_spec.rb +40 -0
  206. data/spec/vandalism_detection/features/removed_emoticons_frequency_spec.rb +30 -0
  207. data/spec/vandalism_detection/features/removed_markup_frequency_spec.rb +30 -0
  208. data/spec/vandalism_detection/features/removed_pronoun_frequency_spec.rb +30 -0
  209. data/spec/vandalism_detection/features/removed_sex_frequency_spec.rb +30 -0
  210. data/spec/vandalism_detection/features/removed_size_spec.rb +29 -0
  211. data/spec/vandalism_detection/features/removed_vulgarism_frequency_spec.rb +30 -0
  212. data/spec/vandalism_detection/features/removed_words_spec.rb +29 -0
  213. data/spec/vandalism_detection/features/replacement_similarity_spec.rb +37 -0
  214. data/spec/vandalism_detection/features/reverted_spec.rb +24 -0
  215. data/spec/vandalism_detection/features/revisions_character_distribution_spec.rb +40 -0
  216. data/spec/vandalism_detection/features/same_editor_spec.rb +71 -0
  217. data/spec/vandalism_detection/features/sex_frequency_spec.rb +30 -0
  218. data/spec/vandalism_detection/features/sex_impact_spec.rb +53 -0
  219. data/spec/vandalism_detection/features/size_increment_spec.rb +29 -0
  220. data/spec/vandalism_detection/features/size_ratio_spec.rb +48 -0
  221. data/spec/vandalism_detection/features/term_frequency_spec.rb +32 -0
  222. data/spec/vandalism_detection/features/time_interval_spec.rb +56 -0
  223. data/spec/vandalism_detection/features/time_of_day_spec.rb +16 -0
  224. data/spec/vandalism_detection/features/upper_case_ratio_spec.rb +30 -0
  225. data/spec/vandalism_detection/features/upper_case_words_ratio_spec.rb +33 -0
  226. data/spec/vandalism_detection/features/upper_to_lower_case_ratio_spec.rb +30 -0
  227. data/spec/vandalism_detection/features/vulgarism_frequency_spec.rb +30 -0
  228. data/spec/vandalism_detection/features/vulgarism_impact_spec.rb +52 -0
  229. data/spec/vandalism_detection/features/weekday_spec.rb +16 -0
  230. data/spec/vandalism_detection/features/words_increment_spec.rb +29 -0
  231. data/spec/vandalism_detection/instances_spec.rb +146 -0
  232. data/spec/vandalism_detection/page_parser_spec.rb +190 -0
  233. data/spec/vandalism_detection/page_spec.rb +134 -0
  234. data/spec/vandalism_detection/revision_parser_spec.rb +53 -0
  235. data/spec/vandalism_detection/revision_spec.rb +148 -0
  236. data/spec/vandalism_detection/test_dataset_spec.rb +227 -0
  237. data/spec/vandalism_detection/text_spec.rb +29 -0
  238. data/spec/vandalism_detection/training_dataset_spec.rb +266 -0
  239. data/spec/vandalism_detection/wikitext_extractor_spec.rb +97 -0
  240. data/spec/weka/classifiers/meta/one_class_classifier_spec.rb +82 -0
  241. data/spec/weka/classifiers/meta/real_ada_boost_spec.rb +37 -0
  242. data/spec/weka/classifiers/trees/balanced_random_forest_spec.rb +37 -0
  243. data/spec/weka/filters/supervised/instance/smote_spec.rb +5 -0
  244. data/wikipedia-vandalism_detection.gemspec +37 -0
  245. metadata +550 -0
@@ -0,0 +1,37 @@
1
+ require 'spec_helper'
2
+
3
+ describe Weka::Classifiers::Meta::RealAdaBoost do
4
+ it { is_expected.to be_a Java::WekaClassifiersMeta::RealAdaBoost }
5
+
6
+ before do
7
+ @config = test_config
8
+ classifier_type = 'Meta::RealAdaBoost'
9
+ options = '-W weka.classifiers.trees.RandomForest -- -I 100'
10
+
11
+ @config.instance_variable_set(:@classifier_type, classifier_type)
12
+ @config.instance_variable_set(:@classifier_options, options)
13
+ @config.instance_variable_set(:@cross_validation_fold, 2)
14
+
15
+ use_configuration(@config)
16
+ end
17
+
18
+ after do
19
+ arff_file = @config.training_output_arff_file
20
+ build_dir = @config.output_base_directory
21
+
22
+ if File.exist?(arff_file)
23
+ File.delete(arff_file)
24
+ directory = File.dirname(arff_file)
25
+ FileUtils.rm_r(directory)
26
+ end
27
+
28
+ FileUtils.rm_r(build_dir) if Dir.exist?(build_dir)
29
+ end
30
+
31
+ it 'can be used to classify vandalism' do
32
+ classifier = Wikipedia::VandalismDetection::Classifier.new
33
+ features = [0.0, 25, 5]
34
+
35
+ expect(classifier.classify(features)).to be_between(0.0, 1.0)
36
+ end
37
+ end
@@ -0,0 +1,37 @@
1
+ require 'spec_helper'
2
+
3
+ describe Weka::Classifiers::Trees::BalancedRandomForest do
4
+ it { is_expected.to be_a Java::WekaClassifiersTrees::BalancedRandomForest }
5
+
6
+ before do
7
+ @config = test_config
8
+ classifier_type = 'Trees::BalancedRandomForest'
9
+ options = '-I 100'
10
+
11
+ @config.instance_variable_set(:@classifier_type, classifier_type)
12
+ @config.instance_variable_set(:@classifier_options, options)
13
+ @config.instance_variable_set(:@cross_validation_fold, 2)
14
+
15
+ use_configuration(@config)
16
+ end
17
+
18
+ after do
19
+ arff_file = @config.training_output_arff_file
20
+ build_dir = @config.output_base_directory
21
+
22
+ if File.exist?(arff_file)
23
+ File.delete(arff_file)
24
+ directory = File.dirname(arff_file)
25
+ FileUtils.rm_r(directory)
26
+ end
27
+
28
+ FileUtils.rm_r(build_dir) if Dir.exist?(build_dir)
29
+ end
30
+
31
+ it 'can be used to classify vandalism' do
32
+ classifier = Wikipedia::VandalismDetection::Classifier.new
33
+ features = [0.0, 25, 5]
34
+
35
+ expect(classifier.classify(features)).to be_between(0.0, 1.0)
36
+ end
37
+ end
@@ -0,0 +1,5 @@
1
+ require 'spec_helper'
2
+
3
+ describe Weka::Filters::Supervised::Instance::SMOTE do
4
+ it { is_expected.to be_a Java::WekaFiltersSupervisedInstance::SMOTE }
5
+ end
@@ -0,0 +1,37 @@
1
+ # coding: utf-8
2
+
3
+ lib = File.expand_path('../lib', __FILE__)
4
+ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
5
+ require 'wikipedia/vandalism_detection/version'
6
+
7
+ Gem::Specification.new do |spec|
8
+ spec.name = 'wikipedia-vandalism_detection'
9
+ spec.version = Wikipedia::VandalismDetection::VERSION
10
+ spec.authors = ['Paul Götze']
11
+ spec.email = ['paul.christoph.goetze@gmail.com']
12
+ spec.summary = %q{Wikipedia vandalism detection with JRuby.}
13
+ spec.description = %q{Wikipedia vandalism detection with JRuby.}
14
+ spec.homepage = 'https://github.com/paulgoetze/wikipedia-vandalism-detection'
15
+ spec.license = 'GPL v3'
16
+
17
+ spec.files = `git ls-files -z`.split("\x0")
18
+ spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
19
+ spec.extensions = ['Rakefile']
20
+ spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
21
+ spec.require_paths = ['lib']
22
+
23
+ spec.platform = 'java'
24
+ spec.required_ruby_version = '~> 2.0'
25
+
26
+ spec.add_runtime_dependency 'weka', '~> 0.7'
27
+ spec.add_runtime_dependency 'nokogiri', '~> 1.8'
28
+ spec.add_runtime_dependency 'activesupport', '>= 4.0'
29
+ spec.add_runtime_dependency 'hotwater', '~> 0.1.2'
30
+ spec.add_runtime_dependency 'parallel', '~> 1.12'
31
+ spec.add_runtime_dependency 'ruby-progressbar', '~> 1.10'
32
+
33
+ spec.add_development_dependency 'bundler', '>= 1.5'
34
+ spec.add_development_dependency 'rake', '>= 10.0'
35
+ spec.add_development_dependency 'rspec', '~> 3.0'
36
+ spec.add_development_dependency 'factory_bot', '~> 4.0'
37
+ end
metadata ADDED
@@ -0,0 +1,550 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: wikipedia-vandalism_detection
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: java
6
+ authors:
7
+ - Paul Götze
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2018-11-16 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ requirement: !ruby/object:Gem::Requirement
15
+ requirements:
16
+ - - "~>"
17
+ - !ruby/object:Gem::Version
18
+ version: '0.7'
19
+ name: weka
20
+ prerelease: false
21
+ type: :runtime
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - "~>"
25
+ - !ruby/object:Gem::Version
26
+ version: '0.7'
27
+ - !ruby/object:Gem::Dependency
28
+ requirement: !ruby/object:Gem::Requirement
29
+ requirements:
30
+ - - "~>"
31
+ - !ruby/object:Gem::Version
32
+ version: '1.8'
33
+ name: nokogiri
34
+ prerelease: false
35
+ type: :runtime
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - "~>"
39
+ - !ruby/object:Gem::Version
40
+ version: '1.8'
41
+ - !ruby/object:Gem::Dependency
42
+ requirement: !ruby/object:Gem::Requirement
43
+ requirements:
44
+ - - ">="
45
+ - !ruby/object:Gem::Version
46
+ version: '4.0'
47
+ name: activesupport
48
+ prerelease: false
49
+ type: :runtime
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - ">="
53
+ - !ruby/object:Gem::Version
54
+ version: '4.0'
55
+ - !ruby/object:Gem::Dependency
56
+ requirement: !ruby/object:Gem::Requirement
57
+ requirements:
58
+ - - "~>"
59
+ - !ruby/object:Gem::Version
60
+ version: 0.1.2
61
+ name: hotwater
62
+ prerelease: false
63
+ type: :runtime
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - "~>"
67
+ - !ruby/object:Gem::Version
68
+ version: 0.1.2
69
+ - !ruby/object:Gem::Dependency
70
+ requirement: !ruby/object:Gem::Requirement
71
+ requirements:
72
+ - - "~>"
73
+ - !ruby/object:Gem::Version
74
+ version: '1.12'
75
+ name: parallel
76
+ prerelease: false
77
+ type: :runtime
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - "~>"
81
+ - !ruby/object:Gem::Version
82
+ version: '1.12'
83
+ - !ruby/object:Gem::Dependency
84
+ requirement: !ruby/object:Gem::Requirement
85
+ requirements:
86
+ - - "~>"
87
+ - !ruby/object:Gem::Version
88
+ version: '1.10'
89
+ name: ruby-progressbar
90
+ prerelease: false
91
+ type: :runtime
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - "~>"
95
+ - !ruby/object:Gem::Version
96
+ version: '1.10'
97
+ - !ruby/object:Gem::Dependency
98
+ requirement: !ruby/object:Gem::Requirement
99
+ requirements:
100
+ - - ">="
101
+ - !ruby/object:Gem::Version
102
+ version: '1.5'
103
+ name: bundler
104
+ prerelease: false
105
+ type: :development
106
+ version_requirements: !ruby/object:Gem::Requirement
107
+ requirements:
108
+ - - ">="
109
+ - !ruby/object:Gem::Version
110
+ version: '1.5'
111
+ - !ruby/object:Gem::Dependency
112
+ requirement: !ruby/object:Gem::Requirement
113
+ requirements:
114
+ - - ">="
115
+ - !ruby/object:Gem::Version
116
+ version: '10.0'
117
+ name: rake
118
+ prerelease: false
119
+ type: :development
120
+ version_requirements: !ruby/object:Gem::Requirement
121
+ requirements:
122
+ - - ">="
123
+ - !ruby/object:Gem::Version
124
+ version: '10.0'
125
+ - !ruby/object:Gem::Dependency
126
+ requirement: !ruby/object:Gem::Requirement
127
+ requirements:
128
+ - - "~>"
129
+ - !ruby/object:Gem::Version
130
+ version: '3.0'
131
+ name: rspec
132
+ prerelease: false
133
+ type: :development
134
+ version_requirements: !ruby/object:Gem::Requirement
135
+ requirements:
136
+ - - "~>"
137
+ - !ruby/object:Gem::Version
138
+ version: '3.0'
139
+ - !ruby/object:Gem::Dependency
140
+ requirement: !ruby/object:Gem::Requirement
141
+ requirements:
142
+ - - "~>"
143
+ - !ruby/object:Gem::Version
144
+ version: '4.0'
145
+ name: factory_bot
146
+ prerelease: false
147
+ type: :development
148
+ version_requirements: !ruby/object:Gem::Requirement
149
+ requirements:
150
+ - - "~>"
151
+ - !ruby/object:Gem::Version
152
+ version: '4.0'
153
+ description: Wikipedia vandalism detection with JRuby.
154
+ email:
155
+ - paul.christoph.goetze@gmail.com
156
+ executables: []
157
+ extensions:
158
+ - Rakefile
159
+ extra_rdoc_files: []
160
+ files:
161
+ - ".gitignore"
162
+ - ".rspec"
163
+ - ".rubocop.yml"
164
+ - ".travis.yml"
165
+ - Gemfile
166
+ - LICENSE.txt
167
+ - README.md
168
+ - Rakefile
169
+ - config/wikipedia-vandalism-detection.yml.example
170
+ - lib/java/SMOTE.jar
171
+ - lib/java/balancedRandomForest.jar
172
+ - lib/java/diffutils-1.3.0.jar
173
+ - lib/java/oneClassClassifier.jar
174
+ - lib/java/realAdaBoost.jar
175
+ - lib/java/swc-engine-1.1.0-jar-with-dependencies.jar
176
+ - lib/java/sweble-wikitext-extractor.jar
177
+ - lib/weka/classifiers/meta/one_class_classifier.rb
178
+ - lib/weka/classifiers/meta/real_ada_boost.rb
179
+ - lib/weka/classifiers/trees/balanced_random_forest.rb
180
+ - lib/weka/filters/supervised/instance/smote.rb
181
+ - lib/wikipedia.rb
182
+ - lib/wikipedia/vandalism_detection.rb
183
+ - lib/wikipedia/vandalism_detection/algorithms.rb
184
+ - lib/wikipedia/vandalism_detection/algorithms/kullback_leibler_divergence.rb
185
+ - lib/wikipedia/vandalism_detection/classifier.rb
186
+ - lib/wikipedia/vandalism_detection/configuration.rb
187
+ - lib/wikipedia/vandalism_detection/diff.rb
188
+ - lib/wikipedia/vandalism_detection/edit.rb
189
+ - lib/wikipedia/vandalism_detection/evaluator.rb
190
+ - lib/wikipedia/vandalism_detection/exceptions.rb
191
+ - lib/wikipedia/vandalism_detection/feature_calculator.rb
192
+ - lib/wikipedia/vandalism_detection/features.rb
193
+ - lib/wikipedia/vandalism_detection/features/all_wordlists_frequency.rb
194
+ - lib/wikipedia/vandalism_detection/features/all_wordlists_impact.rb
195
+ - lib/wikipedia/vandalism_detection/features/anonymity.rb
196
+ - lib/wikipedia/vandalism_detection/features/anonymity_previous.rb
197
+ - lib/wikipedia/vandalism_detection/features/article_size.rb
198
+ - lib/wikipedia/vandalism_detection/features/bad_frequency.rb
199
+ - lib/wikipedia/vandalism_detection/features/bad_impact.rb
200
+ - lib/wikipedia/vandalism_detection/features/base.rb
201
+ - lib/wikipedia/vandalism_detection/features/biased_frequency.rb
202
+ - lib/wikipedia/vandalism_detection/features/biased_impact.rb
203
+ - lib/wikipedia/vandalism_detection/features/blanking.rb
204
+ - lib/wikipedia/vandalism_detection/features/character_diversity.rb
205
+ - lib/wikipedia/vandalism_detection/features/character_sequence.rb
206
+ - lib/wikipedia/vandalism_detection/features/comment_bad_frequency.rb
207
+ - lib/wikipedia/vandalism_detection/features/comment_biased_frequency.rb
208
+ - lib/wikipedia/vandalism_detection/features/comment_length.rb
209
+ - lib/wikipedia/vandalism_detection/features/comment_markup_frequency.rb
210
+ - lib/wikipedia/vandalism_detection/features/comment_pronoun_frequency.rb
211
+ - lib/wikipedia/vandalism_detection/features/comment_sex_frequency.rb
212
+ - lib/wikipedia/vandalism_detection/features/comment_vulgarism_frequency.rb
213
+ - lib/wikipedia/vandalism_detection/features/compressibility.rb
214
+ - lib/wikipedia/vandalism_detection/features/contains_base.rb
215
+ - lib/wikipedia/vandalism_detection/features/copyedit.rb
216
+ - lib/wikipedia/vandalism_detection/features/digit_ratio.rb
217
+ - lib/wikipedia/vandalism_detection/features/edits_per_user.rb
218
+ - lib/wikipedia/vandalism_detection/features/emoticons_frequency.rb
219
+ - lib/wikipedia/vandalism_detection/features/emoticons_impact.rb
220
+ - lib/wikipedia/vandalism_detection/features/frequency_base.rb
221
+ - lib/wikipedia/vandalism_detection/features/impact_base.rb
222
+ - lib/wikipedia/vandalism_detection/features/inserted_character_distribution.rb
223
+ - lib/wikipedia/vandalism_detection/features/inserted_external_links.rb
224
+ - lib/wikipedia/vandalism_detection/features/inserted_internal_links.rb
225
+ - lib/wikipedia/vandalism_detection/features/inserted_size.rb
226
+ - lib/wikipedia/vandalism_detection/features/inserted_words.rb
227
+ - lib/wikipedia/vandalism_detection/features/longest_word.rb
228
+ - lib/wikipedia/vandalism_detection/features/markup_frequency.rb
229
+ - lib/wikipedia/vandalism_detection/features/markup_impact.rb
230
+ - lib/wikipedia/vandalism_detection/features/non_alphanumeric_ratio.rb
231
+ - lib/wikipedia/vandalism_detection/features/personal_life.rb
232
+ - lib/wikipedia/vandalism_detection/features/pronoun_frequency.rb
233
+ - lib/wikipedia/vandalism_detection/features/pronoun_impact.rb
234
+ - lib/wikipedia/vandalism_detection/features/removed_all_wordlists_frequency.rb
235
+ - lib/wikipedia/vandalism_detection/features/removed_bad_frequency.rb
236
+ - lib/wikipedia/vandalism_detection/features/removed_biased_frequency.rb
237
+ - lib/wikipedia/vandalism_detection/features/removed_character_distribution.rb
238
+ - lib/wikipedia/vandalism_detection/features/removed_emoticons_frequency.rb
239
+ - lib/wikipedia/vandalism_detection/features/removed_markup_frequency.rb
240
+ - lib/wikipedia/vandalism_detection/features/removed_pronoun_frequency.rb
241
+ - lib/wikipedia/vandalism_detection/features/removed_sex_frequency.rb
242
+ - lib/wikipedia/vandalism_detection/features/removed_size.rb
243
+ - lib/wikipedia/vandalism_detection/features/removed_vulgarism_frequency.rb
244
+ - lib/wikipedia/vandalism_detection/features/removed_words.rb
245
+ - lib/wikipedia/vandalism_detection/features/replacement_similarity.rb
246
+ - lib/wikipedia/vandalism_detection/features/reverted.rb
247
+ - lib/wikipedia/vandalism_detection/features/revisions_character_distribution.rb
248
+ - lib/wikipedia/vandalism_detection/features/same_editor.rb
249
+ - lib/wikipedia/vandalism_detection/features/sex_frequency.rb
250
+ - lib/wikipedia/vandalism_detection/features/sex_impact.rb
251
+ - lib/wikipedia/vandalism_detection/features/size_increment.rb
252
+ - lib/wikipedia/vandalism_detection/features/size_ratio.rb
253
+ - lib/wikipedia/vandalism_detection/features/term_frequency.rb
254
+ - lib/wikipedia/vandalism_detection/features/time_interval.rb
255
+ - lib/wikipedia/vandalism_detection/features/time_of_day.rb
256
+ - lib/wikipedia/vandalism_detection/features/upper_case_ratio.rb
257
+ - lib/wikipedia/vandalism_detection/features/upper_case_words_ratio.rb
258
+ - lib/wikipedia/vandalism_detection/features/upper_to_lower_case_ratio.rb
259
+ - lib/wikipedia/vandalism_detection/features/vulgarism_frequency.rb
260
+ - lib/wikipedia/vandalism_detection/features/vulgarism_impact.rb
261
+ - lib/wikipedia/vandalism_detection/features/weekday.rb
262
+ - lib/wikipedia/vandalism_detection/features/words_increment.rb
263
+ - lib/wikipedia/vandalism_detection/instances.rb
264
+ - lib/wikipedia/vandalism_detection/page.rb
265
+ - lib/wikipedia/vandalism_detection/page_parser.rb
266
+ - lib/wikipedia/vandalism_detection/revision.rb
267
+ - lib/wikipedia/vandalism_detection/revision_parser.rb
268
+ - lib/wikipedia/vandalism_detection/test_dataset.rb
269
+ - lib/wikipedia/vandalism_detection/text.rb
270
+ - lib/wikipedia/vandalism_detection/training_dataset.rb
271
+ - lib/wikipedia/vandalism_detection/version.rb
272
+ - lib/wikipedia/vandalism_detection/wikitext_extractor.rb
273
+ - lib/wikipedia/vandalism_detection/word_lists.rb
274
+ - lib/wikipedia/vandalism_detection/word_lists/bad.rb
275
+ - lib/wikipedia/vandalism_detection/word_lists/biased.rb
276
+ - lib/wikipedia/vandalism_detection/word_lists/emoticons.rb
277
+ - lib/wikipedia/vandalism_detection/word_lists/markup.rb
278
+ - lib/wikipedia/vandalism_detection/word_lists/pronouns.rb
279
+ - lib/wikipedia/vandalism_detection/word_lists/sex.rb
280
+ - lib/wikipedia/vandalism_detection/word_lists/vulgarism.rb
281
+ - spec/factories/edit.rb
282
+ - spec/factories/page.rb
283
+ - spec/factories/revision.rb
284
+ - spec/resources/config/wikipedia-vandalism-detection.yml
285
+ - spec/resources/corpora/test/edits.csv
286
+ - spec/resources/corpora/test/ground-truth.txt
287
+ - spec/resources/corpora/test/revisions/part-1/326471754.txt
288
+ - spec/resources/corpora/test/revisions/part-1/326873205.txt
289
+ - spec/resources/corpora/test/revisions/part-1/328774035.txt
290
+ - spec/resources/corpora/test/revisions/part-2/307084144.txt
291
+ - spec/resources/corpora/test/revisions/part-2/326978767.txt
292
+ - spec/resources/corpora/test/revisions/part-2/328774110.txt
293
+ - spec/resources/corpora/training/annotations.csv
294
+ - spec/resources/corpora/training/edits.csv
295
+ - spec/resources/corpora/training/revisions/part-1/326471754.txt
296
+ - spec/resources/corpora/training/revisions/part-1/326873205.txt
297
+ - spec/resources/corpora/training/revisions/part-1/328774035.txt
298
+ - spec/resources/corpora/training/revisions/part-2/307084144.txt
299
+ - spec/resources/corpora/training/revisions/part-2/326978767.txt
300
+ - spec/resources/corpora/training/revisions/part-2/328774110.txt
301
+ - spec/resources/page_with_redirects.xml
302
+ - spec/resources/redirect_page.xml
303
+ - spec/resources/revision_simplified.xml
304
+ - spec/resources/sample_revision.txt
305
+ - spec/resources/sample_revision_clean_text.txt
306
+ - spec/resources/sample_revision_plain_text.txt
307
+ - spec/resources/vandalism_on_wikipedia.xml
308
+ - spec/resources/vandalism_on_wikipedia_simplified.xml
309
+ - spec/resources/wikipedia_tokens.txt
310
+ - spec/spec_helper.rb
311
+ - spec/support/macros/file_reading.rb
312
+ - spec/support/macros/test_configuration.rb
313
+ - spec/vandalism_detection/algorithms/kullback_leibler_divergence_spec.rb
314
+ - spec/vandalism_detection/classifier_spec.rb
315
+ - spec/vandalism_detection/configuration_spec.rb
316
+ - spec/vandalism_detection/diff_spec.rb
317
+ - spec/vandalism_detection/edit_spec.rb
318
+ - spec/vandalism_detection/evaluator_spec.rb
319
+ - spec/vandalism_detection/feature_calculator_spec.rb
320
+ - spec/vandalism_detection/features/all_wordlists_frequency_spec.rb
321
+ - spec/vandalism_detection/features/all_wordlists_impact_spec.rb
322
+ - spec/vandalism_detection/features/anonymity_previous_spec.rb
323
+ - spec/vandalism_detection/features/anonymity_spec.rb
324
+ - spec/vandalism_detection/features/article_size_spec.rb
325
+ - spec/vandalism_detection/features/bad_frequency_spec.rb
326
+ - spec/vandalism_detection/features/bad_impact_spec.rb
327
+ - spec/vandalism_detection/features/base_spec.rb
328
+ - spec/vandalism_detection/features/biased_frequency_spec.rb
329
+ - spec/vandalism_detection/features/biased_impact_spec.rb
330
+ - spec/vandalism_detection/features/blanking_spec.rb
331
+ - spec/vandalism_detection/features/character_diversity_spec.rb
332
+ - spec/vandalism_detection/features/character_sequence_spec.rb
333
+ - spec/vandalism_detection/features/comment_bad_frequency_spec.rb
334
+ - spec/vandalism_detection/features/comment_biased_frequency_spec.rb
335
+ - spec/vandalism_detection/features/comment_length_spec.rb
336
+ - spec/vandalism_detection/features/comment_markup_frequency_spec.rb
337
+ - spec/vandalism_detection/features/comment_pronoun_frequency_spec.rb
338
+ - spec/vandalism_detection/features/comment_sex_frequency_spec.rb
339
+ - spec/vandalism_detection/features/comment_vulgarism_frequency_spec.rb
340
+ - spec/vandalism_detection/features/compressibility_spec.rb
341
+ - spec/vandalism_detection/features/contains_base_spec.rb
342
+ - spec/vandalism_detection/features/copyedit_spec.rb
343
+ - spec/vandalism_detection/features/digit_ratio_spec.rb
344
+ - spec/vandalism_detection/features/edits_per_user_spec.rb
345
+ - spec/vandalism_detection/features/emoticons_frequency_spec.rb
346
+ - spec/vandalism_detection/features/emoticons_impact_spec.rb
347
+ - spec/vandalism_detection/features/frequency_base_spec.rb
348
+ - spec/vandalism_detection/features/impact_base_spec.rb
349
+ - spec/vandalism_detection/features/inserted_character_distribution_spec.rb
350
+ - spec/vandalism_detection/features/inserted_external_links_spec.rb
351
+ - spec/vandalism_detection/features/inserted_internal_links_spec.rb
352
+ - spec/vandalism_detection/features/inserted_size_spec.rb
353
+ - spec/vandalism_detection/features/inserted_words_spec.rb
354
+ - spec/vandalism_detection/features/longest_word_spec.rb
355
+ - spec/vandalism_detection/features/markup_frequency_spec.rb
356
+ - spec/vandalism_detection/features/markup_impact_spec.rb
357
+ - spec/vandalism_detection/features/non_alphanumeric_ratio_spec.rb
358
+ - spec/vandalism_detection/features/personal_life_spec.rb
359
+ - spec/vandalism_detection/features/pronoun_frequency_spec.rb
360
+ - spec/vandalism_detection/features/pronoun_impact_spec.rb
361
+ - spec/vandalism_detection/features/removed_all_wordlists_frequency_spec.rb
362
+ - spec/vandalism_detection/features/removed_bad_frequency_spec.rb
363
+ - spec/vandalism_detection/features/removed_biased_frequency_spec.rb
364
+ - spec/vandalism_detection/features/removed_character_distribution_spec.rb
365
+ - spec/vandalism_detection/features/removed_emoticons_frequency_spec.rb
366
+ - spec/vandalism_detection/features/removed_markup_frequency_spec.rb
367
+ - spec/vandalism_detection/features/removed_pronoun_frequency_spec.rb
368
+ - spec/vandalism_detection/features/removed_sex_frequency_spec.rb
369
+ - spec/vandalism_detection/features/removed_size_spec.rb
370
+ - spec/vandalism_detection/features/removed_vulgarism_frequency_spec.rb
371
+ - spec/vandalism_detection/features/removed_words_spec.rb
372
+ - spec/vandalism_detection/features/replacement_similarity_spec.rb
373
+ - spec/vandalism_detection/features/reverted_spec.rb
374
+ - spec/vandalism_detection/features/revisions_character_distribution_spec.rb
375
+ - spec/vandalism_detection/features/same_editor_spec.rb
376
+ - spec/vandalism_detection/features/sex_frequency_spec.rb
377
+ - spec/vandalism_detection/features/sex_impact_spec.rb
378
+ - spec/vandalism_detection/features/size_increment_spec.rb
379
+ - spec/vandalism_detection/features/size_ratio_spec.rb
380
+ - spec/vandalism_detection/features/term_frequency_spec.rb
381
+ - spec/vandalism_detection/features/time_interval_spec.rb
382
+ - spec/vandalism_detection/features/time_of_day_spec.rb
383
+ - spec/vandalism_detection/features/upper_case_ratio_spec.rb
384
+ - spec/vandalism_detection/features/upper_case_words_ratio_spec.rb
385
+ - spec/vandalism_detection/features/upper_to_lower_case_ratio_spec.rb
386
+ - spec/vandalism_detection/features/vulgarism_frequency_spec.rb
387
+ - spec/vandalism_detection/features/vulgarism_impact_spec.rb
388
+ - spec/vandalism_detection/features/weekday_spec.rb
389
+ - spec/vandalism_detection/features/words_increment_spec.rb
390
+ - spec/vandalism_detection/instances_spec.rb
391
+ - spec/vandalism_detection/page_parser_spec.rb
392
+ - spec/vandalism_detection/page_spec.rb
393
+ - spec/vandalism_detection/revision_parser_spec.rb
394
+ - spec/vandalism_detection/revision_spec.rb
395
+ - spec/vandalism_detection/test_dataset_spec.rb
396
+ - spec/vandalism_detection/text_spec.rb
397
+ - spec/vandalism_detection/training_dataset_spec.rb
398
+ - spec/vandalism_detection/wikitext_extractor_spec.rb
399
+ - spec/weka/classifiers/meta/one_class_classifier_spec.rb
400
+ - spec/weka/classifiers/meta/real_ada_boost_spec.rb
401
+ - spec/weka/classifiers/trees/balanced_random_forest_spec.rb
402
+ - spec/weka/filters/supervised/instance/smote_spec.rb
403
+ - wikipedia-vandalism_detection.gemspec
404
+ homepage: https://github.com/paulgoetze/wikipedia-vandalism-detection
405
+ licenses:
406
+ - GPL v3
407
+ metadata: {}
408
+ post_install_message:
409
+ rdoc_options: []
410
+ require_paths:
411
+ - lib
412
+ required_ruby_version: !ruby/object:Gem::Requirement
413
+ requirements:
414
+ - - "~>"
415
+ - !ruby/object:Gem::Version
416
+ version: '2.0'
417
+ required_rubygems_version: !ruby/object:Gem::Requirement
418
+ requirements:
419
+ - - ">="
420
+ - !ruby/object:Gem::Version
421
+ version: '0'
422
+ requirements: []
423
+ rubyforge_project:
424
+ rubygems_version: 2.7.6
425
+ signing_key:
426
+ specification_version: 4
427
+ summary: Wikipedia vandalism detection with JRuby.
428
+ test_files:
429
+ - spec/factories/edit.rb
430
+ - spec/factories/page.rb
431
+ - spec/factories/revision.rb
432
+ - spec/resources/config/wikipedia-vandalism-detection.yml
433
+ - spec/resources/corpora/test/edits.csv
434
+ - spec/resources/corpora/test/ground-truth.txt
435
+ - spec/resources/corpora/test/revisions/part-1/326471754.txt
436
+ - spec/resources/corpora/test/revisions/part-1/326873205.txt
437
+ - spec/resources/corpora/test/revisions/part-1/328774035.txt
438
+ - spec/resources/corpora/test/revisions/part-2/307084144.txt
439
+ - spec/resources/corpora/test/revisions/part-2/326978767.txt
440
+ - spec/resources/corpora/test/revisions/part-2/328774110.txt
441
+ - spec/resources/corpora/training/annotations.csv
442
+ - spec/resources/corpora/training/edits.csv
443
+ - spec/resources/corpora/training/revisions/part-1/326471754.txt
444
+ - spec/resources/corpora/training/revisions/part-1/326873205.txt
445
+ - spec/resources/corpora/training/revisions/part-1/328774035.txt
446
+ - spec/resources/corpora/training/revisions/part-2/307084144.txt
447
+ - spec/resources/corpora/training/revisions/part-2/326978767.txt
448
+ - spec/resources/corpora/training/revisions/part-2/328774110.txt
449
+ - spec/resources/page_with_redirects.xml
450
+ - spec/resources/redirect_page.xml
451
+ - spec/resources/revision_simplified.xml
452
+ - spec/resources/sample_revision.txt
453
+ - spec/resources/sample_revision_clean_text.txt
454
+ - spec/resources/sample_revision_plain_text.txt
455
+ - spec/resources/vandalism_on_wikipedia.xml
456
+ - spec/resources/vandalism_on_wikipedia_simplified.xml
457
+ - spec/resources/wikipedia_tokens.txt
458
+ - spec/spec_helper.rb
459
+ - spec/support/macros/file_reading.rb
460
+ - spec/support/macros/test_configuration.rb
461
+ - spec/vandalism_detection/algorithms/kullback_leibler_divergence_spec.rb
462
+ - spec/vandalism_detection/classifier_spec.rb
463
+ - spec/vandalism_detection/configuration_spec.rb
464
+ - spec/vandalism_detection/diff_spec.rb
465
+ - spec/vandalism_detection/edit_spec.rb
466
+ - spec/vandalism_detection/evaluator_spec.rb
467
+ - spec/vandalism_detection/feature_calculator_spec.rb
468
+ - spec/vandalism_detection/features/all_wordlists_frequency_spec.rb
469
+ - spec/vandalism_detection/features/all_wordlists_impact_spec.rb
470
+ - spec/vandalism_detection/features/anonymity_previous_spec.rb
471
+ - spec/vandalism_detection/features/anonymity_spec.rb
472
+ - spec/vandalism_detection/features/article_size_spec.rb
473
+ - spec/vandalism_detection/features/bad_frequency_spec.rb
474
+ - spec/vandalism_detection/features/bad_impact_spec.rb
475
+ - spec/vandalism_detection/features/base_spec.rb
476
+ - spec/vandalism_detection/features/biased_frequency_spec.rb
477
+ - spec/vandalism_detection/features/biased_impact_spec.rb
478
+ - spec/vandalism_detection/features/blanking_spec.rb
479
+ - spec/vandalism_detection/features/character_diversity_spec.rb
480
+ - spec/vandalism_detection/features/character_sequence_spec.rb
481
+ - spec/vandalism_detection/features/comment_bad_frequency_spec.rb
482
+ - spec/vandalism_detection/features/comment_biased_frequency_spec.rb
483
+ - spec/vandalism_detection/features/comment_length_spec.rb
484
+ - spec/vandalism_detection/features/comment_markup_frequency_spec.rb
485
+ - spec/vandalism_detection/features/comment_pronoun_frequency_spec.rb
486
+ - spec/vandalism_detection/features/comment_sex_frequency_spec.rb
487
+ - spec/vandalism_detection/features/comment_vulgarism_frequency_spec.rb
488
+ - spec/vandalism_detection/features/compressibility_spec.rb
489
+ - spec/vandalism_detection/features/contains_base_spec.rb
490
+ - spec/vandalism_detection/features/copyedit_spec.rb
491
+ - spec/vandalism_detection/features/digit_ratio_spec.rb
492
+ - spec/vandalism_detection/features/edits_per_user_spec.rb
493
+ - spec/vandalism_detection/features/emoticons_frequency_spec.rb
494
+ - spec/vandalism_detection/features/emoticons_impact_spec.rb
495
+ - spec/vandalism_detection/features/frequency_base_spec.rb
496
+ - spec/vandalism_detection/features/impact_base_spec.rb
497
+ - spec/vandalism_detection/features/inserted_character_distribution_spec.rb
498
+ - spec/vandalism_detection/features/inserted_external_links_spec.rb
499
+ - spec/vandalism_detection/features/inserted_internal_links_spec.rb
500
+ - spec/vandalism_detection/features/inserted_size_spec.rb
501
+ - spec/vandalism_detection/features/inserted_words_spec.rb
502
+ - spec/vandalism_detection/features/longest_word_spec.rb
503
+ - spec/vandalism_detection/features/markup_frequency_spec.rb
504
+ - spec/vandalism_detection/features/markup_impact_spec.rb
505
+ - spec/vandalism_detection/features/non_alphanumeric_ratio_spec.rb
506
+ - spec/vandalism_detection/features/personal_life_spec.rb
507
+ - spec/vandalism_detection/features/pronoun_frequency_spec.rb
508
+ - spec/vandalism_detection/features/pronoun_impact_spec.rb
509
+ - spec/vandalism_detection/features/removed_all_wordlists_frequency_spec.rb
510
+ - spec/vandalism_detection/features/removed_bad_frequency_spec.rb
511
+ - spec/vandalism_detection/features/removed_biased_frequency_spec.rb
512
+ - spec/vandalism_detection/features/removed_character_distribution_spec.rb
513
+ - spec/vandalism_detection/features/removed_emoticons_frequency_spec.rb
514
+ - spec/vandalism_detection/features/removed_markup_frequency_spec.rb
515
+ - spec/vandalism_detection/features/removed_pronoun_frequency_spec.rb
516
+ - spec/vandalism_detection/features/removed_sex_frequency_spec.rb
517
+ - spec/vandalism_detection/features/removed_size_spec.rb
518
+ - spec/vandalism_detection/features/removed_vulgarism_frequency_spec.rb
519
+ - spec/vandalism_detection/features/removed_words_spec.rb
520
+ - spec/vandalism_detection/features/replacement_similarity_spec.rb
521
+ - spec/vandalism_detection/features/reverted_spec.rb
522
+ - spec/vandalism_detection/features/revisions_character_distribution_spec.rb
523
+ - spec/vandalism_detection/features/same_editor_spec.rb
524
+ - spec/vandalism_detection/features/sex_frequency_spec.rb
525
+ - spec/vandalism_detection/features/sex_impact_spec.rb
526
+ - spec/vandalism_detection/features/size_increment_spec.rb
527
+ - spec/vandalism_detection/features/size_ratio_spec.rb
528
+ - spec/vandalism_detection/features/term_frequency_spec.rb
529
+ - spec/vandalism_detection/features/time_interval_spec.rb
530
+ - spec/vandalism_detection/features/time_of_day_spec.rb
531
+ - spec/vandalism_detection/features/upper_case_ratio_spec.rb
532
+ - spec/vandalism_detection/features/upper_case_words_ratio_spec.rb
533
+ - spec/vandalism_detection/features/upper_to_lower_case_ratio_spec.rb
534
+ - spec/vandalism_detection/features/vulgarism_frequency_spec.rb
535
+ - spec/vandalism_detection/features/vulgarism_impact_spec.rb
536
+ - spec/vandalism_detection/features/weekday_spec.rb
537
+ - spec/vandalism_detection/features/words_increment_spec.rb
538
+ - spec/vandalism_detection/instances_spec.rb
539
+ - spec/vandalism_detection/page_parser_spec.rb
540
+ - spec/vandalism_detection/page_spec.rb
541
+ - spec/vandalism_detection/revision_parser_spec.rb
542
+ - spec/vandalism_detection/revision_spec.rb
543
+ - spec/vandalism_detection/test_dataset_spec.rb
544
+ - spec/vandalism_detection/text_spec.rb
545
+ - spec/vandalism_detection/training_dataset_spec.rb
546
+ - spec/vandalism_detection/wikitext_extractor_spec.rb
547
+ - spec/weka/classifiers/meta/one_class_classifier_spec.rb
548
+ - spec/weka/classifiers/meta/real_ada_boost_spec.rb
549
+ - spec/weka/classifiers/trees/balanced_random_forest_spec.rb
550
+ - spec/weka/filters/supervised/instance/smote_spec.rb