wikipedia-vandalism_detection 0.0.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (247) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +17 -0
  3. data/Gemfile +6 -0
  4. data/LICENSE.txt +4 -0
  5. data/README.md +265 -0
  6. data/Rakefile +12 -0
  7. data/lib/java/LibSVM.jar +0 -0
  8. data/lib/java/SMOTE.jar +0 -0
  9. data/lib/java/balancedRandomForest.jar +0 -0
  10. data/lib/java/diffutils-1.3.0.jar +0 -0
  11. data/lib/java/libsvm.jar +0 -0
  12. data/lib/java/oneClassClassifier.jar +0 -0
  13. data/lib/java/realAdaBoost.jar +0 -0
  14. data/lib/java/swc-engine-1.1.0-jar-with-dependencies.jar +0 -0
  15. data/lib/java/sweble-wikitext-extractor.jar +0 -0
  16. data/lib/weka/classifiers/functions/lib_svm.rb +15 -0
  17. data/lib/weka/classifiers/meta/one_class_classifier.rb +25 -0
  18. data/lib/weka/classifiers/meta/real_ada_boost.rb +17 -0
  19. data/lib/weka/classifiers/trees/balanced_random_forest.rb +18 -0
  20. data/lib/weka/filters/supervised/instance/smote.rb +22 -0
  21. data/lib/wikipedia.rb +51 -0
  22. data/lib/wikipedia/vandalism_detection.rb +30 -0
  23. data/lib/wikipedia/vandalism_detection/algorithms.rb +18 -0
  24. data/lib/wikipedia/vandalism_detection/algorithms/kullback_leibler_divergence.rb +69 -0
  25. data/lib/wikipedia/vandalism_detection/classifier.rb +186 -0
  26. data/lib/wikipedia/vandalism_detection/configuration.rb +321 -0
  27. data/lib/wikipedia/vandalism_detection/diff.rb +27 -0
  28. data/lib/wikipedia/vandalism_detection/edit.rb +75 -0
  29. data/lib/wikipedia/vandalism_detection/evaluator.rb +606 -0
  30. data/lib/wikipedia/vandalism_detection/exceptions.rb +40 -0
  31. data/lib/wikipedia/vandalism_detection/feature_calculator.rb +89 -0
  32. data/lib/wikipedia/vandalism_detection/features.rb +67 -0
  33. data/lib/wikipedia/vandalism_detection/features/all_wordlists_frequency.rb +23 -0
  34. data/lib/wikipedia/vandalism_detection/features/all_wordlists_impact.rb +22 -0
  35. data/lib/wikipedia/vandalism_detection/features/anonymity.rb +19 -0
  36. data/lib/wikipedia/vandalism_detection/features/anonymity_previous.rb +29 -0
  37. data/lib/wikipedia/vandalism_detection/features/article_size.rb +18 -0
  38. data/lib/wikipedia/vandalism_detection/features/bad_frequency.rb +23 -0
  39. data/lib/wikipedia/vandalism_detection/features/bad_impact.rb +21 -0
  40. data/lib/wikipedia/vandalism_detection/features/base.rb +54 -0
  41. data/lib/wikipedia/vandalism_detection/features/biased_frequency.rb +23 -0
  42. data/lib/wikipedia/vandalism_detection/features/biased_impact.rb +22 -0
  43. data/lib/wikipedia/vandalism_detection/features/blanking.rb +25 -0
  44. data/lib/wikipedia/vandalism_detection/features/character_diversity.rb +25 -0
  45. data/lib/wikipedia/vandalism_detection/features/character_sequence.rb +19 -0
  46. data/lib/wikipedia/vandalism_detection/features/comment_bad_frequency.rb +22 -0
  47. data/lib/wikipedia/vandalism_detection/features/comment_biased_frequency.rb +22 -0
  48. data/lib/wikipedia/vandalism_detection/features/comment_length.rb +17 -0
  49. data/lib/wikipedia/vandalism_detection/features/comment_markup_frequency.rb +27 -0
  50. data/lib/wikipedia/vandalism_detection/features/comment_pronoun_frequency.rb +22 -0
  51. data/lib/wikipedia/vandalism_detection/features/comment_sex_frequency.rb +22 -0
  52. data/lib/wikipedia/vandalism_detection/features/comment_vulgarism_frequency.rb +22 -0
  53. data/lib/wikipedia/vandalism_detection/features/compressibility.rb +27 -0
  54. data/lib/wikipedia/vandalism_detection/features/contains_base.rb +18 -0
  55. data/lib/wikipedia/vandalism_detection/features/copyedit.rb +18 -0
  56. data/lib/wikipedia/vandalism_detection/features/digit_ratio.rb +24 -0
  57. data/lib/wikipedia/vandalism_detection/features/edits_per_user.rb +65 -0
  58. data/lib/wikipedia/vandalism_detection/features/emoticons_frequency.rb +27 -0
  59. data/lib/wikipedia/vandalism_detection/features/emoticons_impact.rb +29 -0
  60. data/lib/wikipedia/vandalism_detection/features/frequency_base.rb +20 -0
  61. data/lib/wikipedia/vandalism_detection/features/impact_base.rb +22 -0
  62. data/lib/wikipedia/vandalism_detection/features/inserted_character_distribution.rb +22 -0
  63. data/lib/wikipedia/vandalism_detection/features/inserted_external_links.rb +18 -0
  64. data/lib/wikipedia/vandalism_detection/features/inserted_internal_links.rb +18 -0
  65. data/lib/wikipedia/vandalism_detection/features/inserted_size.rb +20 -0
  66. data/lib/wikipedia/vandalism_detection/features/inserted_words.rb +18 -0
  67. data/lib/wikipedia/vandalism_detection/features/longest_word.rb +20 -0
  68. data/lib/wikipedia/vandalism_detection/features/markup_frequency.rb +27 -0
  69. data/lib/wikipedia/vandalism_detection/features/markup_impact.rb +27 -0
  70. data/lib/wikipedia/vandalism_detection/features/non_alphanumeric_ratio.rb +24 -0
  71. data/lib/wikipedia/vandalism_detection/features/personal_life.rb +18 -0
  72. data/lib/wikipedia/vandalism_detection/features/pronoun_frequency.rb +23 -0
  73. data/lib/wikipedia/vandalism_detection/features/pronoun_impact.rb +21 -0
  74. data/lib/wikipedia/vandalism_detection/features/removed_all_wordlists_frequency.rb +23 -0
  75. data/lib/wikipedia/vandalism_detection/features/removed_bad_frequency.rb +23 -0
  76. data/lib/wikipedia/vandalism_detection/features/removed_biased_frequency.rb +23 -0
  77. data/lib/wikipedia/vandalism_detection/features/removed_character_distribution.rb +22 -0
  78. data/lib/wikipedia/vandalism_detection/features/removed_emoticons_frequency.rb +27 -0
  79. data/lib/wikipedia/vandalism_detection/features/removed_markup_frequency.rb +28 -0
  80. data/lib/wikipedia/vandalism_detection/features/removed_pronoun_frequency.rb +23 -0
  81. data/lib/wikipedia/vandalism_detection/features/removed_sex_frequency.rb +23 -0
  82. data/lib/wikipedia/vandalism_detection/features/removed_size.rb +20 -0
  83. data/lib/wikipedia/vandalism_detection/features/removed_vulgarism_frequency.rb +23 -0
  84. data/lib/wikipedia/vandalism_detection/features/removed_words.rb +18 -0
  85. data/lib/wikipedia/vandalism_detection/features/replacement_similarity.rb +22 -0
  86. data/lib/wikipedia/vandalism_detection/features/reverted.rb +18 -0
  87. data/lib/wikipedia/vandalism_detection/features/revisions_character_distribution.rb +21 -0
  88. data/lib/wikipedia/vandalism_detection/features/same_editor.rb +29 -0
  89. data/lib/wikipedia/vandalism_detection/features/sex_frequency.rb +23 -0
  90. data/lib/wikipedia/vandalism_detection/features/sex_impact.rb +21 -0
  91. data/lib/wikipedia/vandalism_detection/features/size_increment.rb +22 -0
  92. data/lib/wikipedia/vandalism_detection/features/size_ratio.rb +26 -0
  93. data/lib/wikipedia/vandalism_detection/features/term_frequency.rb +25 -0
  94. data/lib/wikipedia/vandalism_detection/features/time_interval.rb +31 -0
  95. data/lib/wikipedia/vandalism_detection/features/time_of_day.rb +22 -0
  96. data/lib/wikipedia/vandalism_detection/features/upper_case_ratio.rb +24 -0
  97. data/lib/wikipedia/vandalism_detection/features/upper_case_words_ratio.rb +31 -0
  98. data/lib/wikipedia/vandalism_detection/features/upper_to_lower_case_ratio.rb +24 -0
  99. data/lib/wikipedia/vandalism_detection/features/user_reputation.rb +38 -0
  100. data/lib/wikipedia/vandalism_detection/features/vulgarism_frequency.rb +23 -0
  101. data/lib/wikipedia/vandalism_detection/features/vulgarism_impact.rb +22 -0
  102. data/lib/wikipedia/vandalism_detection/features/weekday.rb +21 -0
  103. data/lib/wikipedia/vandalism_detection/features/words_increment.rb +22 -0
  104. data/lib/wikipedia/vandalism_detection/instances.rb +130 -0
  105. data/lib/wikipedia/vandalism_detection/page.rb +88 -0
  106. data/lib/wikipedia/vandalism_detection/page_parser.rb +52 -0
  107. data/lib/wikipedia/vandalism_detection/revision.rb +69 -0
  108. data/lib/wikipedia/vandalism_detection/revision_parser.rb +43 -0
  109. data/lib/wikipedia/vandalism_detection/test_dataset.rb +367 -0
  110. data/lib/wikipedia/vandalism_detection/text.rb +18 -0
  111. data/lib/wikipedia/vandalism_detection/training_dataset.rb +303 -0
  112. data/lib/wikipedia/vandalism_detection/version.rb +5 -0
  113. data/lib/wikipedia/vandalism_detection/wikitext_extractor.rb +80 -0
  114. data/lib/wikipedia/vandalism_detection/word_lists.rb +19 -0
  115. data/lib/wikipedia/vandalism_detection/word_lists/bad.rb +12 -0
  116. data/lib/wikipedia/vandalism_detection/word_lists/biased.rb +21 -0
  117. data/lib/wikipedia/vandalism_detection/word_lists/emoticons.rb +22 -0
  118. data/lib/wikipedia/vandalism_detection/word_lists/markup.rb +12 -0
  119. data/lib/wikipedia/vandalism_detection/word_lists/pronouns.rb +15 -0
  120. data/lib/wikipedia/vandalism_detection/word_lists/sex.rb +12 -0
  121. data/lib/wikipedia/vandalism_detection/word_lists/vulgarism.rb +97 -0
  122. data/spec/factories/edit.rb +20 -0
  123. data/spec/factories/page.rb +13 -0
  124. data/spec/factories/revision.rb +51 -0
  125. data/spec/resources/config/config.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 +22 -0
  152. data/spec/support/macros/file_reading.rb +7 -0
  153. data/spec/support/macros/test_configuration.rb +71 -0
  154. data/spec/vandalism_detection/algorithms/kullback_leibler_divergence_spec.rb +36 -0
  155. data/spec/vandalism_detection/classifier_spec.rb +317 -0
  156. data/spec/vandalism_detection/configuration_spec.rb +517 -0
  157. data/spec/vandalism_detection/diff_spec.rb +40 -0
  158. data/spec/vandalism_detection/edit_spec.rb +137 -0
  159. data/spec/vandalism_detection/evaluator_spec.rb +671 -0
  160. data/spec/vandalism_detection/feature_calculator_spec.rb +128 -0
  161. data/spec/vandalism_detection/features/all_wordlists_frequency_spec.rb +36 -0
  162. data/spec/vandalism_detection/features/all_wordlists_impact_spec.rb +58 -0
  163. data/spec/vandalism_detection/features/anonymity_previous_spec.rb +61 -0
  164. data/spec/vandalism_detection/features/anonymity_spec.rb +23 -0
  165. data/spec/vandalism_detection/features/article_size_spec.rb +35 -0
  166. data/spec/vandalism_detection/features/bad_frequency_spec.rb +36 -0
  167. data/spec/vandalism_detection/features/bad_impact_spec.rb +59 -0
  168. data/spec/vandalism_detection/features/base_spec.rb +49 -0
  169. data/spec/vandalism_detection/features/biased_frequency_spec.rb +36 -0
  170. data/spec/vandalism_detection/features/biased_impact_spec.rb +58 -0
  171. data/spec/vandalism_detection/features/blanking_spec.rb +38 -0
  172. data/spec/vandalism_detection/features/character_diversity_spec.rb +35 -0
  173. data/spec/vandalism_detection/features/character_sequence_spec.rb +37 -0
  174. data/spec/vandalism_detection/features/comment_bad_frequency_spec.rb +34 -0
  175. data/spec/vandalism_detection/features/comment_biased_frequency_spec.rb +34 -0
  176. data/spec/vandalism_detection/features/comment_length_spec.rb +27 -0
  177. data/spec/vandalism_detection/features/comment_markup_frequency_spec.rb +34 -0
  178. data/spec/vandalism_detection/features/comment_pronoun_frequency_spec.rb +34 -0
  179. data/spec/vandalism_detection/features/comment_sex_frequency_spec.rb +34 -0
  180. data/spec/vandalism_detection/features/comment_vulgarism_frequency_spec.rb +34 -0
  181. data/spec/vandalism_detection/features/compressibility_spec.rb +42 -0
  182. data/spec/vandalism_detection/features/contains_base_spec.rb +33 -0
  183. data/spec/vandalism_detection/features/copyedit_spec.rb +33 -0
  184. data/spec/vandalism_detection/features/digit_ratio_spec.rb +35 -0
  185. data/spec/vandalism_detection/features/edits_per_user_spec.rb +49 -0
  186. data/spec/vandalism_detection/features/emoticons_frequency_spec.rb +36 -0
  187. data/spec/vandalism_detection/features/emoticons_impact_spec.rb +51 -0
  188. data/spec/vandalism_detection/features/frequency_base_spec.rb +26 -0
  189. data/spec/vandalism_detection/features/impact_base_spec.rb +41 -0
  190. data/spec/vandalism_detection/features/inserted_character_distribution_spec.rb +46 -0
  191. data/spec/vandalism_detection/features/inserted_external_links_spec.rb +35 -0
  192. data/spec/vandalism_detection/features/inserted_internal_links_spec.rb +35 -0
  193. data/spec/vandalism_detection/features/inserted_size_spec.rb +35 -0
  194. data/spec/vandalism_detection/features/inserted_words_spec.rb +35 -0
  195. data/spec/vandalism_detection/features/longest_word_spec.rb +35 -0
  196. data/spec/vandalism_detection/features/markup_frequency_spec.rb +36 -0
  197. data/spec/vandalism_detection/features/markup_impact_spec.rb +59 -0
  198. data/spec/vandalism_detection/features/non_alphanumeric_ratio_spec.rb +35 -0
  199. data/spec/vandalism_detection/features/personal_life_spec.rb +26 -0
  200. data/spec/vandalism_detection/features/pronoun_frequency_spec.rb +36 -0
  201. data/spec/vandalism_detection/features/pronoun_impact_spec.rb +59 -0
  202. data/spec/vandalism_detection/features/removed_all_wordlists_frequency_spec.rb +36 -0
  203. data/spec/vandalism_detection/features/removed_bad_frequency_spec.rb +36 -0
  204. data/spec/vandalism_detection/features/removed_biased_frequency_spec.rb +36 -0
  205. data/spec/vandalism_detection/features/removed_character_distribution_spec.rb +46 -0
  206. data/spec/vandalism_detection/features/removed_emoticons_frequency_spec.rb +36 -0
  207. data/spec/vandalism_detection/features/removed_markup_frequency_spec.rb +36 -0
  208. data/spec/vandalism_detection/features/removed_pronoun_frequency_spec.rb +36 -0
  209. data/spec/vandalism_detection/features/removed_sex_frequency_spec.rb +36 -0
  210. data/spec/vandalism_detection/features/removed_size_spec.rb +35 -0
  211. data/spec/vandalism_detection/features/removed_vulgarism_frequency_spec.rb +36 -0
  212. data/spec/vandalism_detection/features/removed_words_spec.rb +35 -0
  213. data/spec/vandalism_detection/features/replacement_similarity_spec.rb +44 -0
  214. data/spec/vandalism_detection/features/reverted_spec.rb +28 -0
  215. data/spec/vandalism_detection/features/revisions_character_distribution_spec.rb +46 -0
  216. data/spec/vandalism_detection/features/same_editor_spec.rb +60 -0
  217. data/spec/vandalism_detection/features/sex_frequency_spec.rb +36 -0
  218. data/spec/vandalism_detection/features/sex_impact_spec.rb +59 -0
  219. data/spec/vandalism_detection/features/size_increment_spec.rb +35 -0
  220. data/spec/vandalism_detection/features/size_ratio_spec.rb +57 -0
  221. data/spec/vandalism_detection/features/term_frequency_spec.rb +38 -0
  222. data/spec/vandalism_detection/features/time_interval_spec.rb +50 -0
  223. data/spec/vandalism_detection/features/time_of_day_spec.rb +22 -0
  224. data/spec/vandalism_detection/features/upper_case_ratio_spec.rb +35 -0
  225. data/spec/vandalism_detection/features/upper_case_words_ratio_spec.rb +37 -0
  226. data/spec/vandalism_detection/features/upper_to_lower_case_ratio_spec.rb +35 -0
  227. data/spec/vandalism_detection/features/user_reputation_spec.rb +52 -0
  228. data/spec/vandalism_detection/features/vulgarism_frequency_spec.rb +36 -0
  229. data/spec/vandalism_detection/features/vulgarism_impact_spec.rb +58 -0
  230. data/spec/vandalism_detection/features/weekday_spec.rb +22 -0
  231. data/spec/vandalism_detection/features/words_increment_spec.rb +35 -0
  232. data/spec/vandalism_detection/instances_spec.rb +156 -0
  233. data/spec/vandalism_detection/page_parser_spec.rb +184 -0
  234. data/spec/vandalism_detection/page_spec.rb +135 -0
  235. data/spec/vandalism_detection/revision_parser_spec.rb +53 -0
  236. data/spec/vandalism_detection/revision_spec.rb +115 -0
  237. data/spec/vandalism_detection/test_dataset_spec.rb +231 -0
  238. data/spec/vandalism_detection/text_spec.rb +29 -0
  239. data/spec/vandalism_detection/training_dataset_spec.rb +264 -0
  240. data/spec/vandalism_detection/wikitext_extractor_spec.rb +72 -0
  241. data/spec/weka/classifiers/functions/lib_svm_spec.rb +38 -0
  242. data/spec/weka/classifiers/meta/one_class_classifier_spec.rb +76 -0
  243. data/spec/weka/classifiers/meta/real_ada_boost_spec.rb +40 -0
  244. data/spec/weka/classifiers/trees/balanced_random_forest_spec.rb +40 -0
  245. data/spec/weka/filters/supervised/instance/smote_spec.rb +6 -0
  246. data/wikipedia-vandalism_detection.gemspec +30 -0
  247. metadata +512 -0
@@ -0,0 +1,40 @@
1
+ require 'spec_helper'
2
+
3
+ describe Weka::Classifiers::Meta::RealAdaBoost do
4
+
5
+ it { should be_a Java::WekaClassifiersMeta::RealAdaBoost }
6
+
7
+ before do
8
+ @config = test_config
9
+ options = "-W weka.classifiers.trees.RandomForest -- -I 100"
10
+
11
+ @config.instance_variable_set :@classifier_type, 'Meta::RealAdaBoost'
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.exists?(arff_file)
23
+ File.delete(arff_file)
24
+ FileUtils.rm_r(File.dirname arff_file)
25
+ end
26
+
27
+ if Dir.exists?(build_dir)
28
+ FileUtils.rm_r(build_dir)
29
+ end
30
+ end
31
+
32
+ it "can be used to classify vandalism" do
33
+ expect {
34
+ classifier = Wikipedia::VandalismDetection::Classifier.new
35
+ features = [0.0, 25, 5]
36
+ confidence = classifier.classify features
37
+ puts "vandalism confidence: #{confidence}}"
38
+ }.not_to raise_error
39
+ end
40
+ end
@@ -0,0 +1,40 @@
1
+ require 'spec_helper'
2
+
3
+ describe Weka::Classifiers::Trees::BalancedRandomForest do
4
+
5
+ it { should be_a Java::WekaClassifiersTrees::BalancedRandomForest }
6
+
7
+ before do
8
+ @config = test_config
9
+ options = "-I 100"
10
+
11
+ @config.instance_variable_set :@classifier_type, 'Trees::BalancedRandomForest'
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.exists?(arff_file)
23
+ File.delete(arff_file)
24
+ FileUtils.rm_r(File.dirname arff_file)
25
+ end
26
+
27
+ if Dir.exists?(build_dir)
28
+ FileUtils.rm_r(build_dir)
29
+ end
30
+ end
31
+
32
+ it "can be used to classify vandalism" do
33
+ expect {
34
+ classifier = Wikipedia::VandalismDetection::Classifier.new
35
+ features = [0.0, 25, 5]
36
+ confidence = classifier.classify features
37
+ puts "vandalism confidence: #{confidence}}"
38
+ }.not_to raise_error
39
+ end
40
+ end
@@ -0,0 +1,6 @@
1
+ require 'spec_helper'
2
+
3
+ describe Weka::Filters::Supervised::Instance::SMOTE do
4
+
5
+ it { should be_a Java::WekaFiltersSupervisedInstance::SMOTE }
6
+ end
@@ -0,0 +1,30 @@
1
+ # coding: utf-8
2
+ lib = File.expand_path('../lib', __FILE__)
3
+ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
4
+ require 'wikipedia/vandalism_detection/version'
5
+
6
+ Gem::Specification.new do |spec|
7
+ spec.name = "wikipedia-vandalism_detection"
8
+ spec.version = Wikipedia::VandalismDetection::VERSION
9
+ spec.authors = ["Paul Götze"]
10
+ spec.email = ["paul.christoph.goetze@gmail.com"]
11
+ spec.summary = %q{Wikipedia vandalism detection with JRuby.}
12
+ spec.description = %q{Wikipedia vandalism detection with JRuby.}
13
+ spec.homepage = ""
14
+ spec.license = "GPL v3"
15
+
16
+ spec.files = `git ls-files -z`.split("\x0")
17
+ spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
18
+ spec.extensions = ["Rakefile"]
19
+ spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
20
+ spec.require_paths = ["lib"]
21
+
22
+ spec.add_runtime_dependency "ruby-band", "~> 0.1"
23
+ spec.add_runtime_dependency "nokogiri"
24
+ spec.add_runtime_dependency "activesupport"
25
+
26
+ spec.add_development_dependency "bundler", "~> 1.5"
27
+ spec.add_development_dependency "rake"
28
+ spec.add_development_dependency "rspec"
29
+ spec.add_development_dependency "factory_girl"
30
+ end
metadata ADDED
@@ -0,0 +1,512 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: wikipedia-vandalism_detection
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.0.1
5
+ platform: ruby
6
+ authors:
7
+ - Paul Götze
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2014-09-21 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: '0.1'
19
+ name: ruby-band
20
+ prerelease: false
21
+ type: :runtime
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - ~>
25
+ - !ruby/object:Gem::Version
26
+ version: '0.1'
27
+ - !ruby/object:Gem::Dependency
28
+ requirement: !ruby/object:Gem::Requirement
29
+ requirements:
30
+ - - '>='
31
+ - !ruby/object:Gem::Version
32
+ version: '0'
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: '0'
41
+ - !ruby/object:Gem::Dependency
42
+ requirement: !ruby/object:Gem::Requirement
43
+ requirements:
44
+ - - '>='
45
+ - !ruby/object:Gem::Version
46
+ version: '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: '0'
55
+ - !ruby/object:Gem::Dependency
56
+ requirement: !ruby/object:Gem::Requirement
57
+ requirements:
58
+ - - ~>
59
+ - !ruby/object:Gem::Version
60
+ version: '1.5'
61
+ name: bundler
62
+ prerelease: false
63
+ type: :development
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - ~>
67
+ - !ruby/object:Gem::Version
68
+ version: '1.5'
69
+ - !ruby/object:Gem::Dependency
70
+ requirement: !ruby/object:Gem::Requirement
71
+ requirements:
72
+ - - '>='
73
+ - !ruby/object:Gem::Version
74
+ version: '0'
75
+ name: rake
76
+ prerelease: false
77
+ type: :development
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - '>='
81
+ - !ruby/object:Gem::Version
82
+ version: '0'
83
+ - !ruby/object:Gem::Dependency
84
+ requirement: !ruby/object:Gem::Requirement
85
+ requirements:
86
+ - - '>='
87
+ - !ruby/object:Gem::Version
88
+ version: '0'
89
+ name: rspec
90
+ prerelease: false
91
+ type: :development
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - '>='
95
+ - !ruby/object:Gem::Version
96
+ version: '0'
97
+ - !ruby/object:Gem::Dependency
98
+ requirement: !ruby/object:Gem::Requirement
99
+ requirements:
100
+ - - '>='
101
+ - !ruby/object:Gem::Version
102
+ version: '0'
103
+ name: factory_girl
104
+ prerelease: false
105
+ type: :development
106
+ version_requirements: !ruby/object:Gem::Requirement
107
+ requirements:
108
+ - - '>='
109
+ - !ruby/object:Gem::Version
110
+ version: '0'
111
+ description: Wikipedia vandalism detection with JRuby.
112
+ email:
113
+ - paul.christoph.goetze@gmail.com
114
+ executables: []
115
+ extensions:
116
+ - Rakefile
117
+ extra_rdoc_files: []
118
+ files:
119
+ - .gitignore
120
+ - Gemfile
121
+ - LICENSE.txt
122
+ - README.md
123
+ - Rakefile
124
+ - lib/java/LibSVM.jar
125
+ - lib/java/SMOTE.jar
126
+ - lib/java/balancedRandomForest.jar
127
+ - lib/java/diffutils-1.3.0.jar
128
+ - lib/java/libsvm.jar
129
+ - lib/java/oneClassClassifier.jar
130
+ - lib/java/realAdaBoost.jar
131
+ - lib/java/swc-engine-1.1.0-jar-with-dependencies.jar
132
+ - lib/java/sweble-wikitext-extractor.jar
133
+ - lib/weka/classifiers/functions/lib_svm.rb
134
+ - lib/weka/classifiers/meta/one_class_classifier.rb
135
+ - lib/weka/classifiers/meta/real_ada_boost.rb
136
+ - lib/weka/classifiers/trees/balanced_random_forest.rb
137
+ - lib/weka/filters/supervised/instance/smote.rb
138
+ - lib/wikipedia.rb
139
+ - lib/wikipedia/vandalism_detection.rb
140
+ - lib/wikipedia/vandalism_detection/algorithms.rb
141
+ - lib/wikipedia/vandalism_detection/algorithms/kullback_leibler_divergence.rb
142
+ - lib/wikipedia/vandalism_detection/classifier.rb
143
+ - lib/wikipedia/vandalism_detection/configuration.rb
144
+ - lib/wikipedia/vandalism_detection/diff.rb
145
+ - lib/wikipedia/vandalism_detection/edit.rb
146
+ - lib/wikipedia/vandalism_detection/evaluator.rb
147
+ - lib/wikipedia/vandalism_detection/exceptions.rb
148
+ - lib/wikipedia/vandalism_detection/feature_calculator.rb
149
+ - lib/wikipedia/vandalism_detection/features.rb
150
+ - lib/wikipedia/vandalism_detection/features/all_wordlists_frequency.rb
151
+ - lib/wikipedia/vandalism_detection/features/all_wordlists_impact.rb
152
+ - lib/wikipedia/vandalism_detection/features/anonymity.rb
153
+ - lib/wikipedia/vandalism_detection/features/anonymity_previous.rb
154
+ - lib/wikipedia/vandalism_detection/features/article_size.rb
155
+ - lib/wikipedia/vandalism_detection/features/bad_frequency.rb
156
+ - lib/wikipedia/vandalism_detection/features/bad_impact.rb
157
+ - lib/wikipedia/vandalism_detection/features/base.rb
158
+ - lib/wikipedia/vandalism_detection/features/biased_frequency.rb
159
+ - lib/wikipedia/vandalism_detection/features/biased_impact.rb
160
+ - lib/wikipedia/vandalism_detection/features/blanking.rb
161
+ - lib/wikipedia/vandalism_detection/features/character_diversity.rb
162
+ - lib/wikipedia/vandalism_detection/features/character_sequence.rb
163
+ - lib/wikipedia/vandalism_detection/features/comment_bad_frequency.rb
164
+ - lib/wikipedia/vandalism_detection/features/comment_biased_frequency.rb
165
+ - lib/wikipedia/vandalism_detection/features/comment_length.rb
166
+ - lib/wikipedia/vandalism_detection/features/comment_markup_frequency.rb
167
+ - lib/wikipedia/vandalism_detection/features/comment_pronoun_frequency.rb
168
+ - lib/wikipedia/vandalism_detection/features/comment_sex_frequency.rb
169
+ - lib/wikipedia/vandalism_detection/features/comment_vulgarism_frequency.rb
170
+ - lib/wikipedia/vandalism_detection/features/compressibility.rb
171
+ - lib/wikipedia/vandalism_detection/features/contains_base.rb
172
+ - lib/wikipedia/vandalism_detection/features/copyedit.rb
173
+ - lib/wikipedia/vandalism_detection/features/digit_ratio.rb
174
+ - lib/wikipedia/vandalism_detection/features/edits_per_user.rb
175
+ - lib/wikipedia/vandalism_detection/features/emoticons_frequency.rb
176
+ - lib/wikipedia/vandalism_detection/features/emoticons_impact.rb
177
+ - lib/wikipedia/vandalism_detection/features/frequency_base.rb
178
+ - lib/wikipedia/vandalism_detection/features/impact_base.rb
179
+ - lib/wikipedia/vandalism_detection/features/inserted_character_distribution.rb
180
+ - lib/wikipedia/vandalism_detection/features/inserted_external_links.rb
181
+ - lib/wikipedia/vandalism_detection/features/inserted_internal_links.rb
182
+ - lib/wikipedia/vandalism_detection/features/inserted_size.rb
183
+ - lib/wikipedia/vandalism_detection/features/inserted_words.rb
184
+ - lib/wikipedia/vandalism_detection/features/longest_word.rb
185
+ - lib/wikipedia/vandalism_detection/features/markup_frequency.rb
186
+ - lib/wikipedia/vandalism_detection/features/markup_impact.rb
187
+ - lib/wikipedia/vandalism_detection/features/non_alphanumeric_ratio.rb
188
+ - lib/wikipedia/vandalism_detection/features/personal_life.rb
189
+ - lib/wikipedia/vandalism_detection/features/pronoun_frequency.rb
190
+ - lib/wikipedia/vandalism_detection/features/pronoun_impact.rb
191
+ - lib/wikipedia/vandalism_detection/features/removed_all_wordlists_frequency.rb
192
+ - lib/wikipedia/vandalism_detection/features/removed_bad_frequency.rb
193
+ - lib/wikipedia/vandalism_detection/features/removed_biased_frequency.rb
194
+ - lib/wikipedia/vandalism_detection/features/removed_character_distribution.rb
195
+ - lib/wikipedia/vandalism_detection/features/removed_emoticons_frequency.rb
196
+ - lib/wikipedia/vandalism_detection/features/removed_markup_frequency.rb
197
+ - lib/wikipedia/vandalism_detection/features/removed_pronoun_frequency.rb
198
+ - lib/wikipedia/vandalism_detection/features/removed_sex_frequency.rb
199
+ - lib/wikipedia/vandalism_detection/features/removed_size.rb
200
+ - lib/wikipedia/vandalism_detection/features/removed_vulgarism_frequency.rb
201
+ - lib/wikipedia/vandalism_detection/features/removed_words.rb
202
+ - lib/wikipedia/vandalism_detection/features/replacement_similarity.rb
203
+ - lib/wikipedia/vandalism_detection/features/reverted.rb
204
+ - lib/wikipedia/vandalism_detection/features/revisions_character_distribution.rb
205
+ - lib/wikipedia/vandalism_detection/features/same_editor.rb
206
+ - lib/wikipedia/vandalism_detection/features/sex_frequency.rb
207
+ - lib/wikipedia/vandalism_detection/features/sex_impact.rb
208
+ - lib/wikipedia/vandalism_detection/features/size_increment.rb
209
+ - lib/wikipedia/vandalism_detection/features/size_ratio.rb
210
+ - lib/wikipedia/vandalism_detection/features/term_frequency.rb
211
+ - lib/wikipedia/vandalism_detection/features/time_interval.rb
212
+ - lib/wikipedia/vandalism_detection/features/time_of_day.rb
213
+ - lib/wikipedia/vandalism_detection/features/upper_case_ratio.rb
214
+ - lib/wikipedia/vandalism_detection/features/upper_case_words_ratio.rb
215
+ - lib/wikipedia/vandalism_detection/features/upper_to_lower_case_ratio.rb
216
+ - lib/wikipedia/vandalism_detection/features/user_reputation.rb
217
+ - lib/wikipedia/vandalism_detection/features/vulgarism_frequency.rb
218
+ - lib/wikipedia/vandalism_detection/features/vulgarism_impact.rb
219
+ - lib/wikipedia/vandalism_detection/features/weekday.rb
220
+ - lib/wikipedia/vandalism_detection/features/words_increment.rb
221
+ - lib/wikipedia/vandalism_detection/instances.rb
222
+ - lib/wikipedia/vandalism_detection/page.rb
223
+ - lib/wikipedia/vandalism_detection/page_parser.rb
224
+ - lib/wikipedia/vandalism_detection/revision.rb
225
+ - lib/wikipedia/vandalism_detection/revision_parser.rb
226
+ - lib/wikipedia/vandalism_detection/test_dataset.rb
227
+ - lib/wikipedia/vandalism_detection/text.rb
228
+ - lib/wikipedia/vandalism_detection/training_dataset.rb
229
+ - lib/wikipedia/vandalism_detection/version.rb
230
+ - lib/wikipedia/vandalism_detection/wikitext_extractor.rb
231
+ - lib/wikipedia/vandalism_detection/word_lists.rb
232
+ - lib/wikipedia/vandalism_detection/word_lists/bad.rb
233
+ - lib/wikipedia/vandalism_detection/word_lists/biased.rb
234
+ - lib/wikipedia/vandalism_detection/word_lists/emoticons.rb
235
+ - lib/wikipedia/vandalism_detection/word_lists/markup.rb
236
+ - lib/wikipedia/vandalism_detection/word_lists/pronouns.rb
237
+ - lib/wikipedia/vandalism_detection/word_lists/sex.rb
238
+ - lib/wikipedia/vandalism_detection/word_lists/vulgarism.rb
239
+ - spec/factories/edit.rb
240
+ - spec/factories/page.rb
241
+ - spec/factories/revision.rb
242
+ - spec/resources/config/config.yml
243
+ - spec/resources/corpora/test/edits.csv
244
+ - spec/resources/corpora/test/ground-truth.txt
245
+ - spec/resources/corpora/test/revisions/part-1/326471754.txt
246
+ - spec/resources/corpora/test/revisions/part-1/326873205.txt
247
+ - spec/resources/corpora/test/revisions/part-1/328774035.txt
248
+ - spec/resources/corpora/test/revisions/part-2/307084144.txt
249
+ - spec/resources/corpora/test/revisions/part-2/326978767.txt
250
+ - spec/resources/corpora/test/revisions/part-2/328774110.txt
251
+ - spec/resources/corpora/training/annotations.csv
252
+ - spec/resources/corpora/training/edits.csv
253
+ - spec/resources/corpora/training/revisions/part-1/326471754.txt
254
+ - spec/resources/corpora/training/revisions/part-1/326873205.txt
255
+ - spec/resources/corpora/training/revisions/part-1/328774035.txt
256
+ - spec/resources/corpora/training/revisions/part-2/307084144.txt
257
+ - spec/resources/corpora/training/revisions/part-2/326978767.txt
258
+ - spec/resources/corpora/training/revisions/part-2/328774110.txt
259
+ - spec/resources/page_with_redirects.xml
260
+ - spec/resources/redirect_page.xml
261
+ - spec/resources/revision_simplified.xml
262
+ - spec/resources/sample_revision.txt
263
+ - spec/resources/sample_revision_clean_text.txt
264
+ - spec/resources/sample_revision_plain_text.txt
265
+ - spec/resources/vandalism_on_wikipedia.xml
266
+ - spec/resources/vandalism_on_wikipedia_simplified.xml
267
+ - spec/resources/wikipedia_tokens.txt
268
+ - spec/spec_helper.rb
269
+ - spec/support/macros/file_reading.rb
270
+ - spec/support/macros/test_configuration.rb
271
+ - spec/vandalism_detection/algorithms/kullback_leibler_divergence_spec.rb
272
+ - spec/vandalism_detection/classifier_spec.rb
273
+ - spec/vandalism_detection/configuration_spec.rb
274
+ - spec/vandalism_detection/diff_spec.rb
275
+ - spec/vandalism_detection/edit_spec.rb
276
+ - spec/vandalism_detection/evaluator_spec.rb
277
+ - spec/vandalism_detection/feature_calculator_spec.rb
278
+ - spec/vandalism_detection/features/all_wordlists_frequency_spec.rb
279
+ - spec/vandalism_detection/features/all_wordlists_impact_spec.rb
280
+ - spec/vandalism_detection/features/anonymity_previous_spec.rb
281
+ - spec/vandalism_detection/features/anonymity_spec.rb
282
+ - spec/vandalism_detection/features/article_size_spec.rb
283
+ - spec/vandalism_detection/features/bad_frequency_spec.rb
284
+ - spec/vandalism_detection/features/bad_impact_spec.rb
285
+ - spec/vandalism_detection/features/base_spec.rb
286
+ - spec/vandalism_detection/features/biased_frequency_spec.rb
287
+ - spec/vandalism_detection/features/biased_impact_spec.rb
288
+ - spec/vandalism_detection/features/blanking_spec.rb
289
+ - spec/vandalism_detection/features/character_diversity_spec.rb
290
+ - spec/vandalism_detection/features/character_sequence_spec.rb
291
+ - spec/vandalism_detection/features/comment_bad_frequency_spec.rb
292
+ - spec/vandalism_detection/features/comment_biased_frequency_spec.rb
293
+ - spec/vandalism_detection/features/comment_length_spec.rb
294
+ - spec/vandalism_detection/features/comment_markup_frequency_spec.rb
295
+ - spec/vandalism_detection/features/comment_pronoun_frequency_spec.rb
296
+ - spec/vandalism_detection/features/comment_sex_frequency_spec.rb
297
+ - spec/vandalism_detection/features/comment_vulgarism_frequency_spec.rb
298
+ - spec/vandalism_detection/features/compressibility_spec.rb
299
+ - spec/vandalism_detection/features/contains_base_spec.rb
300
+ - spec/vandalism_detection/features/copyedit_spec.rb
301
+ - spec/vandalism_detection/features/digit_ratio_spec.rb
302
+ - spec/vandalism_detection/features/edits_per_user_spec.rb
303
+ - spec/vandalism_detection/features/emoticons_frequency_spec.rb
304
+ - spec/vandalism_detection/features/emoticons_impact_spec.rb
305
+ - spec/vandalism_detection/features/frequency_base_spec.rb
306
+ - spec/vandalism_detection/features/impact_base_spec.rb
307
+ - spec/vandalism_detection/features/inserted_character_distribution_spec.rb
308
+ - spec/vandalism_detection/features/inserted_external_links_spec.rb
309
+ - spec/vandalism_detection/features/inserted_internal_links_spec.rb
310
+ - spec/vandalism_detection/features/inserted_size_spec.rb
311
+ - spec/vandalism_detection/features/inserted_words_spec.rb
312
+ - spec/vandalism_detection/features/longest_word_spec.rb
313
+ - spec/vandalism_detection/features/markup_frequency_spec.rb
314
+ - spec/vandalism_detection/features/markup_impact_spec.rb
315
+ - spec/vandalism_detection/features/non_alphanumeric_ratio_spec.rb
316
+ - spec/vandalism_detection/features/personal_life_spec.rb
317
+ - spec/vandalism_detection/features/pronoun_frequency_spec.rb
318
+ - spec/vandalism_detection/features/pronoun_impact_spec.rb
319
+ - spec/vandalism_detection/features/removed_all_wordlists_frequency_spec.rb
320
+ - spec/vandalism_detection/features/removed_bad_frequency_spec.rb
321
+ - spec/vandalism_detection/features/removed_biased_frequency_spec.rb
322
+ - spec/vandalism_detection/features/removed_character_distribution_spec.rb
323
+ - spec/vandalism_detection/features/removed_emoticons_frequency_spec.rb
324
+ - spec/vandalism_detection/features/removed_markup_frequency_spec.rb
325
+ - spec/vandalism_detection/features/removed_pronoun_frequency_spec.rb
326
+ - spec/vandalism_detection/features/removed_sex_frequency_spec.rb
327
+ - spec/vandalism_detection/features/removed_size_spec.rb
328
+ - spec/vandalism_detection/features/removed_vulgarism_frequency_spec.rb
329
+ - spec/vandalism_detection/features/removed_words_spec.rb
330
+ - spec/vandalism_detection/features/replacement_similarity_spec.rb
331
+ - spec/vandalism_detection/features/reverted_spec.rb
332
+ - spec/vandalism_detection/features/revisions_character_distribution_spec.rb
333
+ - spec/vandalism_detection/features/same_editor_spec.rb
334
+ - spec/vandalism_detection/features/sex_frequency_spec.rb
335
+ - spec/vandalism_detection/features/sex_impact_spec.rb
336
+ - spec/vandalism_detection/features/size_increment_spec.rb
337
+ - spec/vandalism_detection/features/size_ratio_spec.rb
338
+ - spec/vandalism_detection/features/term_frequency_spec.rb
339
+ - spec/vandalism_detection/features/time_interval_spec.rb
340
+ - spec/vandalism_detection/features/time_of_day_spec.rb
341
+ - spec/vandalism_detection/features/upper_case_ratio_spec.rb
342
+ - spec/vandalism_detection/features/upper_case_words_ratio_spec.rb
343
+ - spec/vandalism_detection/features/upper_to_lower_case_ratio_spec.rb
344
+ - spec/vandalism_detection/features/user_reputation_spec.rb
345
+ - spec/vandalism_detection/features/vulgarism_frequency_spec.rb
346
+ - spec/vandalism_detection/features/vulgarism_impact_spec.rb
347
+ - spec/vandalism_detection/features/weekday_spec.rb
348
+ - spec/vandalism_detection/features/words_increment_spec.rb
349
+ - spec/vandalism_detection/instances_spec.rb
350
+ - spec/vandalism_detection/page_parser_spec.rb
351
+ - spec/vandalism_detection/page_spec.rb
352
+ - spec/vandalism_detection/revision_parser_spec.rb
353
+ - spec/vandalism_detection/revision_spec.rb
354
+ - spec/vandalism_detection/test_dataset_spec.rb
355
+ - spec/vandalism_detection/text_spec.rb
356
+ - spec/vandalism_detection/training_dataset_spec.rb
357
+ - spec/vandalism_detection/wikitext_extractor_spec.rb
358
+ - spec/weka/classifiers/functions/lib_svm_spec.rb
359
+ - spec/weka/classifiers/meta/one_class_classifier_spec.rb
360
+ - spec/weka/classifiers/meta/real_ada_boost_spec.rb
361
+ - spec/weka/classifiers/trees/balanced_random_forest_spec.rb
362
+ - spec/weka/filters/supervised/instance/smote_spec.rb
363
+ - wikipedia-vandalism_detection.gemspec
364
+ homepage: ''
365
+ licenses:
366
+ - GPL v3
367
+ metadata: {}
368
+ post_install_message:
369
+ rdoc_options: []
370
+ require_paths:
371
+ - lib
372
+ required_ruby_version: !ruby/object:Gem::Requirement
373
+ requirements:
374
+ - - '>='
375
+ - !ruby/object:Gem::Version
376
+ version: '0'
377
+ required_rubygems_version: !ruby/object:Gem::Requirement
378
+ requirements:
379
+ - - '>='
380
+ - !ruby/object:Gem::Version
381
+ version: '0'
382
+ requirements: []
383
+ rubyforge_project:
384
+ rubygems_version: 2.1.9
385
+ signing_key:
386
+ specification_version: 4
387
+ summary: Wikipedia vandalism detection with JRuby.
388
+ test_files:
389
+ - spec/factories/edit.rb
390
+ - spec/factories/page.rb
391
+ - spec/factories/revision.rb
392
+ - spec/resources/config/config.yml
393
+ - spec/resources/corpora/test/edits.csv
394
+ - spec/resources/corpora/test/ground-truth.txt
395
+ - spec/resources/corpora/test/revisions/part-1/326471754.txt
396
+ - spec/resources/corpora/test/revisions/part-1/326873205.txt
397
+ - spec/resources/corpora/test/revisions/part-1/328774035.txt
398
+ - spec/resources/corpora/test/revisions/part-2/307084144.txt
399
+ - spec/resources/corpora/test/revisions/part-2/326978767.txt
400
+ - spec/resources/corpora/test/revisions/part-2/328774110.txt
401
+ - spec/resources/corpora/training/annotations.csv
402
+ - spec/resources/corpora/training/edits.csv
403
+ - spec/resources/corpora/training/revisions/part-1/326471754.txt
404
+ - spec/resources/corpora/training/revisions/part-1/326873205.txt
405
+ - spec/resources/corpora/training/revisions/part-1/328774035.txt
406
+ - spec/resources/corpora/training/revisions/part-2/307084144.txt
407
+ - spec/resources/corpora/training/revisions/part-2/326978767.txt
408
+ - spec/resources/corpora/training/revisions/part-2/328774110.txt
409
+ - spec/resources/page_with_redirects.xml
410
+ - spec/resources/redirect_page.xml
411
+ - spec/resources/revision_simplified.xml
412
+ - spec/resources/sample_revision.txt
413
+ - spec/resources/sample_revision_clean_text.txt
414
+ - spec/resources/sample_revision_plain_text.txt
415
+ - spec/resources/vandalism_on_wikipedia.xml
416
+ - spec/resources/vandalism_on_wikipedia_simplified.xml
417
+ - spec/resources/wikipedia_tokens.txt
418
+ - spec/spec_helper.rb
419
+ - spec/support/macros/file_reading.rb
420
+ - spec/support/macros/test_configuration.rb
421
+ - spec/vandalism_detection/algorithms/kullback_leibler_divergence_spec.rb
422
+ - spec/vandalism_detection/classifier_spec.rb
423
+ - spec/vandalism_detection/configuration_spec.rb
424
+ - spec/vandalism_detection/diff_spec.rb
425
+ - spec/vandalism_detection/edit_spec.rb
426
+ - spec/vandalism_detection/evaluator_spec.rb
427
+ - spec/vandalism_detection/feature_calculator_spec.rb
428
+ - spec/vandalism_detection/features/all_wordlists_frequency_spec.rb
429
+ - spec/vandalism_detection/features/all_wordlists_impact_spec.rb
430
+ - spec/vandalism_detection/features/anonymity_previous_spec.rb
431
+ - spec/vandalism_detection/features/anonymity_spec.rb
432
+ - spec/vandalism_detection/features/article_size_spec.rb
433
+ - spec/vandalism_detection/features/bad_frequency_spec.rb
434
+ - spec/vandalism_detection/features/bad_impact_spec.rb
435
+ - spec/vandalism_detection/features/base_spec.rb
436
+ - spec/vandalism_detection/features/biased_frequency_spec.rb
437
+ - spec/vandalism_detection/features/biased_impact_spec.rb
438
+ - spec/vandalism_detection/features/blanking_spec.rb
439
+ - spec/vandalism_detection/features/character_diversity_spec.rb
440
+ - spec/vandalism_detection/features/character_sequence_spec.rb
441
+ - spec/vandalism_detection/features/comment_bad_frequency_spec.rb
442
+ - spec/vandalism_detection/features/comment_biased_frequency_spec.rb
443
+ - spec/vandalism_detection/features/comment_length_spec.rb
444
+ - spec/vandalism_detection/features/comment_markup_frequency_spec.rb
445
+ - spec/vandalism_detection/features/comment_pronoun_frequency_spec.rb
446
+ - spec/vandalism_detection/features/comment_sex_frequency_spec.rb
447
+ - spec/vandalism_detection/features/comment_vulgarism_frequency_spec.rb
448
+ - spec/vandalism_detection/features/compressibility_spec.rb
449
+ - spec/vandalism_detection/features/contains_base_spec.rb
450
+ - spec/vandalism_detection/features/copyedit_spec.rb
451
+ - spec/vandalism_detection/features/digit_ratio_spec.rb
452
+ - spec/vandalism_detection/features/edits_per_user_spec.rb
453
+ - spec/vandalism_detection/features/emoticons_frequency_spec.rb
454
+ - spec/vandalism_detection/features/emoticons_impact_spec.rb
455
+ - spec/vandalism_detection/features/frequency_base_spec.rb
456
+ - spec/vandalism_detection/features/impact_base_spec.rb
457
+ - spec/vandalism_detection/features/inserted_character_distribution_spec.rb
458
+ - spec/vandalism_detection/features/inserted_external_links_spec.rb
459
+ - spec/vandalism_detection/features/inserted_internal_links_spec.rb
460
+ - spec/vandalism_detection/features/inserted_size_spec.rb
461
+ - spec/vandalism_detection/features/inserted_words_spec.rb
462
+ - spec/vandalism_detection/features/longest_word_spec.rb
463
+ - spec/vandalism_detection/features/markup_frequency_spec.rb
464
+ - spec/vandalism_detection/features/markup_impact_spec.rb
465
+ - spec/vandalism_detection/features/non_alphanumeric_ratio_spec.rb
466
+ - spec/vandalism_detection/features/personal_life_spec.rb
467
+ - spec/vandalism_detection/features/pronoun_frequency_spec.rb
468
+ - spec/vandalism_detection/features/pronoun_impact_spec.rb
469
+ - spec/vandalism_detection/features/removed_all_wordlists_frequency_spec.rb
470
+ - spec/vandalism_detection/features/removed_bad_frequency_spec.rb
471
+ - spec/vandalism_detection/features/removed_biased_frequency_spec.rb
472
+ - spec/vandalism_detection/features/removed_character_distribution_spec.rb
473
+ - spec/vandalism_detection/features/removed_emoticons_frequency_spec.rb
474
+ - spec/vandalism_detection/features/removed_markup_frequency_spec.rb
475
+ - spec/vandalism_detection/features/removed_pronoun_frequency_spec.rb
476
+ - spec/vandalism_detection/features/removed_sex_frequency_spec.rb
477
+ - spec/vandalism_detection/features/removed_size_spec.rb
478
+ - spec/vandalism_detection/features/removed_vulgarism_frequency_spec.rb
479
+ - spec/vandalism_detection/features/removed_words_spec.rb
480
+ - spec/vandalism_detection/features/replacement_similarity_spec.rb
481
+ - spec/vandalism_detection/features/reverted_spec.rb
482
+ - spec/vandalism_detection/features/revisions_character_distribution_spec.rb
483
+ - spec/vandalism_detection/features/same_editor_spec.rb
484
+ - spec/vandalism_detection/features/sex_frequency_spec.rb
485
+ - spec/vandalism_detection/features/sex_impact_spec.rb
486
+ - spec/vandalism_detection/features/size_increment_spec.rb
487
+ - spec/vandalism_detection/features/size_ratio_spec.rb
488
+ - spec/vandalism_detection/features/term_frequency_spec.rb
489
+ - spec/vandalism_detection/features/time_interval_spec.rb
490
+ - spec/vandalism_detection/features/time_of_day_spec.rb
491
+ - spec/vandalism_detection/features/upper_case_ratio_spec.rb
492
+ - spec/vandalism_detection/features/upper_case_words_ratio_spec.rb
493
+ - spec/vandalism_detection/features/upper_to_lower_case_ratio_spec.rb
494
+ - spec/vandalism_detection/features/user_reputation_spec.rb
495
+ - spec/vandalism_detection/features/vulgarism_frequency_spec.rb
496
+ - spec/vandalism_detection/features/vulgarism_impact_spec.rb
497
+ - spec/vandalism_detection/features/weekday_spec.rb
498
+ - spec/vandalism_detection/features/words_increment_spec.rb
499
+ - spec/vandalism_detection/instances_spec.rb
500
+ - spec/vandalism_detection/page_parser_spec.rb
501
+ - spec/vandalism_detection/page_spec.rb
502
+ - spec/vandalism_detection/revision_parser_spec.rb
503
+ - spec/vandalism_detection/revision_spec.rb
504
+ - spec/vandalism_detection/test_dataset_spec.rb
505
+ - spec/vandalism_detection/text_spec.rb
506
+ - spec/vandalism_detection/training_dataset_spec.rb
507
+ - spec/vandalism_detection/wikitext_extractor_spec.rb
508
+ - spec/weka/classifiers/functions/lib_svm_spec.rb
509
+ - spec/weka/classifiers/meta/one_class_classifier_spec.rb
510
+ - spec/weka/classifiers/meta/real_ada_boost_spec.rb
511
+ - spec/weka/classifiers/trees/balanced_random_forest_spec.rb
512
+ - spec/weka/filters/supervised/instance/smote_spec.rb