style: safe-auto-correct Layout cops

DirtyF · DirtyF · commit 9d67f4e36c54 · 2018-11-30T00:39:04.000+01:00
diff --git a/lib/classifier-reborn.rb b/lib/classifier-reborn.rb
@@ -36,4 +36,4 @@
 require_relative 'classifier-reborn/category_namer'
 require_relative 'classifier-reborn/bayes'
 require_relative 'classifier-reborn/lsi'
-require_relative 'classifier-reborn/validators/classifier_validator'
+require_relative 'classifier-reborn/validators/classifier_validator'
diff --git a/lib/classifier-reborn/backends/bayes_memory_backend.rb b/lib/classifier-reborn/backends/bayes_memory_backend.rb
@@ -69,7 +69,7 @@ def reset
     private
 
     def category_counts(category)
-      @category_counts[category] ||= {training: 0, word: 0}
+      @category_counts[category] ||= { training: 0, word: 0 }
     end
   end
 end
diff --git a/lib/classifier-reborn/bayes.rb b/lib/classifier-reborn/bayes.rb
@@ -29,12 +29,11 @@ class Bayes
     #   backend:          BayesMemoryBackend.new  Alternatively, BayesRedisBackend.new for persistent storage
     def initialize(*args)
       @initial_categories = []
-      options = { language:         'en',
+      options = { language: 'en',
                   enable_threshold: false,
-                  threshold:        0.0,
-                  enable_stemmer:   true,
-                  backend:          BayesMemoryBackend.new
-                }
+                  threshold: 0.0,
+                  enable_stemmer: true,
+                  backend: BayesMemoryBackend.new }
       args.flatten.each do |arg|
         if arg.is_a?(Hash)
           options.merge!(arg)
@@ -79,6 +78,7 @@ def train(category, text)
       word_hash = Hasher.word_hash(text, @enable_stemmer,
                                    tokenizer: @tokenizer, token_filters: @token_filters)
       return if word_hash.empty?
+
       category = CategoryNamer.prepare_name(category)
 
       # Add the category dynamically or raise an error
@@ -110,9 +110,11 @@ def untrain(category, text)
       word_hash = Hasher.word_hash(text, @enable_stemmer,
                                    tokenizer: @tokenizer, token_filters: @token_filters)
       return if word_hash.empty?
+
       category = CategoryNamer.prepare_name(category)
       word_hash.each do |word, count|
         next if @backend.total_words < 0
+
         orig = @backend.category_word_frequency(category, word) || 0
         @backend.update_category_word_frequency(category, word, -count)
         if @backend.category_word_frequency(category, word) <= 0
diff --git a/lib/classifier-reborn/extensions/hasher.rb b/lib/classifier-reborn/extensions/hasher.rb
@@ -1,4 +1,5 @@
 # encoding: utf-8
+
 # Author::    Lucas Carlson  (mailto:lucas@rufy.com)
 # Copyright:: Copyright (c) 2005 Lucas Carlson
 # License::   LGPL
diff --git a/lib/classifier-reborn/extensions/token_filter/stemmer.rb b/lib/classifier-reborn/extensions/token_filter/stemmer.rb
@@ -1,4 +1,5 @@
 # encoding: utf-8
+
 # Author::    Lucas Carlson  (mailto:lucas@rufy.com)
 # Copyright:: Copyright (c) 2005 Lucas Carlson
 # License::   LGPL
diff --git a/lib/classifier-reborn/extensions/token_filter/stopword.rb b/lib/classifier-reborn/extensions/token_filter/stopword.rb
@@ -1,4 +1,5 @@
 # encoding: utf-8
+
 # Author::    Lucas Carlson  (mailto:lucas@rufy.com)
 # Copyright:: Copyright (c) 2005 Lucas Carlson
 # License::   LGPL
diff --git a/lib/classifier-reborn/extensions/token_filter/symbol.rb b/lib/classifier-reborn/extensions/token_filter/symbol.rb
@@ -1,4 +1,5 @@
 # encoding: utf-8
+
 # Author::    Lucas Carlson  (mailto:lucas@rufy.com)
 # Copyright:: Copyright (c) 2005 Lucas Carlson
 # License::   LGPL
diff --git a/lib/classifier-reborn/extensions/tokenizer/token.rb b/lib/classifier-reborn/extensions/tokenizer/token.rb
@@ -1,4 +1,5 @@
 # encoding: utf-8
+
 # Author::    Lucas Carlson  (mailto:lucas@rufy.com)
 # Copyright:: Copyright (c) 2005 Lucas Carlson
 # License::   LGPL
diff --git a/lib/classifier-reborn/extensions/tokenizer/whitespace.rb b/lib/classifier-reborn/extensions/tokenizer/whitespace.rb
@@ -1,4 +1,5 @@
 # encoding: utf-8
+
 # Author::    Lucas Carlson  (mailto:lucas@rufy.com)
 # Copyright:: Copyright (c) 2005 Lucas Carlson
 # License::   LGPL
diff --git a/lib/classifier-reborn/extensions/zero_vector.rb b/lib/classifier-reborn/extensions/zero_vector.rb
@@ -1,5 +1,5 @@
 class Vector
   def zero?
-    self.all? {|_| _ == 0}
+    self.all? { |_| _ == 0 }
   end
 end
diff --git a/lib/classifier-reborn/lsi.rb b/lib/classifier-reborn/lsi.rb
@@ -8,7 +8,6 @@
   require 'gsl' # requires https://github.com/SciRuby/rb-gsl
   require_relative 'extensions/vector_serialize'
   $GSL = true
-
 rescue LoadError
   $GSL = false
   require_relative 'extensions/vector'
@@ -133,6 +132,7 @@ def items
     # turning the LSI class into a simple vector search engine.
     def build_index(cutoff = 0.75)
       return unless needs_rebuild?
+
       make_word_list
 
       doc_list = @items.values
@@ -247,6 +247,7 @@ def content_node_norms(content_node)
     # it is actually the same algorithm, just applied on a smaller document.
     def search(string, max_nearest = 3)
       return [] if needs_rebuild?
+
       carry = proximity_norms_for_content(string)
       unless carry.nil?
         result = carry.collect { |x| x[0] }
@@ -308,6 +309,7 @@ def scored_categories(doc, cutoff = 0.30, &block)
     # it's supposed to.
     def highest_ranked_stems(doc, count = 3)
       raise 'Requested stem ranking on non-indexed content!' unless @items[doc]
+
       content_vector_array = node_for_content(doc).lsi_vector.to_a
       top_n = content_vector_array.sort.reverse[0..count - 1]
       top_n.collect { |x| @word_list.word_for_index(content_vector_array.index(x)) }
diff --git a/lib/classifier-reborn/validators/classifier_validator.rb b/lib/classifier-reborn/validators/classifier_validator.rb
@@ -1,9 +1,8 @@
 module ClassifierReborn
   module ClassifierValidator
-
     module_function
 
-    def cross_validate(classifier, sample_data, fold=10, *options)
+    def cross_validate(classifier, sample_data, fold = 10, *options)
       classifier = ClassifierReborn::const_get(classifier).new(options) if classifier.is_a?(String)
       sample_data.shuffle!
       partition_size = sample_data.length / fold
@@ -48,7 +47,7 @@ def generate_report(*conf_mats)
       if conf_mats.length > 1
         conf_mats.each_with_index do |conf_mat, i|
           run_report = build_run_report(conf_mat)
-          print_run_report(run_report, i+1)
+          print_run_report(run_report, i + 1)
           conf_mat.each do |actual, cols|
             cols.each do |predicted, v|
               accumulated_conf_mat[actual][predicted] += v
@@ -78,11 +77,11 @@ def build_run_report(conf_mat)
         end
       end
       total = correct + incorrect
-      {total: total, correct: correct, incorrect: incorrect, accuracy: divide(correct, total)}
+      { total: total, correct: correct, incorrect: incorrect, accuracy: divide(correct, total) }
     end
 
     def conf_mat_to_tab(conf_mat)
-      conf_tab = Hash.new {|h, k| h[k] = {p: {t: 0, f: 0}, n: {t: 0, f: 0}}}
+      conf_tab = Hash.new { |h, k| h[k] = { p: { t: 0, f: 0 }, n: { t: 0, f: 0 } } }
       conf_mat.each_key do |positive|
         conf_mat.each do |actual, cols|
           cols.each do |predicted, v|
@@ -93,32 +92,32 @@ def conf_mat_to_tab(conf_mat)
       conf_tab
     end
 
-    def print_run_report(stats, prefix="", print_header=false)
+    def print_run_report(stats, prefix = "", print_header = false)
       puts "#{"Run".rjust([3, prefix.length].max)}     Total   Correct Incorrect  Accuracy" if print_header
       puts "#{prefix.to_s.rjust(3)} #{stats[:total].to_s.rjust(9)} #{stats[:correct].to_s.rjust(9)} #{stats[:incorrect].to_s.rjust(9)} #{stats[:accuracy].round(5).to_s.ljust(7, '0').rjust(9)}"
     end
 
     def print_conf_mat(conf_mat)
       header = ["Predicted ->"] + conf_mat.keys + ["Total", "Recall"]
       cell_size = header.map(&:length).max
-      header = header.map{|h| h.rjust(cell_size)}.join(" ")
+      header = header.map { |h| h.rjust(cell_size) }.join(" ")
       puts " Confusion Matrix ".center(header.length, "-")
       puts header
       puts "-" * header.length
-      predicted_totals = conf_mat.keys.map{|predicted| [predicted, 0]}.to_h
+      predicted_totals = conf_mat.keys.map { |predicted| [predicted, 0] }.to_h
       correct = 0
       conf_mat.each do |k, rec|
         actual_total = rec.values.reduce(:+)
-        puts ([k.ljust(cell_size)] + rec.values.map{|v| v.to_s.rjust(cell_size)} + [actual_total.to_s.rjust(cell_size), divide(rec[k], actual_total).round(5).to_s.rjust(cell_size)]).join(" ")
+        puts ([k.ljust(cell_size)] + rec.values.map { |v| v.to_s.rjust(cell_size) } + [actual_total.to_s.rjust(cell_size), divide(rec[k], actual_total).round(5).to_s.rjust(cell_size)]).join(" ")
         rec.each do |cat, val|
           predicted_totals[cat] += val
           correct += val if cat == k
         end
       end
       total = predicted_totals.values.reduce(:+)
       puts "-" * header.length
-      puts (["Total".ljust(cell_size)] + predicted_totals.values.map{|v| v.to_s.rjust(cell_size)} + [total.to_s.rjust(cell_size), "".rjust(cell_size)]).join(" ")
-      puts (["Precision".ljust(cell_size)] + predicted_totals.keys.map{|k| divide(conf_mat[k][k], predicted_totals[k]).round(5).to_s.rjust(cell_size)} + ["Accuracy ->".rjust(cell_size), divide(correct, total).round(5).to_s.rjust(cell_size)]).join(" ")
+      puts (["Total".ljust(cell_size)] + predicted_totals.values.map { |v| v.to_s.rjust(cell_size) } + [total.to_s.rjust(cell_size), "".rjust(cell_size)]).join(" ")
+      puts (["Precision".ljust(cell_size)] + predicted_totals.keys.map { |k| divide(conf_mat[k][k], predicted_totals[k]).round(5).to_s.rjust(cell_size) } + ["Accuracy ->".rjust(cell_size), divide(correct, total).round(5).to_s.rjust(cell_size)]).join(" ")
     end
 
     def print_conf_tab(conf_tab)
@@ -135,19 +134,19 @@ def conf_tab_derivations(tab)
       negatives = tab[:n][:t] + tab[:p][:f]
       total     = positives + negatives
       {
-        total_population:   positives + negatives,
+        total_population: positives + negatives,
         condition_positive: positives,
         condition_negative: negatives,
-        true_positive:      tab[:p][:t],
-        true_negative:      tab[:n][:t],
-        false_positive:     tab[:p][:f],
-        false_negative:     tab[:n][:f],
-        prevalence:         divide(positives, total),
-        specificity:        divide(tab[:n][:t], negatives),
-        recall:             divide(tab[:p][:t], positives),
-        precision:          divide(tab[:p][:t], tab[:p][:t] + tab[:p][:f]),
-        accuracy:           divide(tab[:p][:t] + tab[:n][:t], total),
-        f1_score:           divide(2 * tab[:p][:t], 2 * tab[:p][:t] + tab[:p][:f] + tab[:n][:f])
+        true_positive: tab[:p][:t],
+        true_negative: tab[:n][:t],
+        false_positive: tab[:p][:f],
+        false_negative: tab[:n][:f],
+        prevalence: divide(positives, total),
+        specificity: divide(tab[:n][:t], negatives),
+        recall: divide(tab[:p][:t], positives),
+        precision: divide(tab[:p][:t], tab[:p][:t] + tab[:p][:f]),
+        accuracy: divide(tab[:p][:t] + tab[:n][:t], total),
+        f1_score: divide(2 * tab[:p][:t], 2 * tab[:p][:t] + tab[:p][:f] + tab[:n][:f])
       }
     end
 
@@ -159,7 +158,7 @@ def print_derivations(derivations)
     end
 
     def empty_conf_mat(categories)
-      categories.map{|actual| [actual, categories.map{|predicted| [predicted, 0]}.to_h]}.to_h
+      categories.map { |actual| [actual, categories.map { |predicted| [predicted, 0] }.to_h] }.to_h
     end
 
     def divide(dividend, divisor)
diff --git a/script/release b/script/release
@@ -0,0 +1,7 @@
+#!/bin/sh
+# Tag and push a release.
+
+set -e
+
+script/cibuild
+bundle exec rake release
diff --git a/test/bayes/bayesian_integration_test.rb b/test/bayes/bayesian_integration_test.rb
@@ -33,8 +33,8 @@ def test_equality_of_backends
     train_model @memory_classifier
     train_model @redis_classifier
     assert_equal classification_scores(@memory_classifier).hash, classification_scores(@redis_classifier).hash
-    untrain_model @memory_classifier, TRAINING_SIZE/2
-    untrain_model @redis_classifier, TRAINING_SIZE/2
+    untrain_model @memory_classifier, TRAINING_SIZE / 2
+    untrain_model @redis_classifier, TRAINING_SIZE / 2
     assert_equal classification_scores(@memory_classifier).hash, classification_scores(@redis_classifier).hash
   end
 
@@ -45,9 +45,10 @@ def train_model(classifier)
     end
   end
 
-  def untrain_model(classifier, limit=Float::INFINITY)
+  def untrain_model(classifier, limit = Float::INFINITY)
     @training_set.each_with_index do |line, i|
       break if i >= limit
+
       parts = line.strip.split("\t")
       classifier.untrain(parts.first, parts.last)
     end
diff --git a/test/extensions/hasher_test.rb b/test/extensions/hasher_test.rb
@@ -13,6 +13,7 @@ def test_word_hash
 
   module BigramTokenizer
     module_function
+
     def call(str)
       str.each_char
          .each_cons(2)
@@ -56,6 +57,7 @@ def test_custom_tokenizer_lambda
 
   module CatFilter
     module_function
+
     def call(tokens)
       tokens.reject do |token|
         /\Acat\z/i === token
diff --git a/test/lsi/lsi_test.rb b/test/lsi/lsi_test.rb
@@ -191,6 +191,7 @@ def test_keyword_search
 
   def test_invalid_searching_when_using_gsl
     return unless $GSL
+
     lsi = ClassifierReborn::LSI.new
     lsi.add_item @str1, 'Dog'
     lsi.add_item @str2, 'Dog'
diff --git a/test/validators/classifier_validation.rb b/test/validators/classifier_validation.rb
@@ -69,7 +69,7 @@ def test_bayes_classifier_3_fold_cross_validate_redis
   def test_lsi_classifier_5_fold_cross_validate
     lsi = ClassifierReborn::LSI.new
     required_methods = [:train, :classify, :categories]
-    unless required_methods.reduce(true){|m, o| m && lsi.respond_to?(o)}
+    unless required_methods.reduce(true) { |m, o| m && lsi.respond_to?(o) }
       puts "TODO: LSI is not validatable until all of the #{required_methods} methods are implemented!"
       skip
     end

Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,5 @@`
`1`	`1`	`# encoding: utf-8`
	`2`	`+`
`2`	`3`	`# Author:: Lucas Carlson (mailto:lucas@rufy.com)`
`3`	`4`	`# Copyright:: Copyright (c) 2005 Lucas Carlson`
`4`	`5`	`# License:: LGPL`