adaboost 0.0.1 → 0.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 2144b2d6abb1c701c8dbf955673a9a5ffd96e00e
-  data.tar.gz: 74dbd52e82039ca79e2dcfa3ef8c2b2ac20bd3e7
+  metadata.gz: c0f5373579f8f93316192361c02c0b29e176f09b
+  data.tar.gz: 6f1c7a127b3b2283fab1b2bf3b4679e32e4587b7
 SHA512:
-  metadata.gz: 035ca3856d5343afde2f968f43cc5de165f0f69fb1f8284c87fe2ba4525599221eb711ffeced58346ddbfbf2b89f640a240fbf336c3c2e367d6e6f99826a932b
-  data.tar.gz: d6f6adc39fa2327ea37e986f759976d83c9c0efda519f429af0d9325927fffe9dc8c540b84556ba890434fd59674b550191dd7d1f8df8ad9e39759795e697be8
+  metadata.gz: 28f2c7b14a2e372be409a593c0ec45fda9feedbb08d700ae85b2714dbea3121aba8660b271711a4dac67245293fed1c579cebc662040dfc6d89e6db7d85f9c84
+  data.tar.gz: 6ea5ebf0d20243bbb5ba409990d3f7950d842a6a713ee6f14169ab96832e95d7b0296c884c63322f9c5066fc3511387fc775350fc1e63102625af2aa848734ed

data/lib/adaboost/adaboost.rb

@@ -12,6 +12,39 @@ module AdaBoost
       @y_index = y_index
     end
 
+    def train samples
+      if Config::OVER_SAMPLING_TRAINING_SET 
+        resampler = Resampler.new @y_index
+        resampler.over_sample samples
+      end
+      initialize_weights samples
+      0.upto @number_of_classifiers - 1 do |i|
+        weak_classifier = @weak_learner.generate_weak_classifier samples, @weights
+        weak_classifier.compute_alpha
+        update_weights weak_classifier, samples
+        @weak_classifiers << weak_classifier
+      end
+    end
+
+    def classify sample
+      score = 0.0
+      @weak_classifiers.each do |weak_classifier| 
+        score += weak_classifier.classify_with_alpha sample
+      end
+      score
+    end
+
+    def self.build_from_model model, y_index = 0
+      classifiers = model.weak_classifiers
+      adaboost = AdaBoost.new classifiers.size, y_index
+      classifiers.each do |classifier|
+        adaboost.weak_classifiers << WeakClassifier.new(classifier.feature_number, classifier.split, classifier.alpha)
+      end
+      adaboost
+    end
+
+    private
+
     def initialize_weights samples
       samples_size = samples.size.to_f
       negative_weight = 1 / samples_size
@@ -46,29 +79,5 @@ module AdaBoost
           @weights[i] /= sum
       end
     end
-
-    def train samples
-        puts "boom2"
-      if Config::OVER_SAMPLING_TRAINING_SET 
-        resampler = Resampler.new @y_index
-        resampler.over_sample samples
-      end
-      initialize_weights samples
-      0.upto @number_of_classifiers - 1 do |i|
-        puts "boom"
-        weak_classifier = @weak_learner.generate_weak_classifier samples, @weights
-        weak_classifier.compute_alpha
-        update_weights weak_classifier, samples
-        @weak_classifiers << weak_classifier
-      end
-    end
-
-    def classify sample
-      score = 0.0
-      @weak_classifiers.each do |weak_classifier| 
-        score += weak_classifier.classify_with_alpha sample
-      end
-      score
-    end
   end
 end

data/lib/adaboost/evaluator.rb

@@ -21,6 +21,26 @@ module AdaBoost
       contingency_table
     end
 
+    def used_feature_numbers unique = false
+      used_feature_numbers = []
+      @classifier.weak_classifiers.each do |weak_classifier|
+        used_feature_numbers << weak_classifier.feature_number
+      end
+      unique ? used_feature_numbers.uniq : used_feature_numbers
+    end
+
+    def feature_occurrences
+      used_numbers = used_feature_numbers
+      occurrences = {}
+      used_numbers.each do |number|
+        occurrences[number] = 0 if occurrences[number].nil?
+        occurrences[number] += 1
+      end
+      occurrences
+    end
+
+    private
+
     def threshold
       if @threshold == Float::MAX
         @threshold = 0
@@ -31,6 +51,10 @@ module AdaBoost
       @threshold
     end
 
+    def classify_normally sample
+      @classifier.classify(sample > 0) ? 1 : -1
+    end
+
     def classify_using_threshold sample
       score = 0.0
       @classifier.weak_classifiers.each do |weak_classifier|
@@ -40,27 +64,5 @@ module AdaBoost
       end
       score > threshold ? 1 : -1
     end
-
-    def classify_normally sample
-      @classifier.classify(sample > 0) ? 1 : -1
-    end
-
-    def used_feature_numbers unique = false
-      used_feature_numbers = []
-      @classifier.weak_classifiers.each do |weak_classifier|
-        used_feature_numbers << weak_classifier.feature_number
-      end
-      unique ? used_feature_numbers.uniq : used_feature_numbers
-    end
-
-    def feature_occurrences
-      used_numbers = used_feature_numbers
-      occurrences = {}
-      used_numbers.each do |number|
-        occurrences[number] = 0 if occurrences[number].nil?
-        occurrences[number] += 1
-      end
-      occurrences
-    end
   end
 end

data/lib/adaboost/resampler.rb

@@ -23,6 +23,8 @@ module AdaBoost
       end
     end
 
+    private
+
     def distribution instances
       analyzer = FeaturesAnalyzer.new @y_index
       analyzer.analyze(instances).distribution

data/lib/adaboost/weak_classifier.rb

@@ -5,11 +5,11 @@ module AdaBoost
     attr_accessor :error
     attr_reader :feature_number, :split, :alpha
 
-    def initialize feature_number, split
+    def initialize feature_number, split, alpha = 0.0, error = 0.0
       @feature_number = feature_number
       @split = split
-      @error = 0.0
-      @alpha = 0.0
+      @error = error
+      @alpha = alpha
     end
 
     def compute_alpha

data/lib/adaboost/weak_learner.rb

@@ -50,6 +50,8 @@ module AdaBoost
       best
     end
 
+    private
+
     def generate_random_classifiers samples, number_of_features
       classifiers = []
       statistics = features_satistics samples

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: adaboost
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - Dalmir da Silva