scoruby 0.2.5 → 0.2.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6d01f41ef6e3e3485acb65587892402866004bd2
-  data.tar.gz: 7d898f2a4c86915e19952a3641286dd252d7c3fd
+  metadata.gz: 2a1c339dc5c029d90d8e3a495af90499368bc92d
+  data.tar.gz: 5ff3c0147290c83d76261b9a6907e35ca493b678
 SHA512:
-  metadata.gz: de6e7acbbcf5acd97f2b980253be94c7eb2fb7c31fb76c9c9d1fe6ca09447751974734370826d1477db639685a6ab37108ced5d85e4fc9b397285e1b61468a4e
-  data.tar.gz: 92e5728b151d7c3daa24e5fccebe6b7e8567c92af4fb03cdbc5b5ef20f5a75b53c88b5ef79e6d4db20df157995f45b6222677a0e1634702e3769240b61f025d4
+  metadata.gz: 8843f6c37d4b4d4e30f018348b5ec113e66558b2c78c945f4755ea01554b609af3dbb4a50334143ffa8f4bab205303b833831273a97bd18a2ecc9fa4e214f401
+  data.tar.gz: 94078bb11bd0cf3490c93c90e822fed248d4721e24a2623004d2cd3af8805407d6a69599ba2d753bd024caefb0d7e08eb8ddebefef1f37b3dbfe2dcdf49a3bad

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    scoruby (0.2.4)
+    scoruby (0.2.5)
       nokogiri (~> 1.7)
 
 GEM
@@ -18,9 +18,9 @@ GEM
     docile (1.1.5)
     json (2.1.0)
     method_source (0.8.2)
-    mini_portile2 (2.1.0)
-    nokogiri (1.7.0.1)
-      mini_portile2 (~> 2.1.0)
+    mini_portile2 (2.2.0)
+    nokogiri (1.8.0)
+      mini_portile2 (~> 2.2.0)
     pry (0.10.3)
       coderay (~> 1.1.0)
       method_source (~> 0.8.1)
@@ -64,4 +64,4 @@ DEPENDENCIES
   scoruby!
 
 BUNDLED WITH
-   1.11.2
+   1.15.4

data/lib/scoruby/models/naive_bayes/model.rb

@@ -0,0 +1,64 @@
+require 'scoruby/models/naive_bayes/model_data'
+require 'forwardable'
+
+module Scoruby
+  module Models
+    module NaiveBayes
+      class Model
+        extend Forwardable
+        def_delegators :@model_data, :threshold, :labels, :numerical_features, :category_features
+
+        def initialize(xml)
+          @model_data = ModelData.new(xml)
+        end
+
+        def lvalues(features)
+          calc_label_feature_values(features)
+          calc_label_values
+        end
+
+        def score(features, label)
+          lvalues(features)[label] / lvalues(features).values.reduce(:+)
+        end
+
+        private
+
+        def calc_label_values
+          label_values = {}
+          labels.each do |label, label_data|
+            label_data.each do |key, value|
+              label_data[key] = threshold if value.round(5).zero?
+            end
+            label_values[label] = label_data.values.reduce(:*)
+          end
+          label_values
+        end
+
+        def calc_label_feature_values(features)
+          labels.each do |label, _|
+            features.each do |feature_name, feature_value|
+              label_value = calc_category(feature_name, feature_value, label)
+              label_value ||= calc_numerical(feature_name, feature_value, label)
+              labels[label][feature_name] = label_value if label_value
+            end
+          end
+        end
+
+        def calc_category(feature_name, feature_value, label)
+          return unless category_features[feature_name] && category_features[feature_name][feature_value]
+          value_count = category_features[feature_name][feature_value][label].to_f
+          overall_count = category_features[feature_name].sum { |_, value| value[label].to_f }
+          value_count / overall_count
+        end
+
+        def calc_numerical(feature_name, feature_value, label)
+          return unless numerical_features[feature_name] && numerical_features[feature_name][label]
+          variance = numerical_features[feature_name][label][:variance].to_f
+          mean = numerical_features[feature_name][label][:mean].to_f
+          feature_value = feature_value.to_f
+          Math.exp(-(feature_value - mean)**2 / (2 * variance)) / Math.sqrt(2 * Math::PI * variance)
+        end
+      end
+    end
+  end
+end

data/lib/scoruby/models/naive_bayes/model_data.rb

@@ -0,0 +1,68 @@
+module Scoruby
+  module Models
+    module NaiveBayes
+      class ModelData
+        attr_reader :threshold, :labels, :numerical_features, :category_features
+
+        def initialize(xml)
+          @xml = xml
+          fetch_threshold
+          fetch_features_data
+          fetch_label_counts
+        end
+
+        private
+
+        def fetch_threshold
+          @threshold = @xml.xpath('//NaiveBayesModel').attr('threshold').value.to_f
+        end
+
+        def fetch_features_data
+          @category_features = {}
+          @numerical_features = {}
+          @xml.xpath('//BayesInput').each do |feature|
+            @category_features[feature.attr('fieldName').to_sym] = fetch_category_feature(feature)
+            @numerical_features[feature.attr('fieldName').to_sym] = fetch_numerical_feature(feature)
+          end
+        end
+
+        def fetch_label_counts
+          @labels = {}
+          @xml.xpath('//BayesOutput//TargetValueCount').each do |l|
+            l.attr('value')
+            @labels[l.attr('value')] = {'count': l.attr('count').to_f}
+          end
+        end
+        
+        def fetch_numerical_feature(feature)
+          return unless feature.child.name == 'TargetValueStats'
+          features_data = {}
+          feature.child.children.each do |child|
+            features_data[child.attr('value').strip] = {
+                mean: child.child.attr('mean'),
+                variance: child.child.attr('variance')
+            }
+          end
+          features_data
+        end
+
+        def fetch_category_feature(feature)
+          return unless feature.children.any? { |f| f.name == 'PairCounts' }
+          feature_data = {}
+          feature.children.each do |category|
+            feature_data[category.attr('value')] = fetch_category(category)
+          end
+          feature_data
+        end
+
+        def fetch_category(category)
+          category_data = {}
+          category.child.children.each do |label|
+            category_data[label.attr('value')] = label.attr('count')
+          end
+          category_data
+        end
+      end
+    end
+  end
+end

data/lib/scoruby/models_factory.rb

@@ -1,6 +1,7 @@
 require 'scoruby/models/decision_tree'
 require 'scoruby/models/gbm'
 require 'scoruby/models/random_forest'
+require 'scoruby/models/naive_bayes/model'
 
 module Scoruby
   class ModelsFactory
@@ -12,10 +13,15 @@ module Scoruby
       return Models::RandomForest.new(xml) if random_forest?(xml)
       return Models::Gbm.new(xml) if gbm?(xml)
       return Models::DecisionTree.new(xml.child) if decision_tree?(xml)
+      return Models::NaiveBayes::Model.new(xml) if naive_bayes?(xml)
 
       raise MODEL_NOT_SUPPORTED_ERROR
     end
 
+    def self.naive_bayes?(xml)
+      !xml.xpath('PMML/NaiveBayesModel').empty?
+    end
+
     def self.decision_tree?(xml)
       !xml.xpath('PMML/TreeModel').empty?
     end

data/lib/scoruby/version.rb

@@ -1,3 +1,3 @@
 module Scoruby
-  VERSION = '0.2.5'
+  VERSION = '0.2.6'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: scoruby
 version: !ruby/object:Gem::Version
-  version: 0.2.5
+  version: 0.2.6
 platform: ruby
 authors:
 - Asaf Schers
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-09-14 00:00:00.000000000 Z
+date: 2017-09-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -131,7 +131,8 @@ files:
 - lib/scoruby/features.rb
 - lib/scoruby/models/decision_tree.rb
 - lib/scoruby/models/gbm.rb
-- lib/scoruby/models/naive_bayes.rb
+- lib/scoruby/models/naive_bayes/model.rb
+- lib/scoruby/models/naive_bayes/model_data.rb
 - lib/scoruby/models/random_forest.rb
 - lib/scoruby/models_factory.rb
 - lib/scoruby/node.rb

data/lib/scoruby/models/naive_bayes.rb

@@ -1,92 +0,0 @@
-module Scoruby
-  module Models
-    class NaiveBayes
-      attr_reader :data
-
-      def initialize(xml)
-        @threshold = xml.xpath('//NaiveBayesModel').attr('threshold').value.to_f
-        @data = {}
-        xml.xpath('//BayesInput').each do |feature|
-          @data[feature.attr('fieldName').to_sym] = fetch_feature(feature)
-        end
-
-        @labels = {}
-        xml.xpath('//BayesOutput//TargetValueCount').each do |l| l.attr('value')
-          @labels[l.attr('value')] = { 'count': l.attr('count').to_f }
-        end
-      end
-
-      def lvalues(features)
-        @labels.each do |label, _|
-          features.each do |feature_name, feature_value|
-
-            if @data[feature_name][feature_value]
-              value_count = @data[feature_name][feature_value][label].to_f
-              overall_count = @data[feature_name].sum { |_, value| value[label].to_f }
-
-              @labels[label][feature_name] = value_count / overall_count
-            elsif @data[feature_name][label]
-              @labels[label][feature_name] = calc_numerical(@data[feature_name][label], feature_value)
-            end
-          end
-        end
-
-        lvalues = {}
-        @labels.each do |label, label_data|
-          label_data.each do |key, value|
-            label_data[key] = @threshold if value.round(5).zero?
-          end
-          lvalues[label] = label_data.values.reduce(:*)
-        end
-        lvalues
-      end
-
-      def score(features, label)
-        lvalues = lvalues(features)
-        lvalues[label] / lvalues.values.reduce(:+)
-      end
-
-      private
-
-      def calc_numerical(label_data, feature_value)
-        variance = label_data[:variance].to_f
-        mean = label_data[:mean].to_f
-        feature_value = feature_value.to_f
-
-        Math.exp(-(feature_value - mean)**2 / (2 * variance)) / Math.sqrt(2 * Math::PI * variance)
-      end
-
-      def fetch_feature(feature)
-        return fetch_numerical_feature(feature) if feature.child.name == 'TargetValueStats'
-        fetch_category_feature(feature)
-      end
-
-      def fetch_numerical_feature(feature)
-        features_data = {}
-        feature.child.children.each do |child|
-          features_data[child.attr('value').strip] = {
-            mean: child.child.attr('mean'),
-            variance: child.child.attr('variance')
-          }
-        end
-        features_data
-      end
-
-      def fetch_category_feature(feature)
-        feature_data = {}
-        feature.children.each do |category|
-          feature_data[category.attr('value')] = fetch_category(category)
-        end
-        feature_data
-      end
-
-      def fetch_category(category)
-        category_data = {}
-        category.child.children.each do |label|
-          category_data[label.attr('value')] = label.attr('count')
-        end
-        category_data
-      end
-    end
-  end
-end