idhja22 2.0.0 → 2.0.1

data/lib/idhja22/tree/node.rb

@@ -1,26 +1,26 @@
 module Idhja22
   class Node
     class << self
-      def build_node(dataset, attributes_available, depth, parent_probability = nil)
+      def build_node(dataset, attributes_available, depth, prior = nil)
         if(dataset.size < Idhja22.config.min_dataset_size)
-          return Idhja22::LeafNode.new(dataset.m_estimate(parent_probability), dataset.category_label)
+          return Idhja22::LeafNode.build(dataset, prior)
         end
 
         #if successful termination - create and return a leaf node
         if(dataset.terminating? && depth > 0) # don't terminate without splitting the data at least once
-          return Idhja22::LeafNode.new(dataset.m_estimate(parent_probability), dataset.category_label)
+          return Idhja22::LeafNode.build(dataset, prior)
         end
 
         if(depth >= 3) # don't let trees get too long
-          return Idhja22::LeafNode.new(dataset.m_estimate(parent_probability), dataset.category_label)
+          return Idhja22::LeafNode.build(dataset, prior)
         end
 
         #if we have no more attributes left to split the dataset on, then return a leafnode
         if(attributes_available.empty?)
-          return Idhja22::LeafNode.new(dataset.m_estimate(parent_probability), dataset.category_label)
+          return Idhja22::LeafNode.build(dataset, prior)
         end
 
-        node = DecisionNode.build(dataset, attributes_available, depth, dataset.m_estimate(parent_probability))
+        node = DecisionNode.build(dataset, attributes_available, depth, prior)
 
         return node
       end
@@ -55,13 +55,15 @@ module Idhja22
     attr_accessor :branches, :decision_attribute, :default_probability
 
     class << self
-      def build(dataset, attributes_available, depth, parent_probability=nil)
+      def build(dataset, attributes_available, depth, prior=nil)
         data_split, best_attribute = best_attribute(dataset, attributes_available)
 
-        output_node = new(best_attribute, parent_probability)
+        probability_guess = dataset.m_estimate(prior)
 
-        data_split.each do |value, dataset|
-          node = Node.build_node(dataset, attributes_available-[best_attribute], depth+1, dataset.m_estimate(parent_probability))
+        output_node = new(best_attribute, probability_guess)
+
+        data_split.each do |value, ds|
+          node = Node.build_node(ds, attributes_available-[best_attribute], depth+1, probability_guess)
           
           output_node.add_branch(value, node) if node && !(node.is_a?(DecisionNode) && node.branches.empty?)
         end
@@ -139,6 +141,13 @@ module Idhja22
 
   class LeafNode < Node
     attr_reader :probability, :category_label
+    class << self
+      def build(dataset, prior)
+        return new(dataset.m_estimate(prior), dataset.category_label)
+      end
+    end
+
+
     def initialize(probability, category_label)
       @probability = probability
       @category_label = category_label

data/lib/idhja22/version.rb

@@ -1,3 +1,3 @@
 module Idhja22
-  VERSION = "2.0.0"
+  VERSION = "2.0.1"
 end

data/spec/tree_spec.rb

@@ -21,7 +21,7 @@ describe Idhja22::Tree do
 
   describe('#get_rules') do
     it 'should list the rules of the tree' do
-      Idhja22::Tree.train(@ds).get_rules.should == "if 2 == a and 4 == a and then chance of C = 0.88\nelsif 2 == a and 4 == b and then chance of C = 0.48\nelsif 2 == b and then chance of C = 0.38"
+      Idhja22::Tree.train(@ds).get_rules.should == "if 2 == a and 4 == a and then chance of C = 0.77\nelsif 2 == a and 4 == b and then chance of C = 0.53\nelsif 2 == b and then chance of C = 0.46"
     end
   end
 
@@ -48,7 +48,7 @@ describe Idhja22::Tree do
     it 'should return the probabilty at the leaf of the tree' do
       tree = Idhja22::Tree.train(@ds)
       query = Idhja22::Dataset::Datum.new(['z','z','a','z','a'],['0', '1','2','3','4'],'C')
-      tree.evaluate(query).should be_within(0.001).of(0.878)
+      tree.evaluate(query).should be_within(0.001).of(0.774)
     end
   end
 

data/spec/version_spec.rb

@@ -3,7 +3,7 @@ require 'spec_helper'
 describe Idhja22 do
   describe 'VERSION' do
     it 'should be current version' do
-      Idhja22::VERSION.should == '2.0.0'
+      Idhja22::VERSION.should == '2.0.1'
     end
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: idhja22
 version: !ruby/object:Gem::Version
-  version: 2.0.0
+  version: 2.0.1
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-12-21 00:00:00.000000000 Z
+date: 2013-01-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -177,7 +177,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -4074205080648422327
+      hash: 3616736987678555050
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -186,7 +186,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -4074205080648422327
+      hash: 3616736987678555050
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.24