solid_naive_bayes 0.0.3

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: e76c76d77d5b450025bae114082124feaeb0adc06da2ff80135f0d20ec7911ca
+  data.tar.gz: 7b7b16848ed4cea466afcfaae2eb644c2417c0b052958c21858d2b71b18d49ea
+SHA512:
+  metadata.gz: a26f0e3250f6724091c117c6c43f33a681a8c611a52971d131b86fed3cdf4a55245604de5d4850ea18c70858b3ba60be5cdb28ed18c2cabe5f2de06604c6a9a7
+  data.tar.gz: 2e590688e26cd3481ddb5a48f3d08bc36d6fbd1fef2536c67b774386d287c6820f4eca14781e9c12147fd56b807b8909962ddc65868ce839dc3d40c2257fcf5b

data/.document

@@ -0,0 +1,5 @@
+README.rdoc
+lib/**/*.rb
+bin/*
+features/**/*.feature
+LICENSE

data/.gitignore

@@ -0,0 +1,21 @@
+## MAC OS
+.DS_Store
+
+## TEXTMATE
+*.tmproj
+tmtags
+
+## EMACS
+*~
+\#*
+.\#*
+
+## VIM
+*.swp
+
+## PROJECT::GENERAL
+coverage
+rdoc
+pkg
+
+## PROJECT::SPECIFIC

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2009 reddavis
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.rdoc

@@ -0,0 +1,53 @@
+= Naive Bayes Classifier
+
+This is an extremely simple, straight forward Naive Bayes implementation.
+
+== Install
+
+  gem sources -a -http://gemcutter.org
+  sudo gem install naive_bayes
+  
+== How To Use
+
+  require 'rubygems'
+  require 'naive_bayes'
+  
+  a = NaiveBayes.new(:spam, :ham)
+  
+  a.train(:spam, 'bad', 'word')
+  a.train(:ham, 'good', 'word')
+  
+  b = "this is a bad sentence".split(' ')
+  
+  a.classify(*b)
+    #=> [:spam, 0.03125]
+    
+You can also tell your classifier to save itself, so its easy for you to pick up where you left off:
+
+  require 'rubygems'
+  require 'naive_bayes'
+
+  a = NaiveBayes.new(:spam, :ham)
+  a.db_filepath = 'path/to/anywhere.nb'
+  
+  a.train(:spam, 'bad', 'word')
+  a.train(:ham, 'good', 'word')
+  
+  a.save
+
+Some time goes past and we want to classify a new document we just received...
+  
+  require 'rubygems'
+  require 'naive_bayes'
+  
+  a = NaiveBayes.load('path/to/file') 
+  
+  b = "this is a bad sentence".split(' ')
+  
+  # It's as if we were never apart
+  a.classify(*b)
+    #=> [:spam, 0.03125]
+  
+== Copyright
+
+Copyright (c) 2009 Red Davis. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,45 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "naive_bayes"
+    gem.summary = %Q{Simple straight forward Naive Bayes classifier implementation}
+    gem.description = %Q{Simple straight forward Naive Bayes classifier implementation}
+    gem.email = "reddavis@gmail.com"
+    gem.homepage = "http://github.com/reddavis/Naive-Bayes"
+    gem.authors = ["reddavis"]
+    gem.add_development_dependency "rspec", ">= 1.2.9"
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+  end
+  Jeweler::GemcutterTasks.new
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
+end
+
+require 'spec/rake/spectask'
+Spec::Rake::SpecTask.new(:spec) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.spec_files = FileList['spec/**/*_spec.rb']
+end
+
+Spec::Rake::SpecTask.new(:rcov) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.rcov = true
+end
+
+task :spec => :check_dependencies
+
+task :default => :spec
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  version = File.exist?('VERSION') ? File.read('VERSION') : ""
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "naive_bayes #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end

data/VERSION

@@ -0,0 +1 @@
+0.0.3

data/lib/naive_bayes.rb

@@ -0,0 +1,98 @@
+# Bayes Theorem
+# P(A|B) = P(B|A) * P(A) / P(B)
+
+# Terminology
+# An ITEM is made up of FEATURES
+# An ITEM belongs to a CLASS
+
+# Bayes With Our Terminology
+# P(Class | Item) = P(Item | Class) * P(Class) / P(Item)
+
+# However, when classifying, P(Item) is the same across all calcualtions
+# So we don't bother to calculate it
+class NaiveBayes
+  
+  class << self
+    def load(db_path)
+      data = ""
+      File.open(db_path) do |f|
+        while line = f.gets
+          data << line
+        end
+      end
+      Marshal.load(data)
+    end
+  end
+    
+  attr_accessor :db_filepath  
+  
+  def initialize(*klasses)
+    @features_count = {}
+    @klass_count = {}
+    @klasses = klasses
+    
+    klasses.each do |klass|
+      @features_count[klass] = Hash.new(0.0)
+      @klass_count[klass] = 0.0
+    end
+  end
+  
+  def train(klass, *features)
+    features.uniq.each do |feature|
+      @features_count[klass][feature] += 1
+    end
+    @klass_count[klass] += 1
+  end
+  
+  def untrain(klass, *features)
+    features.uniq.each do |feature|
+      @features_count[klass][feature] -= 1
+    end
+    @klass_count[klass] -= 1
+  end
+  
+  #P(Class | Item) = P(Item | Class) * P(Class)
+  def classify(*features)
+    scores = {}
+    @klasses.each do |klass|
+      scores[klass] = (prob_of_item_given_a_class(features, klass) * prob_of_class(klass))
+    end
+    return [] if scores.values.reduce(:+) == 0.0
+    scores.sort {|a,b| b[1] <=> a[1]}[0]
+  end
+  
+  def save
+    raise "You haven't set a db_filpath, I dont know where to save" if @db_filepath.nil?
+    File.open(@db_filepath, "w+") do |f|
+      f.write(Marshal.dump(self))
+    end
+  end
+  
+  private
+    
+  # P(Item | Class)
+  def prob_of_item_given_a_class(features, klass)
+    a = features.inject(1.0) do |sum, feature|
+      prob = prob_of_feature_given_a_class(feature, klass)
+    end
+  end
+  
+  # P(Feature | Class)
+  def prob_of_feature_given_a_class(feature, klass)
+    # If there is not any sentence in our trained models we return nil value
+    @feature = @features_count[klass][feature.to_sym]
+    feature.nil? ? feature : @features_count[klass][feature.to_sym] / @klass_count[klass]
+  end
+  
+  # P(Class)
+  def prob_of_class(klass)
+    @klass_count[klass] / total_items
+  end
+  
+  def total_items
+    @klass_count.inject(0) do |sum, klass|
+      sum += klass[1]
+    end
+  end
+  
+end

data/naive_bayes.gemspec

@@ -0,0 +1,56 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{solid_naive_bayes}
+  s.version = "0.0.3"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["reddavis"]
+  s.date = %q{2010-03-11}
+  s.description = %q{Simple straight forward Naive Bayes classifier implementation}
+  s.email = %q{reddavis@gmail.com}
+  s.extra_rdoc_files = [
+    "LICENSE",
+     "README.rdoc"
+  ]
+  s.files = [
+    ".document",
+     ".gitignore",
+     "LICENSE",
+     "README.rdoc",
+     "Rakefile",
+     "VERSION",
+     "lib/naive_bayes.rb",
+     "naive_bayes.gemspec",
+     "spec/db/naive.nb",
+     "spec/naive_bayes_spec.rb",
+     "spec/spec.opts",
+     "spec/spec_helper.rb"
+  ]
+  s.homepage = %q{http://github.com/reddavis/Naive-Bayes}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.6}
+  s.summary = %q{Simple straight forward Naive Bayes classifier implementation}
+  s.test_files = [
+    "spec/naive_bayes_spec.rb",
+     "spec/spec_helper.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+      s.add_development_dependency(%q<rspec>, [">= 1.2.9"])
+    else
+      s.add_dependency(%q<rspec>, [">= 1.2.9"])
+    end
+  else
+    s.add_dependency(%q<rspec>, [">= 1.2.9"])
+  end
+end
+

data/spec/db/naive.nb

@@ -0,0 +1 @@
+o:NaiveBayes	:@features_count{:	spam}I"bad:EFf1I"	word;Ff1f0:ham}I"we;Ff1I"bad;Ff1@:@klass_count{;f1;	f1:

data/spec/naive_bayes_spec.rb

@@ -0,0 +1,75 @@
+require File.expand_path(File.dirname(__FILE__) + '/spec_helper')
+
+describe "NaiveBayes" do
+    
+  describe "Classification" do
+    before do
+      @classifier = create_and_train_classifier
+    end
+    
+    it "should classify as spam with a score of 0.5" do
+      a = @classifier.classify('bad', 'word')
+      a[0].should == :spam
+      a[1].should == 0.5
+    end
+    
+    it "should change information" do
+      @classifier.untrain(:spam, 'bad', 'word')
+      a = @classifier.classify('bad', 'word')
+      a[0].should == :ham
+      a[1].should == 1.0
+    end
+  end
+  
+  describe "Saving the NB" do
+    describe "DB filepath has been set" do
+      before do
+        @classifier = NaiveBayes.new(:spam, :ham)
+        @classifier.db_filepath = db_filepath
+      end
+    
+      it "should save to the filepath provided" do
+        FileUtils.rm(db_filepath, :force => true)
+        @classifier.save
+        File.exists?(db_filepath).should be_true
+      end
+    end
+    
+    describe "DB filepath has no been set" do
+      it "should raise an error" do
+        lambda do  
+          NaiveBayes.new(:spam, :ham).save
+        end.should raise_error
+      end
+    end
+  end
+  
+  describe "Load" do
+    before do
+      classifier = NaiveBayes.new(:spam, :ham)
+      classifier.db_filepath = db_filepath
+      classifier.train(:spam, 'bad', 'word')
+      classifier.train(:ham, 'we', 'bad')
+      classifier.save
+    end
+    
+    it "should return 0.5" do
+      classifier = NaiveBayes.load(db_filepath)
+      classifier.classify('bad', 'word')[1].should == 0.5
+    end
+  end
+  
+  private
+  
+  def create_and_train_classifier
+    a = NaiveBayes.new(:spam, :ham)
+    a.train(:spam, 'bad', 'word')
+    a.train(:ham, 'we', 'bad')
+    a
+  end
+  
+  def db_filepath
+    File.expand_path(File.dirname(__FILE__) + '/db/naive.nb')
+  end
+  
+end

data/spec/spec.opts

@@ -0,0 +1 @@
+--color

data/spec/spec_helper.rb

@@ -0,0 +1,9 @@
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+require 'naive_bayes'
+require 'spec'
+require 'spec/autorun'
+
+Spec::Runner.configure do |config|
+  
+end

metadata

@@ -0,0 +1,73 @@
+--- !ruby/object:Gem::Specification
+name: solid_naive_bayes
+version: !ruby/object:Gem::Version
+  version: 0.0.3
+platform: ruby
+authors:
+- reddavis
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2010-03-11 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.2.9
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.2.9
+description: Simple straight forward Naive Bayes classifier implementation
+email: reddavis@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files:
+- LICENSE
+- README.rdoc
+files:
+- ".document"
+- ".gitignore"
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- lib/naive_bayes.rb
+- naive_bayes.gemspec
+- spec/db/naive.nb
+- spec/naive_bayes_spec.rb
+- spec/spec.opts
+- spec/spec_helper.rb
+homepage: http://github.com/reddavis/Naive-Bayes
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options:
+- "--charset=UTF-8"
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 3.0.0.beta3
+signing_key: 
+specification_version: 3
+summary: Simple straight forward Naive Bayes classifier implementation
+test_files:
+- spec/naive_bayes_spec.rb
+- spec/spec_helper.rb