Did a lot of refactoring...

.gitignore

@@ -0,0 +1,2 @@
+.bundle
+bayesdata.yml

.ruby-version

@@ -0,0 +1 @@
+2.1.3

CHANGELOG.md

@@ -0,0 +1,10 @@
+# Revisions
+##0.5.0
+* Lots of refactoring, cleanup, making methods private, etc.
+* Added tests
+* Removed uid from train/untrain - couldn't think of a good use case, and the logic didn't seem right since the system doesn't keep track of which call to train created a token the untrain option would blindly remove them.
+* Changed BayesData to BayesPool since that seems more explanatory
+* Moved some pool manipulation functions into BayesPool for better encapsulation
+* Add to_json method
+* Removed data_class from Bayes initializer since I couldn't think of a reason to make that configurable
+* Create corpus in build cache instead of maintaining it in parallel

Gemfile

@@ -0,0 +1,7 @@
+source 'http://rubygems.org'
+ruby '2.1.3'
+gem 'stemmer'
+
+group :test do
+  gem 'minitest'
+end

Gemfile.lock

@@ -0,0 +1,12 @@
+GEM
+  remote: http://rubygems.org/
+  specs:
+    minitest (5.4.2)
+    stemmer (1.0.1)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  minitest
+  stemmer

README.md

@@ -0,0 +1,40 @@
+# Introduction
+This is a Naive Bayes classifier that can be used to categorize text based on trained "pools".
+Training counts how often each word is used, except for any specified stop words.
+The Bayes::Bishop.guess method tokenizes the message and then calculates for each pool the probability that the message is the same "classification" as that pool.
+For example, you could train the system with one pool of "spam" email and one pool of "non-spam" email.  Then you could ask the guess method which pool each incoming message belongs to.
+
+# Usage
+1. Create a Bishop::Bayes object:
+
+	b = Bishop::Bayes.new
+
+2. Train with multiple pools of text:
+
+	b.train('pool1')  
+	b.train('pool2')  
+	b.train('pool3')  
+
+3. Call the guess method with a message to categorize:
+
+	guesses = b.guess('This is a sentence')
+
+   The return value is a hash where the keys are pool names and the values are the probability
+   that the message belongs to that pool.  
+
+# Features
+* Stop words may be specified
+
+	b.add_stop_words(an_array_words)  
+	b.add_stop_word('word')  
+
+* You can include the default stop words list  
+
+	b.load_default_stop_words  
+
+* You can choose between the default tokenizer, a stemming tokenizer, or a custom tokenizer
+
+	b = Bishop::Bayes.new
+	b = Bishop::Bayes.new(Bishop::StemmingTokenizer)
+	b = Bishop::Bayes.new(CustomTokenizer)
+

Rakefile

@@ -0,0 +1,30 @@
+require 'rake/testtask'
+require 'rdoc/task'
+
+#desc "Default task: test"
+task :default => [:test]
+
+desc "Run Tests"
+Rake::TestTask.new( :test ) do |t|
+  t.pattern = "test/test_*.rb"
+  t.verbose = true
+end
+
+RDoc::Task.new(:rdoc) do |rdoc|
+  rdoc.main = 'README.md'
+  rdoc.rdoc_files.include 'README.md', 'CHANGELOG.md', "lib/**/*\.rb" 
+  rdoc.rdoc_dir = 'docs/rdoc'
+  rdoc.title = "Bayes::Bishop Documentation"
+  rdoc.options << '--line-numbers'
+  rdoc.options << '--fileboxes'
+end
+
+RDoc::Task.new(:rdoc => "rdoc_markdown",:clobber_rdoc => "clobber_rdoc_markdown", :rerdoc => "rerdoc_markdown") do |rdoc|
+  rdoc.main = 'README.md'
+  rdoc.rdoc_files.include 'README.md', 'CHANGELOG.md', "lib/**/*\.rb" 
+  rdoc.rdoc_dir = 'docs/md'
+  rdoc.title = "Bayes::Bishop Documentation"
+  rdoc.markup = 'MARKUP' 
+  rdoc.options << '--line-numbers'
+  rdoc.options << '--fileboxes'
+end

bishop.gemspec

@@ -2,21 +2,21 @@ require 'rubygems'
 
 SPEC = Gem::Specification.new do |s|
 	s.name			=		"bishop"
-	s.version		=		"0.4.0"
-	s.author		=		"Matt Mower"
-	s.email			=		"self@mattmower.com"
-	s.homepage		=		"http://rubyforge.org/projects/bishop/"
+	s.version		=		"0.5.0"
+	s.author		=		"Richard Harrington"
+	s.email			=		"richard@maymount.com"
+  s.license  = 'LGPL-3.0+'
+	s.homepage		=		"https://github.com/maymount/bishop"
 	s.platform		=		Gem::Platform::RUBY
-	s.summary		=		"Bayesian classification and ART-2 clustering library."
-
-	candidates		=		Dir.glob( "{bin,docs,lib,test}/**/*" )
+	s.summary		=		"Bayesian classification library. Refactoring of mmowers/bishop version."
+	s.description		=		"Bayesian classification library. Refactoring of mmowers/bishop version."
+	s.add_runtime_dependency 'stemmer'
+	candidates		=		Dir.glob( "{docs,lib,test}/**/*" )
 
 	s.files 		=		candidates.delete_if do |item|
 								item.include?( "CVS" ) || item.include?( "rdoc" )
 							end
+  s.extra_rdoc_files = ['README.md','CHANGELOG.md','COPYING','COPYING.LESSER']
 	s.require_path	=		"lib"
-# 	s.autorequire	=		"bishop"
 	s.has_rdoc		=		true
-
-	#s.add_dependency( "stemmer", ">= 1.0.1" )
 end

docs/md/Bishop.html

@@ -0,0 +1,202 @@
+<!DOCTYPE html>
+
+<html>
+<head>
+<meta charset="UTF-8">
+
+<title>module Bishop - Bayes::Bishop Documentation</title>
+
+<link href="./fonts.css" rel="stylesheet">
+<link href="./rdoc.css" rel="stylesheet">
+
+<script type="text/javascript">
+  var rdoc_rel_prefix = "./";
+</script>
+
+<script src="./js/jquery.js"></script>
+<script src="./js/navigation.js"></script>
+<script src="./js/search_index.js"></script>
+<script src="./js/search.js"></script>
+<script src="./js/searcher.js"></script>
+<script src="./js/darkfish.js"></script>
+
+
+<body id="top" role="document" class="module">
+<nav role="navigation">
+  <div id="project-navigation">
+    <div id="home-section" role="region" title="Quick navigation" class="nav-section">
+  <h2>
+    <a href="./index.html" rel="home">Home</a>
+  </h2>
+
+  <div id="table-of-contents-navigation">
+    <a href="./table_of_contents.html#pages">Pages</a>
+    <a href="./table_of_contents.html#classes">Classes</a>
+    <a href="./table_of_contents.html#methods">Methods</a>
+  </div>
+</div>
+
+    <div id="search-section" role="search" class="project-section initially-hidden">
+  <form action="#" method="get" accept-charset="utf-8">
+    <div id="search-field-wrapper">
+      <input id="search-field" role="combobox" aria-label="Search"
+             aria-autocomplete="list" aria-controls="search-results"
+             type="text" name="search" placeholder="Search" spellcheck="false"
+             title="Type to search, Up and Down to navigate, Enter to load">
+    </div>
+
+    <ul id="search-results" aria-label="Search Results"
+        aria-busy="false" aria-expanded="false"
+        aria-atomic="false" class="initially-hidden"></ul>
+  </form>
+</div>
+
+  </div>
+
+
+
+  <div id="class-metadata">
+
+
+
+
+    <!-- Method Quickref -->
+<div id="method-list-section" class="nav-section">
+  <h3>Methods</h3>
+
+  <ul class="link-list" role="directory">
+
+    <li ><a href="#method-c-robinson">::robinson</a>
+
+    <li ><a href="#method-c-robinson_fisher">::robinson_fisher</a>
+
+  </ul>
+</div>
+
+  </div>
+</nav>
+
+<main role="main" aria-labelledby="module-Bishop">
+  <h1 id="module-Bishop" class="module">
+    module Bishop
+  </h1>
+
+  <section class="description">
+
+  </section>
+
+
+
+
+  <section id="5Buntitled-5D" class="documentation-section">
+
+
+
+
+
+
+
+
+
+     <section id="public-class-5Buntitled-5D-method-details" class="method-section">
+       <header>
+         <h3>Public Class Methods</h3>
+       </header>
+
+
+      <div id="method-c-robinson" class="method-detail ">
+
+        <div class="method-heading">
+          <span class="method-name">robinson</span><span
+            class="method-args">( probs, ignore )</span>
+
+          <span class="method-click-advice">click to toggle source</span>
+
+        </div>
+
+
+        <div class="method-description">
+
+          <p>default “combiner” set in initialize ignore is truly ignored</p>
+
+
+
+
+          <div class="method-source-code" id="robinson-source">
+            <pre><span class="ruby-comment"># File lib/bayes/bishop.rb, line 419</span>
+<span class="ruby-keyword">def</span> <span class="ruby-keyword">self</span>.<span class="ruby-identifier">robinson</span>( <span class="ruby-identifier">probs</span>, <span class="ruby-identifier">ignore</span> )
+  <span class="ruby-identifier">nth</span> = <span class="ruby-value">1.0</span><span class="ruby-operator">/</span><span class="ruby-identifier">probs</span>.<span class="ruby-identifier">length</span>
+  <span class="ruby-identifier">what_is_p</span> = <span class="ruby-value">1.0</span> <span class="ruby-operator">-</span> <span class="ruby-identifier">probs</span>.<span class="ruby-identifier">map</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">p</span><span class="ruby-operator">|</span> <span class="ruby-value">1.0</span> <span class="ruby-operator">-</span> <span class="ruby-identifier">p</span>[<span class="ruby-value">1</span>] }.<span class="ruby-identifier">inject</span>( <span class="ruby-value">1.0</span> ) { <span class="ruby-operator">|</span><span class="ruby-identifier">s</span>,<span class="ruby-identifier">v</span><span class="ruby-operator">|</span> <span class="ruby-identifier">s</span> <span class="ruby-operator">*</span> <span class="ruby-identifier">v</span> } <span class="ruby-operator">**</span> <span class="ruby-identifier">nth</span>
+  <span class="ruby-identifier">what_is_q</span> = <span class="ruby-value">1.0</span> <span class="ruby-operator">-</span> <span class="ruby-identifier">probs</span>.<span class="ruby-identifier">map</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">p</span><span class="ruby-operator">|</span> <span class="ruby-identifier">p</span>[<span class="ruby-value">1</span>] }.<span class="ruby-identifier">inject</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">s</span>,<span class="ruby-identifier">v</span><span class="ruby-operator">|</span> <span class="ruby-identifier">s</span> <span class="ruby-operator">*</span> <span class="ruby-identifier">v</span> } <span class="ruby-operator">**</span> <span class="ruby-identifier">nth</span>
+  <span class="ruby-identifier">what_is_s</span> = ( <span class="ruby-identifier">what_is_p</span> <span class="ruby-operator">-</span> <span class="ruby-identifier">what_is_q</span> ) <span class="ruby-operator">/</span> ( <span class="ruby-identifier">what_is_p</span> <span class="ruby-operator">+</span> <span class="ruby-identifier">what_is_q</span> )
+  ( <span class="ruby-value">1</span> <span class="ruby-operator">+</span> <span class="ruby-identifier">what_is_s</span> ) <span class="ruby-operator">/</span> <span class="ruby-value">2</span>
+<span class="ruby-keyword">end</span></pre>
+          </div>
+
+        </div>
+
+
+
+
+      </div>
+
+
+      <div id="method-c-robinson_fisher" class="method-detail ">
+
+        <div class="method-heading">
+          <span class="method-name">robinson_fisher</span><span
+            class="method-args">( probs, ignore )</span>
+
+          <span class="method-click-advice">click to toggle source</span>
+
+        </div>
+
+
+        <div class="method-description">
+
+          <p>Alternative combiner</p>
+
+
+
+
+          <div class="method-source-code" id="robinson_fisher-source">
+            <pre><span class="ruby-comment"># File lib/bayes/bishop.rb, line 428</span>
+<span class="ruby-keyword">def</span> <span class="ruby-keyword">self</span>.<span class="ruby-identifier">robinson_fisher</span>( <span class="ruby-identifier">probs</span>, <span class="ruby-identifier">ignore</span> )
+  <span class="ruby-identifier">n</span> = <span class="ruby-identifier">probs</span>.<span class="ruby-identifier">length</span>
+
+  <span class="ruby-keyword">begin</span>
+    <span class="ruby-identifier">h</span> = <span class="ruby-identifier">chi2p</span>( <span class="ruby-value">-2.0</span> <span class="ruby-operator">*</span> <span class="ruby-constant">Math</span>.<span class="ruby-identifier">log</span>( <span class="ruby-identifier">probs</span>.<span class="ruby-identifier">map</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">p</span><span class="ruby-operator">|</span> <span class="ruby-identifier">p</span>[<span class="ruby-value">1</span>] }.<span class="ruby-identifier">inject</span>( <span class="ruby-value">1.0</span> ) { <span class="ruby-operator">|</span><span class="ruby-identifier">s</span>,<span class="ruby-identifier">v</span><span class="ruby-operator">|</span> <span class="ruby-identifier">s</span><span class="ruby-operator">*</span><span class="ruby-identifier">v</span> } ), <span class="ruby-value">2</span><span class="ruby-operator">*</span><span class="ruby-identifier">n</span> )
+  <span class="ruby-keyword">rescue</span>
+    <span class="ruby-identifier">h</span> = <span class="ruby-value">0.0</span>
+  <span class="ruby-keyword">end</span>
+
+  <span class="ruby-keyword">begin</span>      
+    <span class="ruby-identifier">s</span> = <span class="ruby-identifier">chi2p</span>( <span class="ruby-value">-2.0</span> <span class="ruby-operator">*</span> <span class="ruby-constant">Math</span>.<span class="ruby-identifier">log</span>( <span class="ruby-identifier">probs</span>.<span class="ruby-identifier">map</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">p</span><span class="ruby-operator">|</span> <span class="ruby-value">1.0</span> <span class="ruby-operator">-</span> <span class="ruby-identifier">p</span>[<span class="ruby-value">1</span>] }.<span class="ruby-identifier">inject</span>( <span class="ruby-value">1.0</span> ) { <span class="ruby-operator">|</span><span class="ruby-identifier">s</span>,<span class="ruby-identifier">v</span><span class="ruby-operator">|</span> <span class="ruby-identifier">s</span><span class="ruby-operator">*</span><span class="ruby-identifier">v</span> } ), <span class="ruby-value">2</span><span class="ruby-operator">*</span><span class="ruby-identifier">n</span> )
+  <span class="ruby-keyword">rescue</span>
+    <span class="ruby-identifier">s</span> = <span class="ruby-value">0.0</span>
+  <span class="ruby-keyword">end</span>
+
+  ( <span class="ruby-value">1</span> <span class="ruby-operator">+</span> <span class="ruby-identifier">h</span> <span class="ruby-operator">-</span> <span class="ruby-identifier">s</span> ) <span class="ruby-operator">/</span> <span class="ruby-value">2</span>
+<span class="ruby-keyword">end</span></pre>
+          </div>
+
+        </div>
+
+
+
+
+      </div>
+
+
+    </section>
+
+  </section>
+</main>
+
+
+<footer id="validator-badges" role="contentinfo">
+  <p><a href="http://validator.w3.org/check/referer">Validate</a>
+  <p>Generated by <a href="http://rdoc.rubyforge.org">RDoc</a> 4.1.0.
+  <p>Based on <a href="http://deveiate.org/projects/Darkfish-Rdoc/">Darkfish</a> by <a href="http://deveiate.org">Michael Granger</a>.
+</footer>
+