ankusa 0.0.3 → 0.0.4

data/Rakefile

@@ -22,7 +22,7 @@ Rake::TestTask.new("test") { |t|
 
 spec = Gem::Specification.new do |s|
   s.name = "ankusa"
-  s.version = "0.0.3"
+  s.version = "0.0.4"
   s.authors = ["Brian Muller"]
   s.date = %q{2010-12-02}
   s.description = "Naive Bayes classifier with HBase storage"
@@ -32,7 +32,7 @@ spec = Gem::Specification.new do |s|
   s.homepage = "https://github.com/livingsocial/ankusa"
   s.require_paths = ["lib"]
   s.rubygems_version = "1.3.5"
-  s.add_dependency('hbaserb', '>= 0.0.1')
+  s.add_dependency('hbaserb', '>= 0.0.3')
   s.add_dependency('fast-stemmer', '>= 1.0.0')
 end
 

data/docs/classes/Ankusa/Classifier.html

@@ -167,7 +167,7 @@
             onclick="toggleCode('M000007-source');return false;">[Source]</a></p>
           <div class="method-source-code" id="M000007-source">
 <pre>
-<span class="ruby-comment cmt"># File lib/ankusa/classifier.rb, line 44</span>
+<span class="ruby-comment cmt"># File lib/ankusa/classifier.rb, line 46</span>
     <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">classifications</span>(<span class="ruby-identifier">text</span>)
       <span class="ruby-identifier">result</span> = <span class="ruby-constant">Hash</span>.<span class="ruby-identifier">new</span> <span class="ruby-value">0</span>
 
@@ -206,7 +206,7 @@
             onclick="toggleCode('M000006-source');return false;">[Source]</a></p>
           <div class="method-source-code" id="M000006-source">
 <pre>
-<span class="ruby-comment cmt"># File lib/ankusa/classifier.rb, line 39</span>
+<span class="ruby-comment cmt"># File lib/ankusa/classifier.rb, line 41</span>
     <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">classify</span>(<span class="ruby-identifier">text</span>)
       <span class="ruby-comment cmt"># return the most probable class</span>
       <span class="ruby-identifier">classifications</span>(<span class="ruby-identifier">text</span>).<span class="ruby-identifier">sort_by</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">c</span><span class="ruby-operator">|</span> <span class="ruby-operator">-</span><span class="ruby-identifier">c</span>[<span class="ruby-value">1</span>] }.<span class="ruby-identifier">first</span>.<span class="ruby-identifier">first</span>
@@ -244,6 +244,7 @@ text can be either an array of strings or a string klass is a symbol
       <span class="ruby-identifier">doccount</span> = (<span class="ruby-identifier">text</span>.<span class="ruby-identifier">kind_of?</span> <span class="ruby-constant">Array</span>) <span class="ruby-operator">?</span> <span class="ruby-identifier">text</span>.<span class="ruby-identifier">length</span> <span class="ruby-operator">:</span> <span class="ruby-value">1</span>
       <span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">incr_doc_count</span> <span class="ruby-identifier">klass</span>, <span class="ruby-identifier">doccount</span>
       <span class="ruby-ivar">@classnames</span> <span class="ruby-operator">&lt;&lt;</span> <span class="ruby-identifier">klass</span> <span class="ruby-keyword kw">if</span> <span class="ruby-keyword kw">not</span> <span class="ruby-ivar">@classnames</span>.<span class="ruby-identifier">include?</span> <span class="ruby-identifier">klass</span>
+      <span class="ruby-identifier">th</span>
     <span class="ruby-keyword kw">end</span>
 </pre>
           </div>
@@ -267,7 +268,7 @@ text can be either an array of strings or a string klass is a symbol
             onclick="toggleCode('M000005-source');return false;">[Source]</a></p>
           <div class="method-source-code" id="M000005-source">
 <pre>
-<span class="ruby-comment cmt"># File lib/ankusa/classifier.rb, line 28</span>
+<span class="ruby-comment cmt"># File lib/ankusa/classifier.rb, line 29</span>
     <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">untrain</span>(<span class="ruby-identifier">klass</span>, <span class="ruby-identifier">text</span>)
       <span class="ruby-identifier">th</span> = <span class="ruby-constant">TextHash</span>.<span class="ruby-identifier">new</span>(<span class="ruby-identifier">text</span>)
       <span class="ruby-identifier">th</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">word</span>, <span class="ruby-identifier">count</span><span class="ruby-operator">|</span>
@@ -277,6 +278,7 @@ text can be either an array of strings or a string klass is a symbol
       <span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">incr_total_word_count</span> <span class="ruby-identifier">klass</span>, <span class="ruby-operator">-</span><span class="ruby-identifier">th</span>.<span class="ruby-identifier">word_count</span>
       <span class="ruby-identifier">doccount</span> = (<span class="ruby-identifier">text</span>.<span class="ruby-identifier">kind_of?</span> <span class="ruby-constant">Array</span>) <span class="ruby-operator">?</span> <span class="ruby-identifier">text</span>.<span class="ruby-identifier">length</span> <span class="ruby-operator">:</span> <span class="ruby-value">1</span>
       <span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">incr_doc_count</span> <span class="ruby-identifier">klass</span>, <span class="ruby-operator">-</span><span class="ruby-identifier">doccount</span>
+      <span class="ruby-identifier">th</span>
     <span class="ruby-keyword kw">end</span>
 </pre>
           </div>
@@ -299,7 +301,7 @@ text can be either an array of strings or a string klass is a symbol
             onclick="toggleCode('M000008-source');return false;">[Source]</a></p>
           <div class="method-source-code" id="M000008-source">
 <pre>
-<span class="ruby-comment cmt"># File lib/ankusa/classifier.rb, line 65</span>
+<span class="ruby-comment cmt"># File lib/ankusa/classifier.rb, line 67</span>
     <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">get_word_probs</span>(<span class="ruby-identifier">word</span>)
       <span class="ruby-identifier">probs</span> = <span class="ruby-ivar">@storage</span>.<span class="ruby-identifier">get_word_counts</span>(<span class="ruby-identifier">word</span>)
       <span class="ruby-ivar">@classnames</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">cn</span><span class="ruby-operator">|</span> 

data/docs/created.rid

@@ -1 +1 @@
-Thu, 02 Dec 2010 16:24:45 -0500
+Fri, 03 Dec 2010 10:45:32 -0500

data/docs/files/lib/ankusa/classifier_rb.html

@@ -56,7 +56,7 @@
     </tr>
     <tr class="top-aligned-row">
       <td><strong>Last Update:</strong></td>
-      <td>Thu Dec 02 16:20:44 -0500 2010</td>
+      <td>Fri Dec 03 07:36:13 -0500 2010</td>
     </tr>
     </table>
   </div>

data/lib/ankusa/classifier.rb

@@ -21,6 +21,7 @@ module Ankusa
       doccount = (text.kind_of? Array) ? text.length : 1
       @storage.incr_doc_count klass, doccount
       @classnames << klass if not @classnames.include? klass
+      th
     end
 
     # text can be either an array of strings or a string
@@ -34,6 +35,7 @@ module Ankusa
       @storage.incr_total_word_count klass, -th.word_count
       doccount = (text.kind_of? Array) ? text.length : 1
       @storage.incr_doc_count klass, -doccount
+      th
     end
 
     def classify(text)

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: ankusa
 version: !ruby/object:Gem::Version 
-  hash: 25
+  hash: 23
   prerelease: false
   segments: 
   - 0
   - 0
-  - 3
-  version: 0.0.3
+  - 4
+  version: 0.0.4
 platform: ruby
 authors: 
 - Brian Muller
@@ -26,12 +26,12 @@ dependencies:
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        hash: 29
+        hash: 25
         segments: 
         - 0
         - 0
-        - 1
-        version: 0.0.1
+        - 3
+        version: 0.0.3
   type: :runtime
   version_requirements: *id001
 - !ruby/object:Gem::Dependency