lib/ankusa/classifier.rb in ankusa-0.0.6 vs lib/ankusa/classifier.rb in ankusa-0.0.7

@@ -1,8 +1,8 @@
 module Ankusa
 
-  class Classifier
+  module Classifier
     attr_reader :classnames
 
     def initialize(storage)
       @storage = storage
       @storage.init_tables
@@ -40,47 +40,9 @@
       @storage.incr_doc_count klass, -doccount
       # cache is now dirty of these vars
       @doc_count_totals = nil
       @vocab_sizes = nil
       th
-    end
-
-    def classify(text, classes=nil)
-      # return the most probable class
-      log_likelihoods(text, classes).sort_by { |c| -c[1] }.first.first
-    end
-    
-    # Classes is an array of classes to look at
-    def classifications(text, classnames=nil)
-      result = log_likelihoods text, classnames
-      result.keys.each { |k|
-        result[k] = Math.exp result[k] 
-      }
-
-      # normalize to get probs
-      sum = result.values.inject { |x,y| x+y }
-      result.keys.each { |k| result[k] = result[k] / sum }
-      result
-    end
-
-    # Classes is an array of classes to look at
-    def log_likelihoods(text, classnames=nil)
-      classnames ||= @classnames
-      result = Hash.new 0
-
-      TextHash.new(text).each { |word, count|
-        probs = get_word_probs(word, classnames)
-        classnames.each { |k| result[k] += (Math.log(probs[k]) * count) }
-      }
-
-      # add the prior and exponentiate
-      doc_counts = doc_count_totals.select { |k,v| classnames.include? k }.map { |k,v| v }
-      doc_count_total = (doc_counts.inject { |x,y| x+y } + classnames.length).to_f
-      classnames.each { |k| 
-        result[k] += Math.log((@storage.get_doc_count(k) + 1).to_f / doc_count_total) 
-      }
-      
-      result
     end
 
     protected
     def get_word_probs(word, classnames)
       probs = Hash.new 0