almost done with first implementation

README.rdoc

@@ -30,4 +30,7 @@ Then, install ankusa:
 
   # This will return Hash with classes as keys and 
   # membership probability as values
-  puts c.classes "This is some spammy text"
+  puts c.classifications "This is some spammy text"
+
+  # get a list of all classes
+  puts c.classes

ankusa.gemspec

@@ -14,5 +14,5 @@ Gem::Specification.new do |s|
   s.require_paths = ["lib"]
   s.rubygems_version = "1.3.5"
   s.add_dependency('hbaserb', '>= 0.0.1')
-  s.add_dependency('stemmer', '>= 1.0.1')
+  s.add_dependency('fast-stemmer', '>= 1.0.0')
 end

lib/ankusa.rb

@@ -1,2 +1,4 @@
 $:.unshift File.dirname(__FILE__)
 require 'ankusa/classifier'
+require 'ankusa/hasher'
+

lib/ankusa/classifier.rb

@@ -1,23 +1,112 @@
-require 'stemmer'
-
 module Ankusa
 
   class Classifier
-    def initialize(hbase_client)
+    attr_reader :classnames
+
+    def initialize(hbase_client, frequency_tablename="ankusa_word_frequencies", summary_tablename="ankusa_summary")
       @hbase = hbase_client
+      @ftablename = frequency_tablename
+      @stablename = summary_tablename
+      init_tables
+      @classnames = refresh_classnames
     end
 
     def train(klass, text)
-      # word.stem
+      th = TextHash.new(text)
+      th.each { |word, count|
+        freq_table.atomic_increment word, "classes:#{klass.to_s}", count
+      }
+      summary_table.atomic_increment klass, "totals:wordcount", th.word_count
+      summary_table.atomic_increment klass, "totals:doccount"
+      @classnames << klass if not @classnames.include? klass
     end
 
     def untrain(klass, text)
+      th = TextHash.new(text)
+      th.each { |word, count|
+        freq_table.atomic_increment word, "classes:#{klass.to_s}", -count
+      }
+      summary_table.atomic_increment klass, "totals:wordcount", -th.word_count
+      summary_table.atomic_increment klass, "totals:doccount", -1
     end
 
     def classify(text)
+      # return the most probable class
+      classifications(text).sort { |o,t| o[1] <=> t[1] }.first.first
+    end
+
+    def classifications(text)
+      classes = {}
+      results = {}
+      @classnames.each { |k| 
+        classes[k] = NBClass.new k, summary_table, freq_table
+        result[k] = 0 
+      }
+
+      TextHash.new(text).each { |word,count|
+        probs = get_counts(word)
+        @classnames.each { |k|
+          result[k] += Math.log(probs[k] / classes[k].word_count)
+        }
+      }
+
+      @classnames.each { |k|
+        result[k] += Math.log(classes[k].doc_count / doc_count_total)
+      }
+
+      # todo
+      # normalize logs to make probs
+      # implement get_counts
+
+      result
+    end
+
+    # get all classes
+    def refresh_classnames
+      cs = []
+      summary_table.create_scanner("", "totals") { |row|
+        cs << row.row.intern
+      }
+      cs
+    end
+
+    def drop_tables
+      freq_table.delete
+      summary_table.delete      
+      @stable = nil
+      @ftable = nil
+    end
+
+    def reset
+      drop_tables
+      init_tables
+    end
+
+    def doc_count_total
+      total = 0
+      summary_table.create_scanner("", "totals:doccount") { |row|
+        total += row.columns["totals:doccount"].to_i64
+      }
+      total
     end
 
-    def classes(text)
+    protected
+    def init_tables
+      if not @hbase.has_table? @ftablename
+        @hbase.create_table @ftablename, "classes", "total"
+      end
+
+      if not @hbase.has_table? @stablename
+        @hbase.create_table @stablename, "totals"
+      end
+    end
+
+    def summary_table
+      @stable ||= @hbase.get_table @stablename
+    end
+
+    def freq_table
+      @ftable ||= @hbase.get_table @ftablename
     end
   end
 

lib/ankusa/hasher.rb

@@ -0,0 +1,33 @@
+require 'fast_stemmer'
+require 'ankusa/stopwords'
+
+module Ankusa
+
+  class TextHash < Hash 
+    attr_reader :word_count
+
+    def initialize(text=nil)
+      super 0
+      @word_count = 0
+      add_text(text) if not text.nil?
+    end
+
+    def add_text(text)
+      # replace dashes with spaces, then get rid of non-word/non-space characters, 
+      # then split by space to get words
+      words = text.tr('-', ' ').gsub(/[^\w\s]/,"").split
+      words.each { |word| add_word word }
+      self
+    end
+
+    def add_word(word)
+      word = word.downcase
+      if not Ankusa::STOPWORDS.include? word
+        @word_count += 1
+        key = word.intern
+        store key, fetch(key, 0)+1
+      end
+    end
+  end
+
+end

lib/ankusa/nbclass.rb

@@ -0,0 +1,15 @@
+module Ankusa
+
+  class NBClass
+    attr_reader :doc_count, :word_count
+
+    def initialize(name, summary_table, freq_table)
+      @name = name
+      @summary_table = summary_table
+      @freq_table = freq_table
+      @word_count = @summary_table.get(@name, "totals:wordcount").first.to_i64.to_f
+      @doc_count = @summary_table.get(@name, "totals:doccount").first.to_i64.to_f
+    end
+  end
+
+end

lib/ankusa/stopwords.rb

@@ -0,0 +1,4 @@
+module Ankusa
+  # These are taken from MySQL - http://dev.mysql.com/tech-resources/articles/full-text-revealed.html
+  STOPWORDS = "a able about above according accordingly across actually after afterwards again against ain't all allow allows almost alone along already also although always am among amongst an and another any anybody anyhow anyone anything anyway anyways anywhere apart appear appreciate appropriate are aren't around as aside ask asking associated at available away awfully be became because become becomes becoming been before beforehand behind being believe below beside besides best better between beyond both brief but by c'mon c's came can can't cannot cant cause causes certain certainly changes clearly co com come comes concerning consequently consider considering contain containing contains corresponding could couldn't course currently definitely described despite did didn't different do does doesn't doing don't done down downwards during each edu eg eight either else elsewhere enough entirely especially et etc even ever every everybody everyone everything everywhere ex exactly example except far few fifth first five followed following follows for former formerly forth four from further furthermore get gets getting given gives go goes going gone got gotten greetings had hadn't happens hardly has hasn't have haven't having he he's hello help hence her here here's hereafter hereby herein hereupon hers herself hi him himself his hither hopefully how howbeit however i'd i'll i'm i've ie if ignored immediate in inasmuch inc indeed indicate indicated indicates inner insofar instead into inward is isn't it it'd it'll it's its itself just keep keeps kept know knows known last lately later latter latterly least less lest let let's like liked likely little look looking looks ltd mainly many may maybe me mean meanwhile merely might more moreover most mostly much must my myself name namely nd near nearly necessary need needs neither never nevertheless new next nine no nobody non none noone nor normally not nothing novel now nowhere obviously of off often oh ok okay old on once one ones only onto or other others otherwise ought our ours ourselves out outside over overall own particular particularly per perhaps placed please plus possible presumably probably provides que quite qv rather rd re really reasonably regarding regardless regards relatively respectively right said same saw say saying says second secondly see seeing seem seemed seeming seems seen self selves sensible sent serious seriously seven several shall she should shouldn't since six so some somebody somehow someone something sometime sometimes somewhat somewhere soon sorry specified specify specifying still sub such sup sure t's take taken tell tends th than thank thanks thanx that that's thats the their theirs them themselves then thence there there's thereafter thereby therefore therein theres thereupon these they they'd they'll they're they've think third this thorough thoroughly those though three through throughout thru thus to together too took toward towards tried tries truly try trying twice two un under unfortunately unless unlikely until unto up upon us use used useful uses using usually value various very via viz vs want wants was wasn't way we we'd we'll we're we've welcome well went were weren't what what's whatever when whence whenever where where's whereafter whereas whereby wherein whereupon wherever whether which while whither who who's whoever whole whom whose why will willing wish with within without won't wonder would would wouldn't yes yet you you'd you'll you're you've your yours yourself yourselves zero".split
+end