classifier-reborn 2.0.0.rc1

data/bin/bayes.rb

@@ -0,0 +1,36 @@
+#!/usr/bin/env ruby
+
+begin
+	require 'rubygems'
+	require 'classifier'
+rescue
+	require 'classifier'
+end
+
+require 'madeleine'
+
+m = SnapshotMadeleine.new(File.expand_path("~/.bayes_data")) {
+	ClassifierReborn::Bayes.new 'Interesting', 'Uninteresting'
+}
+
+case ARGV[0]
+when "add"
+	case ARGV[1].downcase
+	when "interesting"
+		m.system.train_interesting File.open(ARGV[2]).read
+		puts "#{ARGV[2]} has been classified as interesting"
+	when "uninteresting"
+		m.system.train_uninteresting File.open(ARGV[2]).read
+		puts "#{ARGV[2]} has been classified as uninteresting"
+	else
+		puts "Invalid category: choose between interesting and uninteresting"
+		exit(1)
+	end
+when "classify"
+	puts m.system.classify(File.open(ARGV[1]).read)
+else
+	puts "Invalid option: choose add [category] [file] or clasify [file]"
+	exit(-1)
+end
+
+m.take_snapshot

data/bin/summarize.rb

@@ -0,0 +1,16 @@
+#!/usr/bin/env ruby
+
+begin
+        require 'rubygems'
+        require 'classifier'
+rescue
+        require 'classifier'
+end
+
+require 'open-uri'
+
+num = ARGV[1].to_i
+num = num < 1 ? 10 : num
+
+text = open(ARGV.first).read
+puts text.gsub(/<[^>]+>/,"").gsub(/[\s]+/," ").summary(num)

data/lib/classifier-reborn.rb

@@ -0,0 +1,30 @@
+#--
+# Copyright (c) 2005 Lucas Carlson
+#
+# 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.
+#++
+# Author::    Lucas Carlson  (mailto:lucas@rufy.com)
+# Copyright:: Copyright (c) 2005 Lucas Carlson
+# License::   LGPL
+
+require 'rubygems'
+require_relative 'classifier-reborn/extensions/string'
+require_relative 'classifier-reborn/bayes'
+require_relative 'classifier-reborn/lsi'

data/lib/classifier-reborn/bayes.rb

@@ -0,0 +1,126 @@
+# Author::    Lucas Carlson  (mailto:lucas@rufy.com)
+# Copyright:: Copyright (c) 2005 Lucas Carlson
+# License::   LGPL
+
+module ClassifierReborn
+  class Bayes
+    # The class can be created with one or more categories, each of which will be
+    # initialized and given a training method. E.g.,
+    #      b = ClassifierReborn::Bayes.new 'Interesting', 'Uninteresting', 'Spam'
+    def initialize(*categories)
+      @categories = Hash.new
+      categories.each { |category| @categories[category.prepare_category_name] = Hash.new }
+      @total_words = 0
+      @category_counts = Hash.new(0)
+    end
+
+    # Provides a general training method for all categories specified in Bayes#new
+    # For example:
+    #     b = ClassifierReborn::Bayes.new 'This', 'That', 'the_other'
+    #     b.train :this, "This text"
+    #     b.train "that", "That text"
+    #     b.train "The other", "The other text"
+    def train(category, text)
+      category = category.prepare_category_name
+                  @category_counts[category] += 1
+      text.word_hash.each do |word, count|
+        @categories[category][word]     ||=     0
+        @categories[category][word]      +=     count
+        @total_words += count
+      end
+    end
+
+    # Provides a untraining method for all categories specified in Bayes#new
+    # Be very careful with this method.
+    #
+    # For example:
+    #     b = ClassifierReborn::Bayes.new 'This', 'That', 'the_other'
+    #     b.train :this, "This text"
+    #     b.untrain :this, "This text"
+    def untrain(category, text)
+      category = category.prepare_category_name
+                  @category_counts[category] -= 1
+      text.word_hash.each do |word, count|
+        if @total_words >= 0
+          orig = @categories[category][word]
+          @categories[category][word]     ||=     0
+          @categories[category][word]      -=     count
+          if @categories[category][word] <= 0
+            @categories[category].delete(word)
+            count = orig
+          end
+          @total_words -= count
+        end
+      end
+    end
+
+    # Returns the scores in each category the provided +text+. E.g.,
+    #    b.classifications "I hate bad words and you"
+    #    =>  {"Uninteresting"=>-12.6997928013932, "Interesting"=>-18.4206807439524}
+    # The largest of these scores (the one closest to 0) is the one picked out by #classify
+    def classifications(text)
+      score = Hash.new
+      training_count = @category_counts.values.inject { |x,y| x+y }.to_f
+      @categories.each do |category, category_words|
+        score[category.to_s] = 0
+        total = category_words.values.inject(0) {|sum, element| sum+element}
+        text.word_hash.each do |word, count|
+          s = category_words.has_key?(word) ? category_words[word] : 0.1
+          score[category.to_s] += Math.log(s/total.to_f)
+        end
+        # now add prior probability for the category
+        s = @category_counts.has_key?(category) ? @category_counts[category] : 0.1
+        score[category.to_s] += Math.log(s / training_count)
+      end
+      return score
+    end
+
+    # Returns the classification of the provided +text+, which is one of the
+    # categories given in the initializer. E.g.,
+    #    b.classify "I hate bad words and you"
+    #    =>  'Uninteresting'
+    def classify(text)
+      (classifications(text).sort_by { |a| -a[1] })[0][0]
+    end
+
+    # Provides training and untraining methods for the categories specified in Bayes#new
+    # For example:
+    #     b = ClassifierReborn::Bayes.new 'This', 'That', 'the_other'
+    #     b.train_this "This text"
+    #     b.train_that "That text"
+    #     b.untrain_that "That text"
+    #     b.train_the_other "The other text"
+    def method_missing(name, *args)
+      category = name.to_s.gsub(/(un)?train_([\w]+)/, '\2').prepare_category_name
+      if @categories.has_key? category
+        args.each { |text| eval("#{$1}train(category, text)") }
+      elsif name.to_s =~ /(un)?train_([\w]+)/
+        raise StandardError, "No such category: #{category}"
+      else
+        super  #raise StandardError, "No such method: #{name}"
+      end
+    end
+
+    # Provides a list of category names
+    # For example:
+    #     b.categories
+    #     =>   ['This', 'That', 'the_other']
+    def categories # :nodoc:
+      @categories.keys.collect {|c| c.to_s}
+    end
+
+    # Allows you to add categories to the classifier.
+    # For example:
+    #     b.add_category "Not spam"
+    #
+    # WARNING: Adding categories to a trained classifier will
+    # result in an undertrained category that will tend to match
+    # more criteria than the trained selective categories. In short,
+    # try to initialize your categories at initialization.
+    def add_category(category)
+      @categories[category.prepare_category_name] = Hash.new
+    end
+
+    alias append_category add_category
+  end
+end

data/lib/classifier-reborn/extensions/string.rb

@@ -0,0 +1,10 @@
+# Author::    Lucas Carlson  (mailto:lucas@rufy.com)
+# Copyright:: Copyright (c) 2005 Lucas Carlson
+# License::   LGPL
+
+require 'fast_stemmer'
+require 'classifier-reborn/extensions/word_hash'
+
+class Object
+  def prepare_category_name; to_s.gsub("_"," ").capitalize.intern end
+end

data/lib/classifier-reborn/extensions/vector.rb

@@ -0,0 +1,112 @@
+# Author::    Ernest Ellingson
+# Copyright:: Copyright (c) 2005
+
+# These are extensions to the std-lib 'matrix' to allow an all ruby SVD
+
+require 'matrix'
+require 'mathn'
+
+class Array
+  def sum(identity = 0, &block)
+    return identity unless size > 0
+
+    if block_given?
+      map(&block).sum
+    else
+      reduce(:+)
+    end
+  end
+end
+
+class Vector
+  def magnitude
+    sumsqs = 0.0
+    self.size.times do |i|
+      sumsqs += self[i] ** 2.0
+    end
+    Math.sqrt(sumsqs)
+  end
+  def normalize
+    nv = []
+    mag = self.magnitude
+    self.size.times do |i|
+
+      nv << (self[i] / mag)
+
+    end
+    Vector[*nv]
+  end
+end
+
+class Matrix
+  def Matrix.diag(s)
+     Matrix.diagonal(*s)
+  end
+
+  alias :trans :transpose
+
+  def SV_decomp(maxSweeps = 20)
+    if self.row_size >= self.column_size
+      q = self.trans * self
+    else
+      q = self * self.trans
+    end
+
+    qrot    = q.dup
+    v       = Matrix.identity(q.row_size)
+    azrot   = nil
+    mzrot   = nil
+    cnt     = 0
+    s_old   = nil
+    mu      = nil
+
+    while true do
+      cnt += 1
+      for row in (0...qrot.row_size-1) do
+        for col in (1..qrot.row_size-1) do
+          next if row == col
+          h = Math.atan((2 * qrot[row,col])/(qrot[row,row]-qrot[col,col]))/2.0
+          hcos = Math.cos(h)
+          hsin = Math.sin(h)
+          mzrot = Matrix.identity(qrot.row_size)
+          mzrot[row,row] = hcos
+          mzrot[row,col] = -hsin
+          mzrot[col,row] = hsin
+          mzrot[col,col] = hcos
+          qrot = mzrot.trans * qrot * mzrot
+          v = v * mzrot
+        end
+      end
+      s_old = qrot.dup if cnt == 1
+      sum_qrot = 0.0
+      if cnt > 1
+        qrot.row_size.times do |r|
+          sum_qrot += (qrot[r,r]-s_old[r,r]).abs if (qrot[r,r]-s_old[r,r]).abs > 0.001
+        end
+        s_old = qrot.dup
+      end
+      break if (sum_qrot <= 0.001 and cnt > 1) or cnt >= maxSweeps
+    end # of do while true
+    s = []
+    qrot.row_size.times do |r|
+      s << Math.sqrt(qrot[r,r])
+    end
+    #puts "cnt = #{cnt}"
+    if self.row_size >= self.column_size
+      mu = self *  v * Matrix.diagonal(*s).inverse
+      return [mu, v, s]
+    else
+      puts v.row_size
+      puts v.column_size
+      puts self.row_size
+      puts self.column_size
+      puts s.size
+
+      mu = (self.trans * v *  Matrix.diagonal(*s).inverse)
+      return [mu, v, s]
+    end
+  end
+  def []=(i,j,val)
+    @rows[i][j] = val
+  end
+end

data/lib/classifier-reborn/extensions/vector_serialize.rb

@@ -0,0 +1,20 @@
+module GSL
+  
+  class Vector
+    def _dump(v)
+      Marshal.dump( self.to_a )
+    end
+    
+    def self._load(arr)
+      arry = Marshal.load(arr)
+      return GSL::Vector.alloc(arry)
+    end
+    
+  end
+  
+  class Matrix
+     class <<self
+        alias :diag :diagonal
+     end
+  end
+end

data/lib/classifier-reborn/extensions/word_hash.rb

@@ -0,0 +1,136 @@
+# Author::    Lucas Carlson  (mailto:lucas@rufy.com)
+# Copyright:: Copyright (c) 2005 Lucas Carlson
+# License::   LGPL
+
+require "set"
+
+# These are extensions to the String class to provide convenience
+# methods for the Classifier package.
+class String
+
+  # Removes common punctuation symbols, returning a new string.
+  # E.g.,
+  #   "Hello (greeting's), with {braces} < >...?".without_punctuation
+  #   => "Hello  greetings   with  braces         "
+  def without_punctuation
+    tr( ',?.!;:"@#$%^&*()_=+[]{}\|<>/`~', " " ) .tr( "'\-", "")
+  end
+
+  # Return a Hash of strings => ints. Each word in the string is stemmed,
+  # interned, and indexes to its frequency in the document.
+	def word_hash
+		word_hash = clean_word_hash()
+		symbol_hash = word_hash_for_symbols(gsub(/[\w]/," ").split)
+		return word_hash.merge(symbol_hash)
+	end
+
+	# Return a word hash without extra punctuation or short symbols, just stemmed words
+	def clean_word_hash
+		word_hash_for_words gsub(/[^\w\s]/,"").split
+	end
+
+	private
+
+	def word_hash_for_words(words)
+		d = Hash.new(0)
+		words.each do |word|
+			word.downcase!
+			if ! CORPUS_SKIP_WORDS.include?(word) && word.length > 2
+				d[word.stem.intern] += 1
+			end
+		end
+		return d
+	end
+
+
+	def word_hash_for_symbols(words)
+		d = Hash.new(0)
+		words.each do |word|
+			d[word.intern] += 1
+		end
+		return d
+	end
+
+	CORPUS_SKIP_WORDS = Set.new([
+      "a",
+      "again",
+      "all",
+      "along",
+      "are",
+      "also",
+      "an",
+      "and",
+      "as",
+      "at",
+      "but",
+      "by",
+      "came",
+      "can",
+      "cant",
+      "couldnt",
+      "did",
+      "didn",
+      "didnt",
+      "do",
+      "doesnt",
+      "dont",
+      "ever",
+      "first",
+      "from",
+      "have",
+      "her",
+      "here",
+      "him",
+      "how",
+      "i",
+      "if",
+      "in",
+      "into",
+      "is",
+      "isnt",
+      "it",
+      "itll",
+      "just",
+      "last",
+      "least",
+      "like",
+      "most",
+      "my",
+      "new",
+      "no",
+      "not",
+      "now",
+      "of",
+      "on",
+      "or",
+      "should",
+      "sinc",
+      "so",
+      "some",
+      "th",
+      "than",
+      "this",
+      "that",
+      "the",
+      "their",
+      "then",
+      "those",
+      "to",
+      "told",
+      "too",
+      "true",
+      "try",
+      "until",
+      "url",
+      "us",
+      "were",
+      "when",
+      "whether",
+      "while",
+      "with",
+      "within",
+      "yes",
+      "you",
+      "youll",
+      ])
+end