Class: Classifier::Bayes

Inherits:
Object show all
Defined in:
lib/classifier/bayes.rb

Instance Method Summary collapse

Constructor Details

#initialize(*categories) ⇒ 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 = Classifier::Bayes.new 'Interesting', 'Uninteresting', 'Spam'



11
12
13
14
15
 
# File 'lib/classifier/bayes.rb', line 11

def initialize(*categories)
	@categories = Hash.new
	categories.each { |category| @categories[category.prepare_category_name] = Hash.new }
	@total_words = 0
end

Dynamic Method Handling

This class handles dynamic methods through the method_missing method

#method_missing(name, *args) ⇒ Object

Provides training and untraining methods for the categories specified in Bayes#new For example:

b = Classifier::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"



132
133
134
135
136
137
138
139
140
141
 
# File 'lib/classifier/bayes.rb', line 132

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

Instance Method Details

#add_category(category) ⇒ Object Also known as: append_category

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.



161
162
163
 
# File 'lib/classifier/bayes.rb', line 161

def add_category(category)
	@categories[category.prepare_category_name] = Hash.new
end

#categories ⇒ Object

Provides a list of category names For example:

b.categories
=>   ['This', 'That', 'the_other']



148
149
150
 
# File 'lib/classifier/bayes.rb', line 148

def categories # :nodoc:
	@categories.keys.collect {|c| c.to_s}
end

#classifications(text) ⇒ Object

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



67
68
69
70
71
72
73
74
75
76
77
78
 
# File 'lib/classifier/bayes.rb', line 67

def classifications(text)
	score = Hash.new
	@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
	end
	return score
end

#classify(text) ⇒ Object

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'



120
121
122
 
# File 'lib/classifier/bayes.rb', line 120

def classify(text)
	(classifications(text).sort_by { |a| -a[1] })[0][0]
end

#myclassify(text) ⇒ Object

These assume that the classes are Member and Not Member



81
82
83
 
# File 'lib/classifier/bayes.rb', line 81

def myclassify(text)
  myclassify_with_word_hash(text.word_hash)
end

#myclassify_with_word_hash(word_hash, debugging_info = nil) ⇒ Object 



85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
 
# File 'lib/classifier/bayes.rb', line 85

def myclassify_with_word_hash(word_hash, debugging_info = nil)
  member_term_count = @categories[:Member].size
  nonmember_term_count = @categories[:"Not member"].size

  term_count = member_term_count + nonmember_term_count
  score = 0
  word_hash.each do |word, count|
    # count of words in each category
    member_count = @categories[:Member][word].to_i + 0.1
    nonmember_count = @categories[:"Not member"][word].to_i + 0.1
    next if member_count == 0.1 && nonmember_count == 0.1

    # find relative prob word is in class -- p(w|c)
    word_member_p = (member_count) / (total_member_count_correct + term_count).to_f
    word_nonmember_p =  (nonmember_count) / (total_nonmember_count_correct + term_count).to_f
    
    word_pr = Math.log(word_member_p / word_nonmember_p)
    score += word_pr * count
    if debugging_info
      debugging_info[word] = word_pr * count
    end
    #print "#{word_pr * count}: #{word}\n"
  end 
  if score > 0
    return "Member", score
  else
    return "Not member", score
  end
end

#remove_low_frequency_words(threshold = 5) ⇒ Object 



165
166
167
168
169
170
171
172
173
174
 
# File 'lib/classifier/bayes.rb', line 165

def remove_low_frequency_words(threshold = 5)
  @categories.each do |_, word_counts|
    word_counts.to_a.each do |word, count|
      if count < threshold
        word_counts.delete(word)
      end
    end
  end
  reset_correct_counts!
end

#train(category, text) ⇒ Object

Provides a general training method for all categories specified in Bayes#new For example:

b = Classifier::Bayes.new 'This', 'That', 'the_other'
b.train :this, "This text"
b.train "that", "That text"
b.train "The other", "The other text"



24
25
26
27
28
29
30
31
32
 
# File 'lib/classifier/bayes.rb', line 24

def train(category, text)
	category = category.prepare_category_name
	text.word_hash.each do |word, count|
		@categories[category][word]     ||=     0
		@categories[category][word]      +=     count
		@total_words += count
	end
   reset_correct_counts!
end

#untrain(category, text) ⇒ Object

Provides a untraining method for all categories specified in Bayes#new Be very careful with this method.

For example:

b = Classifier::Bayes.new 'This', 'That', 'the_other'
b.train :this, "This text"
b.untrain :this, "This text"



42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
 
# File 'lib/classifier/bayes.rb', line 42

def untrain(category, text)
	category = category.prepare_category_name
	text.word_hash.each do |word, count|
		if @total_words >= 0
       # Sometimes items can be untrained before they are trained,
       # be tolerant of that case
       next if @categories[category][word].nil?
			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
   reset_correct_counts!
end