Class: Classifier::Bayes

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

Instance Method Summary collapse

Constructor Details

#initialize(lang, *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'



13
14
15
16
17
18
19
20
 
# File 'lib/classifier/bayes.rb', line 13

def initialize(lang, *categories)
	#@categories = Hash.new
	#categories.each { |category| @categories[category.prepare_category_name] = Hash.new }
	# RedisStore.total_words = 0
	@categories = RedisStore.new lang, categories
	@categories.init_total
	@stemmer = Lingua::Stemmer.new(:language => lang.downcase)
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"



123
124
125
126
127
128
129
130
131
132
133
 
# File 'lib/classifier/bayes.rb', line 123

def method_missing(name, *args)
	category = name.to_s.gsub(/(un)?train_([\w]+)/, '\2').prepare_category_name
	# categories.has_key?(key)
	if @categories.names.include? 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.



153
154
155
 
# File 'lib/classifier/bayes.rb', line 153

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']



140
141
142
 
# File 'lib/classifier/bayes.rb', line 140

def categories # :nodoc:
	@categories
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



83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
 
# File 'lib/classifier/bayes.rb', line 83

def classifications(text)
	score = Hash.new
	# actual categories saved in the beggining but each do |category|
	@categories.each do |category, category_words|
		score[category.to_s] = 0

		# total = category_words.values.inject(0) {|sum, element| sum+element}
		begin
			total = category_words.inject(0) { |sum, element| sum + element }
		rescue
			raise "Bayes needs to be trained before trying to classify"
		end

		text.word_hash(@stemmer).each do |word, count|
			#s = category_words.has_key?(word) ? category_words[word] : 0.1
			s = @categories.has_word?(category, word) ? @categories.get(category, 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'



111
112
113
 
# File 'lib/classifier/bayes.rb', line 111

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



29
30
31
32
33
34
35
36
37
38
39
40
41
 
# File 'lib/classifier/bayes.rb', line 29

def train(category, text)
	category = category.prepare_category_name
	text.word_hash(@stemmer).each do |word, count|
		# @categories[category][word] ||= 0
		@categories.init(category, word)

		# @categories[category][word] += count
		@categories.incr(category, word, count)

		# @total_words += count
		@categories.incr_total(count)
	end
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"



51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
 
# File 'lib/classifier/bayes.rb', line 51

def untrain(category, text)
	category = category.prepare_category_name
	text.word_hash(@stemmer).each do |word, count|
		# @total_words >= 0
		if @categories.total_words >= 0
			# orig = @categories[category][word]
			orig = @categories.get(category,word)

			# @categories[category][word] ||= 0
			@categories.init(category, word)

			# @categories[category][word] -= count
			@categories.decr(category, word, count)


			#if @categories[category][word] <= 0
			if @categories.get(category,word) <= 0
				# @categories[category].delete(word)
				@categories.remove(category,word)
				count = orig
			end
			#@total_words -= count
			@categories.decr_total(count)
		end
	end
end