classifier 1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/README +33 -0
- data/Rakefile +77 -0
- data/bin/bayes.rb +30 -0
- data/lib/classifier.rb +28 -0
- data/lib/classifier/bayes.rb +53 -0
- data/lib/classifier/string_extensions.rb +11 -0
- data/lib/classifier/string_extensions/porter_stemmer.rb +188 -0
- data/lib/classifier/string_extensions/word_hash.rb +24 -0
- data/test/bayes/bayesian_test.rb +20 -0
- data/test/bayes/string_extensions_test.rb +8 -0
- data/test/test_helper.rb +4 -0
- metadata +50 -0
data/README
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
== Welcome to Classifier
|
2
|
+
|
3
|
+
Classifier is a general module to allow Bayesian and other types of classifications.
|
4
|
+
|
5
|
+
== Usage
|
6
|
+
require 'classifier'
|
7
|
+
b = Classifier::Bayes.new 'Interesting', 'Uninteresting'
|
8
|
+
b.train_interesting "here are some good words. I hope you love them"
|
9
|
+
b.train_uninteresting "here are some bad words, I hate you"
|
10
|
+
b.classify "I hate bad words and you" # returns 'Uninsteresting'
|
11
|
+
|
12
|
+
require 'madeleine'
|
13
|
+
m = SnapshotMadeleine.new("bayes_data") {
|
14
|
+
Classifier::Bayes.new 'Interesting', 'Uninteresting'
|
15
|
+
}
|
16
|
+
m.system.train_interesting "here are some good words. I hope you love them"
|
17
|
+
m.system.train_uninteresting "here are some bad words, I hate you"
|
18
|
+
m.take_snapshot
|
19
|
+
m.system.classify "I love you" # returns 'Interesting'
|
20
|
+
|
21
|
+
Using Madeleine, your application can persist the learned data over time.
|
22
|
+
|
23
|
+
== Bayesian Classification
|
24
|
+
|
25
|
+
* http://www.process.com/precisemail/bayesian_filtering.htm
|
26
|
+
* http://en.wikipedia.org/wiki/Bayesian_filtering
|
27
|
+
* http://www.paulgraham.com/spam.html
|
28
|
+
|
29
|
+
== About
|
30
|
+
|
31
|
+
Author:: Lucas Carlson (mailto:lucas@rufy.com)
|
32
|
+
Copyright:: Copyright (c) 2005 Lucas Carlson
|
33
|
+
License:: GPL
|
data/Rakefile
ADDED
@@ -0,0 +1,77 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
require 'rake/testtask'
|
4
|
+
require 'rake/rdoctask'
|
5
|
+
require 'rake/gempackagetask'
|
6
|
+
require 'rake/contrib/rubyforgepublisher'
|
7
|
+
|
8
|
+
PKG_VERSION = "1.0.0"
|
9
|
+
|
10
|
+
PKG_FILES = FileList[
|
11
|
+
"lib/**/*", "bin/*", "test/**/*", "[A-Z]*", "Rakefile"
|
12
|
+
]
|
13
|
+
|
14
|
+
desc "Default Task"
|
15
|
+
task :default => [ :test ]
|
16
|
+
|
17
|
+
# Run the unit tests
|
18
|
+
desc "Run all unit tests"
|
19
|
+
Rake::TestTask.new("test") { |t|
|
20
|
+
t.libs << "lib"
|
21
|
+
t.pattern = 'test/*/*_test.rb'
|
22
|
+
t.verbose = true
|
23
|
+
}
|
24
|
+
|
25
|
+
# Genereate the RDoc documentation
|
26
|
+
desc "Create documentation"
|
27
|
+
Rake::RDocTask.new("doc") { |rdoc|
|
28
|
+
rdoc.rdoc_dir = 'doc'
|
29
|
+
rdoc.title = "Classifier library"
|
30
|
+
rdoc.options << '--line-numbers --inline-source --accessor'
|
31
|
+
rdoc.rdoc_files.include('README')
|
32
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
33
|
+
}
|
34
|
+
|
35
|
+
# Genereate the package
|
36
|
+
spec = Gem::Specification.new do |s|
|
37
|
+
|
38
|
+
#### Basic information.
|
39
|
+
|
40
|
+
s.name = 'classifier'
|
41
|
+
s.version = "1.0"
|
42
|
+
s.summary = <<-EOF
|
43
|
+
A general classifier module to allow Bayesian and other types of classifications.
|
44
|
+
EOF
|
45
|
+
s.description = <<-EOF
|
46
|
+
A general classifier module to allow Bayesian and other types of classifications.
|
47
|
+
EOF
|
48
|
+
|
49
|
+
#### Which files are to be included in this gem? Everything! (Except CVS directories.)
|
50
|
+
|
51
|
+
s.files = PKG_FILES
|
52
|
+
|
53
|
+
#### Load-time details: library and application (you will need one or both).
|
54
|
+
|
55
|
+
s.require_path = 'lib'
|
56
|
+
s.autorequire = 'classifier'
|
57
|
+
|
58
|
+
#### Documentation and testing.
|
59
|
+
|
60
|
+
s.has_rdoc = true
|
61
|
+
|
62
|
+
#### Author and project details.
|
63
|
+
|
64
|
+
s.author = "Lucas Carlson"
|
65
|
+
s.email = "lucas@rufy.com"
|
66
|
+
s.homepage = "http://rubyforge.org/projects/classifier/"
|
67
|
+
end
|
68
|
+
|
69
|
+
Rake::GemPackageTask.new(spec) do |pkg|
|
70
|
+
pkg.need_zip = false
|
71
|
+
pkg.need_tar = true
|
72
|
+
end
|
73
|
+
|
74
|
+
desc "Publish to RubyForge"
|
75
|
+
task :rubyforge do
|
76
|
+
Rake::RubyForgePublisher.new('classifier', 'cardmagic').upload
|
77
|
+
end
|
data/bin/bayes.rb
ADDED
@@ -0,0 +1,30 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'classifier'
|
4
|
+
require 'madeleine'
|
5
|
+
|
6
|
+
m = SnapshotMadeleine.new(File.expand_path("~/.bayes_data")) {
|
7
|
+
Classifier::Bayes.new 'Interesting', 'Uninteresting'
|
8
|
+
}
|
9
|
+
|
10
|
+
case ARGV[0]
|
11
|
+
when "add"
|
12
|
+
case ARGV[1].downcase
|
13
|
+
when "interesting"
|
14
|
+
m.system.train_interesting File.open(ARGV[2]).read
|
15
|
+
puts "#{ARGV[2]} has been classified as interesting"
|
16
|
+
when "uninteresting"
|
17
|
+
m.system.train_uninteresting File.open(ARGV[2]).read
|
18
|
+
puts "#{ARGV[2]} has been classified as uninteresting"
|
19
|
+
else
|
20
|
+
puts "Invalid category: choose between interesting and uninteresting"
|
21
|
+
exit(1)
|
22
|
+
end
|
23
|
+
when "classify"
|
24
|
+
puts m.system.classify(File.open(ARGV[1]).read)
|
25
|
+
else
|
26
|
+
puts "Invalid option: choose add [category] [file] or clasify [file]"
|
27
|
+
exit(1)
|
28
|
+
end
|
29
|
+
|
30
|
+
m.take_snapshot
|
data/lib/classifier.rb
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
#--
|
2
|
+
# Copyright (c) 2005 Lucas Carlson
|
3
|
+
#
|
4
|
+
# Permission is hereby granted, free of charge, to any person obtaining
|
5
|
+
# a copy of this software and associated documentation files (the
|
6
|
+
# "Software"), to deal in the Software without restriction, including
|
7
|
+
# without limitation the rights to use, copy, modify, merge, publish,
|
8
|
+
# distribute, sublicense, and/or sell copies of the Software, and to
|
9
|
+
# permit persons to whom the Software is furnished to do so, subject to
|
10
|
+
# the following conditions:
|
11
|
+
#
|
12
|
+
# The above copyright notice and this permission notice shall be
|
13
|
+
# included in all copies or substantial portions of the Software.
|
14
|
+
#
|
15
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
16
|
+
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
17
|
+
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
18
|
+
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
19
|
+
# LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
20
|
+
# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
21
|
+
# WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
22
|
+
#++
|
23
|
+
# Author:: Lucas Carlson (mailto:lucas@rufy.com)
|
24
|
+
# Copyright:: Copyright (c) 2005 Lucas Carlson
|
25
|
+
# License:: LGPL
|
26
|
+
|
27
|
+
require 'classifier/string_extensions'
|
28
|
+
require 'classifier/bayes'
|
@@ -0,0 +1,53 @@
|
|
1
|
+
# Author:: Lucas Carlson (mailto:lucas@rufy.com)
|
2
|
+
# Copyright:: Copyright (c) 2005 Lucas Carlson
|
3
|
+
# License:: LGPL
|
4
|
+
|
5
|
+
module Classifier
|
6
|
+
|
7
|
+
class Bayes
|
8
|
+
def initialize(*categories)
|
9
|
+
@categories = Hash.new
|
10
|
+
categories.each { |category| @categories[category.capitalize.intern] = Hash.new }
|
11
|
+
@total_words = 0
|
12
|
+
end
|
13
|
+
|
14
|
+
def classify(text)
|
15
|
+
(classifications(text).sort { |a, b| b[1] <=> a[1] })[0][0]
|
16
|
+
end
|
17
|
+
|
18
|
+
def classifications(text)
|
19
|
+
score = Hash.new
|
20
|
+
@categories.each do |category, category_words|
|
21
|
+
score[category.to_s] = 0
|
22
|
+
total = category_words.values.inject(0) {|sum, element| sum+element}
|
23
|
+
text.word_hash.each do |word, count|
|
24
|
+
s = category_words.has_key?(word) ? category_words[word] : 0.1
|
25
|
+
score[category.to_s] += Math.log(s/total.to_f)
|
26
|
+
end
|
27
|
+
end
|
28
|
+
return score
|
29
|
+
end
|
30
|
+
|
31
|
+
def method_missing(name, *args)
|
32
|
+
category = name.to_s.gsub(/train_([\w]+)/, '\1').capitalize.intern
|
33
|
+
if @categories.has_key? category
|
34
|
+
args.each {|text| add_words category, text}
|
35
|
+
elsif name.to_s =~ /train_([\w]+)/
|
36
|
+
raise StandardError, "No such category: #{category}"
|
37
|
+
else
|
38
|
+
raise StandardError, "No such method: #{name}"
|
39
|
+
end
|
40
|
+
end
|
41
|
+
|
42
|
+
private
|
43
|
+
|
44
|
+
def add_words(category, text)
|
45
|
+
text.word_hash.each do |word, count|
|
46
|
+
@categories[category][word] ||= 0
|
47
|
+
@categories[category][word] += count
|
48
|
+
@total_words += count
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
end
|
@@ -0,0 +1,11 @@
|
|
1
|
+
# Author:: Lucas Carlson (mailto:lucas@rufy.com)
|
2
|
+
# Copyright:: Copyright (c) 2005 Lucas Carlson
|
3
|
+
# License:: LGPL
|
4
|
+
|
5
|
+
require 'classifier/string_extensions/porter_stemmer'
|
6
|
+
require 'classifier/string_extensions/word_hash'
|
7
|
+
|
8
|
+
class String
|
9
|
+
include Classifier::Stemmable
|
10
|
+
include Classifier::WordHash
|
11
|
+
end
|
@@ -0,0 +1,188 @@
|
|
1
|
+
module Classifier
|
2
|
+
|
3
|
+
module Stemmable
|
4
|
+
|
5
|
+
STEP_2_LIST = {
|
6
|
+
'ational'=>'ate', 'tional'=>'tion', 'enci'=>'ence', 'anci'=>'ance',
|
7
|
+
'izer'=>'ize', 'bli'=>'ble',
|
8
|
+
'alli'=>'al', 'entli'=>'ent', 'eli'=>'e', 'ousli'=>'ous',
|
9
|
+
'ization'=>'ize', 'ation'=>'ate',
|
10
|
+
'ator'=>'ate', 'alism'=>'al', 'iveness'=>'ive', 'fulness'=>'ful',
|
11
|
+
'ousness'=>'ous', 'aliti'=>'al',
|
12
|
+
'iviti'=>'ive', 'biliti'=>'ble', 'logi'=>'log'
|
13
|
+
}
|
14
|
+
|
15
|
+
STEP_3_LIST = {
|
16
|
+
'icate'=>'ic', 'ative'=>'', 'alize'=>'al', 'iciti'=>'ic',
|
17
|
+
'ical'=>'ic', 'ful'=>'', 'ness'=>''
|
18
|
+
}
|
19
|
+
|
20
|
+
|
21
|
+
SUFFIX_1_REGEXP = /(
|
22
|
+
ational |
|
23
|
+
tional |
|
24
|
+
enci |
|
25
|
+
anci |
|
26
|
+
izer |
|
27
|
+
bli |
|
28
|
+
alli |
|
29
|
+
entli |
|
30
|
+
eli |
|
31
|
+
ousli |
|
32
|
+
ization |
|
33
|
+
ation |
|
34
|
+
ator |
|
35
|
+
alism |
|
36
|
+
iveness |
|
37
|
+
fulness |
|
38
|
+
ousness |
|
39
|
+
aliti |
|
40
|
+
iviti |
|
41
|
+
biliti |
|
42
|
+
logi)$/x
|
43
|
+
|
44
|
+
|
45
|
+
SUFFIX_2_REGEXP = /(
|
46
|
+
al |
|
47
|
+
ance |
|
48
|
+
ence |
|
49
|
+
er |
|
50
|
+
ic |
|
51
|
+
able |
|
52
|
+
ible |
|
53
|
+
ant |
|
54
|
+
ement |
|
55
|
+
ment |
|
56
|
+
ent |
|
57
|
+
ou |
|
58
|
+
ism |
|
59
|
+
ate |
|
60
|
+
iti |
|
61
|
+
ous |
|
62
|
+
ive |
|
63
|
+
ize)$/x
|
64
|
+
|
65
|
+
|
66
|
+
C = "[^aeiou]" # consonant
|
67
|
+
V = "[aeiouy]" # vowel
|
68
|
+
CC = "#{C}(?>[^aeiouy]*)" # consonant sequence
|
69
|
+
VV = "#{V}(?>[aeiou]*)" # vowel sequence
|
70
|
+
|
71
|
+
MGR0 = /^(#{CC})?#{VV}#{CC}/o # [cc]vvcc... is m>0
|
72
|
+
MEQ1 = /^(#{CC})?#{VV}#{CC}(#{VV})?$/o # [cc]vvcc[vv] is m=1
|
73
|
+
MGR1 = /^(#{CC})?#{VV}#{CC}#{VV}#{CC}/o # [cc]vvccvvcc... is m>1
|
74
|
+
VOWEL_IN_STEM = /^(#{CC})?#{V}/o # vowel in stem
|
75
|
+
|
76
|
+
#
|
77
|
+
# Porter stemmer in Ruby.
|
78
|
+
#
|
79
|
+
# This is the Porter stemming algorithm, ported to Ruby from the
|
80
|
+
# version coded up in Perl. It's easy to follow against the rules
|
81
|
+
# in the original paper in:
|
82
|
+
#
|
83
|
+
# Porter, 1980, An algorithm for suffix stripping, Program, Vol. 14,
|
84
|
+
# no. 3, pp 130-137,
|
85
|
+
#
|
86
|
+
# See also http://www.tartarus.org/~martin/PorterStemmer
|
87
|
+
#
|
88
|
+
# Send comments to raypereda@hotmail.com
|
89
|
+
#
|
90
|
+
|
91
|
+
def stem_porter
|
92
|
+
|
93
|
+
# make a copy of the given object and convert it to a string.
|
94
|
+
w = self.dup.to_str
|
95
|
+
|
96
|
+
return w if w.length < 3
|
97
|
+
|
98
|
+
# now map initial y to Y so that the patterns never treat it as vowel
|
99
|
+
w[0] = 'Y' if w[0] == ?y
|
100
|
+
|
101
|
+
# Step 1a
|
102
|
+
if w =~ /(ss|i)es$/
|
103
|
+
w = $` + $1
|
104
|
+
elsif w =~ /([^s])s$/
|
105
|
+
w = $` + $1
|
106
|
+
end
|
107
|
+
|
108
|
+
# Step 1b
|
109
|
+
if w =~ /eed$/
|
110
|
+
w.chop! if $` =~ MGR0
|
111
|
+
elsif w =~ /(ed|ing)$/
|
112
|
+
stem = $`
|
113
|
+
if stem =~ VOWEL_IN_STEM
|
114
|
+
w = stem
|
115
|
+
case w
|
116
|
+
when /(at|bl|iz)$/ then w << "e"
|
117
|
+
when /([^aeiouylsz])\1$/ then w.chop!
|
118
|
+
when /^#{CC}#{V}[^aeiouwxy]$/o then w << "e"
|
119
|
+
end
|
120
|
+
end
|
121
|
+
end
|
122
|
+
|
123
|
+
if w =~ /y$/
|
124
|
+
stem = $`
|
125
|
+
w = stem + "i" if stem =~ VOWEL_IN_STEM
|
126
|
+
end
|
127
|
+
|
128
|
+
# Step 2
|
129
|
+
if w =~ SUFFIX_1_REGEXP
|
130
|
+
stem = $`
|
131
|
+
suffix = $1
|
132
|
+
# print "stem= " + stem + "\n" + "suffix=" + suffix + "\n"
|
133
|
+
if stem =~ MGR0
|
134
|
+
w = stem + STEP_2_LIST[suffix]
|
135
|
+
end
|
136
|
+
end
|
137
|
+
|
138
|
+
# Step 3
|
139
|
+
if w =~ /(icate|ative|alize|iciti|ical|ful|ness)$/
|
140
|
+
stem = $`
|
141
|
+
suffix = $1
|
142
|
+
if stem =~ MGR0
|
143
|
+
w = stem + STEP_3_LIST[suffix]
|
144
|
+
end
|
145
|
+
end
|
146
|
+
|
147
|
+
# Step 4
|
148
|
+
if w =~ SUFFIX_2_REGEXP
|
149
|
+
stem = $`
|
150
|
+
if stem =~ MGR1
|
151
|
+
w = stem
|
152
|
+
end
|
153
|
+
elsif w =~ /(s|t)(ion)$/
|
154
|
+
stem = $` + $1
|
155
|
+
if stem =~ MGR1
|
156
|
+
w = stem
|
157
|
+
end
|
158
|
+
end
|
159
|
+
|
160
|
+
# Step 5
|
161
|
+
if w =~ /e$/
|
162
|
+
stem = $`
|
163
|
+
if (stem =~ MGR1) ||
|
164
|
+
(stem =~ MEQ1 && stem !~ /^#{CC}#{V}[^aeiouwxy]$/o)
|
165
|
+
w = stem
|
166
|
+
end
|
167
|
+
end
|
168
|
+
|
169
|
+
if w =~ /ll$/ && w =~ MGR1
|
170
|
+
w.chop!
|
171
|
+
end
|
172
|
+
|
173
|
+
# and turn initial Y back to y
|
174
|
+
w[0] = 'y' if w[0] == ?Y
|
175
|
+
|
176
|
+
w
|
177
|
+
end
|
178
|
+
|
179
|
+
|
180
|
+
#
|
181
|
+
# make the stem_porter the default stem method, just in case we
|
182
|
+
# feel like having multiple stemmers available later.
|
183
|
+
#
|
184
|
+
alias stem stem_porter
|
185
|
+
|
186
|
+
end
|
187
|
+
|
188
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# Author:: Lucas Carlson (mailto:lucas@rufy.com)
|
2
|
+
# Copyright:: Copyright (c) 2005 Lucas Carlson
|
3
|
+
# License:: LGPL
|
4
|
+
|
5
|
+
module Classifier
|
6
|
+
|
7
|
+
module WordHash
|
8
|
+
def without_punctuation
|
9
|
+
tr( ',?.!;:\'"@#$%^&*()_=+[]{}\|<>/`~', " " )
|
10
|
+
end
|
11
|
+
|
12
|
+
def word_hash
|
13
|
+
d = Hash.new
|
14
|
+
corpus = without_punctuation
|
15
|
+
(corpus.split + gsub(/[\w]/,"").split).each do |word|
|
16
|
+
key = word.downcase.stem.intern
|
17
|
+
d[key] ||= 0
|
18
|
+
d[key] += 1
|
19
|
+
end
|
20
|
+
return d
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/../test_helper'
|
2
|
+
class BayesianTest < Test::Unit::TestCase
|
3
|
+
def setup
|
4
|
+
@classifier = Classifier::Bayes.new 'Interesting', 'Uninteresting'
|
5
|
+
end
|
6
|
+
|
7
|
+
def test_good_training
|
8
|
+
assert_nothing_raised { @classifier.train_interesting "love" }
|
9
|
+
end
|
10
|
+
|
11
|
+
def test_bad_training
|
12
|
+
assert_raise(StandardError) { @classifier.train_no_category "words" }
|
13
|
+
end
|
14
|
+
|
15
|
+
def test_classification
|
16
|
+
@classifier.train_interesting "here are some good words. I hope you love them"
|
17
|
+
@classifier.train_uninteresting "here are some bad words, I hate you"
|
18
|
+
assert_equal 'Uninteresting', @classifier.classify("I hate bad words and you")
|
19
|
+
end
|
20
|
+
end
|
@@ -0,0 +1,8 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/../test_helper'
|
2
|
+
class StringExtensionsTest < Test::Unit::TestCase
|
3
|
+
def test_word_hash
|
4
|
+
hash = {:some=>1, :good=>1, :hope=>1, :word=>1, :you=>1, :here=>1, :love=>1, :i=>1, :ar=>1, :them=>1, :"."=>1, :"!"=>1}
|
5
|
+
|
6
|
+
assert_equal hash, "here are some good words. I hope you love them!".word_hash
|
7
|
+
end
|
8
|
+
end
|
data/test/test_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,50 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
rubygems_version: 0.8.6
|
3
|
+
specification_version: 1
|
4
|
+
name: classifier
|
5
|
+
version: !ruby/object:Gem::Version
|
6
|
+
version: "1.0"
|
7
|
+
date: 2005-04-10
|
8
|
+
summary: A general classifier module to allow Bayesian and other types of classifications.
|
9
|
+
require_paths:
|
10
|
+
- lib
|
11
|
+
email: lucas@rufy.com
|
12
|
+
homepage: http://rubyforge.org/projects/classifier/
|
13
|
+
rubyforge_project:
|
14
|
+
description: A general classifier module to allow Bayesian and other types of classifications.
|
15
|
+
autorequire: classifier
|
16
|
+
default_executable:
|
17
|
+
bindir: bin
|
18
|
+
has_rdoc: true
|
19
|
+
required_ruby_version: !ruby/object:Gem::Version::Requirement
|
20
|
+
requirements:
|
21
|
+
-
|
22
|
+
- ">"
|
23
|
+
- !ruby/object:Gem::Version
|
24
|
+
version: 0.0.0
|
25
|
+
version:
|
26
|
+
platform: ruby
|
27
|
+
authors:
|
28
|
+
- Lucas Carlson
|
29
|
+
files:
|
30
|
+
- lib/classifier
|
31
|
+
- lib/classifier.rb
|
32
|
+
- lib/classifier/bayes.rb
|
33
|
+
- lib/classifier/string_extensions
|
34
|
+
- lib/classifier/string_extensions.rb
|
35
|
+
- lib/classifier/string_extensions/porter_stemmer.rb
|
36
|
+
- lib/classifier/string_extensions/word_hash.rb
|
37
|
+
- bin/bayes.rb
|
38
|
+
- test/bayes
|
39
|
+
- test/test_helper.rb
|
40
|
+
- test/bayes/bayesian_test.rb
|
41
|
+
- test/bayes/string_extensions_test.rb
|
42
|
+
- Rakefile
|
43
|
+
- README
|
44
|
+
test_files: []
|
45
|
+
rdoc_options: []
|
46
|
+
extra_rdoc_files: []
|
47
|
+
executables: []
|
48
|
+
extensions: []
|
49
|
+
requirements: []
|
50
|
+
dependencies: []
|