yanbi-ml 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.travis.yml +4 -0
- data/Gemfile +4 -0
- data/README.md +34 -0
- data/Rakefile +5 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/bayes/bayes.rb +112 -0
- data/lib/bayes/fisher.rb +62 -0
- data/lib/corpus.rb +63 -0
- data/lib/version.rb +7 -0
- data/lib/wordbags/diadbag.rb +36 -0
- data/lib/wordbags/stembag.rb +20 -0
- data/lib/wordbags/stemmed_diadbag.rb +16 -0
- data/lib/wordbags/wordbag.rb +104 -0
- data/lib/yanbi.rb +17 -0
- data/yanbi-ml.gemspec +25 -0
- metadata +126 -0
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/README.md
ADDED
@@ -0,0 +1,34 @@
|
|
1
|
+
# YANBI-ML
|
2
|
+
|
3
|
+
Yet Another Naive Bayes Implementation
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'yanbi-ml'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install yanbi-ml
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
TODO: Write usage instructions here
|
24
|
+
|
25
|
+
|
26
|
+
## Contributing
|
27
|
+
|
28
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/rdormer/yanbi-ml.
|
29
|
+
|
30
|
+
|
31
|
+
## License
|
32
|
+
|
33
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
34
|
+
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "yanbi/ml"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start
|
data/bin/setup
ADDED
data/lib/bayes/bayes.rb
ADDED
@@ -0,0 +1,112 @@
|
|
1
|
+
# Author:: Robert Dormer (mailto:rdormer@gmail.com)
|
2
|
+
# Copyright:: Copyright (c) 2016 Robert Dormer
|
3
|
+
# License:: MIT
|
4
|
+
|
5
|
+
# Naive Bayesian classifier. Training and classification are both done via passed in
|
6
|
+
# word bags, as opposed to raw text. The first argument to new is the class of WordBag
|
7
|
+
# that you want newdoc to create. From then on, you can use newdoc to process text instead
|
8
|
+
# of manually creating word bags yourself, which will help to keep the word bag type
|
9
|
+
# consistent for a given classifier object. Note that if you really want to, you can train
|
10
|
+
# or classify with a different type of word bag then you passed in, although I can't imagine
|
11
|
+
# why you would want to. There's also a default constructor if you just want to create a
|
12
|
+
# classifier without being bothered about which word bag it uses.
|
13
|
+
|
14
|
+
module Yanbi
|
15
|
+
|
16
|
+
class Bayes
|
17
|
+
|
18
|
+
def initialize(klass, *categories)
|
19
|
+
raise ArgumentError unless categories.size > 1
|
20
|
+
@categories = categories
|
21
|
+
@category_counts = {}
|
22
|
+
@document_counts = {}
|
23
|
+
|
24
|
+
@categories.each do |category|
|
25
|
+
cat = category.to_sym
|
26
|
+
@category_counts[cat] = {}
|
27
|
+
@document_counts[cat] = 0
|
28
|
+
end
|
29
|
+
|
30
|
+
@bag_class = klass.to_s.split('::').last
|
31
|
+
end
|
32
|
+
|
33
|
+
def self.default(*categories)
|
34
|
+
self.new(WordBag, *categories)
|
35
|
+
end
|
36
|
+
|
37
|
+
def train(category, document)
|
38
|
+
cat = category.to_sym
|
39
|
+
@document_counts[cat] += 1
|
40
|
+
|
41
|
+
document.words.uniq.each do |word|
|
42
|
+
@category_counts[cat][word] ||= 0
|
43
|
+
@category_counts[cat][word] += 1
|
44
|
+
end
|
45
|
+
end
|
46
|
+
|
47
|
+
def classify(document)
|
48
|
+
max_score(document) do |cat, doc|
|
49
|
+
cond_prob(cat, doc)
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
def train_raw(category, text)
|
54
|
+
train(category, self.newdoc(text))
|
55
|
+
end
|
56
|
+
|
57
|
+
def classify_raw(text)
|
58
|
+
classify(self.newdoc(text))
|
59
|
+
end
|
60
|
+
|
61
|
+
def set_significance(cutoff, category=nil)
|
62
|
+
categories = (category.nil? ? @categories : [category])
|
63
|
+
categories.each do |category|
|
64
|
+
cat = category.to_sym
|
65
|
+
@category_counts[cat].reject! {|k,v| v < cutoff}
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
def newdoc(doc)
|
70
|
+
Yanbi.const_get(@bag_class).new(doc)
|
71
|
+
end
|
72
|
+
|
73
|
+
def save(name)
|
74
|
+
File.open(name + ".obj", 'w') do |out|
|
75
|
+
YAML.dump(self, out)
|
76
|
+
end
|
77
|
+
end
|
78
|
+
|
79
|
+
private
|
80
|
+
|
81
|
+
def cond_prob(cat, document)
|
82
|
+
total_docs = @document_counts.values.reduce(:+).to_f
|
83
|
+
document_prob = document.words.uniq.map {|word| word_prob(cat, word)}.reduce(:+)
|
84
|
+
document_prob + Math.log(@document_counts[cat] / total_docs)
|
85
|
+
end
|
86
|
+
|
87
|
+
def word_prob(cat, word)
|
88
|
+
all_word_count = @category_counts[cat].values.reduce(&:+)
|
89
|
+
count = @category_counts[cat].has_key?(word) ? @category_counts[cat][word].to_f : 0.1
|
90
|
+
Math.log(count / all_word_count)
|
91
|
+
end
|
92
|
+
|
93
|
+
def max_score(document)
|
94
|
+
scores = []
|
95
|
+
|
96
|
+
@categories.each do |c|
|
97
|
+
score = yield c, document
|
98
|
+
scores << score
|
99
|
+
end
|
100
|
+
|
101
|
+
i = scores.rindex(scores.max)
|
102
|
+
@categories[i]
|
103
|
+
end
|
104
|
+
|
105
|
+
# def weighted_prob(word, category, basicprob, weight=1.0, ap=0.5)
|
106
|
+
# #basicprob = word_prob(category, word) if basicprob.nil?
|
107
|
+
# totals = @category_counts.inject(0) {|sum, cat| sum += cat.last[word].to_i}
|
108
|
+
# ((weight * ap) + (totals*basicprob)) / (weight + totals)
|
109
|
+
# end
|
110
|
+
end
|
111
|
+
|
112
|
+
end
|
data/lib/bayes/fisher.rb
ADDED
@@ -0,0 +1,62 @@
|
|
1
|
+
module Yanbi
|
2
|
+
|
3
|
+
class Fisher < Yanbi::Bayes
|
4
|
+
|
5
|
+
def classify(text)
|
6
|
+
max_score(text) do |cat, doc|
|
7
|
+
fisher_score(cat, doc)
|
8
|
+
end
|
9
|
+
end
|
10
|
+
|
11
|
+
private
|
12
|
+
|
13
|
+
def fisher_score(category, document)
|
14
|
+
features = document.words.uniq
|
15
|
+
pscores = 1
|
16
|
+
|
17
|
+
|
18
|
+
###
|
19
|
+
#compute weighted probabilities for each word/cat tuple
|
20
|
+
#and then multiply them all together...
|
21
|
+
##
|
22
|
+
|
23
|
+
|
24
|
+
|
25
|
+
features.each do |word|
|
26
|
+
clf = word_prob(category, word)
|
27
|
+
freqsum = @categories.reduce(0) {|sum, x| sum + word_prob(x, word)}
|
28
|
+
pscores *= (clf / freqsum) if clf > 0
|
29
|
+
end
|
30
|
+
|
31
|
+
#####
|
32
|
+
|
33
|
+
|
34
|
+
#compute fisher factor of pscores
|
35
|
+
score = -2 * Math.log(pscores)
|
36
|
+
|
37
|
+
#this is okay
|
38
|
+
invchi2(score, features.count * 2)
|
39
|
+
end
|
40
|
+
|
41
|
+
def word_prob(cat, word)
|
42
|
+
@category_counts[cat][word].to_f / @document_counts[cat]
|
43
|
+
end
|
44
|
+
|
45
|
+
def invchi2(chi, df)
|
46
|
+
m = chi / 2.0
|
47
|
+
sum = Math.exp(-m)
|
48
|
+
term = Math.exp(-m)
|
49
|
+
|
50
|
+
(1..df/2).each do |i|
|
51
|
+
term *= (m / i)
|
52
|
+
sum += term
|
53
|
+
end
|
54
|
+
|
55
|
+
[sum, 1.0].min
|
56
|
+
|
57
|
+
rescue
|
58
|
+
1.0
|
59
|
+
end
|
60
|
+
end
|
61
|
+
|
62
|
+
end
|
data/lib/corpus.rb
ADDED
@@ -0,0 +1,63 @@
|
|
1
|
+
# Author:: Robert Dormer (mailto:rdormer@gmail.com)
|
2
|
+
# Copyright:: Copyright (c) 2016 Robert Dormer
|
3
|
+
# License:: MIT
|
4
|
+
|
5
|
+
# This is the class for managing a corpus of documents. It's recommended, though not necessary,
|
6
|
+
# that all of the documents in a given corpus be in the same category, if you're using the corpus
|
7
|
+
# to train your classifier. Can accept either raw strings through add_doc, or files through add_file.
|
8
|
+
# Files can be delimited so that you can have more than one document in them, and commenting is
|
9
|
+
# available
|
10
|
+
|
11
|
+
$: << File.dirname(__FILE__)
|
12
|
+
require 'yanbi'
|
13
|
+
|
14
|
+
module Yanbi
|
15
|
+
|
16
|
+
class Corpus
|
17
|
+
|
18
|
+
attr_reader :docs
|
19
|
+
attr_reader :bags
|
20
|
+
attr_reader :all
|
21
|
+
|
22
|
+
def initialize(klass=WordBag)
|
23
|
+
@all = klass.new
|
24
|
+
@docs = []
|
25
|
+
@bags = []
|
26
|
+
end
|
27
|
+
|
28
|
+
def size
|
29
|
+
@docs.size
|
30
|
+
end
|
31
|
+
|
32
|
+
def add_file(docpath, delim=nil, comment=nil)
|
33
|
+
infile = File.open(docpath, 'r')
|
34
|
+
raw = infile.read
|
35
|
+
infile.close
|
36
|
+
|
37
|
+
if delim
|
38
|
+
docs = raw.split(delim)
|
39
|
+
docs.each {|d| add_doc(d, comment)}
|
40
|
+
else
|
41
|
+
add_doc(raw, comment)
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
def add_doc(doc, comment=nil)
|
46
|
+
doc.gsub! comment, '' if comment
|
47
|
+
doc.strip!
|
48
|
+
|
49
|
+
unless doc.length.zero?
|
50
|
+
@bags << @all.class.new(doc)
|
51
|
+
@all.add_text doc
|
52
|
+
@docs << doc
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
def each_doc
|
57
|
+
@bags.each do |bag|
|
58
|
+
yield bag
|
59
|
+
end
|
60
|
+
end
|
61
|
+
end
|
62
|
+
|
63
|
+
end
|
data/lib/version.rb
ADDED
@@ -0,0 +1,36 @@
|
|
1
|
+
# Author:: Robert Dormer (mailto:rdormer@gmail.com)
|
2
|
+
# Copyright:: Copyright (c) 2016 Robert Dormer
|
3
|
+
# License:: MIT
|
4
|
+
|
5
|
+
# A word bag that stores the words as diads instead of individual words.
|
6
|
+
# i.e. "the quick brown fox" becomes "the quick", "quick brown", "brown fox".
|
7
|
+
# This type of shingling is often recommended as a way to boost the accuracy
|
8
|
+
# of Bayes classifiers
|
9
|
+
|
10
|
+
$: << File.dirname(__FILE__)
|
11
|
+
require 'wordbag'
|
12
|
+
|
13
|
+
module Yanbi
|
14
|
+
|
15
|
+
class DiadBag < WordBag
|
16
|
+
def process(raw)
|
17
|
+
processed = raw.downcase
|
18
|
+
processed.gsub!(/[^\w\s'\-]/, ' ')
|
19
|
+
words = processed.split
|
20
|
+
words = words.map {|x| x.split /-/}.flatten
|
21
|
+
|
22
|
+
if block_given?
|
23
|
+
words.map! {|x| yield x}
|
24
|
+
end
|
25
|
+
|
26
|
+
diads = []
|
27
|
+
words.each_with_index {|w, i| diads << [w, words[i+1]]}
|
28
|
+
diads.delete_at(-1)
|
29
|
+
|
30
|
+
words = diads.map {|x| "#{x.first} #{x.last}"}
|
31
|
+
update_counts(words)
|
32
|
+
@words.concat(words)
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
# Author:: Robert Dormer (mailto:rdormer@gmail.com)
|
2
|
+
# Copyright:: Copyright (c) 2016 Robert Dormer
|
3
|
+
# License:: MIT
|
4
|
+
|
5
|
+
# This is a word bag with a post-processing step to stem (lemmatize)
|
6
|
+
# the words in the bag
|
7
|
+
|
8
|
+
$: << File.dirname(__FILE__)
|
9
|
+
require 'fast_stemmer'
|
10
|
+
require 'wordbag'
|
11
|
+
|
12
|
+
module Yanbi
|
13
|
+
|
14
|
+
class StemmedWordBag < WordBag
|
15
|
+
def standardize(raw)
|
16
|
+
process(raw) {|word| word.stem}
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
end
|
@@ -0,0 +1,16 @@
|
|
1
|
+
# Author:: Robert Dormer (mailto:rdormer@gmail.com)
|
2
|
+
# Copyright:: Copyright (c) 2016 Robert Dormer
|
3
|
+
# License:: MIT
|
4
|
+
|
5
|
+
$: << File.dirname(__FILE__)
|
6
|
+
require 'diadbag'
|
7
|
+
|
8
|
+
module Yanbi
|
9
|
+
|
10
|
+
class StemmedDiadBag < DiadBag
|
11
|
+
def standardize(raw)
|
12
|
+
process(raw) {|word| word.stem}
|
13
|
+
end
|
14
|
+
end
|
15
|
+
|
16
|
+
end
|
@@ -0,0 +1,104 @@
|
|
1
|
+
# Author:: Robert Dormer (mailto:rdormer@gmail.com)
|
2
|
+
# Copyright:: Copyright (c) 2016 Robert Dormer
|
3
|
+
# License:: MIT
|
4
|
+
|
5
|
+
# Word bag class, implementing the bag of words / multi-set that is so popular in text
|
6
|
+
# classification literature. A single bag can contain multiple documents if you want
|
7
|
+
# it to, although for training a Bayes classifier this is probably not recommended.
|
8
|
+
|
9
|
+
$: << File.dirname(__FILE__)
|
10
|
+
require 'yaml'
|
11
|
+
|
12
|
+
module Yanbi
|
13
|
+
|
14
|
+
class WordBag
|
15
|
+
|
16
|
+
attr_reader :words
|
17
|
+
|
18
|
+
def initialize(corpus=nil)
|
19
|
+
@words = []
|
20
|
+
@counts = {}
|
21
|
+
standardize(corpus) if corpus
|
22
|
+
end
|
23
|
+
|
24
|
+
def add_file(filename)
|
25
|
+
raw = File.open(filename).read
|
26
|
+
standardize(raw)
|
27
|
+
end
|
28
|
+
|
29
|
+
def add_text(text)
|
30
|
+
standardize(text)
|
31
|
+
end
|
32
|
+
|
33
|
+
def save(filename)
|
34
|
+
out = File.new(filename + ".yml", "w")
|
35
|
+
out.write(@words.to_yaml)
|
36
|
+
out.close
|
37
|
+
end
|
38
|
+
|
39
|
+
def load(filename)
|
40
|
+
@words = YAML.load_file(filename + ".yml")
|
41
|
+
update_counts(@words)
|
42
|
+
end
|
43
|
+
|
44
|
+
def self.load(filename)
|
45
|
+
WordBag.new.load(filename)
|
46
|
+
end
|
47
|
+
|
48
|
+
def word_counts(min=1)
|
49
|
+
@counts.select {|key, value| value >= min}
|
50
|
+
end
|
51
|
+
|
52
|
+
def remove(words)
|
53
|
+
words.each do |word|
|
54
|
+
@words.reject! {|x| x == word}
|
55
|
+
@counts.delete(word)
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
59
|
+
def between_counts(min, max=nil)
|
60
|
+
counts = @counts.select{|key, value| value >= min}
|
61
|
+
counts.select! {|key, value| value <= max} unless max.nil?
|
62
|
+
@words.select {|word| counts.keys.include? word}
|
63
|
+
end
|
64
|
+
|
65
|
+
def intersection(other)
|
66
|
+
self.words & other.words
|
67
|
+
end
|
68
|
+
|
69
|
+
def empty?
|
70
|
+
@words.empty?
|
71
|
+
end
|
72
|
+
|
73
|
+
private
|
74
|
+
|
75
|
+
def standardize(raw)
|
76
|
+
process(raw)
|
77
|
+
end
|
78
|
+
|
79
|
+
def process(raw)
|
80
|
+
processed = raw.downcase
|
81
|
+
processed.gsub!(/[^\w\s'\-]/, ' ')
|
82
|
+
words = processed.split
|
83
|
+
words = words.map {|x| x.split /-/}.flatten
|
84
|
+
|
85
|
+
if block_given?
|
86
|
+
words.map! {|x| yield x}
|
87
|
+
end
|
88
|
+
|
89
|
+
update_counts(words)
|
90
|
+
@words.concat(words)
|
91
|
+
end
|
92
|
+
|
93
|
+
def update_counts(data)
|
94
|
+
data.each do |word|
|
95
|
+
if @counts[word].nil?
|
96
|
+
@counts[word] = 1
|
97
|
+
else
|
98
|
+
@counts[word] += 1
|
99
|
+
end
|
100
|
+
end
|
101
|
+
end
|
102
|
+
end
|
103
|
+
|
104
|
+
end
|
data/lib/yanbi.rb
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
# Author:: Robert Dormer (mailto:rdormer@gmail.com)
|
2
|
+
# Copyright:: Copyright (c) 2016 Robert Dormer
|
3
|
+
# License:: MIT
|
4
|
+
|
5
|
+
base = File.dirname(__FILE__)
|
6
|
+
$: << base
|
7
|
+
|
8
|
+
Dir[base + "/wordbags/**/*.rb"].each do |bag|
|
9
|
+
require bag
|
10
|
+
end
|
11
|
+
|
12
|
+
Dir[base + "/bayes/**/*.rb"].each do |c|
|
13
|
+
require c
|
14
|
+
end
|
15
|
+
|
16
|
+
require 'corpus'
|
17
|
+
require 'version'
|
data/yanbi-ml.gemspec
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "yanbi-ml"
|
8
|
+
spec.version = Yanbi::VERSION
|
9
|
+
spec.authors = ["Robert Dormer"]
|
10
|
+
spec.email = ["rdormer@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{Yet Another Naive Bayes Implementation}
|
13
|
+
spec.homepage = "http://github.com/rdormer/yanbi-ml"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
17
|
+
spec.bindir = "exe"
|
18
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.11"
|
22
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
23
|
+
spec.add_development_dependency "rspec", "~> 3.4.0"
|
24
|
+
spec.add_development_dependency "fast-stemmer", "~> 1.0.2"
|
25
|
+
end
|
metadata
ADDED
@@ -0,0 +1,126 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: yanbi-ml
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Robert Dormer
|
9
|
+
autorequire:
|
10
|
+
bindir: exe
|
11
|
+
cert_chain: []
|
12
|
+
date: 2016-07-05 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: bundler
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ~>
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '1.11'
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ~>
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '1.11'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: rake
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ~>
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '10.0'
|
38
|
+
type: :development
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ~>
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '10.0'
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: rspec
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ~>
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: 3.4.0
|
54
|
+
type: :development
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ~>
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 3.4.0
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: fast-stemmer
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
65
|
+
none: false
|
66
|
+
requirements:
|
67
|
+
- - ~>
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: 1.0.2
|
70
|
+
type: :development
|
71
|
+
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ~>
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: 1.0.2
|
78
|
+
description:
|
79
|
+
email:
|
80
|
+
- rdormer@gmail.com
|
81
|
+
executables: []
|
82
|
+
extensions: []
|
83
|
+
extra_rdoc_files: []
|
84
|
+
files:
|
85
|
+
- .travis.yml
|
86
|
+
- Gemfile
|
87
|
+
- README.md
|
88
|
+
- Rakefile
|
89
|
+
- bin/console
|
90
|
+
- bin/setup
|
91
|
+
- lib/bayes/bayes.rb
|
92
|
+
- lib/bayes/fisher.rb
|
93
|
+
- lib/corpus.rb
|
94
|
+
- lib/version.rb
|
95
|
+
- lib/wordbags/diadbag.rb
|
96
|
+
- lib/wordbags/stembag.rb
|
97
|
+
- lib/wordbags/stemmed_diadbag.rb
|
98
|
+
- lib/wordbags/wordbag.rb
|
99
|
+
- lib/yanbi.rb
|
100
|
+
- yanbi-ml.gemspec
|
101
|
+
homepage: http://github.com/rdormer/yanbi-ml
|
102
|
+
licenses:
|
103
|
+
- MIT
|
104
|
+
post_install_message:
|
105
|
+
rdoc_options: []
|
106
|
+
require_paths:
|
107
|
+
- lib
|
108
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
109
|
+
none: false
|
110
|
+
requirements:
|
111
|
+
- - ! '>='
|
112
|
+
- !ruby/object:Gem::Version
|
113
|
+
version: '0'
|
114
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
115
|
+
none: false
|
116
|
+
requirements:
|
117
|
+
- - ! '>='
|
118
|
+
- !ruby/object:Gem::Version
|
119
|
+
version: '0'
|
120
|
+
requirements: []
|
121
|
+
rubyforge_project:
|
122
|
+
rubygems_version: 1.8.25
|
123
|
+
signing_key:
|
124
|
+
specification_version: 3
|
125
|
+
summary: Yet Another Naive Bayes Implementation
|
126
|
+
test_files: []
|