Class: NekonekoGen::TextClassifierGenerator

Inherits:
Object
  • Object
show all
Defined in:
lib/nekoneko_gen/text_classifier_generator.rb

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(filename, files, options = {}) ⇒ TextClassifierGenerator

Returns a new instance of TextClassifierGenerator.



10
11
12
13
14
15
16
17
18
19
20
# File 'lib/nekoneko_gen/text_classifier_generator.rb', line 10

def initialize(filename, files, options = {})
  @quiet = false
  @options = options
  @filename = filename
  @files = files
  @word2id = {}
  @id2word = {}
  @classifier = ClassifierFactory.create(files.size, options)
  @name = safe_name(@filename).split("_").map(&:capitalize).join
  @labels = files.map {|file| "#{safe_name(file).upcase}"}
end

Instance Attribute Details

#quietObject

Returns the value of attribute quiet.



9
10
11
# File 'lib/nekoneko_gen/text_classifier_generator.rb', line 9

def quiet
  @quiet
end

Instance Method Details

#generate(lang = :ruby) ⇒ Object



67
68
69
70
71
72
73
74
75
76
# File 'lib/nekoneko_gen/text_classifier_generator.rb', line 67

def generate(lang = :ruby)
  lang ||= :ruby
  case lang
  when :ruby
    generate_ruby_code
  else
    raise NotImplementedError
  end
  @name
end

#generate_ruby_codeObject



77
78
79
80
81
82
83
84
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
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
# File 'lib/nekoneko_gen/text_classifier_generator.rb', line 77

def generate_ruby_code
  labels = @labels.each_with_index.map{|v, i| "  #{v} = #{i}"}.join("\n")
  File.open(@filename, "w") do |f|
    f.write <<MODEL
# -*- coding: utf-8 -*-
require 'rubygems'
require 'json'
require 'bimyou_segmenter'

class #{@name}
  def self.k
K
  end
  def self.predict(text)
classify(fv(text))
  end
  
#{labels}
  LABELS = #{@labels.inspect}
  K = #{@classifier.k}
  
  private
  def self.fv(text)
prev = nil
BimyouSegmenter.segment(text).map do |word|
  if (prev)
    if (NGRAM_TARGET =~ word)
      nword = [prev + word, word]
      prev = word
      nword
    else
      prev = nil
      word
    end
  else
    if (NGRAM_TARGET =~ word)
      prev = word
    end
    word
  end
end.flatten(1)
  end
#{@classifier.classify_method_code(:ruby)}
  
  NGRAM_TARGET = Regexp.new('(^[ァ-ヾ]+$)|(^[a-zA-Z\\-_a-zA-Z‐_0-90-9]+$)|' +
                     '(^[々〇ヵヶ' + [0x3400].pack('U') + '-' + [0x9FFF].pack('U') +
                     [0xF900].pack('U') + '-' + [0xFAFF].pack('U') +
                        [0x20000].pack('U') + '-' + [0x2FFFF].pack('U') + ']+$)')
#{@classifier.parameter_code(:ruby, lambda{|id| id2word(id) })}
end
MODEL
  end
end

#train(iteration = nil) ⇒ Object



22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
# File 'lib/nekoneko_gen/text_classifier_generator.rb', line 22

def train(iteration = nil)
  iteration ||= @classifier.default_iteration
  data = []
  @classifier.k.times do |i|
    t = Time.now
    data[i] = []
    print "loading #{@files[i]}... "
    
    content = nil
    File.open(@files[i]) do |f|
      content = f.read
    end
    content = NKF.nkf('-w', content)
    content.lines do |line|
      vec = fv(line.chomp)
      if (vec.size > 0)
        data[i] << normalize(vec)
      end
    end
    puts sprintf("%.4fs", Time.now - t)
  end
  samples = data.map{|v| v.size}.min
  iteration.times do |step|
    loss = 0.0
    c = 0
    t = Time.now
    print sprintf("step %3d...", step)
    
    @classifier.k.times.map do |i|
      sampling(data[i], samples).map {|vec| [vec, i] }
    end.flatten(1).shuffle!.each do |v|
      loss += @classifier.update(v[0], v[1])
      c += 1
    end
    print sprintf(" %.6f, %.4fs\n", 1.0 - loss / c.to_f, Time.now - t)
  end
  if (@classifier.k > 2)
    @classifier.k.times do |i|
      puts "#{@labels[i]} : #{@classifier.features(i)} features"
    end
  else
    puts "#{@labels[0]}, #{@labels[1]} : #{@classifier.features(0)} features"
  end
  puts "done nyan! "
end