Class: VectorModel

Inherits:
Object
  • Object
show all
Defined in:
lib/rbbt/vector/model.rb

Direct Known Subclasses

SVMModel

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(directory, extract_features = nil, train_model = nil, eval_model = nil) ⇒ VectorModel

Returns a new instance of VectorModel.



49
50
51
52
53
54
55
56
57
58
 
# File 'lib/rbbt/vector/model.rb', line 49

def initialize(directory, extract_features = nil, train_model = nil, eval_model = nil)
  @directory = directory
  FileUtils.mkdir_p @directory unless File.exists? @directory
  @model_file = File.join(@directory, "model")
  extract_features = @extract_features 
  train_model = @train_model 
  eval_model = @eval_model
  @features = []
  @labels = []
end

Instance Attribute Details

#directory ⇒ Object

Returns the value of attribute directory.



4
5
6
 
# File 'lib/rbbt/vector/model.rb', line 4

def directory
  @directory
end

#eval_model ⇒ Object

Returns the value of attribute eval_model.



4
5
6
 
# File 'lib/rbbt/vector/model.rb', line 4

def eval_model
  @eval_model
end

#extract_features ⇒ Object

Returns the value of attribute extract_features.



4
5
6
 
# File 'lib/rbbt/vector/model.rb', line 4

def extract_features
  @extract_features
end

#features ⇒ Object

Returns the value of attribute features.



5
6
7
 
# File 'lib/rbbt/vector/model.rb', line 5

def features
  @features
end

#labels ⇒ Object

Returns the value of attribute labels.



5
6
7
 
# File 'lib/rbbt/vector/model.rb', line 5

def labels
  @labels
end

#model_file ⇒ Object

Returns the value of attribute model_file.



4
5
6
 
# File 'lib/rbbt/vector/model.rb', line 4

def model_file
  @model_file
end

#train_model ⇒ Object

Returns the value of attribute train_model.



4
5
6
 
# File 'lib/rbbt/vector/model.rb', line 4

def train_model
  @train_model
end

Class Method Details

.R_eval(model_file, features, list, code) ⇒ 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
 
# File 'lib/rbbt/vector/model.rb', line 22

def self.R_eval(model_file, features, list, code)
  TmpFile.with_file do |feature_file|
    TmpFile.with_file do |results|
      if list
        Open.write(feature_file, features.collect{|feat| feat * "\t"} * "\n" + "\n")
      else
        Open.write(feature_file, features * "\t" + "\n")
      end

      io = R.run <<-EOF
features = read.table("#{ feature_file }", sep ="\\t", stringsAsFactors=FALSE);
load(file="#{model_file}");
#{code}
cat(paste(label, sep="\\n"));
      EOF

      res = io.read.sub(/WARNING: .*?\n/s,'').split(/\s+/).collect{|l| l.to_f}

      if list
        res
      else
        res.first
      end
    end
  end
end

.R_train(model_file, features, labels, code) ⇒ Object 



7
8
9
10
11
12
13
14
15
16
17
18
19
20
 
# File 'lib/rbbt/vector/model.rb', line 7

def self.R_train(model_file, features, labels, code)
  TmpFile.with_file do |feature_file|
    Open.write(feature_file, features.collect{|feats| feats * "\t"} * "\n")
    Open.write(feature_file + '.class', labels * "\n")

    R.run <<-EOF
features = read.table("#{ feature_file }", sep ="\\t", stringsAsFactors=FALSE);
labels = scan("#{ feature_file }.class");
features = cbind(features, class = labels);
#{code}
save(model, file='#{model_file}')
    EOF
  end
end

Instance Method Details

#add(element, label = nil) ⇒ Object 



60
61
62
63
 
# File 'lib/rbbt/vector/model.rb', line 60

def add(element, label = nil)
  @features << extract_features.call(element)
  @labels << label unless label.nil?
end

#cross_validation(folds = 10) ⇒ Object 



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
 
# File 'lib/rbbt/vector/model.rb', line 92

def cross_validation(folds = 10)
  saved_features = @features
  saved_labels = @labels
  seq = (0..features.length - 1).to_a

  chunk_size = features.length / folds

  acc = []
  folds.times do
    seq = seq.shuffle
    eval_chunk = seq[0..chunk_size]
    train_chunk = seq[chunk_size.. -1]

    eval_features = @features.values_at *eval_chunk
    eval_labels = @labels.values_at *eval_chunk

    @features = @features.values_at *train_chunk
    @labels = @labels.values_at *train_chunk

    train
    predictions = eval_list eval_features, false

    acc << predictions.zip(eval_labels).collect{|pred,lab| pred - lab < 0.5 ? 1 : 0}.inject(0){|acc,e| acc +=e} / chunk_size

    @features = saved_features
    @labels = saved_labels
  end

  acc
end

#eval(element) ⇒ Object 



74
75
76
77
78
79
80
81
 
# File 'lib/rbbt/vector/model.rb', line 74

def eval(element)
  case 
  when Proc === eval_model
    eval_model.call(@model_file, extract_features.call(element), false)
  when String === eval_model
    SVMModel.R_eval(@model_file,  extract_features.call(element), false, eval_model)
  end
end

#eval_list(elements, extract = true) ⇒ Object 



83
84
85
86
87
88
89
90
 
# File 'lib/rbbt/vector/model.rb', line 83

def eval_list(elements, extract = true)
  case 
  when Proc === eval_model
    eval_model.call(@model_file, extract ? elements.collect{|element| extract_features.call(element)} : elements, true)
  when String === eval_model
    SVMModel.R_eval(@model_file, extract ? elements.collect{|element| extract_features.call(element)} : elements, true, eval_model)
  end
end

#train ⇒ Object 



65
66
67
68
69
70
71
72
 
# File 'lib/rbbt/vector/model.rb', line 65

def train
  case 
  when Proc === train_model
    train_model.call(@model_file, @features, @labels)
  when String === train_model
    SVMModel.R_train(@model_file,  @features, @labels, train_model)
  end
end