Class: SpaCyModel

Inherits:
VectorModel show all
Defined in:
lib/rbbt/vector/model/spaCy.rb

Instance Attribute Summary collapse

Attributes inherited from VectorModel

#directory, #eval_model, #extract_features, #factor_levels, #features, #labels, #model_file, #names, #train_model

Class Method Summary collapse

Instance Method Summary collapse

Methods inherited from VectorModel

R_eval, R_run, R_train, #__load_method, #add, #add_list, #clear, #cross_validation, #eval, #eval_list, f1_metrics, #run, #save_models, #train

Constructor Details

#initialize(dir, config, categories = %w(positive negative),, lang = 'en_core_web_md') ⇒ SpaCyModel

Returns a new instance of SpaCyModel.



13
14
15
16
17
18
19
20
21
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
67
68
69
70
71
72
73
74
75
76
 
# File 'lib/rbbt/vector/model/spaCy.rb', line 13

def initialize(dir, config, categories = %w(positive negative), lang = 'en_core_web_md')
  @config = case
            when Path === config
              config.read
            when Misc.is_filename?(config)
              Open.read(config)
            when (Misc.is_filename?(config, false) && Rbbt.share.spaCy.cpu[config].exists?)
              Rbbt.share.spaCy.cpu[config].read
            when (Misc.is_filename?(config, false) && Rbbt.share.spaCy[config].exists?)
              Rbbt.share.spaCy[config].read
            else
              config
            end
  @lang = lang

  super(dir)

  @train_model = Proc.new do |file, features, labels|
    texts = features
    docs = []
    tmpconfig = File.join(file, 'config')
    tmptrain = File.join(file, 'train.spacy')
    SpaCy.config(@config, tmpconfig)
    SpaCyModel.spacy do
      nlp = SpaCy.nlp(lang)
      docs = []
      RbbtPython.iterate nlp.pipe(texts.zip(labels), as_tuples: true), :bar => "Training documents into spacy format" do |doc,label|
        doc.cats[label] = 1
        #if %w(1 true pos).include?(label.to_s.downcase) 
        #  doc.cats["positive"] = 1
        #  doc.cats["negative"] = 0
        #else
        #  doc.cats["positive"] = 0
        #  doc.cats["negative"] = 1
        #end
        docs << doc
      end

      doc_bin = spacy.tokens.DocBin.new(docs: docs)
      doc_bin.to_disk(tmptrain)
    end

    gpu = Rbbt::Config.get('gpu_id', :spacy, :spacy_train, :default => 0)
    CMD.cmd_log(:spacy, "train #{tmpconfig} --output #{file} --paths.train #{tmptrain} --paths.dev #{tmptrain}",  "--gpu-id" => gpu)
  end
 
  @eval_model = Proc.new do |file, features|
    texts = features

    docs = []
    SpaCyModel.spacy do
      nlp = spacy.load("#{file}/model-best")

      Log::ProgressBar.with_bar texts.length, :desc => "Evaluating documents" do |bar|
        texts.collect do |text|
          cats = nlp.(text).cats
          bar.tick
          cats.sort_by{|l,v| v.to_f }.last.first
          #cats['positive'] > cats['negative']  ? 1 : 0
        end
      end
    end
  end
end

Instance Attribute Details

#config ⇒ Object

Returns the value of attribute config.



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

def config
  @config
end

Class Method Details

.spacy(&block) ⇒ Object 



7
8
9
10
11
 
# File 'lib/rbbt/vector/model/spaCy.rb', line 7

def self.spacy(&block)
  RbbtPython.run "spacy" do 
    RbbtPython.module_eval(&block)
  end
end