Class: OpenTox::Validation

Inherits:
Object show all
Defined in:
lib/validation.rb

Class Method Summary collapse

Instance Method Summary collapse

Class Method Details

.create(model, training_set, test_set, crossvalidation = nil) ⇒ Object



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
# File 'lib/validation.rb', line 25

def self.create model, training_set, test_set, crossvalidation=nil
  
  atts = model.attributes.dup # do not modify attributes from original model
  atts["_id"] = BSON::ObjectId.new
  atts[:training_dataset_id] = training_set.id
  validation_model = model.class.create training_set, atts
  validation_model.save
  cids = test_set.compound_ids

  test_set_without_activities = Dataset.new(:compound_ids => cids.uniq) # remove duplicates and make sure that activities cannot be used
  prediction_dataset = validation_model.predict test_set_without_activities
  predictions = []
  nr_unpredicted = 0
  activities = test_set.data_entries.collect{|de| de.first}
  prediction_dataset.data_entries.each_with_index do |de,i|
    if de[0] #and de[1] 
      cid = prediction_dataset.compound_ids[i]
      rows = cids.each_index.select{|r| cids[r] == cid }
      activities = rows.collect{|r| test_set.data_entries[r][0]}
      prediction = de.first
      confidence = de[1]
      predictions << [prediction_dataset.compound_ids[i], activities, prediction, de[1]]
    else
      nr_unpredicted += 1
    end
  end
  validation = self.new(
    :model_id => validation_model.id,
    :prediction_dataset_id => prediction_dataset.id,
    :test_dataset_id => test_set.id,
    :nr_instances => test_set.compound_ids.size,
    :nr_unpredicted => nr_unpredicted,
    :predictions => predictions#.sort{|a,b| p a; b[3] <=> a[3]} # sort according to confidence
  )
  validation.crossvalidation_id = crossvalidation.id if crossvalidation
  validation.save
  validation
end

Instance Method Details

#modelObject



21
22
23
# File 'lib/validation.rb', line 21

def model
  Model::Lazar.find model_id
end

#prediction_datasetObject



13
14
15
# File 'lib/validation.rb', line 13

def prediction_dataset
  Dataset.find prediction_dataset_id
end

#test_datasetObject



17
18
19
# File 'lib/validation.rb', line 17

def test_dataset
  Dataset.find test_dataset_id
end