summaryrefslogtreecommitdiff
path: root/test/experiment.rb
blob: 2c4073dee799303a6b3a64dafcb0da77d37467fe (plain)
1
2
3
4
5
6
7
8
9
10
11
12
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
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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
require_relative "setup.rb"

class ExperimentTest < MiniTest::Test

  def test_regression_experiment
    datasets = [
      "EPAFHM.medi.csv",
      #"EPAFHM.csv",
      #"FDA_v3b_Maximum_Recommended_Daily_Dose_mmol.csv",
      "LOAEL_mmol_corrected_smiles.csv"
    ]
    experiment = Experiment.create(
      :name => "Default regression for datasets #{datasets}.",
      :dataset_ids => datasets.collect{|d| Dataset.from_csv_file(File.join(DATA_DIR, d)).id},
      :model_settings => [
        {
          :algorithm => "OpenTox::Model::LazarRegression",
        }
      ]
    )
    #experiment.run
    puts experiment.report.to_yaml
    assert_equal datasets.size, experiment.results.size
    experiment.results.each do |dataset_id, result|
      assert_equal 1, result.size
      result.each do |r|
        assert_kind_of BSON::ObjectId, r[:model_id]
        assert_kind_of BSON::ObjectId, r[:repeated_crossvalidation_id]
      end
    end
  end

  def test_classification_experiment

    datasets = [ "hamster_carcinogenicity.csv" ]
    experiment = Experiment.create(
      :name => "Fminer vs fingerprint classification for datasets #{datasets}.",
      :dataset_ids => datasets.collect{|d| Dataset.from_csv_file(File.join(DATA_DIR, d)).id},
      :model_settings => [
        {
          :algorithm => "OpenTox::Model::LazarClassification",
        },{
          :algorithm => "OpenTox::Model::LazarClassification",
          :neighbor_algorithm_parameter => {:min_sim => 0.3}
        },
        #{
          #:algorithm => "OpenTox::Model::LazarFminerClassification",
        #}
      ]
    )
    #experiment.run
=begin
    experiment = Experiment.find "55f944a22b72ed7de2000000"
=end
    puts experiment.report.to_yaml
    experiment.results.each do |dataset_id, result|
      assert_equal 2, result.size
      result.each do |r|
        assert_kind_of BSON::ObjectId, r[:model_id]
        assert_kind_of BSON::ObjectId, r[:repeated_crossvalidation_id]
      end
    end
  end

  def test_regression_fingerprints
#=begin
    datasets = [
      "EPAFHM.medi.csv",
      #"LOAEL_mmol_corrected_smiles.csv"
    ]
    min_sims = [0.3,0.7]
    #min_sims = [0.7]
    #types = ["FP2","FP3","FP4","MACCS","mpd"]
    types = ["mpd","FP3"]
    experiment = Experiment.create(
      :name => "Fingerprint regression with different types for datasets #{datasets}.",
      :dataset_ids => datasets.collect{|d| Dataset.from_csv_file(File.join(DATA_DIR, d)).id},
    )
    types.each do |type|
      min_sims.each do |min_sim|
        experiment.model_settings << {
          :model_algorithm => "OpenTox::Model::LazarRegression",
          :prediction_algorithm => "OpenTox::Algorithm::Regression.weighted_average",
          :neighbor_algorithm => "fingerprint_neighbors",
          :neighbor_algorithm_parameters => {
            :type => type,
            :min_sim => min_sim,
          }
        }
      end
    end
    experiment.run
#=end
=begin
    experiment = Experiment.find '56029cb92b72ed673d000000'
=end
    p experiment.id
    experiment.results.each do |dataset,result|
      result.each do |r|
        params = Model::Lazar.find(r["model_id"])[:neighbor_algorithm_parameters]
        RepeatedCrossValidation.find(r["repeated_crossvalidation_id"]).crossvalidations.each do |cv|
          cv.validation_ids.each do |vid|
            model_params = Model::Lazar.find(Validation.find(vid).model_id)[:neighbor_algorithm_parameters]
            assert_equal params[:type], model_params[:type]
            assert_equal params[:min_sim], model_params[:min_sim]
            refute_equal params[:training_dataset_id], model_params[:training_dataset_id]
          end
        end
      end
    end
    puts experiment.report.to_yaml
    p experiment.summary
  end

  def test_mpd_fingerprints
=begin
    datasets = [
      "EPAFHM.medi.csv",
    ]
    types = ["FP2","mpd"]
    experiment = Experiment.create(
      :name => "FP2 vs mpd fingerprint regression for datasets #{datasets}.",
      :dataset_ids => datasets.collect{|d| Dataset.from_csv_file(File.join(DATA_DIR, d)).id},
    )
    types.each do |type|
    experiment.model_settings << {
      :algorithm => "OpenTox::Model::LazarRegression",
      :neighbor_algorithm => "fingerprint_neighbors",
      :neighbor_algorithm_parameter => {
        :type => type,
        :min_sim => 0.7,
      }
    }
    end
    experiment.run
    p experiment.id
=end
    experiment = Experiment.find '55ffd0c02b72ed123c000000'
    p experiment
    puts experiment.report.to_yaml
  end

  def test_multiple_datasets
    datasets = [
      "EPAFHM.medi.csv",
      "LOAEL_mmol_corrected_smiles.csv"
    ]
    min_sims = [0.3]
    types = ["FP2"]
    experiment = Experiment.create(
      :name => "Fingerprint regression with mutiple datasets #{datasets}.",
      :dataset_ids => datasets.collect{|d| Dataset.from_csv_file(File.join(DATA_DIR, d)).id},
    )
    types.each do |type|
      min_sims.each do |min_sim|
        experiment.model_settings << {
          :model_algorithm => "OpenTox::Model::LazarRegression",
          :prediction_algorithm => "OpenTox::Algorithm::Regression.weighted_average",
          :neighbor_algorithm => "fingerprint_neighbors",
          :neighbor_algorithm_parameters => {
            :type => type,
            :min_sim => min_sim,
          }
        }
      end
    end
    experiment.run
    p experiment.id
    experiment.results.each do |dataset,result|
      result.each do |r|
        params = Model::Lazar.find(r["model_id"])[:neighbor_algorithm_parameters]
        RepeatedCrossValidation.find(r["repeated_crossvalidation_id"]).crossvalidations.each do |cv|
          cv.validation_ids.each do |vid|
            model_params = Model::Lazar.find(Validation.find(vid).model_id)[:neighbor_algorithm_parameters]
            assert_equal params[:type], model_params[:type]
            assert_equal params[:min_sim], model_params[:min_sim]
            refute_equal params[:training_dataset_id], model_params[:training_dataset_id]
          end
        end
      end
    end
    puts experiment.report.to_yaml
    p experiment.summary
  end
end