From 8d2f1c8a0f6cc9f7a481d1117bf8b3351130b1ea Mon Sep 17 00:00:00 2001
From: Christoph Helma <helma@in-silico.ch>
Date: Wed, 7 Oct 2015 12:34:02 +0200
Subject: generalised fingerprints

---
 test/experiment.rb | 121 ++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 115 insertions(+), 6 deletions(-)

(limited to 'test/experiment.rb')

diff --git a/test/experiment.rb b/test/experiment.rb
index 2c4073d..b49f349 100644
--- a/test/experiment.rb
+++ b/test/experiment.rb
@@ -70,8 +70,8 @@ class ExperimentTest < MiniTest::Test
     ]
     min_sims = [0.3,0.7]
     #min_sims = [0.7]
-    #types = ["FP2","FP3","FP4","MACCS","mpd"]
-    types = ["mpd","FP3"]
+    #types = ["FP2","FP3","FP4","MACCS","MP2D"]
+    types = ["MP2D","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},
@@ -113,13 +113,12 @@ class ExperimentTest < MiniTest::Test
   end
 
   def test_mpd_fingerprints
-=begin
     datasets = [
       "EPAFHM.medi.csv",
     ]
-    types = ["FP2","mpd"]
+    types = ["FP2","MP2D"]
     experiment = Experiment.create(
-      :name => "FP2 vs mpd fingerprint regression for datasets #{datasets}.",
+      :name => "FP2 vs MP2D fingerprint regression for datasets #{datasets}.",
       :dataset_ids => datasets.collect{|d| Dataset.from_csv_file(File.join(DATA_DIR, d)).id},
     )
     types.each do |type|
@@ -134,8 +133,9 @@ class ExperimentTest < MiniTest::Test
     end
     experiment.run
     p experiment.id
+=begin
 =end
-    experiment = Experiment.find '55ffd0c02b72ed123c000000'
+    #experiment = Experiment.find '55ffd0c02b72ed123c000000'
     p experiment
     puts experiment.report.to_yaml
   end
@@ -182,4 +182,113 @@ class ExperimentTest < MiniTest::Test
     puts experiment.report.to_yaml
     p experiment.summary
   end
+
+  def test_mpd_mna_regression_fingerprints
+    datasets = [
+      "EPAFHM.medi.csv",
+      #"hamster_carcinogenicity.csv" 
+    ]
+    min_sims = [0.0,0.3]
+    types = ["MP2D","MNA"]
+    neighbor_algos = [
+      "fingerprint_neighbors",
+      "fingerprint_count_neighbors",
+    ]
+    experiment = Experiment.create(
+      :name => "MNA vs MPD descriptors",
+      :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|
+        neighbor_algos.each do |neighbor_algo|
+          experiment.model_settings << {
+            :model_algorithm => "OpenTox::Model::LazarRegression",
+            :prediction_algorithm => "OpenTox::Algorithm::Regression.weighted_average",
+            :neighbor_algorithm => neighbor_algo,
+            :neighbor_algorithm_parameters => {
+              :type => type,
+              :min_sim => min_sim,
+            }
+          }
+        end
+      end
+    end
+    experiment.run
+#=end
+=begin
+    experiment = Experiment.find '56029cb92b72ed673d000000'
+=end
+    p experiment.id
+    puts experiment.report.to_yaml
+    #p experiment.summary
+    experiment.results.each do |dataset,result|
+      result.each do |r|
+        p r
+        # TODO fix r["model_id"]
+        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
+  end
+
+  def test_mpd_mna_classification_fingerprints
+    datasets = [
+      #"EPAFHM.medi.csv",
+      "hamster_carcinogenicity.csv" 
+    ]
+    min_sims = [0.0,0.3]
+    types = ["MP2D","MNA"]
+    neighbor_algos = [
+      "fingerprint_count_neighbors",
+      "fingerprint_neighbors",
+    ]
+    experiment = Experiment.create(
+      :name => "MNA vs MPD descriptors",
+      :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|
+        neighbor_algos.each do |neighbor_algo|
+          experiment.model_settings << {
+            :model_algorithm => "OpenTox::Model::LazarClassification",
+            :prediction_algorithm => "OpenTox::Algorithm::Classification.weighted_majority_vote",
+            :neighbor_algorithm => neighbor_algo,
+            :neighbor_algorithm_parameters => {
+              :type => type,
+              :min_sim => min_sim,
+            }
+          }
+        end
+      end
+    end
+    experiment.run
+#=end
+=begin
+    experiment = Experiment.find '56029cb92b72ed673d000000'
+=end
+    p experiment.id
+    puts experiment.report.to_yaml
+    #p experiment.summary
+    experiment.results.each do |dataset,result|
+      result.each do |r|
+        # TODO fix r["model_id"]
+        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
+  end
 end
-- 
cgit v1.2.3