lazar 0.0.6 → 0.0.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: d12695cc30f60a81485f2db0be93a14074a9f4bf
-  data.tar.gz: 226d76ec4b778d08022a8af3a7b16b12bbc62c9d
+  metadata.gz: 56f51ab78b66037e55ff41d7515b0c4bc3876481
+  data.tar.gz: 893b5f4827406df36ff6abc186767889e4b2cb6c
 SHA512:
-  metadata.gz: 00613fdfbc30f7353851ec82c24c4aeac75ced9324d795a82f7c473f48b4c883ec14a4a168dd4e5d5355809a28c9d9313f080ce44ec133413e0f2c529c4cc035
-  data.tar.gz: b4d427c70b096ae0ae05e1bdde94119bc61518c3b3edd37ed919387c732d8d6a1e6e34735e1e300d33bf02dfff881acdd9c95d134d43e29b9fd576bc381472f0
+  metadata.gz: b0d402841c42990b7d2a3d8efcbb9c3c7e1839939ad61774a906d289d5a0c7a33277833827175eb006d922f13da24d7c489aaba5e9c25b967dc6ea18964d9333
+  data.tar.gz: 2242413832ffe15e2ec4bcbb8bf33a0fe126e365d163fe55c804bcd6dc3741ae6f0058dd3c39b7a70121a82e81586b190787dcce96fc504bc1e5aae32af3ec10

data/VERSION

@@ -1 +1 @@
-0.0.6
+0.0.7

data/lib/crossvalidation.rb

@@ -2,11 +2,16 @@ module OpenTox
 
   class CrossValidation
     field :validation_ids, type: Array, default: []
+    field :model_id, type: BSON::ObjectId
     field :folds, type: Integer
     field :nr_instances, type: Integer
     field :nr_unpredicted, type: Integer
     field :predictions, type: Array
     field :finished_at, type: Time 
+
+    def time
+      finished_at - created_at
+    end
   end
 
   class ClassificationCrossValidation < CrossValidation
@@ -22,6 +27,7 @@ module OpenTox
 
     def self.create model, n=10
       cv = self.new
+      cv.save # set created_at
       validation_ids = []
       nr_instances = 0
       nr_unpredicted = 0
@@ -64,6 +70,10 @@ module OpenTox
         end
       end
       cv.update_attributes(
+        name: model.name,
+        model_id: model.id,
+        folds: n,
+        validation_ids: validation_ids,
         nr_instances: nr_instances,
         nr_unpredicted: nr_unpredicted,
         accept_values: accept_values,
@@ -85,10 +95,8 @@ module OpenTox
     #F measure carcinogen: 0.769, noncarcinogen: 0.348
   end
 
-  class RegressionCrossValidation < Validation
+  class RegressionCrossValidation < CrossValidation
 
-    field :validation_ids, type: Array, default: []
-    field :folds, type: Integer
     field :rmse, type: Float
     field :mae, type: Float
     field :weighted_rmse, type: Float
@@ -96,6 +104,7 @@ module OpenTox
 
     def self.create model, n=10
       cv = self.new
+      cv.save # set created_at
       validation_ids = []
       nr_instances = 0
       nr_unpredicted = 0
@@ -145,6 +154,8 @@ module OpenTox
       rmse = Math.sqrt(rmse/n)
       weighted_rmse = Math.sqrt(weighted_rmse/confidence_sum)
       cv.update_attributes(
+        name: model.name,
+        model_id: model.id,
         folds: n,
         validation_ids: validation_ids,
         nr_instances: nr_instances,

data/lib/dataset.rb

@@ -49,7 +49,7 @@ module OpenTox
           @data_entries = Marshal.load(data_entry_file.data)
           bad_request_error "Data entries (#{data_entries_id}) are not a 2D-Array" unless @data_entries.is_a? Array and @data_entries.first.is_a? Array
           bad_request_error "Data entries (#{data_entries_id}) have #{@data_entries.size} rows, but dataset (#{id}) has #{compound_ids.size} compounds" unless @data_entries.size == compound_ids.size
-          bad_request_error "Data entries (#{data_entries_id}) have #{@data_entries..first.size} columns, but dataset (#{id}) has #{feature_ids.size} features" unless @data_entries.first.size == feature_ids.size
+          bad_request_error "Data entries (#{data_entries_id}) have #{@data_entries.first.size} columns, but dataset (#{id}) has #{feature_ids.size} features" unless @data_entries.first.size == feature_ids.size
           $logger.debug "Retrieving data: #{Time.now-t}"
         end
       end

data/lib/lazar.rb

@@ -58,7 +58,7 @@ CLASSES = ["Feature","Compound","Dataset","Validation","CrossValidation"]# Algor
   "algorithm.rb",
   "descriptor.rb",
   "bbrc.rb",
-  "lazar-model.rb",
+  "model.rb",
   "similarity.rb",
   "neighbor.rb",
   "classification.rb",

data/lib/{lazar-model.rb → model.rb}

@@ -8,7 +8,7 @@ module OpenTox
       include Mongoid::Timestamps
       store_in collection: "models"
 
-      field :title, type: String
+      field :title, as: :name, type: String
       field :creator, type: String, default: __FILE__
       # datasets
       field :training_dataset_id, type: BSON::ObjectId
@@ -156,9 +156,16 @@ module OpenTox
 
     end
 
-    class PredictionModel < Lazar
-      field :category, type: String
+    class PredictionModel
+      include OpenTox
+      include Mongoid::Document
+      include Mongoid::Timestamps
+      store_in collection: "models"
+
+      # TODO field Validations
       field :endpoint, type: String
+      field :species, type: String
+      field :source, type: String
       field :unit, type: String
       field :model_id, type: BSON::ObjectId
       field :crossvalidation_id, type: BSON::ObjectId

data/lib/regression.rb

@@ -34,6 +34,30 @@ module OpenTox
         {:value => prediction,:confidence => confidence}
       end
 
+      def self.weighted_average_with_relevant_fingerprints neighbors
+        weighted_sum = 0.0
+        sim_sum = 0.0
+        fingerprint_features = []
+        neighbors.each do |row|
+          n,sim,acts = row
+          neighbor = Compound.find n
+          fingerprint_features += neighbor.fp4
+        end
+        fingerprint_features.uniq!
+        p fingerprint_features
+=begin
+          p n
+          acts.each do |act|
+            weighted_sum += sim*Math.log10(act)
+            sim_sum += sim
+          end
+        end
+=end
+        confidence = sim_sum/neighbors.size.to_f
+        sim_sum == 0 ? prediction = nil : prediction = 10**(weighted_sum/sim_sum)
+        {:value => prediction,:confidence => confidence}
+      end
+
       # Local support vector regression from neighbors 
       # @param [Hash] params Keys `:props, :activities, :sims, :min_train_performance` are required
       # @return [Numeric] A prediction value.

data/test/lazar-physchem-short.rb

@@ -2,6 +2,7 @@ require_relative "setup.rb"
 
 class LazarPhyschemDescriptorTest < MiniTest::Test
   def test_epafhm
+    skip "Physchem Regression not yet implemented."
     # check available descriptors
     @descriptors = OpenTox::Algorithm::Descriptor::DESCRIPTORS.keys
     assert_equal 111,@descriptors.size,"wrong number of physchem descriptors"

data/test/lazar-regression.rb

@@ -0,0 +1,27 @@
+require_relative "setup.rb"
+
+class LazarRegressionTest < MiniTest::Test
+
+  def test_weighted_average
+    training_dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi.csv"
+    model = Model::LazarRegression.create training_dataset
+    compound = Compound.from_smiles "CC(C)(C)CN"
+    prediction = model.predict compound
+    assert_equal 13.6, prediction[:value].round(1)
+    assert_equal 0.83, prediction[:confidence].round(2)
+    assert_equal 1, prediction[:neighbors].size
+  end
+
+  def test_weighted_average_with_relevant_fingerprints
+    training_dataset = Dataset.from_csv_file "#{DATA_DIR}/EPAFHM.medi.csv"
+    model = Model::LazarRegression.create training_dataset
+    model.update(:prediction_algorithm => "OpenTox::Algorithm::Regression.weighted_average_with_relevant_fingerprints")
+    compound = Compound.from_smiles "CC(C)(C)CN"
+    prediction = model.predict compound
+    p prediction
+    #assert_equal 13.6, prediction[:value].round(1)
+    #assert_equal 0.83, prediction[:confidence].round(2)
+    #assert_equal 1, prediction[:neighbors].size
+  end
+
+end

data/test/validation.rb

@@ -4,10 +4,11 @@ class ValidationTest < MiniTest::Test
 
   def test_fminer_crossvalidation
     dataset = Dataset.from_csv_file "#{DATA_DIR}/hamster_carcinogenicity.csv"
-    model = Model::LazarFminerClassification.create dataset#, features
+    model = Model::LazarFminerClassification.create dataset
     cv = ClassificationCrossValidation.create model
     p cv.accuracy
     p cv.weighted_accuracy
+    refute_empty cv.validation_ids
     assert cv.accuracy > 0.8
     assert cv.weighted_accuracy > cv.accuracy, "Weighted accuracy (#{cv.weighted_accuracy}) larger than unweighted accuracy(#{cv.accuracy}) "
   end
@@ -31,7 +32,7 @@ class ValidationTest < MiniTest::Test
     p cv.weighted_rmse
     p cv.mae
     p cv.weighted_mae
-    `inkview #{cv.plot}`
+    #`inkview #{cv.plot}`
     assert cv.rmse < 30, "RMSE > 30"
     assert cv.weighted_rmse < cv.rmse, "Weighted RMSE (#{cv.weighted_rmse}) larger than unweighted RMSE(#{cv.rmse}) "
     assert cv.mae < 12

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: lazar
 version: !ruby/object:Gem::Version
-  version: 0.0.6
+  version: 0.0.7
 platform: ruby
 authors:
 - Christoph Helma, Martin Guetlein, Andreas Maunz, Micha Rautenberg, David Vorgrimmler,
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-08-19 00:00:00.000000000 Z
+date: 2015-08-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -122,8 +122,8 @@ files:
 - lib/descriptor.rb
 - lib/error.rb
 - lib/feature.rb
-- lib/lazar-model.rb
 - lib/lazar.rb
+- lib/model.rb
 - lib/neighbor.rb
 - lib/opentox.rb
 - lib/overwrite.rb
@@ -184,6 +184,7 @@ files:
 - test/lazar-fminer.rb
 - test/lazar-long.rb
 - test/lazar-physchem-short.rb
+- test/lazar-regression.rb
 - test/setup.rb
 - test/validation.rb
 homepage: http://github.com/opentox/lazar
@@ -262,5 +263,6 @@ test_files:
 - test/lazar-fminer.rb
 - test/lazar-long.rb
 - test/lazar-physchem-short.rb
+- test/lazar-regression.rb
 - test/setup.rb
 - test/validation.rb