diff options
author | Christoph Helma <helma@in-silico.ch> | 2016-05-08 12:57:10 +0200 |
---|---|---|
committer | Christoph Helma <helma@in-silico.ch> | 2016-05-08 12:57:10 +0200 |
commit | ab652ac85036c5b372e7f1a08cdb75a19db5b19a (patch) | |
tree | 3f2c99604f202e7000d0cf4b947f06ef8218d932 /lib | |
parent | 06fc914653face2c58fd4e6c47161cb03e217582 (diff) |
regression crossvalidation fixed
Diffstat (limited to 'lib')
-rw-r--r-- | lib/compound.rb | 5 | ||||
-rw-r--r-- | lib/leave-one-out-validation.rb | 6 |
2 files changed, 7 insertions, 4 deletions
diff --git a/lib/compound.rb b/lib/compound.rb index 3af6f6c..0a9111b 100644 --- a/lib/compound.rb +++ b/lib/compound.rb @@ -288,7 +288,10 @@ module OpenTox training_dataset.compounds.each do |compound| candidate_fingerprint = compound.fingerprint params[:type] sim = (query_fingerprint & candidate_fingerprint).size/(query_fingerprint | candidate_fingerprint).size.to_f - neighbors << {"_id" => compound.id, "toxicities" => {prediction_feature.id.to_s => {training_dataset_id.to_s => compound.toxicities[prediction_feature.id.to_s][training_dataset_id.to_s]}}, "tanimoto" => sim} if sim >= params[:min_sim] + fid = prediction_feature.id.to_s + did = params[:training_dataset_id].to_s + v = compound.toxicities[prediction_feature.id.to_s] + neighbors << {"_id" => compound.id, "toxicities" => {fid => {did => v[params[:training_dataset_id].to_s]}}, "tanimoto" => sim} if sim >= params[:min_sim] and v end neighbors.sort!{|a,b| b["tanimoto"] <=> a["tanimoto"]} end diff --git a/lib/leave-one-out-validation.rb b/lib/leave-one-out-validation.rb index 2306041..7189617 100644 --- a/lib/leave-one-out-validation.rb +++ b/lib/leave-one-out-validation.rb @@ -3,7 +3,6 @@ module OpenTox class LeaveOneOutValidation field :model_id, type: BSON::ObjectId - field :dataset_id, type: BSON::ObjectId field :nr_instances, type: Integer field :nr_unpredicted, type: Integer field :predictions, type: Hash @@ -13,13 +12,14 @@ module OpenTox $logger.debug "#{model.name}: LOO validation started" t = Time.now model.training_dataset.features.first.nominal? ? klass = ClassificationLeaveOneOutValidation : klass = RegressionLeaveOneOutValidation - loo = klass.new :model_id => model.id, :dataset_id => model.training_dataset_id + loo = klass.new :model_id => model.id predictions = model.predict model.training_dataset.compounds predictions.each{|cid,p| p.delete(:neighbors)} nr_unpredicted = 0 predictions.each do |cid,prediction| if prediction[:value] - prediction[:measured] = Substance.find(cid).toxicities[prediction[:prediction_feature_id].to_s][dataset_id.to_s] + tox = Substance.find(cid).toxicities[prediction[:prediction_feature_id].to_s] + prediction[:measured] = tox[model.training_dataset_id.to_s] if tox else nr_unpredicted += 1 end |