From 13e7865f386603fb784e62feef2ee2a56c015b45 Mon Sep 17 00:00:00 2001 From: "helma@in-silico.ch" Date: Tue, 14 Aug 2018 12:02:03 +0000 Subject: classification min_sim=0.5, 5 repeated cvs --- lib/crossvalidation.rb | 2 +- lib/model.rb | 2 +- lib/train-test-validation.rb | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/lib/crossvalidation.rb b/lib/crossvalidation.rb index 06a1e2a..e94864a 100644 --- a/lib/crossvalidation.rb +++ b/lib/crossvalidation.rb @@ -103,7 +103,7 @@ module OpenTox # @param [Fixnum] number of folds # @param [Fixnum] number of repeats # @return [OpenTox::Validation::RepeatedCrossValidation] - def self.create model, folds=10, repeats=3 + def self.create model, folds=10, repeats=5 repeated_cross_validation = self.new repeats.times do |n| $logger.debug "Crossvalidation #{n+1} for #{model.name}" diff --git a/lib/model.rb b/lib/model.rb index dce53a9..0ed70f2 100644 --- a/lib/model.rb +++ b/lib/model.rb @@ -80,7 +80,7 @@ module OpenTox } model.algorithms[:similarity] = { :method => "Algorithm::Similarity.tanimoto", - :min => 0.1, + :min => 0.5, } elsif model.class == LazarRegression model.algorithms[:prediction] = { diff --git a/lib/train-test-validation.rb b/lib/train-test-validation.rb index 9a5532d..8231728 100644 --- a/lib/train-test-validation.rb +++ b/lib/train-test-validation.rb @@ -28,7 +28,7 @@ module OpenTox end predictions.select!{|cid,p| p[:value] and p[:measurements]} # hack to avoid mongos file size limit error on large datasets - #predictions.each{|cid,p| p[:neighbors] = []} if model.training_dataset.name.match(/mutagenicity/i) + predictions.each{|cid,p| p[:neighbors] = []} #if model.training_dataset.name.match(/mutagenicity/i) validation = self.new( :model_id => validation_model.id, :test_dataset_id => test_set.id, -- cgit v1.2.3