From d3a4c309d48b794f2f60f44bb9a3d94f402cc82f Mon Sep 17 00:00:00 2001 From: Christoph Helma Date: Wed, 16 Sep 2015 13:11:45 +0200 Subject: repeated crossvalidations, improved experiment reports --- lib/dataset.rb | 1 + 1 file changed, 1 insertion(+) (limited to 'lib/dataset.rb') diff --git a/lib/dataset.rb b/lib/dataset.rb index 851fabd..d884716 100644 --- a/lib/dataset.rb +++ b/lib/dataset.rb @@ -47,6 +47,7 @@ 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 + # TODO: data_entries can be empty, poorly reproducible, mongo problem? 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 -- cgit v1.2.3 From 6ac119c32cef094d4f1c2fb5c2daa4e274401f70 Mon Sep 17 00:00:00 2001 From: Christoph Helma Date: Thu, 17 Sep 2015 14:56:25 +0200 Subject: neighbor calculation moved to Compound class --- lib/dataset.rb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib/dataset.rb') diff --git a/lib/dataset.rb b/lib/dataset.rb index d884716..7d889f8 100644 --- a/lib/dataset.rb +++ b/lib/dataset.rb @@ -152,7 +152,7 @@ module OpenTox name = File.basename(file,".*") dataset = self.find_by(:source => source, :name => name) if dataset - $logger.debug "Skipping #{file}, it is already in the database (id: #{dataset.id})." + $logger.debug "Skipping import of #{file}, it is already in the database (id: #{dataset.id})." else $logger.debug "Parsing #{file}." table = CSV.read file, :skip_blanks => true -- cgit v1.2.3 From 33989261450bba279b4e002e5e4ea0475d742abb Mon Sep 17 00:00:00 2001 From: Christoph Helma Date: Fri, 18 Sep 2015 13:01:59 +0200 Subject: fix for empty values --- lib/dataset.rb | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'lib/dataset.rb') diff --git a/lib/dataset.rb b/lib/dataset.rb index 7d889f8..00e2bc3 100644 --- a/lib/dataset.rb +++ b/lib/dataset.rb @@ -203,7 +203,7 @@ module OpenTox feature = NominalFeature.find_or_create_by(metadata) end end - feature_ids << feature.id + feature_ids << feature.id if feature end $logger.debug "Feature values: #{Time.now-time}" @@ -245,7 +245,7 @@ module OpenTox end compound_ids << compound.id - @data_entries << Array.new(table.first.size-1) + @data_entries << Array.new(table.first.size-1) if (table.first.size-1) > 0 vals.each_with_index do |v,j| if v.blank? -- cgit v1.2.3