From 2d02fabfafccb164093062a962f392bb7d13647a Mon Sep 17 00:00:00 2001
From: Christoph Helma <helma@in-silico.ch>
Date: Sat, 1 Aug 2015 18:03:09 +0200
Subject: 50 times faster bbrc setup by eliminating @fminer.add_fminer_data

---
 lib/data_entry.rb     | 40 ----------------------------------------
 lib/dataset.rb        | 13 ++++---------
 lib/feature.rb        |  1 -
 lib/opentox-client.rb |  2 +-
 4 files changed, 5 insertions(+), 51 deletions(-)
 delete mode 100644 lib/data_entry.rb

diff --git a/lib/data_entry.rb b/lib/data_entry.rb
deleted file mode 100644
index 4eeb66d..0000000
--- a/lib/data_entry.rb
+++ /dev/null
@@ -1,40 +0,0 @@
-module OpenTox
-
-  class DataEntry
-    field :feature_id, type: BSON::ObjectId
-    field :compound_id, type: BSON::ObjectId
-    # Kludge because csv import removes type information
-    #field :feature_id, type: String
-    #field :compound_id, type: String
-    field :value
-    field :warnings, type: String
-    field :unit, type: String
-    store_in collection: "data_entries"
-    belongs_to :dataset
-    has_one :compound
-    has_one :feature
-
-    # preferred method for the insertion of data entries
-    # @example DataEntry.find_or_create compound,feature,value
-    # @param compound [OpenTox::Compound]
-    # @param feature [OpenTox::Feature]
-    # @param value
-    def self.find_or_create compound, feature, value
-      self.find_or_create_by(
-        :compound_id => compound.id,
-        :feature_id => feature.id,
-        :value => value
-      )
-    end
-
-    # preferred method for accessing values
-    # @example DataEntry[compound,feature]
-    # @param compound [OpenTox::Compound]
-    # @param feature [OpenTox::Feature]
-    # @return value
-    def self.[](compound,feature)
-      self.where(:compound_id => compound.id.to_s, :feature_id => feature.id.to_s).distinct(:value).first
-    end
-
-  end
-end
diff --git a/lib/dataset.rb b/lib/dataset.rb
index 38e195b..45f7119 100644
--- a/lib/dataset.rb
+++ b/lib/dataset.rb
@@ -5,6 +5,10 @@ module OpenTox
 
   class LazarPrediction < Dataset
     field :creator, type: String
+    def value compound
+    end
+    def confidence compound
+    end
   end
 
   class DescriptorDataset < Dataset
@@ -21,7 +25,6 @@ module OpenTox
   class Dataset
     include Mongoid::Document
 
-    attr_accessor :bulk
     attr_writer :data_entries
 
     # associations like has_many, belongs_to deteriorate performance
@@ -31,11 +34,6 @@ module OpenTox
     field :source, type: String
     field :warnings, type: Array, default: []
 
-    def initialize params=nil
-      super params
-      @bulk = []
-    end
-
     def save_all
       dump = Marshal.dump(@data_entries)
       file = Mongo::Grid::File.new(dump, :filename => "#{self.id.to_s}.data_entries")
@@ -344,10 +342,8 @@ module OpenTox
             next
           elsif numeric[j]
             @data_entries[i][j] = v.to_f
-            #dataset.bulk << [cid,feature_ids[j],v.to_f]
           else
             @data_entries[i][j] = v.strip
-            #dataset.bulk << [cid,feature_ids[j],v.strip]
           end
         end
       end
@@ -359,7 +355,6 @@ module OpenTox
       
       $logger.debug "Value parsing: #{Time.now-time} (Compound creation: #{compound_time})"
       time = Time.now
-      #dataset.bulk_write
       save_all
       $logger.debug "Saving: #{Time.now-time}"
 
diff --git a/lib/feature.rb b/lib/feature.rb
index e565875..0801a47 100644
--- a/lib/feature.rb
+++ b/lib/feature.rb
@@ -9,7 +9,6 @@ module OpenTox
     field :supervised, type: Boolean
     field :source, as: :title, type: String
     #belongs_to :dataset
-    #belongs_to :data_entry
   end
 
   class NominalFeature < Feature
diff --git a/lib/opentox-client.rb b/lib/opentox-client.rb
index f296837..7a5c8c0 100644
--- a/lib/opentox-client.rb
+++ b/lib/opentox-client.rb
@@ -10,7 +10,7 @@ require 'mongoid'
 ENV["MONGOID_ENV"] = "development"
 Mongoid.load!("#{ENV['HOME']}/.opentox/config/mongoid.yml")
 
-CLASSES = ["Compound", "Feature", "DataEntry","Dataset"]#, "Validation", "Task", "Investigation"]
+CLASSES = ["Compound", "Feature", "Dataset"]#, "Validation", "Task", "Investigation"]
 #CLASSES = ["Feature", "Dataset", "Validation", "Task", "Investigation"]
 
 # Regular expressions for parsing classification data
-- 
cgit v1.2.3