From 5a3be4190688bc8240327930b3e953b09ecc9d9e Mon Sep 17 00:00:00 2001
From: gebele <gebele@in-silico.ch>
Date: Tue, 28 May 2019 14:25:52 +0000
Subject: before clean up

---
 batch.rb | 101 ---------------------------------------------------------------
 1 file changed, 101 deletions(-)
 delete mode 100644 batch.rb

(limited to 'batch.rb')

diff --git a/batch.rb b/batch.rb
deleted file mode 100644
index 2e72396..0000000
--- a/batch.rb
+++ /dev/null
@@ -1,101 +0,0 @@
-require 'csv'
-require 'tempfile'
-
-module OpenTox
-
-  class Batch
-
-    include OpenTox
-    include Mongoid::Document
-    include Mongoid::Timestamps
-    store_in collection: "batch"
-    field :name,  type: String
-    field :source,  type: String
-    field :identifiers, type: Array
-    field :ids, type: Array
-    field :compounds, type: Array
-    field :warnings, type: Array, default: []
-
-    def self.from_csv_file file
-      source = file
-      name = File.basename(file,".*")
-      batch = self.find_by(:source => source, :name => name)
-      if batch
-        $logger.debug "Skipping import of #{file}, it is already in the database (id: #{batch.id})."
-      else
-        $logger.debug "Parsing #{file}."
-        table = CSV.read file, :skip_blanks => true, :encoding => 'windows-1251:utf-8'
-        batch = self.new(:source => source, :name => name, :identifiers => [], :ids => [], :compounds => [])
-
-        # original IDs
-        if table[0][0] =~ /ID/i
-          @original_ids = table.collect{|row| row.shift}
-          @original_ids.shift
-        end
-        
-        # features
-        feature_names = table.shift.collect{|f| f.strip}
-        warnings << "Duplicated features in table header." unless feature_names.size == feature_names.uniq.size
-        compound_format = feature_names.shift.strip
-        bad_request_error "#{compound_format} is not a supported compound format. Accepted formats: SMILES, InChI." unless compound_format =~ /SMILES|InChI/i
-        numeric = []
-        features = []
-        # guess feature types
-        feature_names.each_with_index do |f,i|
-          metadata = {:name => f}
-          values = table.collect{|row| val=row[i+1].to_s.strip; val.blank? ? nil : val }.uniq.compact
-          types = values.collect{|v| v.numeric? ? true : false}.uniq
-          feature = nil
-          if values.size == 0 # empty feature
-          elsif  values.size > 5 and types.size == 1 and types.first == true # 5 max classes
-            numeric[i] = true
-            feature = NumericFeature.find_or_create_by(metadata)
-          else
-            metadata["accept_values"] = values
-            numeric[i] = false
-            feature = NominalFeature.find_or_create_by(metadata)
-          end
-          features << feature if feature
-        end
-        
-        table.each_with_index do |vals,i|
-          identifier = vals.shift.strip.gsub(/^'|'$/,"")
-          begin
-            case compound_format
-            when /SMILES/i
-              compound = OpenTox::Compound.from_smiles(identifier)
-            when /InChI/i
-              compound = OpenTox::Compound.from_inchi(identifier)
-            end
-          rescue 
-            compound = nil
-          end
-          # collect only for present compounds
-          unless compound.nil?
-            batch.identifiers << identifier
-            batch.compounds << compound.id
-            batch.ids << @original_ids[i] if @original_ids
-          else
-            batch.warnings << "Cannot parse #{compound_format} compound '#{identifier}' at line #{i+2} of #{source}."
-          end
-        end
-        batch.compounds.duplicates.each do |duplicate|
-          $logger.debug "Duplicates found in #{name}."
-          dup = Compound.find duplicate
-          positions = []
-          batch.compounds.each_with_index do |co,i|
-            c = Compound.find co
-            if !c.blank? and c.inchi and c.inchi == dup.inchi
-              positions << i+1
-            end
-          end
-          batch.warnings << "Duplicate compound at ID #{positions.join(' and ')}."
-        end
-        batch.save
-      end
-      batch
-    end
-
-  end
-
-end
-- 
cgit v1.2.3