determinations_comparison 0.0.6 → 0.0.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 15755c7425cabdc1a71feb14e6b1b3832f5f84d1
-  data.tar.gz: 6501200475ed355b8cdbd04fd4fc9f0525ede3d2
+  metadata.gz: 0a0f9ca9f006e31daea83ccdb02443074130871b
+  data.tar.gz: 68658f42da8933ba16e841168918523928d18dd6
 SHA512:
-  metadata.gz: 4671c104f6650f927717a11a23a7027a05803de1ae91393233d68226e644c16339478142d25441f71072147de2056468991d57a5d93a5bfa73220849ca082407
-  data.tar.gz: 97fe968806cd43cc53f35d0d0842d3ca7926a8f736b6c86b6ebc69b00e10f838cac2fe2f2651109f53ee6d85b6bd9d3192fcf8ff8da60d5c52714fe75aa77618
+  metadata.gz: 75bc295c243700be46a4007d4671db6a0f9f9cd47175eadb4841e064a9ecb9411b54bb2da15f7c3c2371a9a4d7dbb0006a56bd21565fbd0b3134d517db4ca874
+  data.tar.gz: 063e2c27011dc96996b4f6ea5eed4e0775eaa035f793d2885e7b22cf99e00eedee80287fc9994e150064f4f617960f961e999cb9dc3ec771c971808f746afe5e

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    determinations_comparison (0.0.5)
+    determinations_comparison (0.0.7)
       htmlentities
       uuidtools
 

data/README.md

@@ -48,10 +48,25 @@ cmp.png_filepath # => location of PNG plot file
 cmp.baseline_filepath # => location of baseline file (copied to output folder)
 cmp.undertest_filepath # => location of undertest file (copied to output folder)
 
+# a summary categorizing worst discrepancy within determination (if any)
+cmp.hashCategory # =>  e.g. {:desc=>'difference with apex_intensity',:per_diff=>5}
+
 ```
 
 ##Special Options
 
+The hashCategory property uses pre-set thresholds of 1% to determine whether a variation is considered a discrepancy.
+However, these thresholds can be over-ridden by passing in an opt parameter like so:
+```ruby
+baseline_file = 'path/to/baseline/file.po'
+undertest_file = 'path/to/undertest/file.json'
+opts = Hash.new
+opts[:hashPropertyThresholds] = {:area=>3,:apex_time=>1,:apex_intensity=>5}
+cmp = DeterminationsComparison::Comparison.new baseline_filepath , undertest_filepath, opts}
+
+cmp.hashCategory # this will use thresholds described by hashPropertyThresholds parameter above
+```
+
 If you have ComputeDeterminations.py and/or CppLogReader.py libraries installed (see prerequisites), then Plot charts and pertinent peak-peaking information will be included in the HTML report.
 
 However, these must be within your system path.  If they are not, you can specify the locations using the optional opts parameter like so:
@@ -76,6 +91,7 @@ opts[:folderpath_with_log] = '/path/to/folder/containing/logfile'
 
 cmp = DeterminationsComparison::Comparison.new baseline_filepath , undertest_filepath, opts}
 ```
+
 ##Key Mapping File (key_mapping.yaml)
 
 Assumption is made that all keys within .po files follow lower camel-case naming convention (e.g. myKey) and that keys within .json (compound) files follow snake-case naming convention and therefore a simple conversion from one key name is another is possible.  However, there are cases where the naming conventions are not followed.

data/lib/determinations_comparison.rb

@@ -14,13 +14,15 @@ LIB_FOLDER = File.dirname(__FILE__)
 module DeterminationsComparison
 
   class Comparison
-    attr_accessor :hashStd, :hashTgt, :html_filepath, :png_filepath, :baseline_filepath, :undertest_filepath
+    attr_accessor :hashStd, :hashTgt, :html_filepath, :png_filepath, :baseline_filepath, :undertest_filepath, :hashCategory
 
     def initialize(filepath_baseline,filepath_undertest,opts={})
 
       @filepath_comparedeterminations = opts[:filepath_comparedeterminations]
       @filepath_cpplogreader =          opts[:filepath_cpplogreader]
 
+      hashPropertyThresholds = opts[:hashPropertyThresholds] || {:area=>1,:apex_time=>1,:apex_intensity=>1}
+
       @folderpath_with_log = opts[:folderpath_with_log] || File.dirname(filepath_baseline)
 
       @filepath_baseline_origin = filepath_baseline
@@ -36,8 +38,174 @@ module DeterminationsComparison
       differences 'Compound', hashCompoundUnderTest, hashCompoundBaseLine, @hashDiffs
       differences_extrapolated
 
+      @hashCategory = categorize hashPropertyThresholds
+
+    end
+
+    def to_html(folderpath_output)
+
+      FileUtils.mkdir_p folderpath_output
+
+      html_filepath = File.join      folderpath_output, "#{@uuid}.html"
+      png_filepath = File.join       folderpath_output, "#{@uuid}.png"
+      baseline_filepath = File.join  folderpath_output, "#{@uuid}_baseline.json"
+      undertest_filepath = File.join folderpath_output, "#{@uuid}_undertest.json"
+
+      @plotter = Exe_CompareDeterminations.new @filepath_baseline_origin, @filepath_undertest_origin, @filepath_comparedeterminations
+
+      # these are necessary for cpplogreader
+      @sample_index = hashCompoundBaseLine['Sample_Index']
+      @analyte_name = hashCompoundBaseLine['Analyte']
+
+
+      str = ""
+      arr = Array.new
+
+      begin
+        coder = HTMLEntities.new
+        retcodePNG,rundetailsPNG = @plotter.generate_png png_filepath
+
+        FileUtils.copy_file @filepath_baseline_origin, baseline_filepath
+        FileUtils.copy_file @filepath_undertest_origin, undertest_filepath
+
+        str += "<p>baseline file: <a href=#{File.basename(baseline_filepath)}>#{File.basename(@filepath_baseline_origin)}</a></p>"
+        str += "<p>undertest file: <a href=#{File.basename(undertest_filepath)}>#{File.basename(@filepath_undertest_origin)}</a></p>"
+
+        if retcodePNG
+          str += "<p><p><p><img src='#{File.basename(png_filepath)}' alt='chromatogram' height='500' width='800' align='top'></p>"
+        end
+
+        @hashDiffs.each_pair do |k,v|
+
+          chrom_type = k
+
+          v.each_pair do |k,v|
+            if k == 'peak'
+              v.each_pair do |k,v|
+                arr << property_diff_to_hash(chrom_type,k,v)
+              end
+            else
+              unless k == 'peak_picked'
+                arr << property_diff_to_hash(chrom_type,k,v)
+              end
+            end
+
+          end
+
+          peak_picked = "unknown"
+          arrPP = v.select { |h| h['peak_picked'] }
+          unless arrPP.empty?
+            peak_picked = "#{arrPP.first[0]} #{arrPP.first[1]}"
+          end
+
+          str += "<p><p>"
+          str += "<p><b>#{k}</b> - #{peak_picked}</p>"
+
+          ht = HTML_Table_of_Peak_Picking_Log.new(@folderpath_with_log,@sample_index,@analyte_name,k)
+          str_pp = ht.render
+          unless str_pp.nil?
+            str += "<p><p>"
+            str += str_pp
+            str += "</p>"
+          end
+
+        end
+
+        ht = HTML_Table_of_Property_Differences.new(arr)
+        str_p = ht.render
+        unless str_p.nil?
+          str += "<p><p>"
+          str += str_p
+          str += "</p>"
+        end
+
+        File.open(html_filepath, "w") do |f|
+          f.write(str)
+        end
+
+        retcode = true
+
+      rescue Exception => e
+        retcode = false
+        $log_detercomp.error "unable to render html"
+      end
+
+      @html_filepath = html_filepath
+      @png_filepath = png_filepath
+      @baseline_filepath = baseline_filepath
+      @undertest_filepath = undertest_filepath
+
+
+      return retcode
+
+    end
+
+    def as_hash
+      @hashDiffs
+    end
+
+    private
+
+    def categorize(hashPropertyThresholds)
+
+      hashCategory = Hash.new
+
+      @hashDiffs.each_pair do |chrom,hashChrom|
+
+        # peak picked by baseline and not undertest?
+        if hashChrom['peak_picked'] == 'by baseline but not by undertest'
+          hashCategory[:desc] = "peak picked #{hashChrom['peak_picked']}"
+        end
+
+        break unless hashCategory.empty?
+
+        if hashChrom['peak_picked'] == 'by baseline (simpsons rule) but not by undertest'
+          hashCategory[:desc] = "peak picked #{hashChrom['peak_picked']}"
+        end
+
+        break unless hashCategory.empty?
+
+        # area within threshold?
+        per_diff = hashChrom['peak']['area'][:percent_diff]
+        threshold = hashPropertyThresholds[:area]
+        if per_diff > threshold
+          hashCategory[:desc] = 'difference in area'
+          hashCategory[:per_diff] = per_diff
+        end
+
+        break unless hashCategory.empty?
+
+        # apex time within threshold
+        per_diff = hashChrom['peak']['apex_time'][:percent_diff]
+        threshold = hashPropertyThresholds[:apex_time]
+        if per_diff > threshold
+          hashCategory[:desc] = 'difference in apex_time'
+          hashCategory[:per_diff] = per_diff
+        end
+
+        break unless hashCategory.empty?
+
+        # apex intensity within threshould
+        per_diff = hashChrom['peak']['apex_intensity'][:percent_diff]
+        threshold = hashPropertyThresholds[:apex_intensity]
+        if per_diff > threshold
+          hashCategory[:desc] = 'difference in apex_intensity'
+          hashCategory[:per_diff] = per_diff
+        end
+
+        break unless hashCategory.empty?
+
+      end
+
+      if hashCategory.empty?
+        hashCategory[:desc] = 'match within thresholds'
+      end
+
+      return hashCategory
+
     end
 
+
     def differences(item, hashUnderTest, hashBaseLine, hashDifferences)
 
       hashUnderTest.each_pair do |k_undertest,v_undertest|
@@ -59,7 +227,7 @@ module DeterminationsComparison
               @hashChromUnderTest = hashChromUnderTest
 
               chromtype_key_undertest =
-                filetype_undertest == 'json' ? 'classifier' : 'SampleType'
+                  filetype_undertest == 'json' ? 'classifier' : 'SampleType'
 
               chromtype_undertest = hashChromUnderTest[chromtype_key_undertest]
 
@@ -82,12 +250,12 @@ module DeterminationsComparison
             $log_detercomp.info "'#{k_undertest}' - comparing traces not supported yet"
           elsif(k_undertest == 'Peaks' || k_undertest == 'peak')
 
-              @hashPeakUnderTest = v_undertest
-              @hashPeakBaseLine = v_baseline
+            @hashPeakUnderTest = v_undertest
+            @hashPeakBaseLine = v_baseline
 
-              hashDiff_Peak = Hash.new
-              hashDifferences['peak'] = hashDiff_Peak
-              differences 'Peak', @hashPeakUnderTest, @hashPeakBaseLine, hashDiff_Peak
+            hashDiff_Peak = Hash.new
+            hashDifferences['peak'] = hashDiff_Peak
+            differences 'Peak', @hashPeakUnderTest, @hashPeakBaseLine, hashDiff_Peak
 
           elsif v_undertest.respond_to? :each
             $log_detercomp.info "'#{k_undertest}' - comparison not supported"
@@ -111,8 +279,8 @@ module DeterminationsComparison
         end
 
       end
-      
-      
+
+
     end
 
     def differences_extrapolated
@@ -120,13 +288,13 @@ module DeterminationsComparison
       @hashDiffs.each_pair do |k,v|
 
         boolPeakPickedByBaseline =
-          v['peak']['area'][:baseline] == 0 ? false:true
+            v['peak']['area'][:baseline] == 0 ? false:true
 
         boolPeakPickedByUnderTest =
-          v['peak']['area'][:undertest] == 0 ? false:true
+            v['peak']['area'][:undertest] == 0 ? false:true
 
         boolSimpsonsRuleByBaseLine =
-          v['peak']['nls_amp'][:baseline] == 0
+            v['peak']['nls_amp'][:baseline] == 0
 
         if boolPeakPickedByBaseline && !(boolPeakPickedByUnderTest)
 
@@ -153,107 +321,9 @@ module DeterminationsComparison
 
     end
 
-    def to_html(folderpath_output)
-
-      FileUtils.mkdir_p folderpath_output
-
-      html_filepath = File.join      folderpath_output, "#{@uuid}.html"
-      png_filepath = File.join       folderpath_output, "#{@uuid}.png"
-      baseline_filepath = File.join  folderpath_output, "#{@uuid}_baseline.json"
-      undertest_filepath = File.join folderpath_output, "#{@uuid}_undertest.json"
-
-      @plotter = Exe_CompareDeterminations.new @filepath_baseline_origin, @filepath_undertest_origin, @filepath_comparedeterminations
-
-      # these are necessary for cpplogreader
-      @sample_index = hashCompoundBaseLine['Sample_Index']
-      @analyte_name = hashCompoundBaseLine['Analyte']
-
-
-      str = ""
-      arr = Array.new
-
-      begin
-        coder = HTMLEntities.new
-        retcodePNG,rundetailsPNG = @plotter.generate_png png_filepath
-
-        FileUtils.copy_file @filepath_baseline_origin, baseline_filepath
-        FileUtils.copy_file @filepath_undertest_origin, undertest_filepath
-
-        str += "<p>baseline file: <a href=#{File.basename(baseline_filepath)}>#{File.basename(@filepath_baseline_origin)}</a></p>"
-        str += "<p>undertest file: <a href=#{File.basename(undertest_filepath)}>#{File.basename(@filepath_undertest_origin)}</a></p>"
-
-        if retcodePNG
-          str += "<p><p><p><img src='#{File.basename(png_filepath)}' alt='chromatogram' height='500' width='800' align='top'></p>"
-        end
-
-        @hashDiffs.each_pair do |k,v|
-
-          chrom_type = k
-
-          v.each_pair do |k,v|
-            if k == 'peak'
-              v.each_pair do |k,v|
-                arr << property_diff_to_hash(chrom_type,k,v)
-              end
-            else
-              unless k == 'peak_picked'
-                arr << property_diff_to_hash(chrom_type,k,v)
-              end
-            end
-
-          end
-
-          peak_picked = "unknown"
-          arrPP = v.select { |h| h['peak_picked'] }
-          unless arrPP.empty?
-            peak_picked = "#{arrPP.first[0]} #{arrPP.first[1]}"
-          end
-
-          str += "<p><p>"
-          str += "<p><b>#{k}</b> - #{peak_picked}</p>"
-
-          ht = HTML_Table_of_Peak_Picking_Log.new(@folderpath_with_log,@sample_index,@analyte_name,k)
-          str_pp = ht.render
-          unless str_pp.nil?
-            str += "<p><p>"
-            str += str_pp
-            str += "</p>"
-          end
-
-        end
-
-        ht = HTML_Table_of_Property_Differences.new(arr)
-        str_p = ht.render
-        unless str_p.nil?
-          str += "<p><p>"
-          str += str_p
-          str += "</p>"
-        end
-
-        File.open(html_filepath, "w") do |f|
-          f.write(str)
-        end
-
-        retcode = true
-
-      rescue Exception => e
-        retcode = false
-        $log_detercomp.error "unable to render html"
-      end
-
-      @html_filepath = html_filepath
-      @png_filepath = png_filepath
-      @baseline_filepath = baseline_filepath
-      @undertest_filepath = undertest_filepath
-
-
-      return retcode
-
-    end
-
     def get_baseline_and_undertest_values(item, hashParent, opts)
-      
-      k_baseline = opts[:k_baseline]      
+
+      k_baseline = opts[:k_baseline]
       k_undertest = opts[:k_undertest]
       k_generic = opts[:k_generic]
 
@@ -272,37 +342,37 @@ module DeterminationsComparison
       end
 
       return val
-      
-      
+
+
     end
-    
+
     def get_corresponding_key_value_from_other_file(file_type_to_get_key_value_for, item, unknown_hashParent, k_known)
 
       # guess at name of corresponding baseline key based on convention (i.e. convert snakecase to camelcase or vice-versa)
-          if file_type_to_get_key_value_for == 'baseline'
-            naming_convention_of_unknown = naming_convention_baseline
-            naming_convention_of_known = naming_convention_undertest
-            #naming_convention = naming_convention_baseline
-            keytype_unknown = "#{filetype_baseline}_key"
-            keytype_known = "#{filetype_undertest}_key"
+      if file_type_to_get_key_value_for == 'baseline'
+        naming_convention_of_unknown = naming_convention_baseline
+        naming_convention_of_known = naming_convention_undertest
+        #naming_convention = naming_convention_baseline
+        keytype_unknown = "#{filetype_baseline}_key"
+        keytype_known = "#{filetype_undertest}_key"
 
-          else
-            naming_convention_of_unknown = naming_convention_undertest
-            naming_convention_of_known = naming_convention_baseline
+      else
+        naming_convention_of_unknown = naming_convention_undertest
+        naming_convention_of_known = naming_convention_baseline
 
-            #naming_convention = naming_convention_undertest
-            keytype_unknown = "#{filetype_undertest}_key"
-            keytype_known = "#{filetype_baseline}_key"
+        #naming_convention = naming_convention_undertest
+        keytype_unknown = "#{filetype_undertest}_key"
+        keytype_known = "#{filetype_baseline}_key"
 
-          end
+      end
 
       #convert known key to naming convention used by unknown file
       k_unknown =
-        if naming_convention_of_unknown == 'snakecase'
-          k_known.to_snakecase
-        else
-          k_known.to_camelcase_lower
-        end
+          if naming_convention_of_unknown == 'snakecase'
+            k_known.to_snakecase
+          else
+            k_known.to_camelcase_lower
+          end
 
       if unknown_hashParent.has_key? k_unknown
         v_unknown = unknown_hashParent[k_unknown]
@@ -362,9 +432,9 @@ module DeterminationsComparison
         chg = diff / a.to_f
         calc = "#{b} - #{a} / #{a}"
       else a.to_f == 0
-        diff = a.to_f - b.to_f
-        chg = diff / b.to_f
-        calc = "#{a} - #{b} / #{b}"
+      diff = a.to_f - b.to_f
+      chg = diff / b.to_f
+      calc = "#{a} - #{b} / #{b}"
       end
 
       diff = (chg * 100.0).round(2)
@@ -402,12 +472,6 @@ module DeterminationsComparison
 
     end
 
-    def as_hash
-      @hashDiffs
-    end
-
-    private
-
     def generic_key(key)
 
       unless key.downcase == key

data/lib/determinations_comparison/version.rb

@@ -1,3 +1,3 @@
 module DeterminationsComparison
-  VERSION = "0.0.6"
+  VERSION = "0.0.7"
 end

data/spec/determinations_comparison_spec.rb

@@ -29,6 +29,12 @@ describe 'determinations_comparison' do
     expect(hash.size).to eq(2)
   end
 
+  it 'should categorize determination' do
+    comparison = DeterminationsComparison::Comparison.new( baseline_file, undertest_file, {:folderpath_output=>folderpath_output})
+
+    expect(comparison.hashCategory[:desc]).to eq('peak picked by baseline but not by undertest')
+  end
+
   it 'should show differences in html table and peak plots' do
     comparison = DeterminationsComparison::Comparison.new( baseline_file, undertest_file)
 

data/spec/html_table_of_property_differences_spec.rb

@@ -18,7 +18,7 @@ describe 'generating html table of differences' do
   end
 
   after :each do
-   # FileUtils.remove file
+    FileUtils.remove file
   end
 
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: determinations_comparison
 version: !ruby/object:Gem::Version
-  version: 0.0.6
+  version: 0.0.7
 platform: ruby
 authors:
 - Shawn Hooper
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-07-05 00:00:00.000000000 Z
+date: 2013-07-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler