Merge pull request #65 from MITLibraries/tco54-historical-snapshot-jo…

…urnals

Adds exact journal matches to historical analysis

app/models/metrics/algorithms.rb

@@ -4,15 +4,16 @@
 #
 # Table name: metrics_algorithms
 #
-#  id         :integer          not null, primary key
-#  month      :date
-#  doi        :integer
-#  issn       :integer
-#  isbn       :integer
-#  pmid       :integer
-#  unmatched  :integer
-#  created_at :datetime         not null
-#  updated_at :datetime         not null
+#  id            :integer          not null, primary key
+#  month         :date
+#  doi           :integer
+#  issn          :integer
+#  isbn          :integer
+#  pmid          :integer
+#  unmatched     :integer
+#  created_at    :datetime         not null
+#  updated_at    :datetime         not null
+#  journal_exact :integer
 #
 module Metrics
   # Algorithms aggregates statistics for matches for all SearchEvents
@@ -43,30 +44,68 @@ def generate(month = nil)
                   count_matches(SearchEvent.all.includes(:term))
                 end
       Metrics::Algorithms.create(month:, doi: matches[:doi], issn: matches[:issn], isbn: matches[:isbn],
-                                 pmid: matches[:pmid], unmatched: matches[:unmatched])
+                                 pmid: matches[:pmid], journal_exact: matches[:journal_exact],
+                                 unmatched: matches[:unmatched])
     end
 
-    # Counts matches supplied events
+    # Counts matches for supplied events
     #
-    # @note We currently only have StandardIdentifiers to match. As we add new algorithms, this method will need to
-    #   expand to handle additional match types.
     # @param events [Array of SearchEvents] An array of SearchEvents to check for matches.
     # @return [Hash] A Hash with keys for each known algorithm and the count of matched SearchEvents.
     def count_matches(events)
       matches = Hash.new(0)
-      known_ids = %i[unmatched pmid isbn issn doi]
 
       events.each do |event|
-        ids = StandardIdentifiers.new(event.term.phrase)
+        event_matches(event, matches)
+      end
+
+      matches
+    end
+
+    # Checks for matches for a single event
+    #
+    # @note We currently match StandardIdentifiers and Exact Journals. As we add new algorithms, this method will need
+    #  to expand to handle additional match types.
+    #
+    # @param event [SearchEvent] an individual search event to check for matches
+    # @param matches [Hash] a Hash that keeps track of how many of each algorithm we match
+    # @return does not return anything (the same matches Hash is passed in each loop but not explicitly sent back)
+    def event_matches(event, matches)
+      ids = match_standard_identifiers(event, matches)
+      journal_exact = process_journals(event, matches)
 
-        matches[:unmatched] += 1 if ids.identifiers.blank?
+      matches[:unmatched] += 1 if ids.identifiers.blank? && journal_exact.count.zero?
+    end
+
+    # Checks for StandardIdentifer matches
+    #
+    # @param event [SearchEvent] an individual search event to check for matches
+    # @param matches [Hash] a Hash that keeps track of how many of each algorithm we match
+    # @return [Array] an array of matched StandardIdentifiers
+    def match_standard_identifiers(event, matches)
+      known_ids = %i[unmatched pmid isbn issn doi]
+      ids = StandardIdentifiers.new(event.term.phrase)
 
-        known_ids.each do |id|
-          matches[id] += 1 if ids.identifiers[id].present?
-        end
+      known_ids.each do |id|
+        matches[id] += 1 if ids.identifiers[id].present?
       end
+      ids
+    end
 
-      matches
+    # Checks for Journal matches
+    #
+    # @note we are only checking for exact matches at this time as the partial match algorithm is more noise than signal
+    # @note this detection is not a guarantee of search intent and should not be considered a guarantee that we
+    #   understand the search intent. We have not yet done validation on this algoritm to understand what percentage it
+    #   is useful. This information should be conveyed in any reports that use this data.
+    #
+    # @param event [SearchEvent] an individual search event to check for matches
+    # @param matches [Hash] a Hash that keeps track of how many of each algorithm we match
+    # @return [Array] an array of matched Detector::Journal records
+    def process_journals(event, matches)
+      journal_exact = Detector::Journal.full_term_match(event.term.phrase)
+      matches[:journal_exact] += 1 if journal_exact.count.positive?
+      journal_exact
     end
   end
 end

db/migrate/20240723202204_add_journal_exact_to_metrics_algorithm.rb

@@ -0,0 +1,5 @@
+class AddJournalExactToMetricsAlgorithm < ActiveRecord::Migration[7.1]
+  def change
+    add_column :metrics_algorithms, :journal_exact, :integer
+  end
+end

test/fixtures/search_events.yml

@@ -31,3 +31,10 @@ current_month_doi:
 current_month_isbn:
   term: isbn_9781319145446
   source: test
+current_month_nature_medicine:
+  term: journal_nature_medicine
+  source: test
+old_month_nature_medicine:
+  term: journal_nature_medicine
+  source: test
+  created_at: <%= 1.year.ago %>

test/fixtures/terms.yml

@@ -25,3 +25,6 @@ doi:
 
 isbn_9781319145446:
   phrase: 'Sadava, D. E., D. M. Hillis, et al. Life: The Science of Biology. 11th ed. W. H. Freeman, 2016. ISBN: 9781319145446'
+
+journal_nature_medicine:
+  phrase: 'nature medicine'

test/models/detector/journal_test.rb

@@ -44,5 +44,13 @@ class JournalTest < ActiveSupport::TestCase
       actual = Detector::Journal.partial_term_match('words and stuff Nature medicine, 1999')
       assert actual.count == 2
     end
+
+    test 'mixed titles are downcased when saved' do
+      mixed_case = 'ThIs Is A tItLe'
+      actual = Detector::Journal.create(name: mixed_case)
+      actual.reload
+      refute_equal(mixed_case, actual.name)
+      assert_equal(mixed_case.downcase, actual.name)
+    end
   end
 end

test/models/metrics/algorithms_test.rb

@@ -4,15 +4,16 @@
 #
 # Table name: metrics_algorithms
 #
-#  id         :integer          not null, primary key
-#  month      :date
-#  doi        :integer
-#  issn       :integer
-#  isbn       :integer
-#  pmid       :integer
-#  unmatched  :integer
-#  created_at :datetime         not null
-#  updated_at :datetime         not null
+#  id            :integer          not null, primary key
+#  month         :date
+#  doi           :integer
+#  issn          :integer
+#  isbn          :integer
+#  pmid          :integer
+#  unmatched     :integer
+#  created_at    :datetime         not null
+#  updated_at    :datetime         not null
+#  journal_exact :integer
 #
 require 'test_helper'
 
@@ -38,6 +39,11 @@ class Algorithms < ActiveSupport::TestCase
     assert aggregate.pmid == 1
   end
 
+  test 'journal exact counts are included in monthly aggregation' do
+    aggregate = Metrics::Algorithms.new.generate(DateTime.now)
+    assert aggregate.journal_exact == 1
+  end
+
   test 'unmatched counts are included are included in monthly aggregation' do
     aggregate = Metrics::Algorithms.new.generate(DateTime.now)
     assert aggregate.unmatched == 2
@@ -102,6 +108,11 @@ class Algorithms < ActiveSupport::TestCase
     assert aggregate.pmid == 2
   end
 
+  test 'journal exact counts are included in total aggregation' do
+    aggregate = Metrics::Algorithms.new.generate
+    assert aggregate.journal_exact == 2
+  end
+
   test 'unmatched counts are included are included in total aggregation' do
     aggregate = Metrics::Algorithms.new.generate
     assert aggregate.unmatched == 2
@@ -131,6 +142,11 @@ class Algorithms < ActiveSupport::TestCase
       SearchEvent.create(term: terms(:pmid_38908367), source: 'test')
     end
 
+    journal_exact_count = rand(1...100)
+    journal_exact_count.times do
+      SearchEvent.create(term: terms(:journal_nature_medicine), source: 'test')
+    end
+
     unmatched_expected_count = rand(1...100)
     unmatched_expected_count.times do
       SearchEvent.create(term: terms(:hi), source: 'test')
@@ -142,6 +158,7 @@ class Algorithms < ActiveSupport::TestCase
     assert issn_expected_count == aggregate.issn
     assert isbn_expected_count == aggregate.isbn
     assert pmid_expected_count == aggregate.pmid
+    assert journal_exact_count == aggregate.journal_exact
     assert unmatched_expected_count == aggregate.unmatched
   end
 end