Merge pull request #49 from MITLibraries/tco17-historical-snapshots-a…

…ggregations

Tco17 historical snapshots aggregations

app/models/metrics/algorithms.rb

@@ -0,0 +1,72 @@
+# frozen_string_literal: true
+
+# == Schema Information
+#
+# 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
+#
+module Metrics
+  # Algorithms aggregates statistics for matches for all SearchEvents
+  class Algorithms < ApplicationRecord
+    self.table_name = 'metrics_algorithms'
+
+    # generate metrics data about SearchEvents matches
+    #
+    # @note This is expected to only be run once per month per type of aggregation (once with no month supplied, once
+    #   with a month supplied), ideally at the beginning of the following month to ensure as
+    #   accurate as possible statistics. Running further from the month in question will work, but matches will use the
+    #   current versions of all algorithms which may not match the algorithm in place during the month the SearchEvent
+    #   occurred.
+    # @note We don't currently prevent this running more than once per month per type of aggregation.
+    # @param month [DateTime] A DateTime object within the `month` to be generated. Defaults to nil will runs is how
+    #   total algorithm statistics are created.
+    # @example
+    #   # Generate metrics for all SearchEvents
+    #   Metrics::Algorithms.new.generate
+    #
+    #   # Generate metrics for all SearchEvents last month
+    #   Metrics::Algorithms.new.generate(1.month.ago)
+    # @return [Metrics::Algorithms] The created Metrics::Algorithms object.
+    def generate(month = nil)
+      matches = if month.present?
+                  count_matches(SearchEvent.single_month(month).includes(:term))
+                else
+                  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])
+    end
+
+    # Counts matches 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)
+
+        matches[:unmatched] += 1 if ids.identifiers.blank?
+
+        known_ids.each do |id|
+          matches[id] += 1 if ids.identifiers[id].present?
+        end
+      end
+
+      matches
+    end
+  end
+end

app/models/search_event.rb

@@ -10,8 +10,16 @@
 #  created_at :datetime         not null
 #  updated_at :datetime         not null
 #
+
+# SearchEvent represents an instance of a logged search Term
 class SearchEvent < ApplicationRecord
   belongs_to :term
 
   validates :source, presence: true
+
+  # :single_month filters to requested month
+  #
+  #   @param month [DateTime] A DateTime object within the `month` to be filtered.
+  #   @return [Array<SearchEvent>] All SearchEvents for the supplied `month`.
+  scope :single_month, ->(month) { where(created_at: month.beginning_of_month..month.end_of_month) }
 end

app/models/standard_identifiers.rb

@@ -41,7 +41,7 @@ def term_patterns
   def strip_invalid_issns
     return unless @identifiers[:issn]
 
-    @identifiers[:issn] = nil unless validate_issn(@identifiers[:issn])
+    @identifiers.delete(:issn) unless validate_issn(@identifiers[:issn])
   end
 
   # validate_issn is only called when the regex for an ISSN has indicated an ISSN

config/environments/development.rb

@@ -1,4 +1,4 @@
-require "active_support/core_ext/integer/time"
+require 'active_support/core_ext/integer/time'
 
 Rails.application.configure do
   # Settings specified here will take precedence over those in config/application.rb.
@@ -19,13 +19,13 @@
 
   # Enable/disable caching. By default caching is disabled.
   # Run rails dev:cache to toggle caching.
-  if Rails.root.join("tmp/caching-dev.txt").exist?
+  if Rails.root.join('tmp/caching-dev.txt').exist?
     config.action_controller.perform_caching = true
     config.action_controller.enable_fragment_cache_logging = true
 
     config.cache_store = :memory_store
     config.public_file_server.headers = {
-      "Cache-Control" => "public, max-age=#{2.days.to_i}"
+      'Cache-Control' => "public, max-age=#{2.days.to_i}"
     }
   else
     config.action_controller.perform_caching = false
@@ -73,4 +73,8 @@
 
   # Raise error when a before_action's only/except options reference missing actions
   config.action_controller.raise_on_missing_callback_actions = true
+
+  # Local logging overrides
+  config.logger = Logger.new(STDOUT)
+  config.log_level = :debug
 end

db/migrate/20240621132136_create_metrics_algorithms.rb

@@ -0,0 +1,13 @@
+class CreateMetricsAlgorithms < ActiveRecord::Migration[7.1]
+  def change
+    create_table :metrics_algorithms do |t|
+      t.date :month
+      t.integer :doi
+      t.integer :issn
+      t.integer :isbn
+      t.integer :pmid
+      t.integer :unmatched
+      t.timestamps
+    end
+  end
+end

test/fixtures/search_events.yml

@@ -15,3 +15,19 @@ timdex_cool:
 bento_hi:
   term: hi
   source: bento
+current_month_pmid:
+  term: pmid_38908367
+  source: test
+old_month_pmid:
+  term: pmid_38908367
+  source: test
+  created_at: <%= 1.year.ago %>
+current_month_issn:
+  term: issn_1075_8623
+  source: test
+current_month_doi:
+  term: doi
+  source: test
+current_month_isbn:
+  term: isbn_9781319145446
+  source: test

test/fixtures/terms.yml

@@ -13,3 +13,15 @@ cool:
 
 hi:
   phrase: hello world
+
+pmid_38908367:
+  phrase: 'TERT activation targets DNA methylation and multiple aging hallmarks. Shim HS, et al. Cell. 2024. PMID: 38908367'
+
+issn_1075_8623:
+  phrase: 1075-8623
+
+doi:
+  phrase: '10.1016/j.physio.2010.12.004'
+
+isbn_9781319145446:
+  phrase: 'Sadava, D. E., D. M. Hillis, et al. Life: The Science of Biology. 11th ed. W. H. Freeman, 2016. ISBN: 9781319145446'

test/models/metrics/algorithms_test.rb

@@ -0,0 +1,147 @@
+# frozen_string_literal: true
+
+# == Schema Information
+#
+# 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
+#
+require 'test_helper'
+
+class Algorithms < ActiveSupport::TestCase
+  # Monthlies
+  test 'dois counts are included in monthly aggregation' do
+    aggregate = Metrics::Algorithms.new.generate(DateTime.now)
+    assert aggregate.doi == 1
+  end
+
+  test 'issns counts are included in monthly aggregation' do
+    aggregate = Metrics::Algorithms.new.generate(DateTime.now)
+    assert aggregate.issn == 1
+  end
+
+  test 'isbns counts are included in monthly aggregation' do
+    aggregate = Metrics::Algorithms.new.generate(DateTime.now)
+    assert aggregate.isbn == 1
+  end
+
+  test 'pmids counts are included in monthly aggregation' do
+    aggregate = Metrics::Algorithms.new.generate(DateTime.now)
+    assert aggregate.pmid == 1
+  end
+
+  test 'unmatched counts are included are included in monthly aggregation' do
+    aggregate = Metrics::Algorithms.new.generate(DateTime.now)
+    assert aggregate.unmatched == 2
+  end
+
+  test 'creating lots of searchevents leads to correct data for monthly' do
+    # drop all searchevents to make math easier and minimize fragility over time as more fixtures are created
+    SearchEvent.delete_all
+
+    doi_expected_count = rand(1...100)
+    doi_expected_count.times do
+      SearchEvent.create(term: terms(:doi), source: 'test')
+    end
+
+    issn_expected_count = rand(1...100)
+    issn_expected_count.times do
+      SearchEvent.create(term: terms(:issn_1075_8623), source: 'test')
+    end
+
+    isbn_expected_count = rand(1...100)
+    isbn_expected_count.times do
+      SearchEvent.create(term: terms(:isbn_9781319145446), source: 'test')
+    end
+
+    pmid_expected_count = rand(1...100)
+    pmid_expected_count.times do
+      SearchEvent.create(term: terms(:pmid_38908367), source: 'test')
+    end
+
+    unmatched_expected_count = rand(1...100)
+    unmatched_expected_count.times do
+      SearchEvent.create(term: terms(:hi), source: 'test')
+    end
+
+    aggregate = Metrics::Algorithms.new.generate(DateTime.now)
+
+    assert doi_expected_count == aggregate.doi
+    assert issn_expected_count == aggregate.issn
+    assert isbn_expected_count == aggregate.isbn
+    assert pmid_expected_count == aggregate.pmid
+    assert unmatched_expected_count == aggregate.unmatched
+  end
+
+  # Total
+  test 'dois counts are included in total aggregation' do
+    aggregate = Metrics::Algorithms.new.generate
+    assert aggregate.doi == 1
+  end
+
+  test 'issns counts are included in total aggregation' do
+    aggregate = Metrics::Algorithms.new.generate
+    assert aggregate.issn == 1
+  end
+
+  test 'isbns counts are included in total aggregation' do
+    aggregate = Metrics::Algorithms.new.generate
+    assert aggregate.isbn == 1
+  end
+
+  test 'pmids counts are included in total aggregation' do
+    aggregate = Metrics::Algorithms.new.generate
+    assert aggregate.pmid == 2
+  end
+
+  test 'unmatched counts are included are included in total aggregation' do
+    aggregate = Metrics::Algorithms.new.generate
+    assert aggregate.unmatched == 2
+  end
+
+  test 'creating lots of searchevents leads to correct data for total' do
+    # drop all searchevents to make math easier and minimize fragility over time as more fixtures are created
+    SearchEvent.delete_all
+
+    doi_expected_count = rand(1...100)
+    doi_expected_count.times do
+      SearchEvent.create(term: terms(:doi), source: 'test')
+    end
+
+    issn_expected_count = rand(1...100)
+    issn_expected_count.times do
+      SearchEvent.create(term: terms(:issn_1075_8623), source: 'test')
+    end
+
+    isbn_expected_count = rand(1...100)
+    isbn_expected_count.times do
+      SearchEvent.create(term: terms(:isbn_9781319145446), source: 'test')
+    end
+
+    pmid_expected_count = rand(1...100)
+    pmid_expected_count.times do
+      SearchEvent.create(term: terms(:pmid_38908367), source: 'test')
+    end
+
+    unmatched_expected_count = rand(1...100)
+    unmatched_expected_count.times do
+      SearchEvent.create(term: terms(:hi), source: 'test')
+    end
+
+    aggregate = Metrics::Algorithms.new.generate
+
+    assert doi_expected_count == aggregate.doi
+    assert issn_expected_count == aggregate.issn
+    assert isbn_expected_count == aggregate.isbn
+    assert pmid_expected_count == aggregate.pmid
+    assert unmatched_expected_count == aggregate.unmatched
+  end
+end

test/models/search_event_test.rb

@@ -28,4 +28,14 @@ class SearchEventTest < ActiveSupport::TestCase
     s.source = nil
     refute(s.valid?)
   end
+
+  test 'monthly scope returns requested month of SearchEvents' do
+    assert SearchEvent.all.include?(search_events(:current_month_pmid))
+    assert SearchEvent.single_month(Time.now).include?(search_events(:current_month_pmid))
+  end
+
+  test 'monthly scope does not return SearchEvents outside the requested month' do
+    assert SearchEvent.all.include?(search_events(:old_month_pmid))
+    refute SearchEvent.single_month(Time.now).include?(search_events(:old_month_pmid))
+  end
 end

test/test_helper.rb

@@ -24,6 +24,14 @@ class TestCase
     # Run tests in parallel with specified workers
     parallelize(workers: :number_of_processors)
 
+    parallelize_setup do |worker|
+      SimpleCov.command_name "#{SimpleCov.command_name}-#{worker}"
+    end
+
+    parallelize_teardown do |worker|
+      SimpleCov.result
+    end
+
     # Setup all fixtures in test/fixtures/*.yml for all tests in alphabetical order.
     fixtures :all