Class: Linkage::Runner

Inherits:
Object
  • Object
show all
Defined in:
lib/linkage/runner.rb

Overview

Use this class to run a configuration created by Dataset#link_with.

During a record linkage, one or more Comparators generate scores. Each score is recorded by a ScoreRecorder, which uses a ScoreSet to actually save the score. After the scoring is complete, a Matcher combines the scores to create matches. Each match is recorded by a MatchRecorder, which uses a MatchSet to actually save the match information.

So to save scores and matches, we need both a ScoreSet and a MatchSet. To make this easier, a ResultSet can be used to configure both ScoreSets and MatchSets.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(config) ⇒ Runner

Returns a new instance of Runner.

Parameters:

See Also:



18
19
20
 
# File 'lib/linkage/runner.rb', line 18

def initialize(config)
  @config = config
end

Instance Attribute Details

#config ⇒ Object (readonly)

Returns the value of attribute config.



14
15
16
 
# File 'lib/linkage/runner.rb', line 14

def config
  @config
end

Instance Method Details

#execute ⇒ Object 



22
23
24
25
 
# File 'lib/linkage/runner.rb', line 22

def execute
  score_records
  match_records
end

#match_records ⇒ Object 



74
75
76
77
78
79
80
 
# File 'lib/linkage/runner.rb', line 74

def match_records
  matcher = config.matcher
  match_recorder = config.match_recorder(matcher)
  match_recorder.start
  matcher.run
  match_recorder.stop
end

#score_records ⇒ Object 



27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
 
# File 'lib/linkage/runner.rb', line 27

def score_records
  score_recorder = config.score_recorder
  score_recorder.start
  dataset_1 = config.dataset_1
  dataset_2 = config.dataset_2
  simple_comparators = []
  config.comparators.each do |comparator|
    if comparator.type == :simple
      simple_comparators << comparator
    else
      if dataset_2
        comparator.score_datasets(dataset_1, dataset_2)
      else
        comparator.score_dataset(dataset_1)
      end
    end
  end

  # Handle simple comparators
  unless simple_comparators.empty?
    if dataset_2
      # Two datasets
      dataset_1.each do |record_1|
        dataset_2.each do |record_2|
          simple_comparators.each do |comparator|
            comparator.score_and_notify(record_1, record_2)
          end
        end
      end
    else
      # One dataset
      # NOTE: very naive implementation
      records = dataset_1.all
      0.upto(records.length - 2) do |i|
        record_1 = records[i]
        (i + 1).upto(records.length - 1) do |j|
          record_2 = records[j]
          simple_comparators.each do |comparator|
            comparator.score_and_notify(record_1, record_2)
          end
        end
      end
    end
  end
  score_recorder.stop
end