Question

我目前正在弄清楚轮胎宝石（我对elasticsearch和lucene也是新手）并尝试了一些事情。我需要做一些（可能是非平凡的）得分，所以我试着抓住它。我阅读了网上关于评分公式的所有内容，并尝试将我发现的内容与解释的查询相匹配。

如果我正确阅读了这些数字，那么标题为“foo foo foo foo＆＃34;有不同的分数，这肯定不是预期的。我想我在索引期间或之后错过了一个步骤，但我无法理解。

以下是我的代码。我并没有完全按照轮胎DSL的意图，因为我想弄清楚事情 - 事情可能会在以后的某个时间看起来更加疲惫。

require 'tire'
require 'pp'

class Model
  INDEX = 'myindex'
  TYPE = 'company'

  class << self
    def delete_index
      Tire.index(INDEX) { delete }
    end

    def create_mapping
      Tire.index INDEX do
        create mappings: {
          TYPE => {
            properties: {
              title: { type: 'string' }
            }
          }
        }
      end
    end

    def refresh_index
      Tire.index INDEX do
        refresh
      end
    end
  end

  def initialize(attributes = {})
    @attributes = attributes.merge(:_id => object_id) #use oid as id, just for testing
  end

  def _type
    TYPE
  end

  def id
    object_id.to_s #convert to string because tire compares to object_id!
  end

  def index
    item = self
    Tire.index INDEX do
      store item
    end
  end

  def to_indexed_json
    @attributes.to_json
  end

  ENTITIES = [
    new(title: "foo foo foo foo"),
    new(title: "foo"),
    new(title: "bar"),
    new(title: "foo bar"),
    new(title: "xxx"),
    new(title: "foo foo foo foo"),
    new(title: "foo foo"),
    new(title: "foo bar baz")
  ]

  QUERIES = {
    :foo => { query_string: { query: "foo" } },
    :all => { match_all: {} }
  }

  def self.custom_explained_search(q)
    Tire.search(Model::INDEX, :wrapper => Model, :explain => true) do |search|
      search.query do |query|
        query.send :instance_variable_set, :@value, q
      end
    end
  end
end

class Tire::Results::Collection
  def explained
    @response["hits"]["hits"].map do |hit|
      {
        "_id" => hit["_id"],
        "_explanation" => hit["_explanation"],
        "title" => hit["_source"]["title"]
      }
    end
  end
end

Model.delete_index
Model.create_mapping
Model::ENTITIES.each &:index
Model.refresh_index
s = Model.custom_explained_search(Model::QUERIES[:foo])
pp s.results.explained

打印结果如下：

[{"_id"=>"2169251840",
  "_explanation"=>
   {"value"=>0.54932046,
    "description"=>"fieldWeight(_all:foo in 0), product of:",
    "details"=>
     [{"value"=>1.4142135,
       "description"=>"btq, product of:",
       "details"=>
        [{"value"=>1.4142135, "description"=>"tf(phraseFreq=2.0)"},
         {"value"=>1.0, "description"=>"allPayload(...)"}]},
      {"value"=>0.7768564, "description"=>"idf(_all:  foo=4)"},
      {"value"=>0.5, "description"=>"fieldNorm(field=_all, doc=0)"}]},
  "title"=>"foo foo foo foo"},
 {"_id"=>"2169251720",
  "_explanation"=>
   {"value"=>0.54932046,
    "description"=>"fieldWeight(_all:foo in 1), product of:",
    "details"=>
     [{"value"=>0.70710677,
       "description"=>"btq, product of:",
       "details"=>
        [{"value"=>0.70710677, "description"=>"tf(phraseFreq=0.5)"},
         {"value"=>1.0, "description"=>"allPayload(...)"}]},
      {"value"=>0.7768564, "description"=>"idf(_all:  foo=4)"},
      {"value"=>1.0, "description"=>"fieldNorm(field=_all, doc=1)"}]},
  "title"=>"foo"},
 {"_id"=>"2169250520",
  "_explanation"=>
   {"value"=>0.48553526,
    "description"=>"fieldWeight(_all:foo in 2), product of:",
    "details"=>
     [{"value"=>1.0,
       "description"=>"btq, product of:",
       "details"=>
        [{"value"=>1.0, "description"=>"tf(phraseFreq=1.0)"},
         {"value"=>1.0, "description"=>"allPayload(...)"}]},
      {"value"=>0.7768564, "description"=>"idf(_all:  foo=4)"},
      {"value"=>0.625, "description"=>"fieldNorm(field=_all, doc=2)"}]},
  "title"=>"foo foo"},
 {"_id"=>"2169251320",
  "_explanation"=>
   {"value"=>0.44194174,
    "description"=>"fieldWeight(_all:foo in 1), product of:",
    "details"=>
     [{"value"=>0.70710677,
       "description"=>"btq, product of:",
       "details"=>
        [{"value"=>0.70710677, "description"=>"tf(phraseFreq=0.5)"},
         {"value"=>1.0, "description"=>"allPayload(...)"}]},
      {"value"=>1.0, "description"=>"idf(_all:  foo=1)"},
      {"value"=>0.625, "description"=>"fieldNorm(field=_all, doc=1)"}]},
  "title"=>"foo bar"},
 {"_id"=>"2169250380",
  "_explanation"=>
   {"value"=>0.27466023,
    "description"=>"fieldWeight(_all:foo in 3), product of:",
    "details"=>
     [{"value"=>0.70710677,
       "description"=>"btq, product of:",
       "details"=>
        [{"value"=>0.70710677, "description"=>"tf(phraseFreq=0.5)"},
         {"value"=>1.0, "description"=>"allPayload(...)"}]},
      {"value"=>0.7768564, "description"=>"idf(_all:  foo=4)"},
      {"value"=>0.5, "description"=>"fieldNorm(field=_all, doc=3)"}]},
  "title"=>"foo bar baz"},
 {"_id"=>"2169250660",
  "_explanation"=>
   {"value"=>0.2169777,
    "description"=>"fieldWeight(_all:foo in 0), product of:",
    "details"=>
     [{"value"=>1.4142135,
       "description"=>"btq, product of:",
       "details"=>
        [{"value"=>1.4142135, "description"=>"tf(phraseFreq=2.0)"},
         {"value"=>1.0, "description"=>"allPayload(...)"}]},
      {"value"=>0.30685282, "description"=>"idf(_all:  foo=1)"},
      {"value"=>0.5, "description"=>"fieldNorm(field=_all, doc=0)"}]},
  "title"=>"foo foo foo foo"}]

我读错了数字吗？或者滥用轮胎？也许只是错过了一些＆＃34;重新索引整个集合＆＃34;步骤

Answer 1

afaik如果没有定义明确的排序字段，则将默认值排序为（变体）tf * idf（http://en.wikipedia.org/wiki/Tf * idf）。

字面意思：术语频率*逆文档频率。

来自维基百科：

期限频率（字词数）：给定文档中的字词数只是给定字词在该文档中出现的次数

逆文档频率衡量该术语在所有文档中是常见还是罕见。它是通过将文档总数除以包含该术语的文档数得到的，然后取该商的对数

在这种情况下，排序中的“术语频率”组件最有可能导致“foo foo foo foo”在搜索“foo”时得分高于其他文档

此外，关于你在更改id时所看到的效果：我不确定，但我猜它必须在内部由id订购ES存储文档（我不确定那...）

如果是这种情况，那么具有相同排序分数的2个文档将根据id作为决胜局进行排序。您当然可以定义多种排序来更改此行为（例如：sort = sorta + desc，sortb + desc。在这种情况下，sortb用作所有在scoreA上得分相同的文档的决胜局）

为什么两个相同的文件得分不同？

1 个答案: