Elasticsearch聚合的作用范围

测试数据

index 结构

PUT /employees/
{
  "mappings" : {
      "properties" : {
        "age" : {
          "type" : "integer"
        },
        "gender" : {
          "type" : "keyword"
        },
        "job" : {
          "type" : "text",
          "fields" : {
            "keyword" : {
              "type" : "keyword",
              "ignore_above" : 50
            }
          }
        },
        "name" : {
          "type" : "keyword"
        },
        "salary" : {
          "type" : "integer"
        }
      }
    }
}

插入20条数据

PUT /employees/_bulk
{ "index" : {  "_id" : "1" } }
{ "name" : "Emma","age":32,"job":"Product Manager","gender":"female","salary":35000 }
{ "index" : {  "_id" : "2" } }
{ "name" : "Underwood","age":41,"job":"Dev Manager","gender":"male","salary": 50000}
{ "index" : {  "_id" : "3" } }
{ "name" : "Tran","age":25,"job":"Web Designer","gender":"male","salary":18000 }
{ "index" : {  "_id" : "4" } }
{ "name" : "Rivera","age":26,"job":"Web Designer","gender":"female","salary": 22000}
{ "index" : {  "_id" : "5" } }
{ "name" : "Rose","age":25,"job":"QA","gender":"female","salary":18000 }
{ "index" : {  "_id" : "6" } }
{ "name" : "Lucy","age":31,"job":"QA","gender":"female","salary": 25000}
{ "index" : {  "_id" : "7" } }
{ "name" : "Byrd","age":27,"job":"QA","gender":"male","salary":20000 }
{ "index" : {  "_id" : "8" } }
{ "name" : "Foster","age":27,"job":"Java Programmer","gender":"male","salary": 20000}
{ "index" : {  "_id" : "9" } }
{ "name" : "Gregory","age":32,"job":"Java Programmer","gender":"male","salary":22000 }
{ "index" : {  "_id" : "10" } }
{ "name" : "Bryant","age":20,"job":"Java Programmer","gender":"male","salary": 9000}
{ "index" : {  "_id" : "11" } }
{ "name" : "Jenny","age":36,"job":"Java Programmer","gender":"female","salary":38000 }
{ "index" : {  "_id" : "12" } }
{ "name" : "Mcdonald","age":31,"job":"Java Programmer","gender":"male","salary": 32000}
{ "index" : {  "_id" : "13" } }
{ "name" : "Jonthna","age":30,"job":"Java Programmer","gender":"female","salary":30000 }
{ "index" : {  "_id" : "14" } }
{ "name" : "Marshall","age":32,"job":"Javascript Programmer","gender":"male","salary": 25000}
{ "index" : {  "_id" : "15" } }
{ "name" : "King","age":33,"job":"Java Programmer","gender":"male","salary":28000 }
{ "index" : {  "_id" : "16" } }
{ "name" : "Mccarthy","age":21,"job":"Javascript Programmer","gender":"male","salary": 16000}
{ "index" : {  "_id" : "17" } }
{ "name" : "Goodwin","age":25,"job":"Javascript Programmer","gender":"male","salary": 16000}
{ "index" : {  "_id" : "18" } }
{ "name" : "Catherine","age":29,"job":"Javascript Programmer","gender":"female","salary": 20000}
{ "index" : {  "_id" : "19" } }
{ "name" : "Boone","age":30,"job":"DBA","gender":"male","salary": 30000}
{ "index" : {  "_id" : "20" } }
{ "name" : "Kathy","age":29,"job":"DBA","gender":"female","salary": 20000}

query

ES聚合分析的默认作用范围是query的查询结果集,也就是说,聚合是在先query之后的结果里面进行的,

# 查询年龄大于等于30岁的员工,并且对符合条件的员工按照职位类型进行分组
POST /employees/_search
{
  "size": 3,
  "query": {
    "range": {
      "age": {
        "gte": 30
      }
    }
  },
  "aggs": {
    "jobs": {
      "terms": {
        "field": "job.keyword"
      }
    }
  }
}

返回结果

{
  "took" : 0,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 10,
      "relation" : "eq"
    },
    "max_score" : 1.0,
    "hits" : [
      {
        "_index" : "employees",
        "_type" : "_doc",
        "_id" : "1",
        "_score" : 1.0,
        "_source" : {
          "name" : "Emma",
          "age" : 32,
          "job" : "Product Manager",
          "gender" : "female",
          "salary" : 35000
        }
      },
      {
        "_index" : "employees",
        "_type" : "_doc",
        "_id" : "2",
        "_score" : 1.0,
        "_source" : {
          "name" : "Underwood",
          "age" : 41,
          "job" : "Dev Manager",
          "gender" : "male",
          "salary" : 50000
        }
      },
      {
        "_index" : "employees",
        "_type" : "_doc",
        "_id" : "6",
        "_score" : 1.0,
        "_source" : {
          "name" : "Lucy",
          "age" : 31,
          "job" : "QA",
          "gender" : "female",
          "salary" : 25000
        }
      }
    ]
  },
  "aggregations" : {
    "jobs" : {
      "doc_count_error_upper_bound" : 0,
      "sum_other_doc_count" : 0,
      "buckets" : [
        {
          "key" : "Java Programmer",
          "doc_count" : 5
        },
        {
          "key" : "DBA",
          "doc_count" : 1
        },
        {
          "key" : "Dev Manager",
          "doc_count" : 1
        },
        {
          "key" : "Javascript Programmer",
          "doc_count" : 1
        },
        {
          "key" : "Product Manager",
          "doc_count" : 1
        },
        {
          "key" : "QA",
          "doc_count" : 1
        }
      ]
    }
  }
}

filter

如果我们想仅仅对聚合的数据进行筛选不影响query的结果,或者我们只想在一个聚合中进行筛选,而不影响其他聚合的结果呢,此时我们可以使用 filter

POST employees/_search
{
  "size": 3,
  "query": {
    "range": {
      "age": {
        "gte": 30
      }
    }
  },
  "aggs": {
    "older_person": {
      "filter": {
        "range": {
          "age": {
            "from": 35
          }
        }
      },
      "aggs": {
        "jobs": {
          "terms": {
            "field": "job.keyword"
          }
        }
      }
    },
    "all_jobs": {
      "terms": {
        "field": "job.keyword"
      }
    }
  }
}

结果如下:

{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 10,
      "relation" : "eq"
    },
    "max_score" : 1.0,
    "hits" : [
      {
        "_index" : "employees",
        "_type" : "_doc",
        "_id" : "1",
        "_score" : 1.0,
        "_source" : {
          "name" : "Emma",
          "age" : 32,
          "job" : "Product Manager",
          "gender" : "female",
          "salary" : 35000
        }
      },
      {
        "_index" : "employees",
        "_type" : "_doc",
        "_id" : "2",
        "_score" : 1.0,
        "_source" : {
          "name" : "Underwood",
          "age" : 41,
          "job" : "Dev Manager",
          "gender" : "male",
          "salary" : 50000
        }
      },
      {
        "_index" : "employees",
        "_type" : "_doc",
        "_id" : "6",
        "_score" : 1.0,
        "_source" : {
          "name" : "Lucy",
          "age" : 31,
          "job" : "QA",
          "gender" : "female",
          "salary" : 25000
        }
      }
    ]
  },
  "aggregations" : {
    "older_person" : {
      "doc_count" : 2,
      "jobs" : {
        "doc_count_error_upper_bound" : 0,
        "sum_other_doc_count" : 0,
        "buckets" : [
          {
            "key" : "Dev Manager",
            "doc_count" : 1
          },
          {
            "key" : "Java Programmer",
            "doc_count" : 1
          }
        ]
      }
    },
    "all_jobs" : {
      "doc_count_error_upper_bound" : 0,
      "sum_other_doc_count" : 0,
      "buckets" : [
        {
          "key" : "Java Programmer",
          "doc_count" : 5
        },
        {
          "key" : "DBA",
          "doc_count" : 1
        },
        {
          "key" : "Dev Manager",
          "doc_count" : 1
        },
        {
          "key" : "Javascript Programmer",
          "doc_count" : 1
        },
        {
          "key" : "Product Manager",
          "doc_count" : 1
        },
        {
          "key" : "QA",
          "doc_count" : 1
        }
      ]
    }
  }
}

我们可以看到query部分和上面query的结果是一样的,然后older_person里面的聚合才使用到了filter里面的条件,all_jobs里面和上面的query里面的一样。

post_filter

如果你想筛选条件只适用于查询,不适用于聚合,那该怎么办?使用 post_filter

比如,我想筛选出年龄小于23岁的员工,并且按照职位类别进行分组,然后查询出小于35岁的员工,按照id排序取前五位

POST employees/_search
{
  "size": 5,
  "aggs": {
    "young_person": {
      "filter": {
        "range": {
          "age": {
            "lte": 23
          }
        }
      },
      "aggs": {
        "jobs": {
          "terms": {
            "field": "job.keyword"
          }
        }
      }
    }
  },
  "post_filter": {
    "range": {
      "age": {
        "lte": 35
      }
    }
  }
}

结果如下:

{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 18,
      "relation" : "eq"
    },
    "max_score" : 1.0,
    "hits" : [
      {
        "_index" : "employees",
        "_type" : "_doc",
        "_id" : "1",
        "_score" : 1.0,
        "_source" : {
          "name" : "Emma",
          "age" : 32,
          "job" : "Product Manager",
          "gender" : "female",
          "salary" : 35000
        }
      },
      {
        "_index" : "employees",
        "_type" : "_doc",
        "_id" : "3",
        "_score" : 1.0,
        "_source" : {
          "name" : "Tran",
          "age" : 25,
          "job" : "Web Designer",
          "gender" : "male",
          "salary" : 18000
        }
      },
      {
        "_index" : "employees",
        "_type" : "_doc",
        "_id" : "4",
        "_score" : 1.0,
        "_source" : {
          "name" : "Rivera",
          "age" : 26,
          "job" : "Web Designer",
          "gender" : "female",
          "salary" : 22000
        }
      },
      {
        "_index" : "employees",
        "_type" : "_doc",
        "_id" : "5",
        "_score" : 1.0,
        "_source" : {
          "name" : "Rose",
          "age" : 25,
          "job" : "QA",
          "gender" : "female",
          "salary" : 18000
        }
      },
      {
        "_index" : "employees",
        "_type" : "_doc",
        "_id" : "6",
        "_score" : 1.0,
        "_source" : {
          "name" : "Lucy",
          "age" : 31,
          "job" : "QA",
          "gender" : "female",
          "salary" : 25000
        }
      }
    ]
  },
  "aggregations" : {
    "young_person" : {
      "doc_count" : 2,
      "jobs" : {
        "doc_count_error_upper_bound" : 0,
        "sum_other_doc_count" : 0,
        "buckets" : [
          {
            "key" : "Java Programmer",
            "doc_count" : 1
          },
          {
            "key" : "Javascript Programmer",
            "doc_count" : 1
          }
        ]
      }
    }
  }
}

这个例子中,post_filter的筛选条件并没有用到聚合里面,所以你可以理解为 post_filter
query
是一对相反的操作,query对聚合的数据先进行筛选再聚合,post_filter和聚合是相互独立的互不影响。

global

最后一个是global,可以无视query的影响,比如我们想筛选出大于35岁的员工,并且按照职业类型分组,然后我们还想获得所有员工的平均工资

POST /employees/_search
{
  "size": 0,
  "query": {
    "range": {
      "age": {
        "gte": 35
      }
    }
  },
  "aggs": {
    "jobs": {
      "terms": {
        "field": "job.keyword"
      }
    },
    "all": {
      "global": {},
      "aggs": {
        "salary_avg": {
          "avg": {
            "field": "salary"
          }
        }
      }
    }
  }
}

结果如下:

{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 2,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [ ]
  },
  "aggregations" : {
    "all" : {
      "doc_count" : 20,
      "salary_avg" : {
        "value" : 24700.0
      }
    },
    "jobs" : {
      "doc_count_error_upper_bound" : 0,
      "sum_other_doc_count" : 0,
      "buckets" : [
        {
          "key" : "Dev Manager",
          "doc_count" : 1
        },
        {
          "key" : "Java Programmer",
          "doc_count" : 1
        }
      ]
    }
  }
}

上面我们可以看到,24700.0是所有员工的平均工资,然后jobs里面是大于35岁的员工的类别,分别是Dev Manager和Java programmer。

当然要想实现上面的需求,我们也可以有其他写法,这里仅仅是为了展示 global
的用法。

比如下面的代码

POST /employees/_search
{
  "size": 0,
  "aggs": {
    "old_persons": {
        "filter": {
          "range": {
            "age": {
              "gte": 35
            }
          }
        },
        "aggs": {
          "jobs": {
            "terms": {
              "field": "job.keyword"
            }
          }
        }
    },
    "avg_salary": {
      "avg": {
        "field": "salary"
      }
    }
  }
}

结果如下:

{
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 20,
      "relation" : "eq"
    },
    "max_score" : null,
    "hits" : [ ]
  },
  "aggregations" : {
    "old_persons" : {
      "doc_count" : 2,
      "jobs" : {
        "doc_count_error_upper_bound" : 0,
        "sum_other_doc_count" : 0,
        "buckets" : [
          {
            "key" : "Dev Manager",
            "doc_count" : 1
          },
          {
            "key" : "Java Programmer",
            "doc_count" : 1
          }
        ]
      }
    },
    "avg_salary" : {
      "value" : 24700.0
    }
  }
}

原文 

https://segmentfault.com/a/1190000020226215

本站部分文章源于互联网,本着传播知识、有益学习和研究的目的进行的转载,为网友免费提供。如有著作权人或出版方提出异议,本站将立即删除。如果您对文章转载有任何疑问请告之我们,以便我们及时纠正。

PS:推荐一个微信公众号: askHarries 或者qq群:474807195,里面会分享一些资深架构师录制的视频录像:有Spring,MyBatis,Netty源码分析,高并发、高性能、分布式、微服务架构的原理,JVM性能优化这些成为架构师必备的知识体系。还能领取免费的学习资源,目前受益良多

转载请注明原文出处:Harries Blog™ » Elasticsearch聚合的作用范围

赞 (0)
分享到:更多 ()

评论 0

  • 昵称 (必填)
  • 邮箱 (必填)
  • 网址