52

我发现的唯一接近的是：Multiple group-by in Elasticsearch

基本上我正在尝试获得与以下MySql查询等效的 ES：

select gender, age_range, count(distinct profile_id) as count 
FROM TABLE group by age_range, gender

年龄和性别本身很容易获得：

{
  "query": {
    "match_all": {}
  },
  "facets": {
    "ages": {
      "terms": {
        "field": "age_range",
        "size": 20
      }
    },
    "gender_by_age": {
      "terms": {
        "fields": [
          "age_range",
          "gender"
        ]
      }
    }
  },
  "size": 0
}

这使：

{
  "ages": {
    "_type": "terms",
    "missing": 0,
    "total": 193961,
    "other": 0,
    "terms": [
      {
        "term": 0,
        "count": 162643
      },
      {
        "term": 3,
        "count": 10683
      },
      {
        "term": 4,
        "count": 8931
      },
      {
        "term": 5,
        "count": 4690
      },
      {
        "term": 6,
        "count": 3647
      },
      {
        "term": 2,
        "count": 3247
      },
      {
        "term": 1,
        "count": 120
      }
    ]
  },
  "total_gender": {
    "_type": "terms",
    "missing": 0,
    "total": 193961,
    "other": 0,
    "terms": [
      {
        "term": 1,
        "count": 94799
      },
      {
        "term": 2,
        "count": 62645
      },
      {
        "term": 0,
        "count": 36517
      }
    ]
  }
}

但现在我需要一些看起来像这样的东西：

[breakdown_gender] => Array
    (
        [1] => Array
            (
                [0] => 264
                [1] => 1
                [2] => 6
                [3] => 67
                [4] => 72
                [5] => 40
                [6] => 23
            )

        [2] => Array
            (
                [0] => 153
                [2] => 2
                [3] => 21
                [4] => 35
                [5] => 22
                [6] => 11
            )

    )

请注意，这0,1,2,3,4,5,6是年龄范围的“映射”，因此它们实际上意味着一些东西:) 而不仅仅是数字。例如，性别[1]（即“男性”）细分为年龄范围 [0]（即“18 岁以下”），计数为 246。

4

2 回答 2

101

从 1.0 版开始ElasticSearch，新的聚合API允许使用子聚合按多个字段进行分组。假设您要按字段分组field1，field2并且field3：

{
  "aggs": {
    "agg1": {
      "terms": {
        "field": "field1"
      },
      "aggs": {
        "agg2": {
          "terms": {
            "field": "field2"
          },
          "aggs": {
            "agg3": {
              "terms": {
                "field": "field3"
              }
            }
          }          
        }
      }
    }
  }
}

当然，这可以适用于您想要的多个领域。

更新：
为了完整起见，以下是上述查询的输出外观。下面还有用于生成聚合查询并将结果展平为字典列表的 python 代码。

{
  "aggregations": {
    "agg1": {
      "buckets": [{
        "doc_count": <count>,
        "key": <value of field1>,
        "agg2": {
          "buckets": [{
            "doc_count": <count>,
            "key": <value of field2>,
            "agg3": {
              "buckets": [{
                "doc_count": <count>,
                "key": <value of field3>
              },
              {
                "doc_count": <count>,
                "key": <value of field3>
              }, ...
              ]
            },
            {
            "doc_count": <count>,
            "key": <value of field2>,
            "agg3": {
              "buckets": [{
                "doc_count": <count>,
                "key": <value of field3>
              },
              {
                "doc_count": <count>,
                "key": <value of field3>
              }, ...
              ]
            }, ...
          ]
        },
        {
        "doc_count": <count>,
        "key": <value of field1>,
        "agg2": {
          "buckets": [{
            "doc_count": <count>,
            "key": <value of field2>,
            "agg3": {
              "buckets": [{
                "doc_count": <count>,
                "key": <value of field3>
              },
              {
                "doc_count": <count>,
                "key": <value of field3>
              }, ...
              ]
            },
            {
            "doc_count": <count>,
            "key": <value of field2>,
            "agg3": {
              "buckets": [{
                "doc_count": <count>,
                "key": <value of field3>
              },
              {
                "doc_count": <count>,
                "key": <value of field3>
              }, ...
              ]
            }, ...
          ]
        }, ...
      ]
    }
  }
}

以下 python 代码在给定字段列表的情况下执行分组。如果您指定include_missing=True，它还包括缺少某些字段的值组合（如果您有 Elasticsearch 2.0 版，则不需要它）

def group_by(es, fields, include_missing):
    current_level_terms = {'terms': {'field': fields[0]}}
    agg_spec = {fields[0]: current_level_terms}

    if include_missing:
        current_level_missing = {'missing': {'field': fields[0]}}
        agg_spec[fields[0] + '_missing'] = current_level_missing

    for field in fields[1:]:
        next_level_terms = {'terms': {'field': field}}
        current_level_terms['aggs'] = {
            field: next_level_terms,
        }

        if include_missing:
            next_level_missing = {'missing': {'field': field}}
            current_level_terms['aggs'][field + '_missing'] = next_level_missing
            current_level_missing['aggs'] = {
                field: next_level_terms,
                field + '_missing': next_level_missing,
            }
            current_level_missing = next_level_missing

        current_level_terms = next_level_terms

    agg_result = es.search(body={'aggs': agg_spec})['aggregations']
    return get_docs_from_agg_result(agg_result, fields, include_missing)


def get_docs_from_agg_result(agg_result, fields, include_missing):
    current_field = fields[0]
    buckets = agg_result[current_field]['buckets']
    if include_missing:
        buckets.append(agg_result[(current_field + '_missing')])

    if len(fields) == 1:
        return [
            {
                current_field: bucket.get('key'),
                'doc_count': bucket['doc_count'],
            }
            for bucket in buckets if bucket['doc_count'] > 0
        ]

    result = []
    for bucket in buckets:
        records = get_docs_from_agg_result(bucket, fields[1:], include_missing)
        value = bucket.get('key')
        for record in records:
            record[current_field] = value
        result.extend(records)

    return result
于 2014-01-23T07:34:22.493 回答
23

由于您只有 2 个字段，因此一种简单的方法是使用单个方面进行两个查询。男性：

{
    "query" : {
      "term" : { "gender" : "Male" }
    },
    "facets" : {
        "age_range" : {
            "terms" : {
                "field" : "age_range"
            }
        }
    }
}

对于女性：

{
    "query" : {
      "term" : { "gender" : "Female" }
    },
    "facets" : {
        "age_range" : {
            "terms" : {
                "field" : "age_range"
            }
        }
    }
}

或者您可以在单个查询中使用构面过滤器执行此操作（有关详细信息，请参阅此链接）

{
    "query" : {
       "match_all": {}
    },
    "facets" : {
        "age_range_male" : {
            "terms" : {
                "field" : "age_range"
            },
            "facet_filter":{
                "term": {
                    "gender": "Male"
                }
            }
        },
        "age_range_female" : {
            "terms" : {
                "field" : "age_range"
            },
            "facet_filter":{
                "term": {
                    "gender": "Female"
                }
            }
        }
    }
}

更新：

因为刻面即将被删除。这是聚合的解决方案：

{
  "query": {
    "match_all": {}
  },
  "aggs": {
    "male": {
      "filter": {
        "term": {
          "gender": "Male"
        }
      },
      "aggs": {
        "age_range": {
          "terms": {
            "field": "age_range"
          }
        }
      }
    },
    "female": {
      "filter": {
        "term": {
          "gender": "Female"
        }
      },
      "aggs": {
        "age_range": {
          "terms": {
            "field": "age_range"
          }
        }
      }
    }
  }
}
于 2013-08-26T18:29:07.710 回答