ElasticSearch聚合查询

聚合分组

select * from table group by title.keyword

{
  "size": 0,
  "aggs": {
    "group_name": {
      "terms": {
        "field": "title.keyword"
      }
    }
  }
}

解释：
size:0 表示只展示聚合结果，不展示原始数据
aggs：表示聚合的操作符
group_name：给聚合操作取名
terms:根据字段的值进行分组
field:根据指定的字段值进行分组

求和

按照title分组求和
select sum(price) from table group by title.

{
  "size": 0,
  "aggs": {
    "group_name": {
      "terms": {
        "field": "title.keyword"
      },
      "aggs":{
          "sum_price":{
              "sum":{
                  "field":"price"
              }
          }
      }
    }
  }
}

平均值

select avg(price) from table group by title.

{
  "size": 0,
  "aggs": {
    "group_name": {
      "terms": {
        "field": "title.keyword"
      },
      "aggs":{
          "avg_price":{
              "avg":{
                  "field":"price"
              }
          }
      }
    }
  }
}

分析每种颜色下每种品牌的平均价格

{
  "size": 0,
  "aggs": {
    "group_name": {
      "terms": {
        "field": "color.keyword"
      },
      "aggs": {
        "group_by_brand": {
          "terms": {
            "field": "brand.keyword"
          },
          "aggs": {
            "avg_price_by_color": {
              "avg": {
                "field": "price"
              }
            }
          }
        }
      }
    }
  }
}

更多的metric学习

{
  "size": 0,
  "aggs": {
    "group_name": {
      "terms": {
        "field": "color.keyword"
      },
      "aggs": {
        "avg_price": {
          "avg": {
            "field": "price"
          }
        },
        "sum_price": {
          "sum": {
            "field": "price"
          }
        },
        "max_price": {
          "max": {
            "field": "price"
          }
        },
        "min_max": {
          "min": {
            "field": "price"
          }
        }
      }
    }
  }
}

输出：

  "took": 66,
  "timed_out": false,
  "_shards": {
    "total": 1,
    "successful": 1,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": {
      "value": 3,
      "relation": "eq"
    },
    "max_score": null,
    "hits": [

    ]
  },
  "aggregations": {
    "group_name": {
      "doc_count_error_upper_bound": 0,
      "sum_other_doc_count": 0,
      "buckets": [
        {
          "key": "white",
          "doc_count": 2,
          "max_price": {
            "value": 5500
          },
          "min_max": {
            "value": 4500
          },
          "avg_price": {
            "value": 5000
          },
          "sum_price": {
            "value": 10000
          }
        },
        {
          "key": "blue",
          "doc_count": 1,
          "max_price": {
            "value": 4000
          },
          "min_max": {
            "value": 4000
          },
          "avg_price": {
            "value": 4000
          },
          "sum_price": {
            "value": 4000
          }
        }
      ]
    }
  }
}

一般来说，90%的常见的数据分析的操作，metric，无非就是count，avg，max，min，sum

Cardinality(唯一值)

cardinality 即去重计算，类似sql中 count（distinct），先去重再求和，计算指定field值的种类数。

{
  "size": 0,
  "aggs": {
    "cartinality_gender": {
      "cardinality": {
        "field": "city.keyword"
      }
    }
  }
}

输出

{
  "took": 2,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": 15,
    "max_score": 0,
    "hits": []
  },
  "aggregations": {
    "cartinality_gender": {
      "value": 15
    }
  }
}```

## stats 一个聚合，输出多值
```java
{
  "size": 0,
  "aggs": {
    "stats_price": {
      "stats": {
        "field": "price"
      }
    }
  }
}

{
  "took": 3,
  "timed_out": false,
  "_shards": {
    "total": 1,
    "successful": 1,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": {
      "value": 3,
      "relation": "eq"
    },
    "max_score": null,
    "hits": [

    ]
  },
  "aggregations": {
    "stats_price": {
      "count": 3,
      "min": 4000,
      "max": 5500,
      "avg": 4666.666666666667,
      "sum": 14000
    }
  }
}

查询+聚合分析

{
    "query":{
        "match":{
            "title":"神州"
        }
    },
    "aggs":{
        "sum_price":{
            "sum":{
                "field":"price"
            }
        }
    }
}

输出

  "took": 54,
  "timed_out": false,
  "_shards": {
    "total": 1,
    "successful": 1,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": {
      "value": 2,
      "relation": "eq"
    },
    "max_score": 0.9983525,
    "hits": [
      {
        "_index": "aggs_index",
        "_type": "_doc",
        "_id": "5",
        "_score": 0.9983525,
        "_source": {
          "brand": "huashuo",
          "color": "white",
          "price": 5500,
          "title": "神州"
        }
      },
      {
        "_index": "aggs_index",
        "_type": "_doc",
        "_id": "6",
        "_score": 0.8416345,
        "_source": {
          "brand": "dell",
          "color": "white",
          "price": 4500,
          "title": "神州dell"
        }
      }
    ]
  },
  "aggregations": {
    "sum_price": {
      "value": 10000
    }
  }
}

查询聚合+全局聚合 深入聚合数据分析_global bucket：单个品牌与所有品牌销量对比

global：就是global bucket，就是将所有数据纳入聚合的scope，而不管之前的query

{
  "query": {
    "match": {
      "title": "神州"
    }
  },
  "aggs": {
    "sum_price": {
      "sum": {
        "field": "price"
      }
    },
    "all": {
      "global": {},
      "aggs": {
        "all_sum_price": {
          "sum": {
            "field": "price"
          }
        }
      }
    }
  }
}

输出

{
  "query": {
    "match": {
      "title": "神州"
    }
  },
  "aggs": {
    "sum_price": {
      "sum": {
        "field": "price"
      }
    },
    "all": {
      "global": {},
      "aggs": {
        "all_sum_price": {
          "sum": {
            "field": "price"
          }
        }
      }
    }
  }
}

过滤+聚合：统计价格大于1200的电视平均价格

{
  "size": 0,
  "query": {
    "constant_score": {
      "filter": {
        "range": {
          "price": {
            "gte": 1200
          }
        }
      }
    }
  },
  "aggs": {
    "avg_price": {
      "avg": {
        "field": "price"
      }
    }
  }
}

统计最近一个月的平均价格

{
  "size": 0,
  "query": {
    "term": {
      "brand": {
        "value": "长虹"
      }
    }
  },
  "aggs": {
    "recent_150d": {
      "filter": {
        "range": {
          "sold_date": {
            "gte": "now-150d"
          }
        }
      },
      "aggs": {
        "recent_150d_avg_price": {
          "avg": {
            "field": "price"
          }
        }
      }
    },
    "recent_140d": {
      "filter": {
        "range": {
          "sold_date": {
            "gte": "now-140d"
          }
        }
      },
      "aggs": {
        "recent_140d_avg_price": {
          "avg": {
            "field": "price"
          }
        }
      }
    },
    "recent_130d": {
      "filter": {
        "range": {
          "sold_date": {
            "gte": "now-130d"
          }
        }
      },
      "aggs": {
        "recent_130d_avg_price": {
          "avg": {
            "field": "price"
          }
        }
      }
    }
  }
}

按照每种品牌的平均价格排序

{
  "size": 0,
  "aggs": {
    "group_by_color": {
      "terms": {
        "field": "brand.keyword",
        "order":{
            "avg_price":"desc"
        }
      },
      "aggs": {
        "avg_price": {
          "avg": {
            "field": "price"
          }
        }
      }
    }
  }
}