1. 程式人生 > >elasticsearch 筆記四:聚合分析

elasticsearch 筆記四:聚合分析

1.第一個分析需求:計算每個tag下的商品數量 


GET /ecommerce/product/_search
{
  "aggs": {
    "group_by_tags": {
      "terms": {
        "field": "tags"
      }
    }
  }
}

-----------------------------------------------------------------------
{
  "took": 48,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "failed": 0
  },
  "hits": {
    "total": 4,
    "max_score": 1,
    "hits": [
      {
        "_index": "ecommerce",
        "_type": "product",
        "_id": "2",
        "_score": 1,
        "_source": {
          "name": "jiajieshi yagao",
          "desc": "youxiao fangzhu",
          "price": 25,
          "producer": "jiajieshi producer",
          "tags": [
            "fangzhu"
          ]
        }
      },
      {
        "_index": "ecommerce",
        "_type": "product",
        "_id": "4",
        "_score": 1,
        "_source": {
          "name": "heiren",
          "desc": "xiren yagao",
          "price": 50,
          "producer": "jiajieshi yagao",
          "tags": [
            "heiren"
          ]
        }
      },
      {
        "_index": "ecommerce",
        "_type": "product",
        "_id": "1",
        "_score": 1,
        "_source": {
          "name": "heiren",
          "desc": "xiren yagao",
          "price": 50,
          "producer": "jiajieshi yagao",
          "tags": [
            "heiren"
          ]
        }
      },
      {
        "_index": "ecommerce",
        "_type": "product",
        "_id": "3",
        "_score": 1,
        "_source": {
          "name": "zhonghua yagao",
          "desc": "caoben zhiwu",
          "price": 40,
          "producer": "zhonghua producer",
          "tags": [
            "qingxin"
          ]
        }
      }
    ]
  },
  "aggregations": {
    "group_by_tags": {
      "doc_count_error_upper_bound": 0,
      "sum_other_doc_count": 0,
      "buckets": [
        {
          "key": "heiren",
          "doc_count": 2
        },
        {
          "key": "fangzhu",
          "doc_count": 1
        },
        {
          "key": "qingxin",
          "doc_count": 1
        }
      ]
    }
  }
}
==============================================================================
GET /ecommerce/product/_search
{
  "size":0,
  "aggs": {
    "group_by_tags": {
      "terms": {
        "field": "tags"
      }
    }
  }
}
-----------------------------------------------------------------------------
{
  "took": 23,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "failed": 0
  },
  "hits": {
    "total": 4,
    "max_score": 0,
    "hits": []
  },
  "aggregations": {
    "group_by_tags": {
      "doc_count_error_upper_bound": 0,
      "sum_other_doc_count": 0,
      "buckets": [
        {
          "key": "heiren",
          "doc_count": 2
        },
        {
          "key": "fangzhu",
          "doc_count": 1
        },
        {
          "key": "qingxin",
          "doc_count": 1
        }
      ]
    }
  }
}

2.將文字field 的fielddata 屬性設為 true

PUT /ecommerce/_mapping/product/
{
  "properties":{
    "tags":{
      "type":"text",
      "fielddata":true
    }
  }
}

3.聚合分析的需求,先分組,再算每組的平均值,計算每個tag 下的平均價格

GET /ecommerce/product/_search
{
  "size": 0,
  "aggs": {
    "group_by_tags": {
      "terms": {
        "field": "tags"
      },
      "aggs": {
        "avg_price": {
          "avg": {
            "field": "price"
          }
        }
      }
    }
  }
}

-----------------------------------------------------------------------------
{
  "took": 15,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "failed": 0
  },
  "hits": {
    "total": 4,
    "max_score": 0,
    "hits": []
  },
  "aggregations": {
    "group_by_tags": {
      "doc_count_error_upper_bound": 0,
      "sum_other_doc_count": 0,
      "buckets": [
        {
          "key": "heiren",
          "doc_count": 2,
          "avg_price": {
            "value": 50
          }
        },
        {
          "key": "fangzhu",
          "doc_count": 1,
          "avg_price": {
            "value": 25
          }
        },
        {
          "key": "qingxin",
          "doc_count": 1,
          "avg_price": {
            "value": 40
          }
        }
      ]
    }
  }
}

4.第四個資料分析需求:計算每個tag下的商品的平均價格,並且按照平均價格降序排序

GET /ecommerce/product/_search
{

  "aggs": {
    "all_tags": {
      "terms": {
        "field": "tags",
        "order": {
          "avg_price": "desc"
        }
      },
      "aggs": {
        "avg_price": {
          "avg": {
            "field": "price"
          }
        }
      }
    }
  }
}

--------------------------------------------------------------------------
{
  "took": 9,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "failed": 0
  },
  "hits": {
    "total": 4,
    "max_score": 0,
    "hits": []
  },
  "aggregations": {
    "all_tags": {
      "doc_count_error_upper_bound": 0,
      "sum_other_doc_count": 0,
      "buckets": [
        {
          "key": "heiren",
          "doc_count": 2,
          "avg_price": {
            "value": 50
          }
        },
        {
          "key": "qingxin",
          "doc_count": 1,
          "avg_price": {
            "value": 40
          }
        },
        {
          "key": "fangzhu",
          "doc_count": 1,
          "avg_price": {
            "value": 25
          }
        }
      ]
    }
  }
}

5.第五個資料分析需求:按照指定的價格範圍區間進行分組,然後在每組內再按照tag進行分組,最後再計算每組的平均價格

GET /ecommerce/product/_search
{
  "size": 0,
  "aggs": {
    "group_by_price": {
      "range": {
        "field": "price",
        "ranges": [
          {
            "from": 0,
            "to": 20
          },
          {
            "from": 20,
            "to": 40
          },
          {
            "from": 40,
            "to": 50
          }
        ]
      },
      "aggs": {
        "group_by_tags": {
          "terms": {
            "field": "tags"
          },
          "aggs": {
            "average_price": {
              "avg": {
                "field": "price"
              }
            }
          }
        }
      }
    }
  }
}
------------------------------------------------------------------------------
{
  "took": 10,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "failed": 0
  },
  "hits": {
    "total": 4,
    "max_score": 0,
    "hits": []
  },
  "aggregations": {
    "group_by_price": {
      "buckets": [
        {
          "key": "0.0-20.0",
          "from": 0,
          "to": 20,
          "doc_count": 0,
          "group_by_tags": {
            "doc_count_error_upper_bound": 0,
            "sum_other_doc_count": 0,
            "buckets": []
          }
        },
        {
          "key": "20.0-40.0",
          "from": 20,
          "to": 40,
          "doc_count": 1,
          "group_by_tags": {
            "doc_count_error_upper_bound": 0,
            "sum_other_doc_count": 0,
            "buckets": [
              {
                "key": "fangzhu",
                "doc_count": 1,
                "average_price": {
                  "value": 25
                }
              }
            ]
          }
        },
        {
          "key": "40.0-50.0",
          "from": 40,
          "to": 50,
          "doc_count": 1,
          "group_by_tags": {
            "doc_count_error_upper_bound": 0,
            "sum_other_doc_count": 0,
            "buckets": [
              {
                "key": "qingxin",
                "doc_count": 1,
                "average_price": {
                  "value": 40
                }
              }
            ]
          }
        }
      ]
    }
  }
}