0

我试图通过聚合嵌套列表来获得加权平均值。每个文档都有一个学生的详细信息，每个学生的科目不同，每个科目的权重也不同。

我正在尝试按主题计算加权平均数。

我的文件是以下形式 -

[{'class': '10th',
 'id': '1',
'subject': [{'marks': 60, 'name': 's1', 'weight': 30},
         {'marks': 80, 'name': 's2', 'weight': 70}]},
{'class': '11th',
 'id': '2',
'subject': [{'marks': 43, 'name': 's10', 'weight': 40},
         {'marks': 54, 'name': 's20', 'weight': 60}]},
{'class': '10th',
 'id': '3',
'subject': [{'marks': 43, 'name': 's1', 'weight': 20},
         {'marks': 54, 'name': 's20', 'weight': 80}]},
{'class': '10th',
 'id': '4',
'subject': [{'marks': 69, 'name': 's10', 'weight': 30},
         {'marks': 45, 'name': 's2', 'weight': 70}]}]

这里 s1,s10,s2,s20 是主题。对于给定的班级，说“第 10 届”，我正在尝试汇总加权平均值。

我提出的查询是

GET students_try/_search
{
 "query": {
"match": {
  "class": "10th"
}
 },
"aggs": {
"subjects": {
  "nested": {
    "path": "subject"
  },
  "aggs": {
    "subjects": {
      "terms": {
        "field": "subject.name"
      },
      "aggs": {
        "avg_score": {
          "avg": {
            "field": "subject.marks"
          }
        },
        "weighted_grade": {
          "weighted_avg": {
            "value": {
              "field": "subject.marks"
            },
            "weight": {
              "field": "subject.weight"
            }
          }
        }
      }
    }
  }
}
  },
 "size": 0
}

我得到的错误是 -

{u'error': {u'col': 211,
        u'line': 1,
        u'reason': u'Unknown BaseAggregationBuilder [weighted_avg]',
        u'root_cause': [{u'col': 211,
                         u'line': 1,
                         u'reason': u'Unknown BaseAggregationBuilder [weighted_avg]',
                         u'type': u'unknown_named_object_exception'}],
        u'type': u'unknown_named_object_exception'},
 u'status': 400}

我不确定是什么导致了错误。

4

1 回答 1

1

是的，Nishant 提到的加权平均值仅出现在 6.4 之后，如A few others本链接中详细介绍 6.4 版本的部分所述

但是，我使用Bucket Script Aggregation提出了以下脚本，该脚本计算每个存储桶的加权平均值：

POST <your_index_name>/_search
{
  "size": 0,
  "query": {
    "match": {
      "class": "10th"
    }
  },
  "aggs": {
    "subjects": {
      "nested": {
        "path": "subject"
      },
      "aggs": {
        "subjects": {
          "terms": {
            "field": "subject.name.keyword"
          },
          "aggs": {
            "avg_score": {
              "avg": {
                "field": "subject.marks"
              }
            },
            "sum_score":{
              "sum_productOfMarksAndWeight": {
                "script": "doc['subject.marks'].value * doc['subject.weight'].value"
              }
            },
            "sum_weights": {
              "sum": {
                "field": "subject.weight"
              }
            },
            "weighted_avg":{
              "bucket_script": {
                "buckets_path": {
                  "sumScore": "sum_productOfMarksAndWeight",
                  "sumWeights": "sum_weights"
                },
                "script": "params.sumScore/params.sumWeights"
              }
            }
          }             
        }
      }
    }
  }
}

如果您仔细查看上面的聚合，对于每个桶，我使用Sum Aggregationsum of weights计算了和然后我使用这两个聚合来计算加权聚合。sum of product of weights and marks

以下是您的回复的显示方式。请注意，您还会在聚合结果中看到sum of weightsand 。sum of product of weights and marks

回复

{
  "took": 12,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": 3,
    "max_score": 0,
    "hits": []
  },
  "aggregations": {
    "subjects": {
      "doc_count": 6,
      "subjects": {
        "doc_count_error_upper_bound": 0,
        "sum_other_doc_count": 0,
        "buckets": [
          {
            "key": "s1",
            "doc_count": 2,
            "sum_weights": {
              "value": 50
            },
            "sum_productOfMarksAndWeight": {
              "value": 2660
            },
            "avg_score": {
              "value": 51.5
            },
            "weighted_avg": {
              "value": 53.2
            }
          },
          {
            "key": "s2",
            "doc_count": 2,
            "sum_weights": {
              "value": 140
            },
            "sum_productOfMarksAndWeight": {
              "value": 8750
            },
            "avg_score": {
              "value": 62.5
            },
            "weighted_avg": {
              "value": 62.5
            }
          },
          {
            "key": "s10",
            "doc_count": 1,
            "sum_weights": {
              "value": 30
            },
            "sum_productOfMarksAndWeight": {
              "value": 2070
            },
            "avg_score": {
              "value": 69
            },
            "weighted_avg": {
              "value": 69
            }
          },
          {
            "key": "s20",
            "doc_count": 1,
            "sum_weights": {
              "value": 80
            },
            "sum_productOfMarksAndWeight": {
              "value": 4320
            },
            "avg_score": {
              "value": 54
            },
            "weighted_avg": {
              "value": 54
            }
          }
        ]
      }
    }
  }
}

我希望这会有所帮助，如果没有，请告诉我，如果您认为这可以解决您正在寻找的问题，请继续接受这个答案；-)

于 2018-11-27T13:20:08.073 回答