Stats bucket aggregation

A sibling pipeline aggregation which calculates a variety of stats across all bucket of a specified metric in a sibling aggregation. The specified metric must be numeric and the sibling aggregation must be a multi-bucket aggregation.

Syntax

edit

A stats_bucket aggregation looks like this in isolation:

{
  "stats_bucket": {
    "buckets_path": "the_sum"
  }
}

Table 81. stats_bucket Parameters

Parameter Name	Description	Required	Default Value
`buckets_path`	The path to the buckets we wish to calculate stats for (see `buckets_path` Syntax for more details)	Required
`gap_policy`	The policy to apply when gaps are found in the data (see Dealing with gaps in the data for more details)	Optional	`skip`
`format`	DecimalFormat pattern for the output value. If specified, the formatted value is returned in the aggregation’s `value_as_string` property	Optional	`null`

The following snippet calculates the stats for monthly sales:

resp = client.search(
    index="sales",
    size=0,
    aggs={
        "sales_per_month": {
            "date_histogram": {
                "field": "date",
                "calendar_interval": "month"
            },
            "aggs": {
                "sales": {
                    "sum": {
                        "field": "price"
                    }
                }
            }
        },
        "stats_monthly_sales": {
            "stats_bucket": {
                "buckets_path": "sales_per_month>sales"
            }
        }
    },
)
print(resp)

response = client.search(
  index: 'sales',
  body: {
    size: 0,
    aggregations: {
      sales_per_month: {
        date_histogram: {
          field: 'date',
          calendar_interval: 'month'
        },
        aggregations: {
          sales: {
            sum: {
              field: 'price'
            }
          }
        }
      },
      stats_monthly_sales: {
        stats_bucket: {
          buckets_path: 'sales_per_month>sales'
        }
      }
    }
  }
)
puts response

const response = await client.search({
  index: "sales",
  size: 0,
  aggs: {
    sales_per_month: {
      date_histogram: {
        field: "date",
        calendar_interval: "month",
      },
      aggs: {
        sales: {
          sum: {
            field: "price",
          },
        },
      },
    },
    stats_monthly_sales: {
      stats_bucket: {
        buckets_path: "sales_per_month>sales",
      },
    },
  },
});
console.log(response);

POST /sales/_search
{
  "size": 0,
  "aggs": {
    "sales_per_month": {
      "date_histogram": {
        "field": "date",
        "calendar_interval": "month"
      },
      "aggs": {
        "sales": {
          "sum": {
            "field": "price"
          }
        }
      }
    },
    "stats_monthly_sales": {
      "stats_bucket": {
        "buckets_path": "sales_per_month>sales" 
      }
    }
  }
}

bucket_paths instructs this stats_bucket aggregation that we want the calculate stats for the sales aggregation in the sales_per_month date histogram.

And the following may be the response:

{
   "took": 11,
   "timed_out": false,
   "_shards": ...,
   "hits": ...,
   "aggregations": {
      "sales_per_month": {
         "buckets": [
            {
               "key_as_string": "2015/01/01 00:00:00",
               "key": 1420070400000,
               "doc_count": 3,
               "sales": {
                  "value": 550.0
               }
            },
            {
               "key_as_string": "2015/02/01 00:00:00",
               "key": 1422748800000,
               "doc_count": 2,
               "sales": {
                  "value": 60.0
               }
            },
            {
               "key_as_string": "2015/03/01 00:00:00",
               "key": 1425168000000,
               "doc_count": 2,
               "sales": {
                  "value": 375.0
               }
            }
         ]
      },
      "stats_monthly_sales": {
         "count": 3,
         "min": 60.0,
         "max": 550.0,
         "avg": 328.3333333333333,
         "sum": 985.0
      }
   }
}

« Serial differencing aggregation Sum bucket aggregation »