Extended stats bucket aggregation
Extended 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.
This aggregation provides a few more statistics (sum of squares, standard deviation, etc) compared to the stats_bucket
aggregation.
Syntax
A extended_stats_bucket
aggregation looks like this in isolation:
{
"extended_stats_bucket": {
"buckets_path": "the_sum"
}
}
Table 62. extended_stats_bucket
Parameters
Parameter Name | Description | Required | Default Value |
---|---|---|---|
| The path to the buckets we wish to calculate stats for (see buckets_path Syntax for more details) | Required | |
| The policy to apply when gaps are found in the data (see Dealing with gaps in the data for more details) | Optional |
|
| DecimalFormat pattern for the output value. If specified, the formatted value is returned in the aggregation’s | Optional |
|
| The number of standard deviations above/below the mean to display | Optional | 2 |
The following snippet calculates the extended stats for monthly sales
bucket:
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": {
"extended_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: {
extended_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: {
extended_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": {
"extended_stats_bucket": {
"buckets_path": "sales_per_month>sales"
}
}
}
}
|
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,
"sum_of_squares": 446725.0,
"variance": 41105.55555555556,
"variance_population": 41105.55555555556,
"variance_sampling": 61658.33333333334,
"std_deviation": 202.74505063146563,
"std_deviation_population": 202.74505063146563,
"std_deviation_sampling": 248.3109609609156,
"std_deviation_bounds": {
"upper": 733.8234345962646,
"lower": -77.15676792959795,
"upper_population" : 733.8234345962646,
"lower_population" : -77.15676792959795,
"upper_sampling" : 824.9552552551645,
"lower_sampling" : -168.28858858849787
}
}
}
}