桶排序聚合
编辑桶排序聚合
编辑一个父管道聚合，对其父多桶聚合的桶进行排序。可以指定零个或多个排序字段以及相应的排序顺序。每个桶可以基于其 _key、_count 或其子聚合进行排序。此外，可以设置参数 from 和 size 以截断结果桶。
像所有管道聚合一样，bucket_sort 聚合在所有其他非管道聚合之后执行。这意味着排序仅适用于从父聚合返回的任何桶。例如，如果父聚合是 terms 并且其 size 设置为 10，则 bucket_sort 将仅对返回的 10 个 term 桶进行排序。
语法
编辑一个独立的 bucket_sort 聚合看起来像这样
{
"bucket_sort": {
"sort": [
{ "sort_field_1": { "order": "asc" } },
{ "sort_field_2": { "order": "desc" } },
"sort_field_3"
],
"from": 1,
"size": 3
}
}
以下代码片段按降序返回总销售额最高的 3 个月对应的桶
resp = client.search(
index="sales",
size=0,
aggs={
"sales_per_month": {
"date_histogram": {
"field": "date",
"calendar_interval": "month"
},
"aggs": {
"total_sales": {
"sum": {
"field": "price"
}
},
"sales_bucket_sort": {
"bucket_sort": {
"sort": [
{
"total_sales": {
"order": "desc"
}
}
],
"size": 3
}
}
}
}
},
)
print(resp)
response = client.search(
index: 'sales',
body: {
size: 0,
aggregations: {
sales_per_month: {
date_histogram: {
field: 'date',
calendar_interval: 'month'
},
aggregations: {
total_sales: {
sum: {
field: 'price'
}
},
sales_bucket_sort: {
bucket_sort: {
sort: [
{
total_sales: {
order: 'desc'
}
}
],
size: 3
}
}
}
}
}
}
)
puts response
const response = await client.search({
index: "sales",
size: 0,
aggs: {
sales_per_month: {
date_histogram: {
field: "date",
calendar_interval: "month",
},
aggs: {
total_sales: {
sum: {
field: "price",
},
},
sales_bucket_sort: {
bucket_sort: {
sort: [
{
total_sales: {
order: "desc",
},
},
],
size: 3,
},
},
},
},
},
});
console.log(response);
POST /sales/_search
{
"size": 0,
"aggs": {
"sales_per_month": {
"date_histogram": {
"field": "date",
"calendar_interval": "month"
},
"aggs": {
"total_sales": {
"sum": {
"field": "price"
}
},
"sales_bucket_sort": {
"bucket_sort": {
"sort": [
{ "total_sales": { "order": "desc" } }
],
"size": 3
}
}
}
}
}
}
以下可能是响应
{
"took": 82,
"timed_out": false,
"_shards": ...,
"hits": ...,
"aggregations": {
"sales_per_month": {
"buckets": [
{
"key_as_string": "2015/01/01 00:00:00",
"key": 1420070400000,
"doc_count": 3,
"total_sales": {
"value": 550.0
}
},
{
"key_as_string": "2015/03/01 00:00:00",
"key": 1425168000000,
"doc_count": 2,
"total_sales": {
"value": 375.0
}
},
{
"key_as_string": "2015/02/01 00:00:00",
"key": 1422748800000,
"doc_count": 2,
"total_sales": {
"value": 60.0
}
}
]
}
}
}
不排序截断
编辑也可以使用此聚合来截断结果桶，而不进行任何排序。为此，只需使用 from 和/或 size 参数，而无需指定 sort。
以下示例仅截断结果，以便仅返回第二个桶
resp = client.search(
index="sales",
size=0,
aggs={
"sales_per_month": {
"date_histogram": {
"field": "date",
"calendar_interval": "month"
},
"aggs": {
"bucket_truncate": {
"bucket_sort": {
"from": 1,
"size": 1
}
}
}
}
},
)
print(resp)
response = client.search(
index: 'sales',
body: {
size: 0,
aggregations: {
sales_per_month: {
date_histogram: {
field: 'date',
calendar_interval: 'month'
},
aggregations: {
bucket_truncate: {
bucket_sort: {
from: 1,
size: 1
}
}
}
}
}
}
)
puts response
const response = await client.search({
index: "sales",
size: 0,
aggs: {
sales_per_month: {
date_histogram: {
field: "date",
calendar_interval: "month",
},
aggs: {
bucket_truncate: {
bucket_sort: {
from: 1,
size: 1,
},
},
},
},
},
});
console.log(response);
POST /sales/_search
{
"size": 0,
"aggs": {
"sales_per_month": {
"date_histogram": {
"field": "date",
"calendar_interval": "month"
},
"aggs": {
"bucket_truncate": {
"bucket_sort": {
"from": 1,
"size": 1
}
}
}
}
}
}
响应
{
"took": 11,
"timed_out": false,
"_shards": ...,
"hits": ...,
"aggregations": {
"sales_per_month": {
"buckets": [
{
"key_as_string": "2015/02/01 00:00:00",
"key": 1422748800000,
"doc_count": 2
}
]
}
}
}