桶相关性聚合
编辑桶相关性聚合
编辑一个兄弟管道聚合，它在配置的兄弟多桶聚合上执行相关性函数。
参数
编辑-
buckets_path - （必需，字符串）包含一组要关联的值的桶的路径。有关语法，请参阅
buckets_path语法。 -
function -
（必需，对象）要执行的相关性函数。
function的属性-
count_correlation -
（必需*，对象）用于计算计数相关性的配置。此函数旨在确定术语值与给定指标的相关性。因此，它需要满足以下要求。
buckets_path必须指向_count指标。- 所有
bucket_path计数值的总计数必须小于或等于indicator.doc_count。 - 当使用此函数时，需要进行初始计算以收集所需的
indicator值。
count_correlation的属性-
indicator -
（必需，对象）用于关联配置的
bucket_path值的指标。indicator的属性-
doc_count - （必需，整数）最初创建
expectations的文档总数。它必须大于或等于buckets_path中所有值的总和，因为这是术语值关联的原始超集数据。 -
expectations - （必需，数组）用于关联配置的
bucket_path值的数字数组。此值的长度必须始终等于bucket_path返回的桶数。 -
fractions - （可选，数组）用于平均和计算方差的分数数组。如果预先计算的数据和
buckets_path存在已知差距，则应使用此数组。如果提供了fractions，则其长度必须等于expectations。
-
-
语法
编辑一个 bucket_correlation 聚合单独看起来像这样
示例
编辑以下代码片段将字段 version 中的各个术语与 latency 指标相关联。未显示的是 latency 指标值的预计算，这是使用 百分位数聚合完成的。
此示例仅使用 10 秒的百分位数。
resp = client.search(
index="correlate_latency",
size="0",
filter_path="aggregations",
aggs={
"buckets": {
"terms": {
"field": "version",
"size": 2
},
"aggs": {
"latency_ranges": {
"range": {
"field": "latency",
"ranges": [
{
"to": 0
},
{
"from": 0,
"to": 105
},
{
"from": 105,
"to": 225
},
{
"from": 225,
"to": 445
},
{
"from": 445,
"to": 665
},
{
"from": 665,
"to": 885
},
{
"from": 885,
"to": 1115
},
{
"from": 1115,
"to": 1335
},
{
"from": 1335,
"to": 1555
},
{
"from": 1555,
"to": 1775
},
{
"from": 1775
}
]
}
},
"bucket_correlation": {
"bucket_correlation": {
"buckets_path": "latency_ranges>_count",
"function": {
"count_correlation": {
"indicator": {
"expectations": [
0,
52.5,
165,
335,
555,
775,
1000,
1225,
1445,
1665,
1775
],
"doc_count": 200
}
}
}
}
}
}
}
},
)
print(resp)
const response = await client.search({
index: "correlate_latency",
size: 0,
filter_path: "aggregations",
aggs: {
buckets: {
terms: {
field: "version",
size: 2,
},
aggs: {
latency_ranges: {
range: {
field: "latency",
ranges: [
{
to: 0,
},
{
from: 0,
to: 105,
},
{
from: 105,
to: 225,
},
{
from: 225,
to: 445,
},
{
from: 445,
to: 665,
},
{
from: 665,
to: 885,
},
{
from: 885,
to: 1115,
},
{
from: 1115,
to: 1335,
},
{
from: 1335,
to: 1555,
},
{
from: 1555,
to: 1775,
},
{
from: 1775,
},
],
},
},
bucket_correlation: {
bucket_correlation: {
buckets_path: "latency_ranges>_count",
function: {
count_correlation: {
indicator: {
expectations: [
0, 52.5, 165, 335, 555, 775, 1000, 1225, 1445, 1665, 1775,
],
doc_count: 200,
},
},
},
},
},
},
},
},
});
console.log(response);
POST correlate_latency/_search?size=0&filter_path=aggregations
{
"aggs": {
"buckets": {
"terms": {
"field": "version",
"size": 2
},
"aggs": {
"latency_ranges": {
"range": {
"field": "latency",
"ranges": [
{ "to": 0.0 },
{ "from": 0, "to": 105 },
{ "from": 105, "to": 225 },
{ "from": 225, "to": 445 },
{ "from": 445, "to": 665 },
{ "from": 665, "to": 885 },
{ "from": 885, "to": 1115 },
{ "from": 1115, "to": 1335 },
{ "from": 1335, "to": 1555 },
{ "from": 1555, "to": 1775 },
{ "from": 1775 }
]
}
},
"bucket_correlation": {
"bucket_correlation": {
"buckets_path": "latency_ranges>_count",
"function": {
"count_correlation": {
"indicator": {
"expectations": [0, 52.5, 165, 335, 555, 775, 1000, 1225, 1445, 1665, 1775],
"doc_count": 200
}
}
}
}
}
}
}
}
}
|
包含范围聚合和桶相关性聚合的术语桶。两者都用于计算术语值与延迟的相关性。 |
|
|
延迟字段上的范围聚合。这些范围是参考延迟字段的百分位数创建的。 |
|
|
桶相关性聚合，它计算每个范围内的术语值数量与先前计算的指标值的相关性。 |
以下可能是响应
{
"aggregations" : {
"buckets" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [
{
"key" : "1.0",
"doc_count" : 100,
"latency_ranges" : {
"buckets" : [
{
"key" : "*-0.0",
"to" : 0.0,
"doc_count" : 0
},
{
"key" : "0.0-105.0",
"from" : 0.0,
"to" : 105.0,
"doc_count" : 1
},
{
"key" : "105.0-225.0",
"from" : 105.0,
"to" : 225.0,
"doc_count" : 9
},
{
"key" : "225.0-445.0",
"from" : 225.0,
"to" : 445.0,
"doc_count" : 0
},
{
"key" : "445.0-665.0",
"from" : 445.0,
"to" : 665.0,
"doc_count" : 0
},
{
"key" : "665.0-885.0",
"from" : 665.0,
"to" : 885.0,
"doc_count" : 0
},
{
"key" : "885.0-1115.0",
"from" : 885.0,
"to" : 1115.0,
"doc_count" : 10
},
{
"key" : "1115.0-1335.0",
"from" : 1115.0,
"to" : 1335.0,
"doc_count" : 20
},
{
"key" : "1335.0-1555.0",
"from" : 1335.0,
"to" : 1555.0,
"doc_count" : 20
},
{
"key" : "1555.0-1775.0",
"from" : 1555.0,
"to" : 1775.0,
"doc_count" : 20
},
{
"key" : "1775.0-*",
"from" : 1775.0,
"doc_count" : 20
}
]
},
"bucket_correlation" : {
"value" : 0.8402398981360937
}
},
{
"key" : "2.0",
"doc_count" : 100,
"latency_ranges" : {
"buckets" : [
{
"key" : "*-0.0",
"to" : 0.0,
"doc_count" : 0
},
{
"key" : "0.0-105.0",
"from" : 0.0,
"to" : 105.0,
"doc_count" : 19
},
{
"key" : "105.0-225.0",
"from" : 105.0,
"to" : 225.0,
"doc_count" : 11
},
{
"key" : "225.0-445.0",
"from" : 225.0,
"to" : 445.0,
"doc_count" : 20
},
{
"key" : "445.0-665.0",
"from" : 445.0,
"to" : 665.0,
"doc_count" : 20
},
{
"key" : "665.0-885.0",
"from" : 665.0,
"to" : 885.0,
"doc_count" : 20
},
{
"key" : "885.0-1115.0",
"from" : 885.0,
"to" : 1115.0,
"doc_count" : 10
},
{
"key" : "1115.0-1335.0",
"from" : 1115.0,
"to" : 1335.0,
"doc_count" : 0
},
{
"key" : "1335.0-1555.0",
"from" : 1335.0,
"to" : 1555.0,
"doc_count" : 0
},
{
"key" : "1555.0-1775.0",
"from" : 1555.0,
"to" : 1775.0,
"doc_count" : 0
},
{
"key" : "1775.0-*",
"from" : 1775.0,
"doc_count" : 0
}
]
},
"bucket_correlation" : {
"value" : -0.5759855613334943
}
}
]
}
}
}