地理距离聚合
编辑地理距离聚合
编辑一种多桶聚合，作用于 geo_point 字段，概念上与 范围 聚合非常相似。用户可以定义一个原点和一组距离范围桶。聚合会评估每个文档值与原点的距离，并根据范围确定它所属的桶（如果文档与原点之间的距离落在桶的距离范围内，则该文档属于该桶）。
resp = client.indices.create(
index="museums",
mappings={
"properties": {
"location": {
"type": "geo_point"
}
}
},
)
print(resp)
resp1 = client.bulk(
index="museums",
refresh=True,
operations=[
{
"index": {
"_id": 1
}
},
{
"location": "POINT (4.912350 52.374081)",
"name": "NEMO Science Museum"
},
{
"index": {
"_id": 2
}
},
{
"location": "POINT (4.901618 52.369219)",
"name": "Museum Het Rembrandthuis"
},
{
"index": {
"_id": 3
}
},
{
"location": "POINT (4.914722 52.371667)",
"name": "Nederlands Scheepvaartmuseum"
},
{
"index": {
"_id": 4
}
},
{
"location": "POINT (4.405200 51.222900)",
"name": "Letterenhuis"
},
{
"index": {
"_id": 5
}
},
{
"location": "POINT (2.336389 48.861111)",
"name": "Musée du Louvre"
},
{
"index": {
"_id": 6
}
},
{
"location": "POINT (2.327000 48.860000)",
"name": "Musée d'Orsay"
}
],
)
print(resp1)
resp2 = client.search(
index="museums",
size="0",
aggs={
"rings_around_amsterdam": {
"geo_distance": {
"field": "location",
"origin": "POINT (4.894 52.3760)",
"ranges": [
{
"to": 100000
},
{
"from": 100000,
"to": 300000
},
{
"from": 300000
}
]
}
}
},
)
print(resp2)
response = client.indices.create(
index: 'museums',
body: {
mappings: {
properties: {
location: {
type: 'geo_point'
}
}
}
}
)
puts response
response = client.bulk(
index: 'museums',
refresh: true,
body: [
{
index: {
_id: 1
}
},
{
location: 'POINT (4.912350 52.374081)',
name: 'NEMO Science Museum'
},
{
index: {
_id: 2
}
},
{
location: 'POINT (4.901618 52.369219)',
name: 'Museum Het Rembrandthuis'
},
{
index: {
_id: 3
}
},
{
location: 'POINT (4.914722 52.371667)',
name: 'Nederlands Scheepvaartmuseum'
},
{
index: {
_id: 4
}
},
{
location: 'POINT (4.405200 51.222900)',
name: 'Letterenhuis'
},
{
index: {
_id: 5
}
},
{
location: 'POINT (2.336389 48.861111)',
name: 'Musée du Louvre'
},
{
index: {
_id: 6
}
},
{
location: 'POINT (2.327000 48.860000)',
name: "Musée d'Orsay"
}
]
)
puts response
response = client.search(
index: 'museums',
size: 0,
body: {
aggregations: {
rings_around_amsterdam: {
geo_distance: {
field: 'location',
origin: 'POINT (4.894 52.3760)',
ranges: [
{
to: 100_000
},
{
from: 100_000,
to: 300_000
},
{
from: 300_000
}
]
}
}
}
}
)
puts response
const response = await client.indices.create({
index: "museums",
mappings: {
properties: {
location: {
type: "geo_point",
},
},
},
});
console.log(response);
const response1 = await client.bulk({
index: "museums",
refresh: "true",
operations: [
{
index: {
_id: 1,
},
},
{
location: "POINT (4.912350 52.374081)",
name: "NEMO Science Museum",
},
{
index: {
_id: 2,
},
},
{
location: "POINT (4.901618 52.369219)",
name: "Museum Het Rembrandthuis",
},
{
index: {
_id: 3,
},
},
{
location: "POINT (4.914722 52.371667)",
name: "Nederlands Scheepvaartmuseum",
},
{
index: {
_id: 4,
},
},
{
location: "POINT (4.405200 51.222900)",
name: "Letterenhuis",
},
{
index: {
_id: 5,
},
},
{
location: "POINT (2.336389 48.861111)",
name: "Musée du Louvre",
},
{
index: {
_id: 6,
},
},
{
location: "POINT (2.327000 48.860000)",
name: "Musée d'Orsay",
},
],
});
console.log(response1);
const response2 = await client.search({
index: "museums",
size: 0,
aggs: {
rings_around_amsterdam: {
geo_distance: {
field: "location",
origin: "POINT (4.894 52.3760)",
ranges: [
{
to: 100000,
},
{
from: 100000,
to: 300000,
},
{
from: 300000,
},
],
},
},
},
});
console.log(response2);
PUT /museums
{
"mappings": {
"properties": {
"location": {
"type": "geo_point"
}
}
}
}
POST /museums/_bulk?refresh
{"index":{"_id":1}}
{"location": "POINT (4.912350 52.374081)", "name": "NEMO Science Museum"}
{"index":{"_id":2}}
{"location": "POINT (4.901618 52.369219)", "name": "Museum Het Rembrandthuis"}
{"index":{"_id":3}}
{"location": "POINT (4.914722 52.371667)", "name": "Nederlands Scheepvaartmuseum"}
{"index":{"_id":4}}
{"location": "POINT (4.405200 51.222900)", "name": "Letterenhuis"}
{"index":{"_id":5}}
{"location": "POINT (2.336389 48.861111)", "name": "Musée du Louvre"}
{"index":{"_id":6}}
{"location": "POINT (2.327000 48.860000)", "name": "Musée d'Orsay"}
POST /museums/_search?size=0
{
"aggs": {
"rings_around_amsterdam": {
"geo_distance": {
"field": "location",
"origin": "POINT (4.894 52.3760)",
"ranges": [
{ "to": 100000 },
{ "from": 100000, "to": 300000 },
{ "from": 300000 }
]
}
}
}
}
响应
{
...
"aggregations": {
"rings_around_amsterdam": {
"buckets": [
{
"key": "*-100000.0",
"from": 0.0,
"to": 100000.0,
"doc_count": 3
},
{
"key": "100000.0-300000.0",
"from": 100000.0,
"to": 300000.0,
"doc_count": 1
},
{
"key": "300000.0-*",
"from": 300000.0,
"doc_count": 2
}
]
}
}
}
指定的字段必须是 geo_point 类型（只能在映射中显式设置）。它也可以包含 geo_point 字段的数组，在这种情况下，所有字段都将在聚合期间被考虑在内。原点可以接受 geo_point 类型 支持的所有格式。
- 对象格式：
{ "lat" : 52.3760, "lon" : 4.894 }- 这是最安全的格式，因为它最明确地说明了lat和lon值。 - 字符串格式：
"52.3760, 4.894"- 其中第一个数字是lat，第二个数字是lon。 - 数组格式：
[4.894, 52.3760]- 基于 GeoJSON 标准，其中第一个数字是lon，第二个数字是lat。
默认情况下，距离单位是 m（米），但它也可以接受：mi（英里），in（英寸），yd（码），km（公里），cm（厘米），mm（毫米）。
resp = client.search(
index="museums",
size="0",
aggs={
"rings": {
"geo_distance": {
"field": "location",
"origin": "POINT (4.894 52.3760)",
"unit": "km",
"ranges": [
{
"to": 100
},
{
"from": 100,
"to": 300
},
{
"from": 300
}
]
}
}
},
)
print(resp)
response = client.search(
index: 'museums',
size: 0,
body: {
aggregations: {
rings: {
geo_distance: {
field: 'location',
origin: 'POINT (4.894 52.3760)',
unit: 'km',
ranges: [
{
to: 100
},
{
from: 100,
to: 300
},
{
from: 300
}
]
}
}
}
}
)
puts response
const response = await client.search({
index: "museums",
size: 0,
aggs: {
rings: {
geo_distance: {
field: "location",
origin: "POINT (4.894 52.3760)",
unit: "km",
ranges: [
{
to: 100,
},
{
from: 100,
to: 300,
},
{
from: 300,
},
],
},
},
},
});
console.log(response);
POST /museums/_search?size=0
{
"aggs": {
"rings": {
"geo_distance": {
"field": "location",
"origin": "POINT (4.894 52.3760)",
"unit": "km",
"ranges": [
{ "to": 100 },
{ "from": 100, "to": 300 },
{ "from": 300 }
]
}
}
}
}
有两种距离计算模式：arc（默认）和 plane。arc 计算是最准确的。plane 是最快的但最不准确的。当您的搜索上下文“狭窄”并且跨越较小的地理区域（约 5 公里）时，请考虑使用 plane。plane 将为跨越大范围的搜索（例如，跨大陆搜索）返回更高的误差范围。可以使用 distance_type 参数设置距离计算类型。
resp = client.search(
index="museums",
size="0",
aggs={
"rings": {
"geo_distance": {
"field": "location",
"origin": "POINT (4.894 52.3760)",
"unit": "km",
"distance_type": "plane",
"ranges": [
{
"to": 100
},
{
"from": 100,
"to": 300
},
{
"from": 300
}
]
}
}
},
)
print(resp)
response = client.search(
index: 'museums',
size: 0,
body: {
aggregations: {
rings: {
geo_distance: {
field: 'location',
origin: 'POINT (4.894 52.3760)',
unit: 'km',
distance_type: 'plane',
ranges: [
{
to: 100
},
{
from: 100,
to: 300
},
{
from: 300
}
]
}
}
}
}
)
puts response
const response = await client.search({
index: "museums",
size: 0,
aggs: {
rings: {
geo_distance: {
field: "location",
origin: "POINT (4.894 52.3760)",
unit: "km",
distance_type: "plane",
ranges: [
{
to: 100,
},
{
from: 100,
to: 300,
},
{
from: 300,
},
],
},
},
},
});
console.log(response);
POST /museums/_search?size=0
{
"aggs": {
"rings": {
"geo_distance": {
"field": "location",
"origin": "POINT (4.894 52.3760)",
"unit": "km",
"distance_type": "plane",
"ranges": [
{ "to": 100 },
{ "from": 100, "to": 300 },
{ "from": 300 }
]
}
}
}
}
键控响应
编辑将 keyed 标志设置为 true 会为每个桶关联一个唯一的字符串键，并将范围作为哈希而不是数组返回。
resp = client.search(
index="museums",
size="0",
aggs={
"rings_around_amsterdam": {
"geo_distance": {
"field": "location",
"origin": "POINT (4.894 52.3760)",
"ranges": [
{
"to": 100000
},
{
"from": 100000,
"to": 300000
},
{
"from": 300000
}
],
"keyed": True
}
}
},
)
print(resp)
response = client.search(
index: 'museums',
size: 0,
body: {
aggregations: {
rings_around_amsterdam: {
geo_distance: {
field: 'location',
origin: 'POINT (4.894 52.3760)',
ranges: [
{
to: 100_000
},
{
from: 100_000,
to: 300_000
},
{
from: 300_000
}
],
keyed: true
}
}
}
}
)
puts response
const response = await client.search({
index: "museums",
size: 0,
aggs: {
rings_around_amsterdam: {
geo_distance: {
field: "location",
origin: "POINT (4.894 52.3760)",
ranges: [
{
to: 100000,
},
{
from: 100000,
to: 300000,
},
{
from: 300000,
},
],
keyed: true,
},
},
},
});
console.log(response);
POST /museums/_search?size=0
{
"aggs": {
"rings_around_amsterdam": {
"geo_distance": {
"field": "location",
"origin": "POINT (4.894 52.3760)",
"ranges": [
{ "to": 100000 },
{ "from": 100000, "to": 300000 },
{ "from": 300000 }
],
"keyed": true
}
}
}
}
响应
{
...
"aggregations": {
"rings_around_amsterdam": {
"buckets": {
"*-100000.0": {
"from": 0.0,
"to": 100000.0,
"doc_count": 3
},
"100000.0-300000.0": {
"from": 100000.0,
"to": 300000.0,
"doc_count": 1
},
"300000.0-*": {
"from": 300000.0,
"doc_count": 2
}
}
}
}
}
也可以自定义每个范围的键。
resp = client.search(
index="museums",
size="0",
aggs={
"rings_around_amsterdam": {
"geo_distance": {
"field": "location",
"origin": "POINT (4.894 52.3760)",
"ranges": [
{
"to": 100000,
"key": "first_ring"
},
{
"from": 100000,
"to": 300000,
"key": "second_ring"
},
{
"from": 300000,
"key": "third_ring"
}
],
"keyed": True
}
}
},
)
print(resp)
response = client.search(
index: 'museums',
size: 0,
body: {
aggregations: {
rings_around_amsterdam: {
geo_distance: {
field: 'location',
origin: 'POINT (4.894 52.3760)',
ranges: [
{
to: 100_000,
key: 'first_ring'
},
{
from: 100_000,
to: 300_000,
key: 'second_ring'
},
{
from: 300_000,
key: 'third_ring'
}
],
keyed: true
}
}
}
}
)
puts response
const response = await client.search({
index: "museums",
size: 0,
aggs: {
rings_around_amsterdam: {
geo_distance: {
field: "location",
origin: "POINT (4.894 52.3760)",
ranges: [
{
to: 100000,
key: "first_ring",
},
{
from: 100000,
to: 300000,
key: "second_ring",
},
{
from: 300000,
key: "third_ring",
},
],
keyed: true,
},
},
},
});
console.log(response);
POST /museums/_search?size=0
{
"aggs": {
"rings_around_amsterdam": {
"geo_distance": {
"field": "location",
"origin": "POINT (4.894 52.3760)",
"ranges": [
{ "to": 100000, "key": "first_ring" },
{ "from": 100000, "to": 300000, "key": "second_ring" },
{ "from": 300000, "key": "third_ring" }
],
"keyed": true
}
}
}
}
响应
{
...
"aggregations": {
"rings_around_amsterdam": {
"buckets": {
"first_ring": {
"from": 0.0,
"to": 100000.0,
"doc_count": 3
},
"second_ring": {
"from": 100000.0,
"to": 300000.0,
"doc_count": 1
},
"third_ring": {
"from": 300000.0,
"doc_count": 2
}
}
}
}
}