地理质心聚合
编辑地理质心聚合
编辑一种度量聚合，它计算地理字段的所有坐标值的加权质心。
示例
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)",
"city": "Amsterdam",
"name": "NEMO Science Museum"
},
{
"index": {
"_id": 2
}
},
{
"location": "POINT (4.901618 52.369219)",
"city": "Amsterdam",
"name": "Museum Het Rembrandthuis"
},
{
"index": {
"_id": 3
}
},
{
"location": "POINT (4.914722 52.371667)",
"city": "Amsterdam",
"name": "Nederlands Scheepvaartmuseum"
},
{
"index": {
"_id": 4
}
},
{
"location": "POINT (4.405200 51.222900)",
"city": "Antwerp",
"name": "Letterenhuis"
},
{
"index": {
"_id": 5
}
},
{
"location": "POINT (2.336389 48.861111)",
"city": "Paris",
"name": "Musée du Louvre"
},
{
"index": {
"_id": 6
}
},
{
"location": "POINT (2.327000 48.860000)",
"city": "Paris",
"name": "Musée d'Orsay"
}
],
)
print(resp1)
resp2 = client.search(
index="museums",
size="0",
aggs={
"centroid": {
"geo_centroid": {
"field": "location"
}
}
},
)
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)',
city: 'Amsterdam',
name: 'NEMO Science Museum'
},
{
index: {
_id: 2
}
},
{
location: 'POINT (4.901618 52.369219)',
city: 'Amsterdam',
name: 'Museum Het Rembrandthuis'
},
{
index: {
_id: 3
}
},
{
location: 'POINT (4.914722 52.371667)',
city: 'Amsterdam',
name: 'Nederlands Scheepvaartmuseum'
},
{
index: {
_id: 4
}
},
{
location: 'POINT (4.405200 51.222900)',
city: 'Antwerp',
name: 'Letterenhuis'
},
{
index: {
_id: 5
}
},
{
location: 'POINT (2.336389 48.861111)',
city: 'Paris',
name: 'Musée du Louvre'
},
{
index: {
_id: 6
}
},
{
location: 'POINT (2.327000 48.860000)',
city: 'Paris',
name: "Musée d'Orsay"
}
]
)
puts response
response = client.search(
index: 'museums',
size: 0,
body: {
aggregations: {
centroid: {
geo_centroid: {
field: 'location'
}
}
}
}
)
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)",
city: "Amsterdam",
name: "NEMO Science Museum",
},
{
index: {
_id: 2,
},
},
{
location: "POINT (4.901618 52.369219)",
city: "Amsterdam",
name: "Museum Het Rembrandthuis",
},
{
index: {
_id: 3,
},
},
{
location: "POINT (4.914722 52.371667)",
city: "Amsterdam",
name: "Nederlands Scheepvaartmuseum",
},
{
index: {
_id: 4,
},
},
{
location: "POINT (4.405200 51.222900)",
city: "Antwerp",
name: "Letterenhuis",
},
{
index: {
_id: 5,
},
},
{
location: "POINT (2.336389 48.861111)",
city: "Paris",
name: "Musée du Louvre",
},
{
index: {
_id: 6,
},
},
{
location: "POINT (2.327000 48.860000)",
city: "Paris",
name: "Musée d'Orsay",
},
],
});
console.log(response1);
const response2 = await client.search({
index: "museums",
size: 0,
aggs: {
centroid: {
geo_centroid: {
field: "location",
},
},
},
});
console.log(response2);
PUT /museums
{
"mappings": {
"properties": {
"location": {
"type": "geo_point"
}
}
}
}
POST /museums/_bulk?refresh
{"index":{"_id":1}}
{"location": "POINT (4.912350 52.374081)", "city": "Amsterdam", "name": "NEMO Science Museum"}
{"index":{"_id":2}}
{"location": "POINT (4.901618 52.369219)", "city": "Amsterdam", "name": "Museum Het Rembrandthuis"}
{"index":{"_id":3}}
{"location": "POINT (4.914722 52.371667)", "city": "Amsterdam", "name": "Nederlands Scheepvaartmuseum"}
{"index":{"_id":4}}
{"location": "POINT (4.405200 51.222900)", "city": "Antwerp", "name": "Letterenhuis"}
{"index":{"_id":5}}
{"location": "POINT (2.336389 48.861111)", "city": "Paris", "name": "Musée du Louvre"}
{"index":{"_id":6}}
{"location": "POINT (2.327000 48.860000)", "city": "Paris", "name": "Musée d'Orsay"}
POST /museums/_search?size=0
{
"aggs": {
"centroid": {
"geo_centroid": {
"field": "location"
}
}
}
}
|
|
上面的聚合演示了如何计算所有博物馆文档的 location 字段的质心。
以上聚合的响应
{
...
"aggregations": {
"centroid": {
"location": {
"lat": 51.00982965203002,
"lon": 3.9662131341174245
},
"count": 6
}
}
}
当与作为其他桶聚合的子聚合组合时，geo_centroid 聚合更有趣。
示例
resp = client.search(
index="museums",
size="0",
aggs={
"cities": {
"terms": {
"field": "city.keyword"
},
"aggs": {
"centroid": {
"geo_centroid": {
"field": "location"
}
}
}
}
},
)
print(resp)
response = client.search(
index: 'museums',
size: 0,
body: {
aggregations: {
cities: {
terms: {
field: 'city.keyword'
},
aggregations: {
centroid: {
geo_centroid: {
field: 'location'
}
}
}
}
}
}
)
puts response
const response = await client.search({
index: "museums",
size: 0,
aggs: {
cities: {
terms: {
field: "city.keyword",
},
aggs: {
centroid: {
geo_centroid: {
field: "location",
},
},
},
},
},
});
console.log(response);
POST /museums/_search?size=0
{
"aggs": {
"cities": {
"terms": { "field": "city.keyword" },
"aggs": {
"centroid": {
"geo_centroid": { "field": "location" }
}
}
}
}
}
上面的示例使用 geo_centroid 作为 词项 桶聚合的子聚合，用于查找每个城市中博物馆的中心位置。
以上聚合的响应
{
...
"aggregations": {
"cities": {
"sum_other_doc_count": 0,
"doc_count_error_upper_bound": 0,
"buckets": [
{
"key": "Amsterdam",
"doc_count": 3,
"centroid": {
"location": {
"lat": 52.371655656024814,
"lon": 4.909563297405839
},
"count": 3
}
},
{
"key": "Paris",
"doc_count": 2,
"centroid": {
"location": {
"lat": 48.86055548675358,
"lon": 2.3316944623366
},
"count": 2
}
},
{
"key": "Antwerp",
"doc_count": 1,
"centroid": {
"location": {
"lat": 51.22289997059852,
"lon": 4.40519998781383
},
"count": 1
}
}
]
}
}
}
geo_shape 字段上的地理质心聚合
编辑地理形状的质心度量比点的质心度量更精细。包含形状的特定聚合桶的质心是桶中最高维度形状类型的质心。例如，如果一个桶包含由多边形和线组成的形状，则线不参与质心度量。每种形状类型的质心计算方式都不同。通过 圆形 摄取的包络和圆形被视为多边形。
| 几何类型 | 质心计算 |
|---|---|
[多]点 |
所有坐标的等权重平均值 |
[多]线串 |
每个线段的质心的加权平均值，其中每个线段的权重是其以度为单位的长度 |
[多]边形 |
一个多边形的所有三角形质心的加权平均值，其中三角形由每两个连续顶点和起点形成。孔具有负权重。权重表示计算出的三角形的面积，单位为 deg^2 |
几何集合 |
所有具有最高维度的底层几何图形的质心。如果是多边形、直线和/或点，则忽略直线和/或点。如果是直线和点，则忽略点 |
示例
resp = client.indices.create(
index="places",
mappings={
"properties": {
"geometry": {
"type": "geo_shape"
}
}
},
)
print(resp)
resp1 = client.bulk(
index="places",
refresh=True,
operations=[
{
"index": {
"_id": 1
}
},
{
"name": "NEMO Science Museum",
"geometry": "POINT(4.912350 52.374081)"
},
{
"index": {
"_id": 2
}
},
{
"name": "Sportpark De Weeren",
"geometry": {
"type": "Polygon",
"coordinates": [
[
[
4.965305328369141,
52.39347642069457
],
[
4.966979026794433,
52.391721758934835
],
[
4.969425201416015,
52.39238958618537
],
[
4.967944622039794,
52.39420969150824
],
[
4.965305328369141,
52.39347642069457
]
]
]
}
}
],
)
print(resp1)
resp2 = client.search(
index="places",
size="0",
aggs={
"centroid": {
"geo_centroid": {
"field": "geometry"
}
}
},
)
print(resp2)
response = client.indices.create(
index: 'places',
body: {
mappings: {
properties: {
geometry: {
type: 'geo_shape'
}
}
}
}
)
puts response
response = client.bulk(
index: 'places',
refresh: true,
body: [
{
index: {
_id: 1
}
},
{
name: 'NEMO Science Museum',
geometry: 'POINT(4.912350 52.374081)'
},
{
index: {
_id: 2
}
},
{
name: 'Sportpark De Weeren',
geometry: {
type: 'Polygon',
coordinates: [
[
[
4.965305328369141,
52.39347642069457
],
[
4.966979026794433,
52.391721758934835
],
[
4.969425201416015,
52.39238958618537
],
[
4.967944622039794,
52.39420969150824
],
[
4.965305328369141,
52.39347642069457
]
]
]
}
}
]
)
puts response
response = client.search(
index: 'places',
size: 0,
body: {
aggregations: {
centroid: {
geo_centroid: {
field: 'geometry'
}
}
}
}
)
puts response
const response = await client.indices.create({
index: "places",
mappings: {
properties: {
geometry: {
type: "geo_shape",
},
},
},
});
console.log(response);
const response1 = await client.bulk({
index: "places",
refresh: "true",
operations: [
{
index: {
_id: 1,
},
},
{
name: "NEMO Science Museum",
geometry: "POINT(4.912350 52.374081)",
},
{
index: {
_id: 2,
},
},
{
name: "Sportpark De Weeren",
geometry: {
type: "Polygon",
coordinates: [
[
[4.965305328369141, 52.39347642069457],
[4.966979026794433, 52.391721758934835],
[4.969425201416015, 52.39238958618537],
[4.967944622039794, 52.39420969150824],
[4.965305328369141, 52.39347642069457],
],
],
},
},
],
});
console.log(response1);
const response2 = await client.search({
index: "places",
size: 0,
aggs: {
centroid: {
geo_centroid: {
field: "geometry",
},
},
},
});
console.log(response2);
PUT /places
{
"mappings": {
"properties": {
"geometry": {
"type": "geo_shape"
}
}
}
}
POST /places/_bulk?refresh
{"index":{"_id":1}}
{"name": "NEMO Science Museum", "geometry": "POINT(4.912350 52.374081)" }
{"index":{"_id":2}}
{"name": "Sportpark De Weeren", "geometry": { "type": "Polygon", "coordinates": [ [ [ 4.965305328369141, 52.39347642069457 ], [ 4.966979026794433, 52.391721758934835 ], [ 4.969425201416015, 52.39238958618537 ], [ 4.967944622039794, 52.39420969150824 ], [ 4.965305328369141, 52.39347642069457 ] ] ] } }
POST /places/_search?size=0
{
"aggs": {
"centroid": {
"geo_centroid": {
"field": "geometry"
}
}
}
}
{
...
"aggregations": {
"centroid": {
"location": {
"lat": 52.39296147599816,
"lon": 4.967404240742326
},
"count": 2
}
}
}
将 geo_centroid 用作 geohash_grid 的子聚合
geohash_grid 聚合将文档（而不是单个地理点）放入桶中。如果文档的 geo_point 字段包含多个值，则该文档可能会被分配到多个桶，即使其一个或多个地理点在桶边界之外。
如果还使用了 geocentroid 子聚合，则每个质心都使用桶中的所有地理点计算，包括桶边界之外的地理点。这可能会导致质心位于桶边界之外。