Geohash 网格聚合
编辑Geohash 网格聚合
编辑一种多桶聚合，它将 geo_point 和 geo_shape 值分组到表示网格的桶中。生成的网格可以是稀疏的，并且仅包含具有匹配数据的单元格。每个单元格都使用 geohash 进行标记，该 geohash 的精度是用户可定义的。
- 高精度 geohash 具有较长的字符串长度，并表示仅覆盖小区域的单元格。
- 低精度 geohash 具有较短的字符串长度，并表示每个覆盖大面积的单元格。
此聚合中使用的 Geohash 可以选择 1 到 12 之间的精度。
长度为 12 的最高精度 geohash 生成的单元格覆盖面积小于一平方米，因此高精度请求在 RAM 和结果大小方面可能非常昂贵。请参阅下面的示例，了解如何在请求高细节级别之前首先将聚合过滤到较小的地理区域。
您只能使用 geohash_grid 来聚合显式映射的 geo_point 或 geo_shape 字段。如果 geo_point 字段包含一个数组，则 geohash_grid 会聚合所有数组值。
简单的低精度请求
编辑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",
aggregations={
"large-grid": {
"geohash_grid": {
"field": "location",
"precision": 3
}
}
},
)
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: {
"large-grid": {
geohash_grid: {
field: 'location',
precision: 3
}
}
}
}
)
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,
aggregations: {
"large-grid": {
geohash_grid: {
field: "location",
precision: 3,
},
},
},
});
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
{
"aggregations": {
"large-grid": {
"geohash_grid": {
"field": "location",
"precision": 3
}
}
}
}
响应
{
...
"aggregations": {
"large-grid": {
"buckets": [
{
"key": "u17",
"doc_count": 3
},
{
"key": "u09",
"doc_count": 2
},
{
"key": "u15",
"doc_count": 1
}
]
}
}
}
高精度请求
编辑当请求详细的桶时（通常用于显示“放大”的地图），应应用类似 geo_bounding_box 的过滤器来缩小主题区域，否则可能会创建并返回数百万个桶。
resp = client.search(
index="museums",
size="0",
aggregations={
"zoomed-in": {
"filter": {
"geo_bounding_box": {
"location": {
"top_left": "POINT (4.9 52.4)",
"bottom_right": "POINT (5.0 52.3)"
}
}
},
"aggregations": {
"zoom1": {
"geohash_grid": {
"field": "location",
"precision": 8
}
}
}
}
},
)
print(resp)
response = client.search(
index: 'museums',
size: 0,
body: {
aggregations: {
"zoomed-in": {
filter: {
geo_bounding_box: {
location: {
top_left: 'POINT (4.9 52.4)',
bottom_right: 'POINT (5.0 52.3)'
}
}
},
aggregations: {
"zoom1": {
geohash_grid: {
field: 'location',
precision: 8
}
}
}
}
}
}
)
puts response
const response = await client.search({
index: "museums",
size: 0,
aggregations: {
"zoomed-in": {
filter: {
geo_bounding_box: {
location: {
top_left: "POINT (4.9 52.4)",
bottom_right: "POINT (5.0 52.3)",
},
},
},
aggregations: {
zoom1: {
geohash_grid: {
field: "location",
precision: 8,
},
},
},
},
},
});
console.log(response);
POST /museums/_search?size=0
{
"aggregations": {
"zoomed-in": {
"filter": {
"geo_bounding_box": {
"location": {
"top_left": "POINT (4.9 52.4)",
"bottom_right": "POINT (5.0 52.3)"
}
}
},
"aggregations": {
"zoom1": {
"geohash_grid": {
"field": "location",
"precision": 8
}
}
}
}
}
}
geohash_grid 聚合返回的 geohash 也可用于放大。要放大上一个示例中返回的第一个 geohash u17，应将其指定为 top_left 和 bottom_right 角。
resp = client.search(
index="museums",
size="0",
aggregations={
"zoomed-in": {
"filter": {
"geo_bounding_box": {
"location": {
"top_left": "u17",
"bottom_right": "u17"
}
}
},
"aggregations": {
"zoom1": {
"geohash_grid": {
"field": "location",
"precision": 8
}
}
}
}
},
)
print(resp)
response = client.search(
index: 'museums',
size: 0,
body: {
aggregations: {
"zoomed-in": {
filter: {
geo_bounding_box: {
location: {
top_left: 'u17',
bottom_right: 'u17'
}
}
},
aggregations: {
"zoom1": {
geohash_grid: {
field: 'location',
precision: 8
}
}
}
}
}
}
)
puts response
const response = await client.search({
index: "museums",
size: 0,
aggregations: {
"zoomed-in": {
filter: {
geo_bounding_box: {
location: {
top_left: "u17",
bottom_right: "u17",
},
},
},
aggregations: {
zoom1: {
geohash_grid: {
field: "location",
precision: 8,
},
},
},
},
},
});
console.log(response);
POST /museums/_search?size=0
{
"aggregations": {
"zoomed-in": {
"filter": {
"geo_bounding_box": {
"location": {
"top_left": "u17",
"bottom_right": "u17"
}
}
},
"aggregations": {
"zoom1": {
"geohash_grid": {
"field": "location",
"precision": 8
}
}
}
}
}
}
{
...
"aggregations": {
"zoomed-in": {
"doc_count": 3,
"zoom1": {
"buckets": [
{
"key": "u173zy3j",
"doc_count": 1
},
{
"key": "u173zvfz",
"doc_count": 1
},
{
"key": "u173zt90",
"doc_count": 1
}
]
}
}
}
}
对于不支持 geohash 的系统上的“放大”，应使用可用的 geohash 库之一将桶键转换为边界框。例如，对于 javascript，可以使用 node-geohash 库
var geohash = require('ngeohash');
// bbox will contain [ 52.03125, 4.21875, 53.4375, 5.625 ]
// [ minlat, minlon, maxlat, maxlon]
var bbox = geohash.decode_bbox('u17');
带有附加边界框过滤的请求
编辑geohash_grid 聚合支持一个可选的 bounds 参数，该参数将考虑的单元格限制为与提供的边界相交的单元格。bounds 参数接受边界框，其格式与地理边界框查询中指定的边界的所有 接受的格式相同。此边界框可以与聚合上下文中的任何其他 geo_bounding_box 查询一起使用，也可以不使用。它是一个独立的边界框，可以与在聚合上下文中定义的任何其他 geo_bounding_box 查询相交、相等或不相交。
resp = client.search(
index="museums",
size="0",
aggregations={
"tiles-in-bounds": {
"geohash_grid": {
"field": "location",
"precision": 8,
"bounds": {
"top_left": "POINT (4.21875 53.4375)",
"bottom_right": "POINT (5.625 52.03125)"
}
}
}
},
)
print(resp)
response = client.search(
index: 'museums',
size: 0,
body: {
aggregations: {
"tiles-in-bounds": {
geohash_grid: {
field: 'location',
precision: 8,
bounds: {
top_left: 'POINT (4.21875 53.4375)',
bottom_right: 'POINT (5.625 52.03125)'
}
}
}
}
}
)
puts response
const response = await client.search({
index: "museums",
size: 0,
aggregations: {
"tiles-in-bounds": {
geohash_grid: {
field: "location",
precision: 8,
bounds: {
top_left: "POINT (4.21875 53.4375)",
bottom_right: "POINT (5.625 52.03125)",
},
},
},
},
});
console.log(response);
POST /museums/_search?size=0
{
"aggregations": {
"tiles-in-bounds": {
"geohash_grid": {
"field": "location",
"precision": 8,
"bounds": {
"top_left": "POINT (4.21875 53.4375)",
"bottom_right": "POINT (5.625 52.03125)"
}
}
}
}
}
{
...
"aggregations": {
"tiles-in-bounds": {
"buckets": [
{
"key": "u173zy3j",
"doc_count": 1
},
{
"key": "u173zvfz",
"doc_count": 1
},
{
"key": "u173zt90",
"doc_count": 1
}
]
}
}
}
赤道的单元格尺寸
编辑下表显示了 geohash 的各种字符串长度所覆盖的单元格的度量尺寸。单元格尺寸随纬度而变化，因此该表适用于赤道的最坏情况。
|
GeoHash 长度 |
区域宽度 x 高度 |
|
1 |
5,009.4km x 4,992.6km |
|
2 |
1,252.3km x 624.1km |
|
3 |
156.5km x 156km |
|
4 |
39.1km x 19.5km |
|
5 |
4.9km x 4.9km |
|
6 |
1.2km x 609.4m |
|
7 |
152.9m x 152.4m |
|
8 |
38.2m x 19m |
|
9 |
4.8m x 4.8m |
|
10 |
1.2m x 59.5cm |
|
11 |
14.9cm x 14.9cm |
|
12 |
3.7cm x 1.9cm |
聚合 geo_shape 字段
编辑对 Geoshape 字段进行聚合的工作方式与对点进行聚合的方式相同，只是一个形状可以在多个图块中进行计数。如果形状的任何部分与该图块相交，则该形状将计入匹配值的计数。下面是一张演示此情况的图像
选项
编辑|
field |
必填。包含索引的地理坐标点或地理形状值的字段。必须显式映射为 |
|
precision |
可选。用于定义结果中单元格/桶的 geohash 的字符串长度。默认为 5。精度可以根据上述整数精度级别定义。将拒绝 [1,12] 之外的值。或者，可以从诸如“1km”、“10m”之类的距离度量来近似精度级别。精度级别的计算方式是，单元格不会超过所需精度的指定大小（对角线）。当这导致高于支持的 12 级的精度级别时（例如，对于小于 5.6 厘米的距离），该值将被拒绝。 |
|
bounds |
可选。用于过滤桶中点的边界框。 |
|
size |
可选。要返回的最大 geohash 桶数（默认为 10,000）。当结果被修剪时，桶会根据它们包含的文档量进行优先级排序。 |
|
shard_size |
可选。为了更准确地计算最终结果中返回的顶部单元格，聚合默认为从每个分片返回 |