求和聚合
编辑求和聚合
编辑一个 单值 指标聚合，它将从聚合文档中提取的数值相加。这些值可以从特定的数值或 直方图 字段中提取。
假设数据包含代表销售记录的文档，我们可以将所有帽子的销售价格求和，如下所示：
resp = client.search(
index="sales",
size="0",
query={
"constant_score": {
"filter": {
"match": {
"type": "hat"
}
}
}
},
aggs={
"hat_prices": {
"sum": {
"field": "price"
}
}
},
)
print(resp)
response = client.search(
index: 'sales',
size: 0,
body: {
query: {
constant_score: {
filter: {
match: {
type: 'hat'
}
}
}
},
aggregations: {
hat_prices: {
sum: {
field: 'price'
}
}
}
}
)
puts response
const response = await client.search({
index: "sales",
size: 0,
query: {
constant_score: {
filter: {
match: {
type: "hat",
},
},
},
},
aggs: {
hat_prices: {
sum: {
field: "price",
},
},
},
});
console.log(response);
POST /sales/_search?size=0
{
"query": {
"constant_score": {
"filter": {
"match": { "type": "hat" }
}
}
},
"aggs": {
"hat_prices": { "sum": { "field": "price" } }
}
}
结果为：
{
...
"aggregations": {
"hat_prices": {
"value": 450.0
}
}
}
聚合的名称（上面的 hat_prices）也作为从返回的响应中检索聚合结果的键。
脚本
编辑如果需要获得比单个字段更复杂的 sum，请在 运行时字段上运行聚合。
resp = client.search(
index="sales",
size="0",
runtime_mappings={
"price.weighted": {
"type": "double",
"script": "\n double price = doc['price'].value;\n if (doc['promoted'].value) {\n price *= 0.8;\n }\n emit(price);\n "
}
},
query={
"constant_score": {
"filter": {
"match": {
"type": "hat"
}
}
}
},
aggs={
"hat_prices": {
"sum": {
"field": "price.weighted"
}
}
},
)
print(resp)
response = client.search(
index: 'sales',
size: 0,
body: {
runtime_mappings: {
'price.weighted' => {
type: 'double',
script: "\n double price = doc['price'].value;\n if (doc['promoted'].value) {\n price *= 0.8;\n }\n emit(price);\n "
}
},
query: {
constant_score: {
filter: {
match: {
type: 'hat'
}
}
}
},
aggregations: {
hat_prices: {
sum: {
field: 'price.weighted'
}
}
}
}
)
puts response
const response = await client.search({
index: "sales",
size: 0,
runtime_mappings: {
"price.weighted": {
type: "double",
script:
"\n double price = doc['price'].value;\n if (doc['promoted'].value) {\n price *= 0.8;\n }\n emit(price);\n ",
},
},
query: {
constant_score: {
filter: {
match: {
type: "hat",
},
},
},
},
aggs: {
hat_prices: {
sum: {
field: "price.weighted",
},
},
},
});
console.log(response);
POST /sales/_search?size=0
{
"runtime_mappings": {
"price.weighted": {
"type": "double",
"script": """
double price = doc['price'].value;
if (doc['promoted'].value) {
price *= 0.8;
}
emit(price);
"""
}
},
"query": {
"constant_score": {
"filter": {
"match": { "type": "hat" }
}
}
},
"aggs": {
"hat_prices": {
"sum": {
"field": "price.weighted"
}
}
}
}
缺失值
编辑missing 参数定义了如何处理缺少值的文档。默认情况下，缺少值的文档将被忽略，但也可能将它们视为具有值。例如，以下示例将所有没有价格的帽子销售额视为 100。
resp = client.search(
index="sales",
size="0",
query={
"constant_score": {
"filter": {
"match": {
"type": "hat"
}
}
}
},
aggs={
"hat_prices": {
"sum": {
"field": "price",
"missing": 100
}
}
},
)
print(resp)
response = client.search(
index: 'sales',
size: 0,
body: {
query: {
constant_score: {
filter: {
match: {
type: 'hat'
}
}
}
},
aggregations: {
hat_prices: {
sum: {
field: 'price',
missing: 100
}
}
}
}
)
puts response
const response = await client.search({
index: "sales",
size: 0,
query: {
constant_score: {
filter: {
match: {
type: "hat",
},
},
},
},
aggs: {
hat_prices: {
sum: {
field: "price",
missing: 100,
},
},
},
});
console.log(response);
直方图字段
编辑当在 直方图字段上计算总和时，聚合的结果是 values 数组中所有元素乘以 counts 数组中相同位置的数字的总和。
例如，对于以下索引，它存储了不同网络的延迟指标的预聚合直方图：
resp = client.indices.create(
index="metrics_index",
mappings={
"properties": {
"latency_histo": {
"type": "histogram"
}
}
},
)
print(resp)
resp1 = client.index(
index="metrics_index",
id="1",
refresh=True,
document={
"network.name": "net-1",
"latency_histo": {
"values": [
0.1,
0.2,
0.3,
0.4,
0.5
],
"counts": [
3,
7,
23,
12,
6
]
}
},
)
print(resp1)
resp2 = client.index(
index="metrics_index",
id="2",
refresh=True,
document={
"network.name": "net-2",
"latency_histo": {
"values": [
0.1,
0.2,
0.3,
0.4,
0.5
],
"counts": [
8,
17,
8,
7,
6
]
}
},
)
print(resp2)
resp3 = client.search(
index="metrics_index",
size="0",
filter_path="aggregations",
aggs={
"total_latency": {
"sum": {
"field": "latency_histo"
}
}
},
)
print(resp3)
response = client.indices.create(
index: 'metrics_index',
body: {
mappings: {
properties: {
latency_histo: {
type: 'histogram'
}
}
}
}
)
puts response
response = client.index(
index: 'metrics_index',
id: 1,
refresh: true,
body: {
'network.name' => 'net-1',
latency_histo: {
values: [
0.1,
0.2,
0.3,
0.4,
0.5
],
counts: [
3,
7,
23,
12,
6
]
}
}
)
puts response
response = client.index(
index: 'metrics_index',
id: 2,
refresh: true,
body: {
'network.name' => 'net-2',
latency_histo: {
values: [
0.1,
0.2,
0.3,
0.4,
0.5
],
counts: [
8,
17,
8,
7,
6
]
}
}
)
puts response
response = client.search(
index: 'metrics_index',
size: 0,
filter_path: 'aggregations',
body: {
aggregations: {
total_latency: {
sum: {
field: 'latency_histo'
}
}
}
}
)
puts response
const response = await client.indices.create({
index: "metrics_index",
mappings: {
properties: {
latency_histo: {
type: "histogram",
},
},
},
});
console.log(response);
const response1 = await client.index({
index: "metrics_index",
id: 1,
refresh: "true",
document: {
"network.name": "net-1",
latency_histo: {
values: [0.1, 0.2, 0.3, 0.4, 0.5],
counts: [3, 7, 23, 12, 6],
},
},
});
console.log(response1);
const response2 = await client.index({
index: "metrics_index",
id: 2,
refresh: "true",
document: {
"network.name": "net-2",
latency_histo: {
values: [0.1, 0.2, 0.3, 0.4, 0.5],
counts: [8, 17, 8, 7, 6],
},
},
});
console.log(response2);
const response3 = await client.search({
index: "metrics_index",
size: 0,
filter_path: "aggregations",
aggs: {
total_latency: {
sum: {
field: "latency_histo",
},
},
},
});
console.log(response3);
PUT metrics_index
{
"mappings": {
"properties": {
"latency_histo": { "type": "histogram" }
}
}
}
PUT metrics_index/_doc/1?refresh
{
"network.name" : "net-1",
"latency_histo" : {
"values" : [0.1, 0.2, 0.3, 0.4, 0.5],
"counts" : [3, 7, 23, 12, 6]
}
}
PUT metrics_index/_doc/2?refresh
{
"network.name" : "net-2",
"latency_histo" : {
"values" : [0.1, 0.2, 0.3, 0.4, 0.5],
"counts" : [8, 17, 8, 7, 6]
}
}
POST /metrics_index/_search?size=0&filter_path=aggregations
{
"aggs" : {
"total_latency" : { "sum" : { "field" : "latency_histo" } }
}
}
对于每个直方图字段，sum 聚合将 values 数组中的每个数字与其在 counts 数组中的关联计数相乘。
最终，它将添加所有直方图的所有值并返回以下结果：
{
"aggregations": {
"total_latency": {
"value": 28.8
}
}
}