本文属于机器翻译版本。若本译文内容与英语原文存在差异，则一律以英文原文为准。
$百分位数
8.0.1 版中的新增内容。
Amazon DocumentDB 中的$percentile运算符计算数字数据的指定百分位值。作为累加器，它在聚合管道$group阶段计算组内文档的百分位值。作为表达式，它计算数字数组的百分位数。
参数
-
input：解析为数值或数值数组的表达式。
-
p：介于 0 和 1 之间的百分位数值的数组，其中每个值代表要计算的百分位数。例如，[0.25, 0.5, 0.75]计算第 25、50 和 75 个百分位数。
-
method：指定计算方法的字符串。目前仅支持 "approximate"。
行为
该"approximate"方法使用 t-digest 算法来计算基于百分位数的近似指标。对于小型数据集，不同的百分位数值可能会解析为相同的结果。例如，如果每组只有 5 个值，则 p90 和 p99 都可能返回该组中的最大值。随着数据点数量的增加，精度也会提高。
示例（MongoDB Shell）
以下示例说明如何使用$percentile运算符计算每个班级分数的第 25 和第 75 个百分位数。
创建示例文档
db.students.insertMany([
{ class: "A", score: 72 },
{ class: "A", score: 85 },
{ class: "A", score: 90 },
{ class: "A", score: 68 },
{ class: "A", score: 95 },
{ class: "B", score: 80 },
{ class: "B", score: 75 },
{ class: "B", score: 92 },
{ class: "B", score: 88 },
{ class: "B", score: 70 }
]);
查询示例
db.students.aggregate([
{ $group: {
_id: "$class",
percentiles: { $percentile: { input: "$score", p: [0.25, 0.75], method: "approximate" } }
}}
]);
输出
[
{ "_id": "A", "percentiles": [72, 90] },
{ "_id": "B", "percentiles": [75, 88] }
]
表达式用法示例（MongoDB Shell）
该$percentile运算符还可用作$project阶段内的表达式来计算数组字段的百分位数。
创建示例文档
db.surveys.insertMany([
{ _id: 1, responses: [2, 4, 6, 8, 10, 12, 14, 16, 18, 20] },
{ _id: 2, responses: [1, 3, 5, 7, 9, 11, 13, 15, 17, 19] }
]);
查询示例
db.surveys.aggregate([
{ $project: {
quartiles: { $percentile: { input: "$responses", p: [0.25, 0.5, 0.75], method: "approximate" } }
}}
]);
输出
[
{ "_id": 1, "quartiles": [6, 10, 16] },
{ "_id": 2, "quartiles": [5, 9, 15] }
]
窗口运算符用法示例（MongoDB Shell）
8.0.2 版中的新内容。
该$percentile操作员还可以在$setWindowFields舞台中用作窗口操作员。在这种情况下，它计算每个窗口中文档的指定百分位值。您可以在output字段下指定运算符，也可以选择使用window文档定义窗口边界。
在中用作窗口运算符时$setWindowFields，中间数据限制$percentile为 100 MB。超过此限制的操作会返回错误。
创建示例文档
db.sensorData.insertMany([
{ _id: 1, sensor: "A", reading: 72 },
{ _id: 2, sensor: "A", reading: 85 },
{ _id: 3, sensor: "A", reading: 90 },
{ _id: 4, sensor: "A", reading: 68 },
{ _id: 5, sensor: "A", reading: 95 },
{ _id: 6, sensor: "B", reading: 80 },
{ _id: 7, sensor: "B", reading: 75 },
{ _id: 8, sensor: "B", reading: 92 },
{ _id: 9, sensor: "B", reading: 88 },
{ _id: 10, sensor: "B", reading: 70 }
]);
查询示例
以下示例按文档分区，sensor并计算每个分区中所有文档的第 25 和第 75 reading 个百分位数。
db.sensorData.aggregate([
{
$setWindowFields: {
partitionBy: "$sensor",
output: {
readingPercentiles: {
$percentile: { input: "$reading", p: [0.25, 0.75], method: "approximate" },
window: { documents: ["unbounded", "unbounded"] }
}
}
}
}
]);
输出
[
{ "_id": 1, "sensor": "A", "reading": 72, "readingPercentiles": [72, 90] },
{ "_id": 2, "sensor": "A", "reading": 85, "readingPercentiles": [72, 90] },
{ "_id": 3, "sensor": "A", "reading": 90, "readingPercentiles": [72, 90] },
{ "_id": 4, "sensor": "A", "reading": 68, "readingPercentiles": [72, 90] },
{ "_id": 5, "sensor": "A", "reading": 95, "readingPercentiles": [72, 90] },
{ "_id": 6, "sensor": "B", "reading": 80, "readingPercentiles": [75, 88] },
{ "_id": 7, "sensor": "B", "reading": 75, "readingPercentiles": [75, 88] },
{ "_id": 8, "sensor": "B", "reading": 92, "readingPercentiles": [75, 88] },
{ "_id": 9, "sensor": "B", "reading": 88, "readingPercentiles": [75, 88] },
{ "_id": 10, "sensor": "B", "reading": 70, "readingPercentiles": [75, 88] }
]
每个文档都增加了其分readingPercentiles区中所有文档的大约第 25 和第 75 reading 个百分位数。
代码示例
要查看使用$percentile运算符的代码示例，请选择要使用的语言的选项卡。以下示例显示累加器的用法 (in$group)、表达式的用法 (in$project) 和窗口运算符的用法 (in$setWindowFields)：
- Node.js
-
const { MongoClient } = require('mongodb');
async function example() {
const uri = 'mongodb://<username>:<password>@<cluster-endpoint>:27017/?tls=true&tlsCAFile=global-bundle.pem&replicaSet=rs0&readPreference=secondaryPreferred&retryWrites=false';
const client = new MongoClient(uri);
try {
await client.connect();
const db = client.db('test');
// Accumulator usage: percentiles across grouped documents
const students = db.collection('students');
await students.insertMany([
{ class: "A", score: 72 },
{ class: "A", score: 85 },
{ class: "A", score: 90 },
{ class: "A", score: 68 },
{ class: "A", score: 95 },
{ class: "B", score: 80 },
{ class: "B", score: 75 },
{ class: "B", score: 92 },
{ class: "B", score: 88 },
{ class: "B", score: 70 }
]);
const accumulatorResult = await students.aggregate([
{ $group: {
_id: "$class",
percentiles: { $percentile: { input: "$score", p: [0.25, 0.75], method: "approximate" } }
}}
]).toArray();
console.log('Accumulator result:', accumulatorResult);
// Expression usage: percentiles of an array field
const surveys = db.collection('surveys');
await surveys.insertMany([
{ _id: 1, responses: [2, 4, 6, 8, 10, 12, 14, 16, 18, 20] },
{ _id: 2, responses: [1, 3, 5, 7, 9, 11, 13, 15, 17, 19] }
]);
const expressionResult = await surveys.aggregate([
{ $project: {
quartiles: { $percentile: { input: "$responses", p: [0.25, 0.5, 0.75], method: "approximate" } }
}}
]).toArray();
console.log('Expression result:', expressionResult);
// Window operator usage: percentiles across each partition
const sensorData = db.collection('sensorData');
await sensorData.insertMany([
{ _id: 1, sensor: "A", reading: 72 },
{ _id: 2, sensor: "A", reading: 85 },
{ _id: 3, sensor: "A", reading: 90 },
{ _id: 4, sensor: "A", reading: 68 },
{ _id: 5, sensor: "A", reading: 95 },
{ _id: 6, sensor: "B", reading: 80 },
{ _id: 7, sensor: "B", reading: 75 },
{ _id: 8, sensor: "B", reading: 92 },
{ _id: 9, sensor: "B", reading: 88 },
{ _id: 10, sensor: "B", reading: 70 }
]);
const windowResult = await sensorData.aggregate([
{
$setWindowFields: {
partitionBy: "$sensor",
output: {
readingPercentiles: {
$percentile: { input: "$reading", p: [0.25, 0.75], method: "approximate" },
window: { documents: ["unbounded", "unbounded"] }
}
}
}
}
]).toArray();
console.log('Window result:', windowResult);
} finally {
await client.close();
}
}
example();
- Python
-
from pymongo import MongoClient
def example():
client = MongoClient('mongodb://<username>:<password>@<cluster-endpoint>:27017/?tls=true&tlsCAFile=global-bundle.pem&replicaSet=rs0&readPreference=secondaryPreferred&retryWrites=false')
try:
db = client['test']
# Accumulator usage: percentiles across grouped documents
students = db['students']
students.insert_many([
{ 'class': 'A', 'score': 72 },
{ 'class': 'A', 'score': 85 },
{ 'class': 'A', 'score': 90 },
{ 'class': 'A', 'score': 68 },
{ 'class': 'A', 'score': 95 },
{ 'class': 'B', 'score': 80 },
{ 'class': 'B', 'score': 75 },
{ 'class': 'B', 'score': 92 },
{ 'class': 'B', 'score': 88 },
{ 'class': 'B', 'score': 70 }
])
accumulator_result = list(students.aggregate([
{ '$group': {
'_id': '$class',
'percentiles': { '$percentile': { 'input': '$score', 'p': [0.25, 0.75], 'method': 'approximate' } }
}}
]))
print('Accumulator result:', accumulator_result)
# Expression usage: percentiles of an array field
surveys = db['surveys']
surveys.insert_many([
{ '_id': 1, 'responses': [2, 4, 6, 8, 10, 12, 14, 16, 18, 20] },
{ '_id': 2, 'responses': [1, 3, 5, 7, 9, 11, 13, 15, 17, 19] }
])
expression_result = list(surveys.aggregate([
{ '$project': {
'quartiles': { '$percentile': { 'input': '$responses', 'p': [0.25, 0.5, 0.75], 'method': 'approximate' } }
}}
]))
print('Expression result:', expression_result)
# Window operator usage: percentiles across each partition
sensor_data = db['sensorData']
sensor_data.insert_many([
{ '_id': 1, 'sensor': 'A', 'reading': 72 },
{ '_id': 2, 'sensor': 'A', 'reading': 85 },
{ '_id': 3, 'sensor': 'A', 'reading': 90 },
{ '_id': 4, 'sensor': 'A', 'reading': 68 },
{ '_id': 5, 'sensor': 'A', 'reading': 95 },
{ '_id': 6, 'sensor': 'B', 'reading': 80 },
{ '_id': 7, 'sensor': 'B', 'reading': 75 },
{ '_id': 8, 'sensor': 'B', 'reading': 92 },
{ '_id': 9, 'sensor': 'B', 'reading': 88 },
{ '_id': 10, 'sensor': 'B', 'reading': 70 }
])
window_result = list(sensor_data.aggregate([
{
'$setWindowFields': {
'partitionBy': '$sensor',
'output': {
'readingPercentiles': {
'$percentile': { 'input': '$reading', 'p': [0.25, 0.75], 'method': 'approximate' },
'window': { 'documents': ['unbounded', 'unbounded'] }
}
}
}
}
]))
print('Window result:', window_result)
finally:
client.close()
example()
