$stdDevSamp

8.0.1 版的新功能。

Amazon DocumentDB 中的$stdDevSamp運算子會計算數值的範例標準差。作為累積器，它會計算彙總管道$group階段中群組內文件之間的範例標準差。做為表達式，它會計算數字陣列的樣本標準差。範例標準差使用 N-1 做為除數 (Bessel 的校正）。會忽略非數值。如果少於兩個數值，則會傳回 null。

參數

• expression：解析為數值或數值陣列的表達式。

範例 (MongoDB Shell)

下列範例示範如何使用 $stdDevSamp 運算子來計算每個主題的分數範例標準差。

建立範例文件

db.scores.insertMany([
  { subject: "math", score: 80 },
  { subject: "math", score: 90 },
  { subject: "math", score: 85 },
  { subject: "math", score: 95 },
  { subject: "science", score: 70 },
  { subject: "science", score: 75 },
  { subject: "science", score: 80 },
  { subject: "science", score: 85 }
]);

查詢範例

db.scores.aggregate([
  { $group: {
      _id: "$subject",
      stdDev: { $stdDevSamp: "$score" }
    }}
]);

輸出

[
  { "_id": "math", "stdDev": 6.454972243679028 },
  { "_id": "science", "stdDev": 6.454972243679028 }
]

表達式用量範例 (MongoDB Shell)

運算$stdDevSamp子也可以用作$project階段內的表達式，以計算陣列欄位的範例標準差。

建立範例文件

db.experiments.insertMany([
  { _id: 1, measurements: [10, 12, 14, 16, 18] },
  { _id: 2, measurements: [5, 5, 5, 5, 5] },
  { _id: 3, measurements: [2, 4, 6, 8, 10] }
]);

查詢範例

db.experiments.aggregate([
  { $project: {
      stdDev: { $stdDevSamp: "$measurements" }
    }}
]);

輸出

[
  { "_id": 1, "stdDev": 3.1622776601683795 },
  { "_id": 2, "stdDev": 0 },
  { "_id": 3, "stdDev": 3.1622776601683795 }
]

視窗運算子用量範例 (MongoDB Shell)

8.0.2 版的新功能。

該$stdDevSamp運算子也可以用作$setWindowFields階段中的視窗運算子。在這種情況下，它會傳回每個視窗中文件指定表達式的範例標準差。您可以在 output 欄位下指定運算子，並選擇性地使用window文件定義視窗邊界。

建立範例文件

db.sensorReadings.insertMany([
  { _id: 1, sensor: "A", time: 1, value: 2 },
  { _id: 2, sensor: "A", time: 2, value: 4 },
  { _id: 3, sensor: "A", time: 3, value: 6 },
  { _id: 4, sensor: "B", time: 1, value: 10 },
  { _id: 5, sensor: "B", time: 2, value: 12 }
]);

查詢範例

下列範例會依 分割文件sensor、依 排序每個分割區time，並傳回value從分割區開始到目前文件的執行中範例標準差 。

db.sensorReadings.aggregate([
  {
    $setWindowFields: {
      partitionBy: "$sensor",
      sortBy: { time: 1 },
      output: {
        runningStdDev: {
          $stdDevSamp: "$value",
          window: { documents: ["unbounded", "current"] }
        }
      }
    }
  }
]);

輸出

[
  { "_id": 1, "sensor": "A", "time": 1, "value": 2, "runningStdDev": null },
  { "_id": 2, "sensor": "A", "time": 2, "value": 4, "runningStdDev": 1.4142135623730951 },
  { "_id": 3, "sensor": "A", "time": 3, "value": 6, "runningStdDev": 2 },
  { "_id": 4, "sensor": "B", "time": 1, "value": 10, "runningStdDev": null },
  { "_id": 5, "sensor": "B", "time": 2, "value": 12, "runningStdDev": 1.4142135623730951 }
]

每個文件都會以 擴增runningStdDev，這是其分割區value內直到並包含目前文件的 範例標準差。當視窗包含少於兩個值 （每個分割區中的第一個文件） 時， $stdDevSamp會傳回 null。

程式碼範例

若要檢視使用 $stdDevSamp 運算子的程式碼範例，請選擇您要使用的語言標籤。下列範例顯示累積器用量 （在 中$group)、表達式用量 （在 中$project) 和視窗運算子用量 （在 中$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: stdDevSamp across grouped documents
    const scores = db.collection('scores');
    await scores.insertMany([
      { subject: "math", score: 80 },
      { subject: "math", score: 90 },
      { subject: "math", score: 85 },
      { subject: "math", score: 95 },
      { subject: "science", score: 70 },
      { subject: "science", score: 75 },
      { subject: "science", score: 80 },
      { subject: "science", score: 85 }
    ]);
    const accumulatorResult = await scores.aggregate([
      { $group: {
          _id: "$subject",
          stdDev: { $stdDevSamp: "$score" }
        }}
    ]).toArray();
    console.log('Accumulator result:', accumulatorResult);

    // Expression usage: stdDevSamp of an array field
    const experiments = db.collection('experiments');
    await experiments.insertMany([
      { _id: 1, measurements: [10, 12, 14, 16, 18] },
      { _id: 2, measurements: [5, 5, 5, 5, 5] },
      { _id: 3, measurements: [2, 4, 6, 8, 10] }
    ]);
    const expressionResult = await experiments.aggregate([
      { $project: {
          stdDev: { $stdDevSamp: "$measurements" }
        }}
    ]).toArray();
    console.log('Expression result:', expressionResult);

    // Window operator usage: running stdDevSamp within each partition
    const sensorReadings = db.collection('sensorReadings');
    await sensorReadings.insertMany([
      { _id: 1, sensor: "A", time: 1, value: 2 },
      { _id: 2, sensor: "A", time: 2, value: 4 },
      { _id: 3, sensor: "A", time: 3, value: 6 },
      { _id: 4, sensor: "B", time: 1, value: 10 },
      { _id: 5, sensor: "B", time: 2, value: 12 }
    ]);
    const windowResult = await sensorReadings.aggregate([
      {
        $setWindowFields: {
          partitionBy: "$sensor",
          sortBy: { time: 1 },
          output: {
            runningStdDev: {
              $stdDevSamp: "$value",
              window: { documents: ["unbounded", "current"] }
            }
          }
        }
      }
    ]).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: stdDevSamp across grouped documents
        scores = db['scores']
        scores.insert_many([
            { 'subject': 'math', 'score': 80 },
            { 'subject': 'math', 'score': 90 },
            { 'subject': 'math', 'score': 85 },
            { 'subject': 'math', 'score': 95 },
            { 'subject': 'science', 'score': 70 },
            { 'subject': 'science', 'score': 75 },
            { 'subject': 'science', 'score': 80 },
            { 'subject': 'science', 'score': 85 }
        ])
        accumulator_result = list(scores.aggregate([
            { '$group': {
                '_id': '$subject',
                'stdDev': { '$stdDevSamp': '$score' }
            }}
        ]))
        print('Accumulator result:', accumulator_result)

        # Expression usage: stdDevSamp of an array field
        experiments = db['experiments']
        experiments.insert_many([
            { '_id': 1, 'measurements': [10, 12, 14, 16, 18] },
            { '_id': 2, 'measurements': [5, 5, 5, 5, 5] },
            { '_id': 3, 'measurements': [2, 4, 6, 8, 10] }
        ])
        expression_result = list(experiments.aggregate([
            { '$project': {
                'stdDev': { '$stdDevSamp': '$measurements' }
            }}
        ]))
        print('Expression result:', expression_result)

        # Window operator usage: running stdDevSamp within each partition
        sensor_readings = db['sensorReadings']
        sensor_readings.insert_many([
            { '_id': 1, 'sensor': 'A', 'time': 1, 'value': 2 },
            { '_id': 2, 'sensor': 'A', 'time': 2, 'value': 4 },
            { '_id': 3, 'sensor': 'A', 'time': 3, 'value': 6 },
            { '_id': 4, 'sensor': 'B', 'time': 1, 'value': 10 },
            { '_id': 5, 'sensor': 'B', 'time': 2, 'value': 12 }
        ])
        window_result = list(sensor_readings.aggregate([
            {
                '$setWindowFields': {
                    'partitionBy': '$sensor',
                    'sortBy': { 'time': 1 },
                    'output': {
                        'runningStdDev': {
                            '$stdDevSamp': '$value',
                            'window': { 'documents': ['unbounded', 'current'] }
                        }
                    }
                }
            }
        ]))
        print('Window result:', window_result)

    finally:
        client.close()

example()