$bucket (aggregation stage)（聚合阶段）

Bucket by Year and Filter by Bucket Results按年份和按桶结果筛选

In mongosh, create a sample collection named artists with the following documents:在mongosh中，使用以下文档创建一个名为artists的样本集：

db.artists.insertMany([
  { "_id" : 1, "last_name" : "Bernard", "first_name" : "Emil", "year_born" : 1868, "year_died" : 1941, "nationality" : "France" },
  { "_id" : 2, "last_name" : "Rippl-Ronai", "first_name" : "Joszef", "year_born" : 1861, "year_died" : 1927, "nationality" : "Hungary" },
  { "_id" : 3, "last_name" : "Ostroumova", "first_name" : "Anna", "year_born" : 1871, "year_died" : 1955, "nationality" : "Russia" },
  { "_id" : 4, "last_name" : "Van Gogh", "first_name" : "Vincent", "year_born" : 1853, "year_died" : 1890, "nationality" : "Holland" },
  { "_id" : 5, "last_name" : "Maurer", "first_name" : "Alfred", "year_born" : 1868, "year_died" : 1932, "nationality" : "USA" },
  { "_id" : 6, "last_name" : "Munch", "first_name" : "Edvard", "year_born" : 1863, "year_died" : 1944, "nationality" : "Norway" },
  { "_id" : 7, "last_name" : "Redon", "first_name" : "Odilon", "year_born" : 1840, "year_died" : 1916, "nationality" : "France" },
  { "_id" : 8, "last_name" : "Diriks", "first_name" : "Edvard", "year_born" : 1855, "year_died" : 1930, "nationality" : "Norway" }
])

The following operation groups the documents into buckets according to the year_born field and filters based on the count of documents in the buckets:以下操作根据year_born字段将文档分组到桶中，并根据桶中的文档计数进行筛选：

 db.artists.aggregate( [
 // First Stage第一阶段
 {
   $bucket: {
     groupBy: "$year_born",                        // Field to group by用来分组的字段
     boundaries: [ 1840, 1850, 1860, 1870, 1880 ], // Boundaries for the buckets桶的边界
     default: "Other",                             // Bucket ID for documents which do not fall into a bucket未放入桶中的文档的桶ID
     output: {                                     // Output for each bucket每个桶的输出每个桶的输出
       "count": { $sum: 1 },
       "artists" :
         {
           $push: {
             "name": { $concat: [ "$first_name", " ", "$last_name"] },
             "year_born": "$year_born"
           }
         }
     }
   }
 },
 // Second Stage第二阶段
 {
   $match: { count: {$gt: 3} }
 }
] )

First Stage第一阶段

The $bucket stage groups the documents into buckets by the year_born field. The buckets have the following boundaries:$bucket阶段按year_born字段将文档分组到桶中。桶有以下boundaries：

• [1840, 1850) with inclusive lowerbound 1840 and exclusive upper bound 1850.，具有包含下限1840和排除上限1850。
• [1850, 1860) with inclusive lowerbound 1850 and exclusive upper bound 1860.，具有包含下限1850和排除上限1860。
• [1860, 1870) with inclusive lowerbound 1860 and exclusive upper bound 1870.，具有包含下限1860和排除上限1870。
• [1870, 1880) with inclusive lowerbound 1870 and exclusive upper bound 1880.，具有包含下限1870和排除上限1880。
• If a document did not contain the year_born field or its year_born field was outside the ranges above, it would be placed in the default bucket with the _id value "Other".如果文档不包含year_born字段或其year_born域超出上述范围，则将其放置在_id值为"Other"的default桶中。

The stage includes the output document to determine the fields to return:该阶段包括output文档，以确定要返回的字段：

Field字段	Description描述
_id	Inclusive lower bound of the bucket.包括桶的下限。
count	Count of documents in the bucket.清点桶中的文件数。
artists	Array of documents containing information on each artist in the bucket. Each document contains the artist's包含桶中每个艺术家信息的文档数组。每个文档都包含艺术家的 name, which is a concatenation (i.e. $concat) of the artist's first_name and last_name.，这是艺术家的first_name和last_name的连接（即$concat）。 year_born

This stage passes the following documents to the next stage:此阶段将以下文件传递到下一阶段：

{ "_id" : 1840, "count" : 1, "artists" : [ { "name" : "Odilon Redon", "year_born" : 1840 } ] }

{ "_id" : 1850, "count" : 2, "artists" : [ { "name" : "Vincent Van Gogh", "year_born" : 1853 },
                                            { "name" : "Edvard Diriks", "year_born" : 1855 } ] }

{ "_id" : 1860, "count" : 4, "artists" : [ { "name" : "Emil Bernard", "year_born" : 1868 },
                                            { "name" : "Joszef Rippl-Ronai", "year_born" : 1861 },
                                            { "name" : "Alfred Maurer", "year_born" : 1868 },
                                            { "name" : "Edvard Munch", "year_born" : 1863 } ] }

{ "_id" : 1870, "count" : 1, "artists" : [ { "name" : "Anna Ostroumova", "year_born" : 1871 } ] }

Second Stage第二阶段

The $match stage filters the output from the previous stage to only return buckets which contain more than 3 documents.$match阶段筛选前一阶段的输出，只返回包含3个以上文档的桶。

The operation returns the following document:该操作返回以下文档：

{ "_id" : 1860, "count" : 4, "artists" :
  [
    { "name" : "Emil Bernard", "year_born" : 1868 },
    { "name" : "Joszef Rippl-Ronai", "year_born" : 1861 },
    { "name" : "Alfred Maurer", "year_born" : 1868 },
    { "name" : "Edvard Munch", "year_born" : 1863 }
  ]
}

Use $bucket with $facet to Bucket by Multiple Fields使用$bucket和$facet按多个字段创建桶

You can use the $facet stage to perform multiple $bucket aggregations in a single stage.您可以使用$facet阶段在单个阶段中执行多个$bucket聚合。

In mongosh, create a sample collection named artwork with the following documents:在mongosh中，使用以下文档创建一个名为artwork的样本集：

db.artwork.insertMany([
  { "_id" : 1, "title" : "The Pillars of Society", "artist" : "Grosz", "year" : 1926,
      "price" : Decimal128("199.99") },
  { "_id" : 2, "title" : "Melancholy III", "artist" : "Munch", "year" : 1902,
      "price" : Decimal128("280.00") },
  { "_id" : 3, "title" : "Dancer", "artist" : "Miro", "year" : 1925,
      "price" : Decimal128("76.04") },
  { "_id" : 4, "title" : "The Great Wave off Kanagawa", "artist" : "Hokusai",
      "price" : Decimal128("167.30") },
  { "_id" : 5, "title" : "The Persistence of Memory", "artist" : "Dali", "year" : 1931,
      "price" : Decimal128("483.00") },
  { "_id" : 6, "title" : "Composition VII", "artist" : "Kandinsky", "year" : 1913,
      "price" : Decimal128("385.00") },
  { "_id" : 7, "title" : "The Scream", "artist" : "Munch", "year" : 1893
      /* No price*/ },
  { "_id" : 8, "title" : "Blue Flower", "artist" : "O'Keefe", "year" : 1918,
      "price" : Decimal128("118.42") }
])

The following operation uses two $bucket stages within a $facet stage to create two groupings, one by price and the other by year:以下操作在$facet阶段中使用两个$bucket阶段来创建两个分组，一个按price，另一个按year：

db.artwork.aggregate( [
  {
    $facet: {                               // Top-level $facet stage顶级$facet阶段
      "price": [                            // Output field 1输出字段1
        {
          $bucket: {
              groupBy: "$price",            // Field to group by用来分组的字段
              boundaries: [ 0, 200, 400 ],  // Boundaries for the buckets桶的边界
              default: "Other",             // Bucket ID for documents which do not fall into a bucket未放入桶中的文档的桶ID
              output: {                     // Output for each bucket每个桶的输出
                "count": { $sum: 1 },
                "artwork" : { $push: { "title": "$title", "price": "$price" } },
                "averagePrice": { $avg: "$price" }
              }
          }
        }
      ],
      "year": [                                      // Output field 2输出字段2
        {
          $bucket: {
            groupBy: "$year",                        // Field to group by用来分组的字段
            boundaries: [ 1890, 1910, 1920, 1940 ],  // Boundaries for the buckets桶的边界
            default: "Unknown",                      // Bucket ID for documents which do not fall into a bucket未放入桶中的文档的桶ID
            output: {                                // Output for each bucket每个桶的输出
              "count": { $sum: 1 },
              "artwork": { $push: { "title": "$title", "year": "$year" } }
            }
          }
        }
      ]
    }
  }
] )

First Facet第一方面

The first facet groups the input documents by price. The buckets have the following boundaries:第一个方面按price对输入文档进行分组。桶有以下边界：

• [0, 200) with inclusive lowerbound 0 and exclusive upper bound 200.具有包含下限0和排除上限200。
• [200, 400) with inclusive lowerbound 200 and exclusive upper bound 400.具有包含下限200和排除上限400。
• "Other", the default bucket containing documents without prices or prices outside the ranges above.，default桶包含没有价格或价格超出上述范围的文档。

The $bucket stage includes the output document to determine the fields to return:$bucket阶段包括output文档，以确定要返回的字段：

Field字段	Description描述
_id	Inclusive lower bound of the bucket.包括桶的下限。
count	Count of documents in the bucket.清点桶中的文件数。
artwork	Array of documents containing information on each artwork in the bucket.包含桶中每件艺术品信息的文档数组。
averagePrice	Employs the $avg operator to display the average price of all artwork in the bucket.使用$avg运算符显示桶中所有艺术品的平均价格。

Second Facet第二方面

The second facet groups the input documents by year. The buckets have the following boundaries:第二个方面按年份对输入文档进行分组。桶有以下边界：

• [1890, 1910) with inclusive lowerbound 1890 and exclusive upper bound 1910.具有包含下限1890和排除上限1910。
• [1910, 1920) with inclusive lowerbound 1910 and exclusive upper bound 1920.具有包含下限1910和排除上限1920。
• [1920, 1940) with inclusive lowerbound 1920 and exclusive upper bound 1940.具有包含下限1920和排除上限1940。
• "Unknown", the default bucket containing documents without years or years outside the ranges above.，default桶包含没有年份或超出上述范围的文档。

The $bucket stage includes the output document to determine the fields to return:$bucket阶段包括output文档，以确定要返回的字段：

Field字段	Description描述
count	Count of documents in the bucket.清点桶中的文件数。
artwork	Array of documents containing information on each artwork in the bucket.包含桶中每件艺术品信息的文档数组。

Output输出

The operation returns the following document:该操作返回以下文档：

 {
  "price" : [ // Output of first facet第一面输出
    {
      "_id" : 0,
      "count" : 4,
      "artwork" : [
        { "title" : "The Pillars of Society", "price" : Decimal128("199.99") },
        { "title" : "Dancer", "price" : Decimal128("76.04") },
        { "title" : "The Great Wave off Kanagawa", "price" : Decimal128("167.30") },
        { "title" : "Blue Flower", "price" : Decimal128("118.42") }
      ],
      "averagePrice" : Decimal128("140.4375")
    },
    {
      "_id" : 200,
      "count" : 2,
      "artwork" : [
        { "title" : "Melancholy III", "price" : Decimal128("280.00") },
        { "title" : "Composition VII", "price" : Decimal128("385.00") }
      ],
      "averagePrice" : Decimal128("332.50")
    },
    {
      // Includes documents without prices and prices greater than 400包括没有价格和价格超过400的文件
      "_id" : "Other",
      "count" : 2,
      "artwork" : [
        { "title" : "The Persistence of Memory", "price" : Decimal128("483.00") },
        { "title" : "The Scream" }
      ],
      "averagePrice" : Decimal128("483.00")
    }
  ],
  "year" : [ // Output of second facet第二面输出
    {
      "_id" : 1890,
      "count" : 2,
      "artwork" : [
        { "title" : "Melancholy III", "year" : 1902 },
        { "title" : "The Scream", "year" : 1893 }
      ]
    },
    {
      "_id" : 1910,
      "count" : 2,
      "artwork" : [
        { "title" : "Composition VII", "year" : 1913 },
        { "title" : "Blue Flower", "year" : 1918 }
      ]
    },
    {
      "_id" : 1920,
      "count" : 3,
      "artwork" : [
        { "title" : "The Pillars of Society", "year" : 1926 },
        { "title" : "Dancer", "year" : 1925 },
        { "title" : "The Persistence of Memory", "year" : 1931 }
      ]
    },
    {
      // Includes documents without a year包括没有年份的文件
      "_id" : "Unknown",
      "count" : 1,
      "artwork" : [
        { "title" : "The Great Wave off Kanagawa" }
      ]
    }
  ]
}