$bucket (estágio de agregação )

Bucket por ano e filtrar por resultados do bucket

In mongosh, create a sample collection named artists with the following documents:

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" }
])

A operação a seguir agrupa os documentos em buckets de acordo com o campo year_born e filtra com base na contagem de documentos nos buckets:

 db.artists.aggregate( [
 // First Stage
 {
   $bucket: {
     groupBy: "$year_born",                        // Field to group by
     boundaries: [ 1840, 1850, 1860, 1870, 1880 ], // Boundaries for the buckets
     default: "Other",                             // Bucket ID for documents which do not fall into a bucket
     output: {                                     // Output for each bucket
       "count": { $sum: 1 },
       "artists" :
         {
           $push: {
             "name": { $concat: [ "$first_name", " ", "$last_name"] },
             "year_born": "$year_born"
           }
         }
     }
   }
 },
 // Second Stage
 {
   $match: { count: {$gt: 3} }
 }
] )

Primeira etapa

The $bucket stage groups the documents into buckets by the year_born field. The buckets have the following boundaries:

• [1840, 1850) com limite inferior inclusivo de 1840 e limite superior exclusivo de 1850.

• [1850, 1860) com limite inferior inclusivo 1850 e limite superior exclusivo 1860.

• [1860, 1870) com limite inferior inclusivo 1860 e limite superior exclusivo 1870.

• [1870, 1880) com limite inferior inclusivo 1870 e limite superior exclusivo 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".

The stage includes the output document to determine the fields to return:

Campo	Descrição
_id	Limite inferior inclusivo do bucket.
count	Contagem de documentos no bucket.
artists	Array de documentos contendo informações sobre cada artista no bucket. Cada documento contém o seguinte sobre o artista: name, que é uma concatenação (ou seja, $concat) do first_name e last_name do artista. year_born

Este estágio passa os seguintes documentos para o próximo estágio:

{ "_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 } ] }

Segunda etapa

O estágio $match filtra a saída do estágio anterior para retornar apenas buckets que contenham mais de três documentos.

A operação retorna o seguinte documento:

{ "_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 com $facet para executar Bucket por vários campos

You can use the $facet stage to perform multiple $bucket aggregations in a single stage.

In mongosh, create a sample collection named artwork with the following documents:

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:

db.artwork.aggregate( [
  {
    $facet: {                               // Top-level $facet stage
      "price": [                            // Output field 1
        {
          $bucket: {
              groupBy: "$price",            // Field to group by
              boundaries: [ 0, 200, 400 ],  // Boundaries for the buckets
              default: "Other",             // Bucket ID for documents which do not fall into a bucket
              output: {                     // Output for each bucket
                "count": { $sum: 1 },
                "artwork" : { $push: { "title": "$title", "price": "$price" } },
                "averagePrice": { $avg: "$price" }
              }
          }
        }
      ],
      "year": [                                      // Output field 2
        {
          $bucket: {
            groupBy: "$year",                        // Field to group by
            boundaries: [ 1890, 1910, 1920, 1940 ],  // Boundaries for the buckets
            default: "Unknown",                      // Bucket ID for documents which do not fall into a bucket
            output: {                                // Output for each bucket
              "count": { $sum: 1 },
              "artwork": { $push: { "title": "$title", "year": "$year" } }
            }
          }
        }
      ]
    }
  }
] )

Primeira faceta

A primeira faceta agrupa os documentos de entrada por price. Os buckets têm os seguintes limites:

• [0, 200) com limite inferior inclusivo 0 e limite superior exclusivo 200.

• [200, 400) com limite inferior inclusivo 200 e limite superior exclusivo 400.

• "Other", o bucket default que contém documentos sem preços ou preços fora das faixas acima.

The $bucket stage includes the output document to determine the fields to return:

Campo	Descrição
_id	Limite inferior inclusivo do bucket.
count	Contagem de documentos no bucket.
artwork	Array de documentos contendo informações sobre cada obra de arte no bucket.
averagePrice	Emprega o operador $avg para exibir o preço médio de todas as obras de arte no bucket.

Segunda faceta

A segunda faceta agrupa os documentos de entrada por year. Os buckets têm os seguintes limites:

• [1890, 1910) com limite inferior inclusivo de 1890 e limite superior exclusivo de 1910.

• [1910, 1920) com limite inferior inclusivo de 1910 e limite superior exclusivo de 1920.

• [1920, 1940) com limite inferior inclusivo de 1910 e limite superior exclusivo de 1940.

• " Unknown ", o bucket default contendo documentos sem anos ou anos fora dos intervalos acima.

The $bucket stage includes the output document to determine the fields to return:

Campo	Descrição
count	Contagem de documentos no bucket.
artwork	Array de documentos contendo informações sobre cada obra de arte no bucket.

Saída

A operação retorna o seguinte documento:

 {
  "price" : [ // Output of first facet
    {
      "_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
      "_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
    {
      "_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
      "_id" : "Unknown",
      "count" : 1,
      "artwork" : [
        { "title" : "The Great Wave off Kanagawa" }
      ]
    }
  ]
}