Question

首先bucket按年龄而boundaries为[0,20,30,40,50,200]

db.user.aggregate(
    {$project: {_id:0, age:{$subtract:[{$year:new Date()}, {$year:"$birthDay"}]} } },
    {$bucket:{
        groupBy:"$age",
        boundaries:[0,20,30,40,50,200]
    }},
    { $project:{ _id:0,age:"$_id",count:1 } }
)

得到以下结果

{ "count" : 5, "age" : 20 }
{ "count" : 1, "age" : 30 }

然后我想进一步统计每个城市的每个年龄段数

{ city : "SH", age: 20, count: 2 }
{ city : "BJ", age: 20, count: 3 }
{ city : "BJ", age: 30, count: 1 }

那么在这种情况下如何实现呢？

另外

db.user.aggregate(
    { $project: {_id:0, city:1, age:{$subtract:[{$year:new Date()}, {$year:"$birthDay"}]} } },
    { $group: { _id:"$city",ages:{$push:"$age"} } },
    { $project: {_id:0, city:"$_id",ages:1} }
)

{ "city" : "SH", "ages" : [ 26, 26 ] }
{ "city" : "BJ", "ages" : [ 27, 26, 26, 36 ] }

Answer 1

您所谈论的内容实际上是使用$switch在常规$group阶段实施的：

db.user.aggregate([
  { "$group": {
    "_id": {
      "city": "$city",
      "age": {
        "$let": {
          "vars": { 
            "age": { "$subtract" :[{ "$year": new Date() },{ "$year": "$birthDay" }] }
          },
          "in": {
            "$switch": {
              "branches": [
                { "case": { "$lt": [ "$$age", 20 ] }, "then": 0 },
                { "case": { "$lt": [ "$$age", 30 ] }, "then": 20 },
                { "case": { "$lt": [ "$$age", 40 ] }, "then": 30 },
                { "case": { "$lt": [ "$$age", 50 ] }, "then": 40 },
                { "case": { "$lt": [ "$$age", 200 ] }, "then": 50 }
              ]
            }
          }
        }
      }
    },
    "count": { "$sum": 1 }
  }}
])

结果：

{ "_id" : { "city" : "BJ", "age" : 30 }, "count" : 1 }
{ "_id" : { "city" : "BJ", "age" : 20 }, "count" : 3 }
{ "_id" : { "city" : "SH", "age" : 20 }, "count" : 2 }

$bucket管道阶段只占用一个字段路径。您可以通过"output"选项拥有多个累加器，但"groupBy"是一个表达式。

请注意，您也可以在此处使用$let，而不是单独的$project管道阶段来计算＆＃34; age＆＃34;。

N.B如果您实际向$bucket抛出一些错误的表达式，您将收到有关$switch的错误，这应该暗示您这是在内部实现的方式。

如果您担心$switch中的编码，那么只需生成它：

var ranges = [0,20,30,40,50,200];
var branches = [];
for ( var i=1; i < ranges.length; i++) {
  branches.push({ "case": { "$lt": [ "$$age", ranges[i] ] }, "then": ranges[i-1] });
}

db.user.aggregate([
  { "$group": {
    "_id": {
      "city": "$city",
      "age": {
        "$let": {
          "vars": {
            "age": { 
              "$subtract": [{ "$year": new Date() },{ "$year": "$birthDay" }]
            }
          },
          "in": {
            "$switch": { "branches": branches }
          }
        }
      }
    },
    "count": { "$sum": 1 }
  }}
])

Answer 2

使用Map-Reduce

提供另一种实现方式

db.user.mapReduce(
    function(){
        var age = new Date().getFullYear() - this.birthDay.getFullYear();
        var ages = [0,20,30,40,50,200]
        for(var i=1; i<ages.length; i++){
            if(age < ages[i]){
                emit({city:this.city,age:ages[i-1]},1);
                break;
            }
        }        
    },
    function(key, counts){
        return Array.sum(counts);
    },
    { out: "user_city_age_count" }
)

如何实现$ bucket以按多个字段分组

2 个答案: