MongoDB group by Functionalities

Question

在MySQL中

select a,b,count(1) as cnt from list group by a, b having cnt > 2;

我必须使用mongodb中的条件来执行group by函数.但我得到以下错误.请分享您的意见.

在MongoDB中

> res = db.list.group({key:{a:true,b:true},
...                      reduce: function(obj,prev) {prev.count++;},
...                      initial: {count:0}}).limit(10);

Sat Jan  7 16:36:30 uncaught exception: group command failed: {
        "errmsg" : "exception: group() can't handle more than 20000 unique keys",
        "code" : 10043,
        "ok" : 0

一旦执行,我们需要在下一个文件上运行以下文件.

for (i in res) {if (res[i].count>2) printjson(res[i])};

此致,库马兰

Answer 1

例如,MongoDB group by在大多数情况下非常有限

- the result set must be lesser than 10000 keys.
- it will not work in sharded environments

所以最好使用map reduce.所以查询会是这样的

map = function(){emit({a:true,b:true},{count:1}); }

reduce = function(k, values) {
    var result = {count: 0};
    values.forEach(function(value) {
        result.count += value.count;
    });
    return result;
}

然后

db.list.mapReduce(map,reduce,{out: { inline : 1}})

它是一个未经测试的版本.让我知道它是否有效

编辑:

早期的地图功能有问题.这就是为什么你没有得到结果.应该是的

map = function () {
    emit({a:this.a, b:this.b}, {count:1});
}

测试数据:

> db.multi_group.insert({a:1,b:2})
> db.multi_group.insert({a:2,b:2})
> db.multi_group.insert({a:3,b:2})
> db.multi_group.insert({a:1,b:2})
> db.multi_group.insert({a:3,b:2})
> db.multi_group.insert({a:7,b:2})


> db.multi_group.mapReduce(map,reduce,{out: { inline : 1}})
{
    "results" : [
        {
            "_id" : {
                "a" : 1,
                "b" : 2
            },
            "value" : {
                "count" : 2
            }
        },
        {
            "_id" : {
                "a" : 2,
                "b" : 2
            },
            "value" : {
                "count" : 1
            }
        },
        {
            "_id" : {
                "a" : 3,
                "b" : 2
            },
            "value" : {
                "count" : 2
            }
        },
        {
            "_id" : {
                "a" : 7,
                "b" : 2
            },
            "value" : {
                "count" : 1
            }
        }
    ],
    "timeMillis" : 1,
    "counts" : {
        "input" : 6,
        "emit" : 6,
        "reduce" : 2,
        "output" : 4
    },
    "ok" : 1,
}

EDIT2:

完整的解决方案,包括应用计数> = 2

map = function () {
    emit({a:this.a, b:this.b}, {count:1,_id:this._id});
}

reduce = function(k, values) {
    var result = {count: 0,_id:[]};
    values.forEach(function(value) {
        result.count += value.count;
        result._id.push(value._id);
    });
    return result;
}

>db.multi_group.mapReduce(map,reduce,{out: { replace : "multi_result"}})

> db.multi_result.find({'value.count' : {$gte : 2}})
{ "_id" : { "a" : 1, "b" : 2 }, "value" : { "_id" : [   ObjectId("4f0adf2884025491024f994c"),   ObjectId("4f0adf3284025491024f994f") ], "count" : 2 } }
{ "_id" : { "a" : 3, "b" : 2 }, "value" : { "_id" : [   ObjectId("4f0adf3084025491024f994e"),   ObjectId("4f0adf3584025491024f9950") ], "count" : 2 } }