我有一个奇怪的 MapReduce 问题。

map 功能:

> mp
function () {
    emit(this.ContractID, {qty:this.Qty, qtybs:this.QtyBs});
}

归约函数

> red
function (key, values) {
    var sum1 = 0, sum2 = 0;
    values.forEach(function (doc) {sum1 += doc.qty;sum2 += doc.qtybs;});
    return {a:sum1, b:sum2};
}

为 7 个合约运行 MR:

> result = db.fact_payments.mapReduce(mp, red, {out:"myout2", query:{ContractID:{$lte:10000100042}}});
{
        "result" : "myout2",
        "timeMillis" : 670,
        "counts" : {
                "input" : 591,
                "emit" : 591,
                "output" : 7
        },
        "ok" : 1,
}
> db.myout2.find()
{ "_id" : NumberLong("10000000042"), "value" : { "a" : 8331.04, "b" : 253835.07999999996 } }
{ "_id" : NumberLong("10000000084"), "value" : { "a" : 4728.480000000001, "b" : 142879.88000000003 } }
{ "_id" : NumberLong("10000000129"), "value" : { "a" : 25421.859999999997, "b" : 756036.9499999998 } }
{ "_id" : NumberLong("10000000140"), "value" : { "a" : 477292.0000000002, "b" : 477292.0000000002 } }
{ "_id" : NumberLong("10000000148"), "value" : { "a" : 7912.0599999999995, "b" : 237926.87999999998 } }
{ "_id" : NumberLong("10000000165"), "value" : { "a" : 35391.31999999999, "b" : 1074180.95 } }
{ "_id" : NumberLong("10000000171"), "value" : { "a" : 62189.52, "b" : 62189.52 } }
>

没关系，所有契约(Contract)都有结果:)

对所有合约运行 MR:

> result = db.fact_payments.mapReduce(mp, red, {out:"myout2", query:{ContractID:{$lte:100100000042}}});
{
        "result" : "myout2",
        "timeMillis" : 26273,
        "counts" : {
                "input" : 295765,
                "emit" : 295765,
                "output" : 7793
        },
        "ok" : 1,
}
> db.myout2.find()
{ "_id" : NumberLong("10000000042"), "value" : { "a" : NaN, "b" : NaN } }
{ "_id" : NumberLong("10000000084"), "value" : { "a" : 4728.480000000001, "b" : 142879.88000000003 } }
{ "_id" : NumberLong("10000000129"), "value" : { "a" : NaN, "b" : NaN } }
{ "_id" : NumberLong("10000000140"), "value" : { "a" : NaN, "b" : NaN } }
{ "_id" : NumberLong("10000000148"), "value" : { "a" : NaN, "b" : NaN } }
{ "_id" : NumberLong("10000000165"), "value" : { "a" : NaN, "b" : NaN } }
{ "_id" : NumberLong("10000000171"), "value" : { "a" : 62189.52, "b" : 62189.52 } }
{ "_id" : NumberLong("10005000172"), "value" : { "a" : NaN, "b" : NaN } }
{ "_id" : NumberLong("10005000173"), "value" : { "a" : NaN, "b" : NaN } }
{ "_id" : NumberLong("10005000189"), "value" : { "a" : NaN, "b" : NaN } }
{ "_id" : NumberLong("10005000191"), "value" : { "a" : 8261.759999999998, "b" : 253916.7 } }
{ "_id" : NumberLong("10005000199"), "value" : { "a" : NaN, "b" : NaN } }
{ "_id" : NumberLong("10005000206"), "value" : { "a" : NaN, "b" : NaN } }
{ "_id" : NumberLong("10005000213"), "value" : { "a" : NaN, "b" : NaN } }
{ "_id" : NumberLong("10010000200"), "value" : { "a" : NaN, "b" : NaN } }
{ "_id" : NumberLong("10010000224"), "value" : { "a" : NaN, "b" : NaN } }
{ "_id" : NumberLong("10010000229"), "value" : { "a" : NaN, "b" : NaN } }
{ "_id" : NumberLong("10010000240"), "value" : { "a" : 32843.32, "b" : 32843.32 } }
{ "_id" : NumberLong("10010000243"), "value" : { "a" : NaN, "b" : NaN } }
{ "_id" : NumberLong("10010000244"), "value" : { "a" : NaN, "b" : NaN } }
has more

相同的合约 id 有不同的结果:

{ "_id" : NumberLong("10000000042"), "value" : { "a" : 8331.04, "b" : 253835.07999999996 } }

和

{ "_id" : NumberLong("10000000042"), "value" : { "a" : NaN, "b" : NaN } }

我一点想法都没有。

最佳答案

如果您将最后一行更改为以下内容，它应该可以工作:

return {qty:sum1, qtybs:sum2};

规则是 reduce 函数的返回值必须与 emit 的第二个参数(它是 reduce 的输入)具有相同的“形状”，因为 reduce 的输出被反馈到 reduce 函数。参见 http://www.mongodb.org/display/DOCS/MapReduce#MapReduce-ReduceFunction了解更多详情。

关于mongodb - MapReduce问题，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/7332763/