来自MongoDB的随机记录

计算所有记录,生成0到计数之间的随机数,然后执行:

db.yourCollection.find().limit(-1).skip(yourRandomNumber).next()

3.2将$ sample引入聚合管道.

关于将其付诸实践的博客文章也很好.

适用于旧版本(上一个答案)

这实际上是一个功能请求:http: //jira.mongodb.org/browse/SERVER-533但它是在"无法修复"下提交的.

这本食谱有一个很好的方法可以从一个集合中选择一个随机文档:http: //cookbook.mongodb.org/patterns/random-attribute/

要解释配方,您可以为文档分配随机数:

db.docs.save( { key : 1, ..., random : Math.random() } )

然后选择一个随机文档:

rand = Math.random()
result = db.docs.findOne( { key : 2, random : { $gte : rand } } )
if ( result == null ) {
  result = db.docs.findOne( { key : 2, random : { $lte : rand } } )
}

查询两者$gte并且$lte必须找到最接近随机数的文档rand.

当然,您需要在随机字段上编制索引:

db.docs.ensureIndex( { key : 1, random :1 } )

如果您已经查询了索引,只需将其删除,附加random: 1到它,然后重新添加即可.

您还可以使用MongoDB的地理空间索引功能来选择最接近随机数的文档.

首先,在集合上启用地理空间索引:

db.docs.ensureIndex( { random_point: '2d' } )

要在X轴上创建一组带有随机点的文档:

for ( i = 0; i < 10; ++i ) {
    db.docs.insert( { key: i, random_point: [Math.random(), 0] } );
}

然后你可以从集合中获得一个随机文档,如下所示:

db.docs.findOne( { random_point : { $near : [Math.random(), 0] } } )

或者您可以检索最接近随机点的多个文档:

db.docs.find( { random_point : { $near : [Math.random(), 0] } } ).limit( 4 )

这只需要一个查询而不需要空检查,而且代码干净,简单且灵活.您甚至可以使用geopoint的Y轴为查询添加第二个随机性维度.

以下配方比mongo cookbook解决方案稍慢(在每个文档上添加随机键),但返回更均匀分布的随机文档.它比skip( random )解决方案的分布更不均匀,但在删除文档的情况下更快,更安全.

function draw(collection, query) {
    // query: mongodb query object (optional)
    var query = query || { };
    query['random'] = { $lte: Math.random() };
    var cur = collection.find(query).sort({ rand: -1 });
    if (! cur.hasNext()) {
        delete query.random;
        cur = collection.find(query).sort({ rand: -1 });
    }
    var doc = cur.next();
    doc.random = Math.random();
    collection.update({ _id: doc._id }, doc);
    return doc;
}

function addRandom(collection) { 
    collection.find().forEach(function (obj) {
        obj.random = Math.random();
        collection.save(obj);
    }); 
} 
db.eval(addRandom, db.things);

// Get the "min" and "max" timestamp values from the _id in the collection and the 
// diff between.
// 4-bytes from a hex string is 8 characters

var min = parseInt(db.collection.find()
        .sort({ "_id": 1 }).limit(1).toArray()[0]._id.str.substr(0,8),16)*1000,
    max = parseInt(db.collection.find()
        .sort({ "_id": -1 })limit(1).toArray()[0]._id.str.substr(0,8),16)*1000,
    diff = max - min;

// Get a random value from diff and divide/multiply be 1000 for The "_id" precision:
var random = Math.floor(Math.floor(Math.random(diff)*diff)/1000)*1000;

// Use "random" in the range and pad the hex string to a valid ObjectId
var _id = new ObjectId(((min + random)/1000).toString(16) + "0000000000000000")

// Then query for the single document:
var randomDoc = db.collection.find({ "_id": { "$gte": _id } })
   .sort({ "_id": 1 }).limit(1).toArray()[0];

import random

def get_random_doc():
    count = collection.count()
    return collection.find()[random.randrange(count)]

lowest = db.coll.find().sort({_id:1}).limit(1).next()._id;
highest = db.coll.find().sort({_id:-1}).limit(1).next()._id;

unsigned long long L = first_8_bytes_of(lowest)
unsigned long long H = first_8_bytes_of(highest)

V = (H - L) * random_from_0_to_1();
N = L + V;
oid = N concat random_4_bytes();

randomobj = db.coll.find({_id:{$gte:oid}}).limit(1);

db.users.aggregate(
   [ { $sample: { size: 3 } } ]
)

var randRec = function() {
    // replace with your collection
    var coll = db.collection
    // get unixtime of first and last record
    var min = coll.find().sort({_id: 1}).limit(1)[0]._id.getTimestamp() - 0;
    var max = coll.find().sort({_id: -1}).limit(1)[0]._id.getTimestamp() - 0;

    // allow to pass additional query params
    return function(query) {
        if (typeof query === 'undefined') query = {}
        var randTime = Math.round(Math.random() * (max - min)) + min;
        var hexSeconds = Math.floor(randTime / 1000).toString(16);
        var id = ObjectId(hexSeconds + "0000000000000000");
        query._id = {$gte: id}
        return coll.find(query).limit(1)
    };
}();

collection.aggregate([{'$sample': {'size': sample_size }}])