我想从一个巨大的集合(1亿条记录)中获得一个随机记录。

最快最有效的方法是什么?

数据已经在那里,没有字段可以生成随机数并获得随机行。


当前回答

您可以选择一个随机时间戳,然后搜索随后创建的第一个对象。 它将只扫描单个文档,尽管它不一定会给您一个统一的分布。

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)
    };
}();

其他回答

我对php的解决方案:

/**
 * Get random docs from Mongo
 * @param $collection
 * @param $where
 * @param $fields
 * @param $limit
 * @author happy-code
 * @url happy-code.com
 */
private function _mongodb_get_random (MongoCollection $collection, $where = array(), $fields = array(), $limit = false) {

    // Total docs
    $count = $collection->find($where, $fields)->count();

    if (!$limit) {
        // Get all docs
        $limit = $count;
    }

    $data = array();
    for( $i = 0; $i < $limit; $i++ ) {

        // Skip documents
        $skip = rand(0, ($count-1) );
        if ($skip !== 0) {
            $doc = $collection->find($where, $fields)->skip($skip)->limit(1)->getNext();
        } else {
            $doc = $collection->find($where, $fields)->limit(1)->getNext();
        }

        if (is_array($doc)) {
            // Catch document
            $data[ $doc['_id']->{'$id'} ] = $doc;
            // Ignore current document when making the next iteration
            $where['_id']['$nin'][] = $doc['_id'];
        }

        // Every iteration catch document and decrease in the total number of document
        $count--;

    }

    return $data;
}

在Python中使用pymongo:

import random

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

为了获得确定数量的无重复的随机文档:

first get all ids get size of documents loop geting random index and skip duplicated number_of_docs=7 db.collection('preguntas').find({},{_id:1}).toArray(function(err, arr) { count=arr.length idsram=[] rans=[] while(number_of_docs!=0){ var R = Math.floor(Math.random() * count); if (rans.indexOf(R) > -1) { continue } else { ans.push(R) idsram.push(arr[R]._id) number_of_docs-- } } db.collection('preguntas').find({}).toArray(function(err1, doc1) { if (err1) { console.log(err1); return; } res.send(doc1) }); });

这工作得很好,它是快速的,适用于多个文档,不需要填充rand字段,它最终会填充自己:

向集合上的.rand字段添加索引 使用查找和刷新,如下所示:

// Install packages:
//   npm install mongodb async
// Add index in mongo:
//   db.ensureIndex('mycollection', { rand: 1 })

var mongodb = require('mongodb')
var async = require('async')

// Find n random documents by using "rand" field.
function findAndRefreshRand (collection, n, fields, done) {
  var result = []
  var rand = Math.random()

  // Append documents to the result based on criteria and options, if options.limit is 0 skip the call.
  var appender = function (criteria, options, done) {
    return function (done) {
      if (options.limit > 0) {
        collection.find(criteria, fields, options).toArray(
          function (err, docs) {
            if (!err && Array.isArray(docs)) {
              Array.prototype.push.apply(result, docs)
            }
            done(err)
          }
        )
      } else {
        async.nextTick(done)
      }
    }
  }

  async.series([

    // Fetch docs with unitialized .rand.
    // NOTE: You can comment out this step if all docs have initialized .rand = Math.random()
    appender({ rand: { $exists: false } }, { limit: n - result.length }),

    // Fetch on one side of random number.
    appender({ rand: { $gte: rand } }, { sort: { rand: 1 }, limit: n - result.length }),

    // Continue fetch on the other side.
    appender({ rand: { $lt: rand } }, { sort: { rand: -1 }, limit: n - result.length }),

    // Refresh fetched docs, if any.
    function (done) {
      if (result.length > 0) {
        var batch = collection.initializeUnorderedBulkOp({ w: 0 })
        for (var i = 0; i < result.length; ++i) {
          batch.find({ _id: result[i]._id }).updateOne({ rand: Math.random() })
        }
        batch.execute(done)
      } else {
        async.nextTick(done)
      }
    }

  ], function (err) {
    done(err, result)
  })
}

// Example usage
mongodb.MongoClient.connect('mongodb://localhost:27017/core-development', function (err, db) {
  if (!err) {
    findAndRefreshRand(db.collection('profiles'), 1024, { _id: true, rand: true }, function (err, result) {
      if (!err) {
        console.log(result)
      } else {
        console.error(err)
      }
      db.close()
    })
  } else {
    console.error(err)
  }
})

ps.如何在mongodb问题中找到随机记录被标记为此问题的副本。不同之处在于,这个问题明确地询问单个记录,而另一个问题明确地询问随机文档。

您可以选择随机_id并返回相应的对象:

 db.collection.count( function(err, count){
        db.collection.distinct( "_id" , function( err, result) {
            if (err)
                res.send(err)
            var randomId = result[Math.floor(Math.random() * (count-1))]
            db.collection.findOne( { _id: randomId } , function( err, result) {
                if (err)
                    res.send(err)
                console.log(result)
            })
        })
    })

在这里,你不需要花空间存储随机数字的集合。