c# - RavenDb 中的映射减少，更新 1

Question

更新 1，按照 Ayende 的回答

这是我第一次进入 RavenDb 并进行试验，我写了一个小 map/reduce，但不幸的是结果是空的？

我在 RavenDb 中加载了大约 160 万份文档

一份文件：

public class Tick
{
    public DateTime Time;
    public decimal Ask;
    public decimal Bid;
    public double AskVolume;
    public double BidVolume;
}

并希望在特定时间段内获得最低和最高询价。

按时间收集的定义为：

var ticks = session.Query<Tick>().Where(x => x.Time > new DateTime(2012, 4, 23) && x.Time < new DateTime(2012, 4, 24, 00, 0, 0)).ToList();

这给了我 90280 份文件，到目前为止一切都很好。

但是然后地图/减少：

Map = rows => from row in rows 
                          select new
                          {
                              Max = row.Bid,
                              Min = row.Bid, 
                              Time = row.Time,
                              Count = 1
                          };

Reduce = results => from result in results
                                group result by new{ result.MaxBid, result.Count} into g
                                select new
                                {
                                    Max = g.Key.MaxBid,
                                    Min = g.Min(x => x.MaxBid),
                                    Time = g.Key.Time,
                                    Count = g.Sum(x => x.Count)

                                };

...

private class TickAggregationResult
{
    public decimal MaxBid { get; set; }
        public decimal MinBid { get; set; }
        public int Count { get; set; }

    }

然后我创建索引并尝试查询它：

Raven.Client.Indexes.IndexCreation.CreateIndexes(typeof(TickAggregation).Assembly, documentStore);


        var session = documentStore.OpenSession();

        var g1 = session.Query<TickAggregationResult>(typeof(TickAggregation).Name);


        var group = session.Query<Tick, TickAggregation>()
                         .Where(x => x.Time > new DateTime(2012, 4, 23) && 
                                     x.Time < new DateTime(2012, 4, 24, 00, 0, 0)
                                  )
            .Customize(x => x.WaitForNonStaleResults())
                                           .AsProjection<TickAggregationResult>();

但是该组只是空的:(

如您所见，我尝试了两种不同的查询，我不确定它们之间的区别，有人可以解释一下吗？

现在我得到一个错误：

该组仍然是空的:(

让我解释一下我要在纯 sql 中完成的工作：

select min(Ask), count(*) as TickCount from Ticks 
where Time between '2012-04-23' and '2012-04-24)

Answer 1

不幸的是，Map/Reduce 不能那样工作。好吧，至少它的 Reduce 部分没有。为了减少您的设置，您必须预先定义特定的时间范围来分组，例如 - 每天、每周、每月等。如果您每天减少，您可以获得每天的最小/最大/计数。

有一种方法可以得到你想要的，但它有一些性能方面的考虑。基本上，您根本不减少，而是按时间索引，然后在转换结果时进行聚合。这类似于您运行第一个查询以过滤然后在客户端代码中聚合。唯一的好处是聚合是在服务器端完成的，因此您不必将所有数据传输到客户端。

这里的性能问题是您要过滤到多大的时间范围，或者更准确地说，您的过滤范围内会有多少项目？如果它比较小，您可以使用这种方法。如果它太大，您将在服务器检查结果集时等待。

下面是一个示例程序来说明这种技术：

using System;
using System.Linq;
using Raven.Client.Document;
using Raven.Client.Indexes;
using Raven.Client.Linq;

namespace ConsoleApplication1
{
  public class Tick
  {
    public string Id { get; set; }
    public DateTime Time { get; set; }
    public decimal Bid { get; set; }
  }

  /// <summary>
  /// This index is a true map/reduce, but its totals are for all time.
  /// You can't filter it by time range.
  /// </summary>
  class Ticks_Aggregate : AbstractIndexCreationTask<Tick, Ticks_Aggregate.Result>
  {
    public class Result
    {
      public decimal Min { get; set; }
      public decimal Max { get; set; }
      public int Count { get; set; }
    }

    public Ticks_Aggregate()
    {
      Map = ticks => from tick in ticks
               select new
                    {
                      Min = tick.Bid,
                      Max = tick.Bid,
                      Count = 1
                    };

      Reduce = results => from result in results
                group result by 0
                  into g
                  select new
                         {
                           Min = g.Min(x => x.Min),
                           Max = g.Max(x => x.Max),
                           Count = g.Sum(x => x.Count)
                         };
    }
  }

  /// <summary>
  /// This index can be filtered by time range, but it does not reduce anything
  /// so it will not be performant if there are many items inside the filter.
  /// </summary>
  class Ticks_ByTime : AbstractIndexCreationTask<Tick>
  {
    public class Result
    {
      public decimal Min { get; set; }
      public decimal Max { get; set; }
      public int Count { get; set; }
    }

    public Ticks_ByTime()
    {
      Map = ticks => from tick in ticks
               select new {tick.Time};

      TransformResults = (database, ticks) =>
                 from tick in ticks
                 group tick by 0
                 into g
                 select new
                      {
                        Min = g.Min(x => x.Bid),
                        Max = g.Max(x => x.Bid),
                        Count = g.Count()
                      };
    }
  }

  class Program
  {
    private static void Main()
    {
      var documentStore = new DocumentStore { Url = "http://localhost:8080" };
      documentStore.Initialize();
      IndexCreation.CreateIndexes(typeof(Program).Assembly, documentStore);


      var today = DateTime.Today;
      var rnd = new Random();

      using (var session = documentStore.OpenSession())
      {
        // Generate 100 random ticks
        for (var i = 0; i < 100; i++)
        {
          var tick = new Tick { Time = today.AddMinutes(i), Bid = rnd.Next(100, 1000) / 100m };
          session.Store(tick);
        }

        session.SaveChanges();
      }


      using (var session = documentStore.OpenSession())
      {
        // Query items with a filter.  This will create a dynamic index.
        var fromTime = today.AddMinutes(20);
        var toTime = today.AddMinutes(80);
        var ticks = session.Query<Tick>()
          .Where(x => x.Time >= fromTime && x.Time <= toTime)
          .OrderBy(x => x.Time);

        // Ouput the results of the above query
        foreach (var tick in ticks)
          Console.WriteLine("{0} {1}", tick.Time, tick.Bid);

        // Get the aggregates for all time
        var total = session.Query<Tick, Ticks_Aggregate>()
          .As<Ticks_Aggregate.Result>()
          .Single();
        Console.WriteLine();
        Console.WriteLine("Totals");
        Console.WriteLine("Min: {0}", total.Min);
        Console.WriteLine("Max: {0}", total.Max);
        Console.WriteLine("Count: {0}", total.Count);

        // Get the aggregates with a filter
        var filtered = session.Query<Tick, Ticks_ByTime>()
          .Where(x => x.Time >= fromTime && x.Time <= toTime)
          .As<Ticks_ByTime.Result>()
          .Take(1024)  // max you can take at once
          .ToList()    // required!
          .Single();
        Console.WriteLine();
        Console.WriteLine("Filtered");
        Console.WriteLine("Min: {0}", filtered.Min);
        Console.WriteLine("Max: {0}", filtered.Max);
        Console.WriteLine("Count: {0}", filtered.Count);
      }

      Console.ReadLine();
    }
  }
}

我可以设想一个解决方案来解决在时间上聚合具有潜在大范围的过滤器的问题。reduce 必须将事物分解为不同级别的越来越小的时间单位。这个代码有点复杂，但我正在为自己的目的工作。完成后，我将在 www.ravendb.net 的知识库中发布。

---

更新

我在玩这个多一点，并在最后一个查询中注意到两件事。

1. 您必须ToList()在调用 single 之前执行 a 才能获得完整的结果集。
2. 即使这在服务器上运行，您在结果范围内可以拥有的最大值是 1024，并且您必须指定 a Take(1024)，否则您将获得默认值 128 max。由于它在服务器上运行，我没想到会这样。但我猜是因为您通常不会在 TransformResults 部分进行聚合。

我已经为此更新了代码。然而，除非你能保证范围足够小，否则我会等待我所说的更好的全图/减少。我在做这个工作。:)