Question

我是LINQ的新手，但我想知道是否可以使用LINQ来转移以下布局中的数据：

CustID | OrderDate | Qty
1      | 1/1/2008  | 100
2      | 1/2/2008  | 200
1      | 2/2/2008  | 350
2      | 2/28/2008 | 221
1      | 3/12/2008 | 250
2      | 3/15/2008 | 2150

这样的事情：

CustID  | Jan- 2008 | Feb- 2008 | Mar - 2008 |
1       | 100       | 350       |  250
2       | 200       | 221       | 2150

Answer 1

这样的东西？

List<CustData> myList = GetCustData();

var query = myList
    .GroupBy(c => c.CustId)
    .Select(g => new {
        CustId = g.Key,
        Jan = g.Where(c => c.OrderDate.Month == 1).Sum(c => c.Qty),
        Feb = g.Where(c => c.OrderDate.Month == 2).Sum(c => c.Qty),
        March = g.Where(c => c.OrderDate.Month == 3).Sum(c => c.Qty)
    });

Linq中的

GroupBy与SQL的工作方式不同。在SQL中，您获得密钥和聚合（行/列形状）。在Linq中，您可以获得键和任何元素作为键的子元素（层次结构形状）。要进行透视，您必须将层次结构投影回您选择的行/列形式。

Answer 2

我使用linq扩展方法回答similar question：

// order s(ource) by OrderDate to have proper column ordering
var r = s.Pivot3(e => e.custID, e => e.OrderDate.ToString("MMM-yyyy")
    , lst => lst.Sum(e => e.Qty));
// order r(esult) by CustID

（+）通用实施
（ - ）肯定比大卫B的慢

任何人都可以改进我的实现（即该方法是否对列和行进行排序）？

Answer 3

我认为最好的方法是使用查找：

var query =
    from c in myList
    group c by c.CustId into gcs
    let lookup = gcs.ToLookup(y => y.OrderDate.Month, y => y.Qty)
    select new
    {
        CustId = gcs.Key,
        Jan = lookup[1].Sum(),
        Feb = lookup[2].Sum(),
        Mar = lookup[3].Sum(),
    };

Answer 4

以下是使用LINQ如何转换数据的更通用的方法：

IEnumerable<CustData> s;
var groupedData = s.ToLookup( 
        k => new ValueKey(
            k.CustID, // 1st dimension
            String.Format("{0}-{1}", k.OrderDate.Month, k.OrderDate.Year // 2nd dimension
        ) ) );
var rowKeys = groupedData.Select(g => (int)g.Key.DimKeys[0]).Distinct().OrderBy(k=>k);
var columnKeys = groupedData.Select(g => (string)g.Key.DimKeys[1]).Distinct().OrderBy(k=>k);
foreach (var row in rowKeys) {
    Console.Write("CustID {0}: ", row);
    foreach (var column in columnKeys) {
        Console.Write("{0:####} ", groupedData[new ValueKey(row,column)].Sum(r=>r.Qty) );
    }
    Console.WriteLine();
}

其中ValueKey是一个表示多维键的特殊类：

public sealed class ValueKey {
    public readonly object[] DimKeys;
    public ValueKey(params object[] dimKeys) {
        DimKeys = dimKeys;
    }
    public override int GetHashCode() {
        if (DimKeys==null) return 0;
        int hashCode = DimKeys.Length;
        for (int i = 0; i < DimKeys.Length; i++) { 
            hashCode ^= DimKeys[i].GetHashCode();
        }
        return hashCode;
    }
    public override bool Equals(object obj) {
        if ( obj==null || !(obj is ValueKey))
            return false;
        var x = DimKeys;
        var y = ((ValueKey)obj).DimKeys;
        if (ReferenceEquals(x,y))
            return true;
        if (x.Length!=y.Length)
            return false;
        for (int i = 0; i < x.Length; i++) {
            if (!x[i].Equals(y[i]))
                return false;
        }
        return true;            
    }
}

此方法可用于按N维（n> 2）进行分组，并且对于相当小的数据集可以正常工作。对于大型数据集（最多1百万条记录等）或者对于无法硬编码数据透视配置的情况，我编写了特殊的PivotData库（它是免费的）：

var pvtData = new PivotData(new []{"CustID","OrderDate"}, new SumAggregatorFactory("Qty"));
pvtData.ProcessData(s, (o, f) => {
    var custData = (TT)o;
    switch (f) {
        case "CustID": return custData.CustID;
        case "OrderDate": 
        return String.Format("{0}-{1}", custData.OrderDate.Month, custData.OrderDate.Year);
        case "Qty": return custData.Qty;
    }
    return null;
} );
Console.WriteLine( pvtData[1, "1-2008"].Value );

Answer 5

这是最有效的方法：

检查以下方法。而不是每个月每次都遍历客户组。

var query = myList
    .GroupBy(c => c.CustId)
    .Select(g => {
        var results = new CustomerStatistics();
        foreach (var customer in g)
        {
            switch (customer.OrderDate.Month)
            {
                case 1:
                    results.Jan += customer.Qty;
                    break;
                case 2:
                    results.Feb += customer.Qty;
                    break;
                case 3:
                    results.March += customer.Qty;
                    break;
                default:
                    break;
            }
        }
        return  new
        {
            CustId = g.Key,
            results.Jan,
            results.Feb,
            results.March
        };
    });

或者这个：

var query = myList
    .GroupBy(c => c.CustId)
    .Select(g => {
        var results = g.Aggregate(new CustomerStatistics(), (result, customer) => result.Accumulate(customer), customerStatistics => customerStatistics.Compute());
        return  new
        {
            CustId = g.Key,
            results.Jan,
            results.Feb,
            results.March
        };
    });

完整的解决方案：

using System;
using System.Collections.Generic;
using System.Linq;

namespace ConsoleApp
{
    internal class Program
    {
        private static void Main(string[] args)
        {
            IEnumerable<CustData> myList = GetCustData().Take(100);

            var query = myList
                .GroupBy(c => c.CustId)
                .Select(g =>
                {
                    CustomerStatistics results = g.Aggregate(new CustomerStatistics(), (result, customer) => result.Accumulate(customer), customerStatistics => customerStatistics.Compute());
                    return new
                    {
                        CustId = g.Key,
                        results.Jan,
                        results.Feb,
                        results.March
                    };
                });
            Console.ReadKey();
        }

        private static IEnumerable<CustData> GetCustData()
        {
            Random random = new Random();
            int custId = 0;
            while (true)
            {
                custId++;
                yield return new CustData { CustId = custId, OrderDate = new DateTime(2018, random.Next(1, 4), 1), Qty = random.Next(1, 50) };
            }
        }

    }
    public class CustData
    {
        public int CustId { get; set; }
        public DateTime OrderDate { get; set; }
        public int Qty { get; set; }
    }
    public class CustomerStatistics
    {
        public int Jan { get; set; }
        public int Feb { get; set; }
        public int March { get; set; }
        internal CustomerStatistics Accumulate(CustData customer)
        {
            switch (customer.OrderDate.Month)
            {
                case 1:
                    Jan += customer.Qty;
                    break;
                case 2:
                    Feb += customer.Qty;
                    break;
                case 3:
                    March += customer.Qty;
                    break;
                default:
                    break;
            }
            return this;
        }
        public CustomerStatistics Compute()
        {
            return this;
        }
    }
}

Answer 6

按月对数据进行分组，然后将其投影到每个月包含列的新数据表中。新表将是您的数据透视表。

是否可以使用LINQ旋转数据？

6 个答案: