Split a collection into `n` parts with LINQ?

Question

Is there a nice way to split a collection into n parts with LINQ? Not necessarily evenly of course.

That is, I want to divide the collection into sub-collections, which each contains a subset of the elements, where the last collection can be ragged.

Answer 1

I have been using the Partition function I posted earlier quite often. The only bad thing about it was that is wasn't completely streaming. This is not a problem if you work with few elements in your sequence. I needed a new solution when i started working with 100.000+ elements in my sequence.

The following solution is a lot more complex (and more code!), but it is very efficient.

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

namespace LuvDaSun.Linq
{
    public static class EnumerableExtensions
    {
        public static IEnumerable<IEnumerable<T>> Partition<T>(this IEnumerable<T> enumerable, int partitionSize)
        {
            /*
            return enumerable
                .Select((item, index) => new { Item = item, Index = index, })
                .GroupBy(item => item.Index / partitionSize)
                .Select(group => group.Select(item => item.Item)                )
                ;
            */

            return new PartitioningEnumerable<T>(enumerable, partitionSize);
        }

    }


    class PartitioningEnumerable<T> : IEnumerable<IEnumerable<T>>
    {
        IEnumerable<T> _enumerable;
        int _partitionSize;
        public PartitioningEnumerable(IEnumerable<T> enumerable, int partitionSize)
        {
            _enumerable = enumerable;
            _partitionSize = partitionSize;
        }

        public IEnumerator<IEnumerable<T>> GetEnumerator()
        {
            return new PartitioningEnumerator<T>(_enumerable.GetEnumerator(), _partitionSize);
        }

        IEnumerator IEnumerable.GetEnumerator()
        {
            return GetEnumerator();
        }
    }


    class PartitioningEnumerator<T> : IEnumerator<IEnumerable<T>>
    {
        IEnumerator<T> _enumerator;
        int _partitionSize;
        public PartitioningEnumerator(IEnumerator<T> enumerator, int partitionSize)
        {
            _enumerator = enumerator;
            _partitionSize = partitionSize;
        }

        public void Dispose()
        {
            _enumerator.Dispose();
        }

        IEnumerable<T> _current;
        public IEnumerable<T> Current
        {
            get { return _current; }
        }
        object IEnumerator.Current
        {
            get { return _current; }
        }

        public void Reset()
        {
            _current = null;
            _enumerator.Reset();
        }

        public bool MoveNext()
        {
            bool result;

            if (_enumerator.MoveNext())
            {
                _current = new PartitionEnumerable<T>(_enumerator, _partitionSize);
                result = true;
            }
            else
            {
                _current = null;
                result = false;
            }

            return result;
        }

    }



    class PartitionEnumerable<T> : IEnumerable<T>
    {
        IEnumerator<T> _enumerator;
        int _partitionSize;
        public PartitionEnumerable(IEnumerator<T> enumerator, int partitionSize)
        {
            _enumerator = enumerator;
            _partitionSize = partitionSize;
        }

        public IEnumerator<T> GetEnumerator()
        {
            return new PartitionEnumerator<T>(_enumerator, _partitionSize);
        }

        IEnumerator IEnumerable.GetEnumerator()
        {
            return GetEnumerator();
        }
    }


    class PartitionEnumerator<T> : IEnumerator<T>
    {
        IEnumerator<T> _enumerator;
        int _partitionSize;
        int _count;
        public PartitionEnumerator(IEnumerator<T> enumerator, int partitionSize)
        {
            _enumerator = enumerator;
            _partitionSize = partitionSize;
        }

        public void Dispose()
        {
        }

        public T Current
        {
            get { return _enumerator.Current; }
        }
        object IEnumerator.Current
        {
            get { return _enumerator.Current; }
        }
        public void Reset()
        {
            if (_count > 0) throw new InvalidOperationException();
        }

        public bool MoveNext()
        {
            bool result;

            if (_count < _partitionSize)
            {
                if (_count > 0)
                {
                    result = _enumerator.MoveNext();
                }
                else
                {
                    result = true;
                }
                _count++;
            }
            else
            {
                result = false;
            }

            return result;
        }

    }
}

Enjoy!

Answer 2

I was looking for a split like the one with string, so the whole List is splitted according to some rule, not only the first part, this is my solution

List<int> sequence = new List<int>();
for (int i = 0; i < 2000; i++)
{
     sequence.Add(i);
}
int splitIndex = 900;
List<List<int>> splitted = new List<List<int>>();
while (sequence.Count != 0)
{
    splitted.Add(sequence.Take(splitIndex).ToList() );
    sequence.RemoveRange(0, Math.Min(splitIndex, sequence.Count));
}

Answer 3

int[] items = new int[] { 0,1,2,3,4,5,6,7,8,9, 10 };

int itemIndex = 0;
int groupSize = 2;
int nextGroup = groupSize;

var seqItems = from aItem in items
               group aItem by 
                            (itemIndex++ < nextGroup) 
                            ? 
                            nextGroup / groupSize
                            :
                            (nextGroup += groupSize) / groupSize
                            into itemGroup
               select itemGroup.AsEnumerable();

Answer 4

Ok, I'll throw my hat in the ring. The advantages of my algorithm:

1. No expensive multiplication, division, or modulus operators
2. All operations are O(1) (see note below)
3. Works for IEnumerable<> source (no Count property needed)
4. Simple

The code:

public static IEnumerable<IEnumerable<T>>
  Section<T>(this IEnumerable<T> source, int length)
{
  if (length <= 0)
    throw new ArgumentOutOfRangeException("length");

  var section = new List<T>(length);

  foreach (var item in source)
  {
    section.Add(item);

    if (section.Count == length)
    {
      yield return section.AsReadOnly();
      section = new List<T>(length);
    }
  }

  if (section.Count > 0)
    yield return section.AsReadOnly();
}

As pointed out in the comments below, this approach doesn't actually address the original question which asked for a fixed number of sections of approximately equal length. That said, you can still use my approach to solve the original question by calling it this way:

myEnum.Section(myEnum.Count() / number_of_sections + 1)

When used in this manner, the approach is no longer O(1) as the Count() operation is O(N).

Answer 5

This is same as the accepted answer, but a much simpler representation:

public static IEnumerable<IEnumerable<T>> Split<T>(this IEnumerable<T> items, 
                                                   int numOfParts)
{
    int i = 0;
    return items.GroupBy(x => i++ % numOfParts);
}

The above method splits an IEnumerable<T> into N number of chunks of equal sizes or close to equal sizes.

public static IEnumerable<IEnumerable<T>> Partition<T>(this IEnumerable<T> items, 
                                                       int partitionSize)
{
    int i = 0;
    return items.GroupBy(x => i++ / partitionSize).ToArray();
}

The above method splits an IEnumerable<T> into chunks of desired fixed size with total number of chunks being unimportant - which is not what the question is about.

The problem with the Split method, besides being slower, is that it scrambles the output in the sense that the grouping will be done on the basis of i'th multiple of N for each position, or in other words you don't get the chunks in the original order.

Almost every answer here either doesn't preserve order, or is about partitioning and not splitting, or is plainly wrong. Try this which is faster, preserves order but a lil' more verbose:

public static IEnumerable<IEnumerable<T>> Split<T>(this ICollection<T> items, 
                                                   int numberOfChunks)
{
    if (numberOfChunks <= 0 || numberOfChunks > items.Count)
        throw new ArgumentOutOfRangeException("numberOfChunks");

    int sizePerPacket = items.Count / numberOfChunks;
    int extra = items.Count % numberOfChunks;

    for (int i = 0; i < numberOfChunks - extra; i++)
        yield return items.Skip(i * sizePerPacket).Take(sizePerPacket);

    int alreadyReturnedCount = (numberOfChunks - extra) * sizePerPacket;
    int toReturnCount = extra == 0 ? 0 : (items.Count - numberOfChunks) / extra + 1;
    for (int i = 0; i < extra; i++)
        yield return items.Skip(alreadyReturnedCount + i * toReturnCount).Take(toReturnCount);
}

The equivalent method for a Partition operation here

Answer 6

A pure linq and the simplest solution is as shown below.

static class LinqExtensions
{
    public static IEnumerable<IEnumerable<T>> Split<T>(this IEnumerable<T> list, int parts)
    {
        int i = 0;
        var splits = from item in list
                     group item by i++ % parts into part
                     select part.AsEnumerable();
        return splits;
    }
}