Develop Reference

Merge Sort C# Invalid Output

My homework is about using Strategy Patterns and implementing Bubble sort, Quick sort, and Merge sort. I have done the first two but my Merge Sort seems to be giving me the wrong output when I input "bonakid" it gives me an output of "abkidon". May I know which part is wrong in the implementation?
Also, I have used this particular ISortStrategy on my Bubble Sort and Quick Sort so it would be nice if they would use the same one so I would not have to change the others.
class mergeSort : ISortStrategy
{
public string Sort(string input)
{
var result = "";
int size = (input.Length % 2 == 0) ? input.Length / 2 : (input.Length + 1) / 2;
if (input.Length > 1)
{
char[] left = input.Substring(0, input.Length / 2).ToCharArray();
char[] right = input.Substring(input.Length / 2, input.Length - (input.Length / 2)).ToCharArray();
// Sorting two halves recursively
Sort(left.Length.ToString());
Sort(right.Length.ToString());
//merging left and right sublists
result = merge(input, left, right);
}
return result;
}
public string merge(string result, char[] left, char[] right)
{
int i1 = 0; // indexing left
int i2 = 0; // indexing right
var theString = result;
var aStringBuilder = new StringBuilder(theString);
for (int i = 0; i < aStringBuilder.Length; i++)
{
if (i2 >= right.Length || (i1 < left.Length && left.GetValue(i1).ToString().CompareTo(right.GetValue(i2).ToString()) < 0))
{
aStringBuilder.Remove(i, 1);
aStringBuilder.Insert(i, left.GetValue(i1).ToString());
i1++;
}
else
{
aStringBuilder.Remove(i, 1);
aStringBuilder.Insert(i, right.GetValue(i2).ToString());
i2++;
}
}
theString = aStringBuilder.ToString();
return theString;
}
}
}
public interface ISortStrategy
{
string Sort(string input);
}

Here is a refined version that minimizes allocations and performs the merge with parallel execution. Taken from this question.
using System;
using System.Collections.Generic;
using System.Threading.Tasks;
public class Program
{
public static void Main()
{
ISortStrategy sort = new MergeSort();
Console.WriteLine(sort.Sort("bonakid"));
}
}
public interface ISortStrategy
{
string Sort(string input);
}
public class MergeSort : ISortStrategy
{
public string Sort(string input)
{
return SortAlgo.Merge(input).Result;
}
}
public static class SortAlgo
{
public async static ValueTask<string> Merge(
string input,
IComparer<char> comparer = null)
{
comparer ??= Comparer<char>.Default;
// buffer to contain the orginal data.
Memory<char> source = new char[input.Length];
input.AsMemory().CopyTo(source);
// other buffer, that starts as the output.
Memory<char> buffer = new char[source.Length];
// copy the stack allocated buffer out as the result;
return (await MergeLadder(
source,
buffer,
comparer)).ToString();
}
public async static ValueTask<T[]> Merge<T>(
T[] input,
IComparer<T> comparer = null)
{
comparer ??= Comparer<T>.Default;
// buffer to contain the orginal data.
Memory<T> source = new T[input.Length];
// intentionally copying input so it is not mutated.
input.AsMemory().CopyTo(source);
// other buffer, that starts as the output.
Memory<T> buffer = new T[source.Length];
// copy the stack allocated buffer out as the result;
return (await MergeLadder(
source,
buffer,
comparer)).ToArray();
}
/// <remarks>
/// Bottom up merge with alternatring buffers.
/// </remarks>
private async static ValueTask<ReadOnlyMemory<T>> MergeLadder<T>(
Memory<T> input,
Memory<T> output,
IComparer<T> comparer,
int width = 2)
{
var half = width / 2;
await WhenAll(GetMergeTasks(
input,
output,
comparer,
width,
half));
// Did the last stride cover the whole input?
if (width >= input.Length)
{
// Yes, everything is sorted
return output;
}
else
{
// No, walk the array again with double the width.
// Switch the buffers so we don't walk over the results.
return await MergeLadder(output, input, comparer, width * 2);
}
}
private async static IAsyncEnumerable<Task> GetMergeTasks<T>(
Memory<T> input,
Memory<T> output,
IComparer<T> comparer,
int width,
int half)
{
// walk the input sequence in mergable strides
// combine the left and right halves into the output
for (int i = 0; i < input.Length; i += width)
{
Memory<T> left;
Memory<T> right;
Memory<T> merge;
var remaining = input.Length - i;
if (remaining <= half)
{
// not enough left for a right.
left = input.Slice(i, remaining);
right = Memory<T>.Empty;
merge = output.Slice(i, remaining);
}
else if (remaining < width)
{
// not enought for a whole right.
left = input.Slice(i, half);
right = input.Slice(i + half, remaining - half);
merge = output.Slice(i, remaining);
}
else
{
// the full stride.
left = input.Slice(i, half);
right = input.Slice(i + half, half);
merge = output.Slice(i, width);
}
// Now merge the left and right for this stride.
yield return Task.Run(() => Merge(left, right, merge, comparer));
await Task.CompletedTask;
}
}
public static async ValueTask WhenAll(IAsyncEnumerable<Task> tasks)
{
ArgumentNullException.ThrowIfNull(tasks);
// We don't allocate the list if no task throws
List<Exception> exceptions = null;
await foreach(var task in tasks)
{
try
{
await task;
}
catch(Exception ex)
{
exceptions ??= new();
exceptions.Add(ex);
}
}
if (!(exceptions is null))
{
throw new AggregateException(exceptions);
}
}
private static void Merge<T>(
ReadOnlyMemory<T> leftMemory,
ReadOnlyMemory<T> rightMemory,
Memory<T> mergeMemory,
IComparer<T> comparer)
{
var left = leftMemory.Span;
var right = rightMemory.Span;
var merge = mergeMemory.Span;
//While either span has an element
for(int m = 0, l = 0, r= 0; l < left.Length || r < right.Length; m++)
{
if (l < left.Length && r < right.Length)
{
//both sides have elements
if (comparer.Compare(left[l], right[r]) <= 0)
{
// left is less than right
merge[m] = left[l];
l++;
}
else
{
// right is less than left
merge[m] = right[r];
r++;
}
}
else if (l < left.Length)
{
// only left has some left
merge[m] = left[l];
l++;
}
else
{
// only right has some left
merge[m] = right[r];
r++;
}
}
}
}
As demonstrated here, here is a working example,
using System;
using System.Linq;
using System.Collections.Generic;
public class Program
{
public static void Main()
{
ISortStrategy mergeSort = new MergeSort();
Console.WriteLine(mergeSort.Sort("bonakid"));
}
}
public interface ISortStrategy
{
string Sort(string input);
}
public class MergeSort : ISortStrategy
{
public string Sort(string input)
{
return new string(Homework.MergeSort(input).ToArray());
}
}
public static class Homework
{
public static IList<T> MergeSort<T>(
IEnumerable<T> inputSequence,
IComparer<T> comparer = null)
{
if (comparer == null)
{
comparer = Comparer<T>.Default;
}
IList<T> input = inputSequence.ToArray();
IList<T> left;
IList<T> right;
IList<T> result = new T[input.Count];
// As this is a recursive algorithm, we need to have a base case to
// avoid an infinite recursion and therfore a stack overflow.
if (input.Count <= 1)
{
return input;
}
// The exact midpoint of our array.
int midPoint = Math.DivRem(input.Count, 2, out int twoRemainder);
// Will represent our 'left' array.
left = new T[midPoint];
if (twoRemainder == 0)
{
//The array has an even number of elements, the left and right array
//will have the same number of elements.
right = new T[midPoint];
}
else
{
// The array has an odd number of elements, the right array
// will have one more element than left.
right = new T[midPoint + 1];
}
//populate left array
for (int i = 0; i < midPoint; i++)
{
left[i] = input[i];
}
// populate right array
// start index from the midpoint, as we have already populated
// the left array from 0 to midpont.
for (int x = 0, i = midPoint; i < input.Count; i++, x++)
{
right[x] = input[i];
}
//Recursively sort the left array
left = MergeSort(left);
//Recursively sort the right array
right = MergeSort(right);
//Merge our two sorted arrays
result = Merge(left, right, comparer);
return result;
}
//This method will be responsible for combining our two sorted arrays into one giant array
private static IList<T> Merge<T>(
IList<T> left,
IList<T> right,
IComparer<T> comparer)
{
int resultLength = right.Count + left.Count;
IList<T> result = new T[resultLength];
int indexLeft = 0, indexRight = 0, indexResult = 0;
//while either array still has an element
while (indexLeft < left.Count || indexRight < right.Count)
{
// if both arrays have elements
if (indexLeft < left.Count && indexRight < right.Count)
{
// If item on left array is less than item on right array, add that item to the result array
if (comparer.Compare(left[indexLeft], right[indexRight]) <= 0)
{
result[indexResult] = left[indexLeft];
indexLeft++;
indexResult++;
}
// else the item in the right array wll be added to the results array
else
{
result[indexResult] = right[indexRight];
indexRight++;
indexResult++;
}
}
//if only the left array still has elements, add all its items to the results array
else if (indexLeft < left.Count)
{
result[indexResult] = left[indexLeft];
indexLeft++;
indexResult++;
}
//if only the right array still has elements, add all its items to the results array
else if (indexRight < right.Count)
{
result[indexResult] = right[indexRight];
indexRight++;
indexResult++;
}
}
return result;
}
}

Lambda for List within a List [duplicate]

Is there any way I can separate a List<SomeObject> into several separate lists of SomeObject, using the item index as the delimiter of each split?
Let me exemplify:
I have a List<SomeObject> and I need a List<List<SomeObject>> or List<SomeObject>[], so that each of these resulting lists will contain a group of 3 items of the original list (sequentially).
eg.:
Original List: [a, g, e, w, p, s, q, f, x, y, i, m, c]
Resulting lists: [a, g, e], [w, p, s], [q, f, x], [y, i, m], [c]
I'd also need the resulting lists size to be a parameter of this function.

Try the following code.
public static List<List<T>> Split<T>(IList<T> source)
{
return source
.Select((x, i) => new { Index = i, Value = x })
.GroupBy(x => x.Index / 3)
.Select(x => x.Select(v => v.Value).ToList())
.ToList();
}
The idea is to first group the elements by indexes. Dividing by three has the effect of grouping them into groups of 3. Then convert each group to a list and the IEnumerable of List to a List of Lists

I just wrote this, and I think it's a little more elegant than the other proposed solutions:
/// <summary>
/// Break a list of items into chunks of a specific size
/// </summary>
public static IEnumerable<IEnumerable<T>> Chunk<T>(this IEnumerable<T> source, int chunksize)
{
while (source.Any())
{
yield return source.Take(chunksize);
source = source.Skip(chunksize);
}
}

In general the approach suggested by CaseyB works fine, in fact if you are passing in a List<T> it is hard to fault it, perhaps I would change it to:
public static IEnumerable<IEnumerable<T>> ChunkTrivialBetter<T>(this IEnumerable<T> source, int chunksize)
{
var pos = 0;
while (source.Skip(pos).Any())
{
yield return source.Skip(pos).Take(chunksize);
pos += chunksize;
}
}
Which will avoid massive call chains. Nonetheless, this approach has a general flaw. It materializes two enumerations per chunk, to highlight the issue try running:
foreach (var item in Enumerable.Range(1, int.MaxValue).Chunk(8).Skip(100000).First())
{
Console.WriteLine(item);
}
// wait forever
To overcome this we can try Cameron's approach, which passes the above test in flying colors as it only walks the enumeration once.
Trouble is that it has a different flaw, it materializes every item in each chunk, the trouble with that approach is that you run high on memory.
To illustrate that try running:
foreach (var item in Enumerable.Range(1, int.MaxValue)
.Select(x => x + new string('x', 100000))
.Clump(10000).Skip(100).First())
{
Console.Write('.');
}
// OutOfMemoryException
Finally, any implementation should be able to handle out of order iteration of chunks, for example:
Enumerable.Range(1,3).Chunk(2).Reverse().ToArray()
// should return [3],[1,2]
Many highly optimal solutions like my first revision of this answer failed there. The same issue can be seen in casperOne's optimized answer.
To address all these issues you can use the following:
namespace ChunkedEnumerator
{
public static class Extensions
{
class ChunkedEnumerable<T> : IEnumerable<T>
{
class ChildEnumerator : IEnumerator<T>
{
ChunkedEnumerable<T> parent;
int position;
bool done = false;
T current;
public ChildEnumerator(ChunkedEnumerable<T> parent)
{
this.parent = parent;
position = -1;
parent.wrapper.AddRef();
}
public T Current
{
get
{
if (position == -1 || done)
{
throw new InvalidOperationException();
}
return current;
}
}
public void Dispose()
{
if (!done)
{
done = true;
parent.wrapper.RemoveRef();
}
}
object System.Collections.IEnumerator.Current
{
get { return Current; }
}
public bool MoveNext()
{
position++;
if (position + 1 > parent.chunkSize)
{
done = true;
}
if (!done)
{
done = !parent.wrapper.Get(position + parent.start, out current);
}
return !done;
}
public void Reset()
{
// per http://msdn.microsoft.com/en-us/library/system.collections.ienumerator.reset.aspx
throw new NotSupportedException();
}
}
EnumeratorWrapper<T> wrapper;
int chunkSize;
int start;
public ChunkedEnumerable(EnumeratorWrapper<T> wrapper, int chunkSize, int start)
{
this.wrapper = wrapper;
this.chunkSize = chunkSize;
this.start = start;
}
public IEnumerator<T> GetEnumerator()
{
return new ChildEnumerator(this);
}
System.Collections.IEnumerator System.Collections.IEnumerable.GetEnumerator()
{
return GetEnumerator();
}
}
class EnumeratorWrapper<T>
{
public EnumeratorWrapper (IEnumerable<T> source)
{
SourceEumerable = source;
}
IEnumerable<T> SourceEumerable {get; set;}
Enumeration currentEnumeration;
class Enumeration
{
public IEnumerator<T> Source { get; set; }
public int Position { get; set; }
public bool AtEnd { get; set; }
}
public bool Get(int pos, out T item)
{
if (currentEnumeration != null && currentEnumeration.Position > pos)
{
currentEnumeration.Source.Dispose();
currentEnumeration = null;
}
if (currentEnumeration == null)
{
currentEnumeration = new Enumeration { Position = -1, Source = SourceEumerable.GetEnumerator(), AtEnd = false };
}
item = default(T);
if (currentEnumeration.AtEnd)
{
return false;
}
while(currentEnumeration.Position < pos)
{
currentEnumeration.AtEnd = !currentEnumeration.Source.MoveNext();
currentEnumeration.Position++;
if (currentEnumeration.AtEnd)
{
return false;
}
}
item = currentEnumeration.Source.Current;
return true;
}
int refs = 0;
// needed for dispose semantics
public void AddRef()
{
refs++;
}
public void RemoveRef()
{
refs--;
if (refs == 0 && currentEnumeration != null)
{
var copy = currentEnumeration;
currentEnumeration = null;
copy.Source.Dispose();
}
}
}
public static IEnumerable<IEnumerable<T>> Chunk<T>(this IEnumerable<T> source, int chunksize)
{
if (chunksize < 1) throw new InvalidOperationException();
var wrapper = new EnumeratorWrapper<T>(source);
int currentPos = 0;
T ignore;
try
{
wrapper.AddRef();
while (wrapper.Get(currentPos, out ignore))
{
yield return new ChunkedEnumerable<T>(wrapper, chunksize, currentPos);
currentPos += chunksize;
}
}
finally
{
wrapper.RemoveRef();
}
}
}
class Program
{
static void Main(string[] args)
{
int i = 10;
foreach (var group in Enumerable.Range(1, int.MaxValue).Skip(10000000).Chunk(3))
{
foreach (var n in group)
{
Console.Write(n);
Console.Write(" ");
}
Console.WriteLine();
if (i-- == 0) break;
}
var stuffs = Enumerable.Range(1, 10).Chunk(2).ToArray();
foreach (var idx in new [] {3,2,1})
{
Console.Write("idx " + idx + " ");
foreach (var n in stuffs[idx])
{
Console.Write(n);
Console.Write(" ");
}
Console.WriteLine();
}
/*
10000001 10000002 10000003
10000004 10000005 10000006
10000007 10000008 10000009
10000010 10000011 10000012
10000013 10000014 10000015
10000016 10000017 10000018
10000019 10000020 10000021
10000022 10000023 10000024
10000025 10000026 10000027
10000028 10000029 10000030
10000031 10000032 10000033
idx 3 7 8
idx 2 5 6
idx 1 3 4
*/
Console.ReadKey();
}
}
}
There is also a round of optimisations you could introduce for out-of-order iteration of chunks, which is out of scope here.
As to which method you should choose? It totally depends on the problem you are trying to solve. If you are not concerned with the first flaw the simple answer is incredibly appealing.
Note as with most methods, this is not safe for multi threading, stuff can get weird if you wish to make it thread safe you would need to amend EnumeratorWrapper.

You could use a number of queries that use Take and Skip, but that would add too many iterations on the original list, I believe.
Rather, I think you should create an iterator of your own, like so:
public static IEnumerable<IEnumerable<T>> GetEnumerableOfEnumerables<T>(
IEnumerable<T> enumerable, int groupSize)
{
// The list to return.
List<T> list = new List<T>(groupSize);
// Cycle through all of the items.
foreach (T item in enumerable)
{
// Add the item.
list.Add(item);
// If the list has the number of elements, return that.
if (list.Count == groupSize)
{
// Return the list.
yield return list;
// Set the list to a new list.
list = new List<T>(groupSize);
}
}
// Return the remainder if there is any,
if (list.Count != 0)
{
// Return the list.
yield return list;
}
}
You can then call this and it is LINQ enabled so you can perform other operations on the resulting sequences.
In light of Sam's answer, I felt there was an easier way to do this without:
Iterating through the list again (which I didn't do originally)
Materializing the items in groups before releasing the chunk (for large chunks of items, there would be memory issues)
All of the code that Sam posted
That said, here's another pass, which I've codified in an extension method to IEnumerable<T> called Chunk:
public static IEnumerable<IEnumerable<T>> Chunk<T>(this IEnumerable<T> source,
int chunkSize)
{
// Validate parameters.
if (source == null) throw new ArgumentNullException(nameof(source));
if (chunkSize <= 0) throw new ArgumentOutOfRangeException(nameof(chunkSize),
"The chunkSize parameter must be a positive value.");
// Call the internal implementation.
return source.ChunkInternal(chunkSize);
}
Nothing surprising up there, just basic error checking.
Moving on to ChunkInternal:
private static IEnumerable<IEnumerable<T>> ChunkInternal<T>(
this IEnumerable<T> source, int chunkSize)
{
// Validate parameters.
Debug.Assert(source != null);
Debug.Assert(chunkSize > 0);
// Get the enumerator. Dispose of when done.
using (IEnumerator<T> enumerator = source.GetEnumerator())
do
{
// Move to the next element. If there's nothing left
// then get out.
if (!enumerator.MoveNext()) yield break;
// Return the chunked sequence.
yield return ChunkSequence(enumerator, chunkSize);
} while (true);
}
Basically, it gets the IEnumerator<T> and manually iterates through each item. It checks to see if there any items currently to be enumerated. After each chunk is enumerated through, if there aren't any items left, it breaks out.
Once it detects there are items in the sequence, it delegates the responsibility for the inner IEnumerable<T> implementation to ChunkSequence:
private static IEnumerable<T> ChunkSequence<T>(IEnumerator<T> enumerator,
int chunkSize)
{
// Validate parameters.
Debug.Assert(enumerator != null);
Debug.Assert(chunkSize > 0);
// The count.
int count = 0;
// There is at least one item. Yield and then continue.
do
{
// Yield the item.
yield return enumerator.Current;
} while (++count < chunkSize && enumerator.MoveNext());
}
Since MoveNext was already called on the IEnumerator<T> passed to ChunkSequence, it yields the item returned by Current and then increments the count, making sure never to return more than chunkSize items and moving to the next item in the sequence after every iteration (but short-circuited if the number of items yielded exceeds the chunk size).
If there are no items left, then the InternalChunk method will make another pass in the outer loop, but when MoveNext is called a second time, it will still return false, as per the documentation (emphasis mine):
If MoveNext passes the end of the collection, the enumerator is
positioned after the last element in the collection and MoveNext
returns false. When the enumerator is at this position, subsequent
calls to MoveNext also return false until Reset is called.
At this point, the loop will break, and the sequence of sequences will terminate.
This is a simple test:
static void Main()
{
string s = "agewpsqfxyimc";
int count = 0;
// Group by three.
foreach (IEnumerable<char> g in s.Chunk(3))
{
// Print out the group.
Console.Write("Group: {0} - ", ++count);
// Print the items.
foreach (char c in g)
{
// Print the item.
Console.Write(c + ", ");
}
// Finish the line.
Console.WriteLine();
}
}
Output:
Group: 1 - a, g, e,
Group: 2 - w, p, s,
Group: 3 - q, f, x,
Group: 4 - y, i, m,
Group: 5 - c,
An important note, this will not work if you don't drain the entire child sequence or break at any point in the parent sequence. This is an important caveat, but if your use case is that you will consume every element of the sequence of sequences, then this will work for you.
Additionally, it will do strange things if you play with the order, just as Sam's did at one point.

Ok, here's my take on it:
completely lazy: works on infinite enumerables
no intermediate copying/buffering
O(n) execution time
works also when inner sequences are only partially consumed
public static IEnumerable<IEnumerable<T>> Chunks<T>(this IEnumerable<T> enumerable,
int chunkSize)
{
if (chunkSize < 1) throw new ArgumentException("chunkSize must be positive");
using (var e = enumerable.GetEnumerator())
while (e.MoveNext())
{
var remaining = chunkSize; // elements remaining in the current chunk
var innerMoveNext = new Func<bool>(() => --remaining > 0 && e.MoveNext());
yield return e.GetChunk(innerMoveNext);
while (innerMoveNext()) {/* discard elements skipped by inner iterator */}
}
}
private static IEnumerable<T> GetChunk<T>(this IEnumerator<T> e,
Func<bool> innerMoveNext)
{
do yield return e.Current;
while (innerMoveNext());
}
Example Usage
var src = new [] {1, 2, 3, 4, 5, 6};
var c3 = src.Chunks(3); // {{1, 2, 3}, {4, 5, 6}};
var c4 = src.Chunks(4); // {{1, 2, 3, 4}, {5, 6}};
var sum = c3.Select(c => c.Sum()); // {6, 15}
var count = c3.Count(); // 2
var take2 = c3.Select(c => c.Take(2)); // {{1, 2}, {4, 5}}
Explanations
The code works by nesting two yield based iterators.
The outer iterator must keep track of how many elements have been effectively consumed by the inner (chunk) iterator. This is done by closing over remaining with innerMoveNext(). Unconsumed elements of a chunk are discarded before the next chunk is yielded by the outer iterator.
This is necessary because otherwise you get inconsistent results, when the inner enumerables are not (completely) consumed (e.g. c3.Count() would return 6).
Note: The answer has been updated to address the shortcomings pointed out by #aolszowka.

Update .NET 6.0
.NET 6.0 added a new native Chunk method to the System.Linq namespace:
public static System.Collections.Generic.IEnumerable<TSource[]> Chunk<TSource> (
this System.Collections.Generic.IEnumerable<TSource> source, int size);
Using this new method every chunk except the last will be of size size. The last chunk will contain the remaining elements and may be of a smaller size.
Here is an example:
var list = Enumerable.Range(1, 100);
var chunkSize = 10;
foreach(var chunk in list.Chunk(chunkSize)) //Returns a chunk with the correct size.
{
Parallel.ForEach(chunk, (item) =>
{
//Do something Parallel here.
Console.WriteLine(item);
});
}
You’re probably thinking, well why not use Skip and Take? Which is true, I think this is just a bit more concise and makes things just that little bit more readable.

completely lazy, no counting or copying:
public static class EnumerableExtensions
{
public static IEnumerable<IEnumerable<T>> Split<T>(this IEnumerable<T> source, int len)
{
if (len == 0)
throw new ArgumentNullException();
var enumer = source.GetEnumerator();
while (enumer.MoveNext())
{
yield return Take(enumer.Current, enumer, len);
}
}
private static IEnumerable<T> Take<T>(T head, IEnumerator<T> tail, int len)
{
while (true)
{
yield return head;
if (--len == 0)
break;
if (tail.MoveNext())
head = tail.Current;
else
break;
}
}
}

I think the following suggestion would be the fastest. I am sacrificing the lazyness of the source Enumerable for the ability to use Array.Copy and knowing ahead of the time the length of each of my sublists.
public static IEnumerable<T[]> Chunk<T>(this IEnumerable<T> items, int size)
{
T[] array = items as T[] ?? items.ToArray();
for (int i = 0; i < array.Length; i+=size)
{
T[] chunk = new T[Math.Min(size, array.Length - i)];
Array.Copy(array, i, chunk, 0, chunk.Length);
yield return chunk;
}
}

For anyone interested in a packaged/maintained solution, the MoreLINQ library provides the Batch extension method which matches your requested behavior:
IEnumerable<char> source = "Example string";
IEnumerable<IEnumerable<char>> chunksOfThreeChars = source.Batch(3);
The Batch implementation is similar to Cameron MacFarland's answer, with the addition of an overload for transforming the chunk/batch before returning, and performs quite well.

I wrote a Clump extension method several years ago. Works great, and is the fastest implementation here. :P
/// <summary>
/// Clumps items into same size lots.
/// </summary>
/// <typeparam name="T"></typeparam>
/// <param name="source">The source list of items.</param>
/// <param name="size">The maximum size of the clumps to make.</param>
/// <returns>A list of list of items, where each list of items is no bigger than the size given.</returns>
public static IEnumerable<IEnumerable<T>> Clump<T>(this IEnumerable<T> source, int size)
{
if (source == null)
throw new ArgumentNullException("source");
if (size < 1)
throw new ArgumentOutOfRangeException("size", "size must be greater than 0");
return ClumpIterator<T>(source, size);
}
private static IEnumerable<IEnumerable<T>> ClumpIterator<T>(IEnumerable<T> source, int size)
{
Debug.Assert(source != null, "source is null.");
T[] items = new T[size];
int count = 0;
foreach (var item in source)
{
items[count] = item;
count++;
if (count == size)
{
yield return items;
items = new T[size];
count = 0;
}
}
if (count > 0)
{
if (count == size)
yield return items;
else
{
T[] tempItems = new T[count];
Array.Copy(items, tempItems, count);
yield return tempItems;
}
}
}

We can improve #JaredPar's solution to do true lazy evaluation. We use a GroupAdjacentBy method that yields groups of consecutive elements with the same key:
sequence
.Select((x, i) => new { Value = x, Index = i })
.GroupAdjacentBy(x=>x.Index/3)
.Select(g=>g.Select(x=>x.Value))
Because the groups are yielded one-by-one, this solution works efficiently with long or infinite sequences.

System.Interactive provides Buffer() for this purpose. Some quick testing shows performance is similar to Sam's solution.

I find this little snippet does the job quite nicely.
public static IEnumerable<List<T>> Chunked<T>(this List<T> source, int chunkSize)
{
var offset = 0;
while (offset < source.Count)
{
yield return source.GetRange(offset, Math.Min(source.Count - offset, chunkSize));
offset += chunkSize;
}
}

Here's a list splitting routine I wrote a couple months ago:
public static List<List<T>> Chunk<T>(
List<T> theList,
int chunkSize
)
{
List<List<T>> result = theList
.Select((x, i) => new {
data = x,
indexgroup = i / chunkSize
})
.GroupBy(x => x.indexgroup, x => x.data)
.Select(g => new List<T>(g))
.ToList();
return result;
}

We found David B's solution worked the best. But we adapted it to a more general solution:
list.GroupBy(item => item.SomeProperty)
.Select(group => new List<T>(group))
.ToArray();

What about this one?
var input = new List<string> { "a", "g", "e", "w", "p", "s", "q", "f", "x", "y", "i", "m", "c" };
var k = 3
var res = Enumerable.Range(0, (input.Count - 1) / k + 1)
.Select(i => input.GetRange(i * k, Math.Min(k, input.Count - i * k)))
.ToList();
As far as I know, GetRange() is linear in terms of number of items taken. So this should perform well.

This is an old question but this is what I ended up with; it enumerates the enumerable only once, but does create lists for each of the partitions. It doesn't suffer from unexpected behavior when ToArray() is called as some of the implementations do:
public static IEnumerable<IEnumerable<T>> Partition<T>(IEnumerable<T> source, int chunkSize)
{
if (source == null)
{
throw new ArgumentNullException("source");
}
if (chunkSize < 1)
{
throw new ArgumentException("Invalid chunkSize: " + chunkSize);
}
using (IEnumerator<T> sourceEnumerator = source.GetEnumerator())
{
IList<T> currentChunk = new List<T>();
while (sourceEnumerator.MoveNext())
{
currentChunk.Add(sourceEnumerator.Current);
if (currentChunk.Count == chunkSize)
{
yield return currentChunk;
currentChunk = new List<T>();
}
}
if (currentChunk.Any())
{
yield return currentChunk;
}
}
}

Old code, but this is what I've been using:
public static IEnumerable<List<T>> InSetsOf<T>(this IEnumerable<T> source, int max)
{
var toReturn = new List<T>(max);
foreach (var item in source)
{
toReturn.Add(item);
if (toReturn.Count == max)
{
yield return toReturn;
toReturn = new List<T>(max);
}
}
if (toReturn.Any())
{
yield return toReturn;
}
}

This following solution is the most compact I could come up with that is O(n).
public static IEnumerable<T[]> Chunk<T>(IEnumerable<T> source, int chunksize)
{
var list = source as IList<T> ?? source.ToList();
for (int start = 0; start < list.Count; start += chunksize)
{
T[] chunk = new T[Math.Min(chunksize, list.Count - start)];
for (int i = 0; i < chunk.Length; i++)
chunk[i] = list[start + i];
yield return chunk;
}
}

If the list is of type system.collections.generic you can use the "CopyTo" method available to copy elements of your array to other sub arrays. You specify the start element and number of elements to copy.
You could also make 3 clones of your original list and use the "RemoveRange" on each list to shrink the list to the size you want.
Or just create a helper method to do it for you.

It's an old solution but I had a different approach. I use Skip to move to desired offset and Take to extract desired number of elements:
public static IEnumerable<IEnumerable<T>> Chunk<T>(this IEnumerable<T> source,
int chunkSize)
{
if (chunkSize <= 0)
throw new ArgumentOutOfRangeException($"{nameof(chunkSize)} should be > 0");
var nbChunks = (int)Math.Ceiling((double)source.Count()/chunkSize);
return Enumerable.Range(0, nbChunks)
.Select(chunkNb => source.Skip(chunkNb*chunkSize)
.Take(chunkSize));
}

Another way is using Rx Buffer operator
//using System.Linq;
//using System.Reactive.Linq;
//using System.Reactive.Threading.Tasks;
var observableBatches = anAnumerable.ToObservable().Buffer(size);
var batches = aList.ToObservable().Buffer(size).ToList().ToTask().GetAwaiter().GetResult();

The question was how to "Split List into Sublists with LINQ", but sometimes you may want those sub-lists to be references to the original list, not copies. This allows you to modify the original list from the sub-lists. In that case, this may work for you.
public static IEnumerable<Memory<T>> RefChunkBy<T>(this T[] array, int size)
{
if (size < 1 || array is null)
{
throw new ArgumentException("chunkSize must be positive");
}
var index = 0;
var counter = 0;
for (int i = 0; i < array.Length; i++)
{
if (counter == size)
{
yield return new Memory<T>(array, index, size);
index = i;
counter = 0;
}
counter++;
if (i + 1 == array.Length)
{
yield return new Memory<T>(array, index, array.Length - index);
}
}
}
Usage:
var src = new[] { 1, 2, 3, 4, 5, 6 };
var c3 = RefChunkBy(src, 3); // {{1, 2, 3}, {4, 5, 6}};
var c4 = RefChunkBy(src, 4); // {{1, 2, 3, 4}, {5, 6}};
// as extension method
var c3 = src.RefChunkBy(3); // {{1, 2, 3}, {4, 5, 6}};
var c4 = src.RefChunkBy(4); // {{1, 2, 3, 4}, {5, 6}};
var sum = c3.Select(c => c.Span.ToArray().Sum()); // {6, 15}
var count = c3.Count(); // 2
var take2 = c3.Select(c => c.Span.ToArray().Take(2)); // {{1, 2}, {4, 5}}
Feel free to make this code better.

Using modular partitioning:
public IEnumerable<IEnumerable<string>> Split(IEnumerable<string> input, int chunkSize)
{
var chunks = (int)Math.Ceiling((double)input.Count() / (double)chunkSize);
return Enumerable.Range(0, chunks).Select(id => input.Where(s => s.GetHashCode() % chunks == id));
}

Just putting in my two cents. If you wanted to "bucket" the list (visualize left to right), you could do the following:
public static List<List<T>> Buckets<T>(this List<T> source, int numberOfBuckets)
{
List<List<T>> result = new List<List<T>>();
for (int i = 0; i < numberOfBuckets; i++)
{
result.Add(new List<T>());
}
int count = 0;
while (count < source.Count())
{
var mod = count % numberOfBuckets;
result[mod].Add(source[count]);
count++;
}
return result;
}

public static List<List<T>> GetSplitItemsList<T>(List<T> originalItemsList, short number)
{
var listGroup = new List<List<T>>();
int j = number;
for (int i = 0; i < originalItemsList.Count; i += number)
{
var cList = originalItemsList.Take(j).Skip(i).ToList();
j += number;
listGroup.Add(cList);
}
return listGroup;
}

To insert my two cents...
By using the list type for the source to be chunked, I found another very compact solution:
public static IEnumerable<IEnumerable<TSource>> Chunk<TSource>(this IEnumerable<TSource> source, int chunkSize)
{
// copy the source into a list
var chunkList = source.ToList();
// return chunks of 'chunkSize' items
while (chunkList.Count > chunkSize)
{
yield return chunkList.GetRange(0, chunkSize);
chunkList.RemoveRange(0, chunkSize);
}
// return the rest
yield return chunkList;
}

I took the primary answer and made it to be an IOC container to determine where to split. (For who is really looking to only split on 3 items, in reading this post while searching for an answer?)
This method allows one to split on any type of item as needed.
public static List<List<T>> SplitOn<T>(List<T> main, Func<T, bool> splitOn)
{
int groupIndex = 0;
return main.Select( item => new
{
Group = (splitOn.Invoke(item) ? ++groupIndex : groupIndex),
Value = item
})
.GroupBy( it2 => it2.Group)
.Select(x => x.Select(v => v.Value).ToList())
.ToList();
}
So for the OP the code would be
var it = new List<string>()
{ "a", "g", "e", "w", "p", "s", "q", "f", "x", "y", "i", "m", "c" };
int index = 0;
var result = SplitOn(it, (itm) => (index++ % 3) == 0 );

So performatic as the Sam Saffron's approach.
public static IEnumerable<IEnumerable<T>> Batch<T>(this IEnumerable<T> source, int size)
{
if (source == null) throw new ArgumentNullException(nameof(source));
if (size <= 0) throw new ArgumentOutOfRangeException(nameof(size), "Size must be greater than zero.");
return BatchImpl(source, size).TakeWhile(x => x.Any());
}
static IEnumerable<IEnumerable<T>> BatchImpl<T>(this IEnumerable<T> source, int size)
{
var values = new List<T>();
var group = 1;
var disposed = false;
var e = source.GetEnumerator();
try
{
while (!disposed)
{
yield return GetBatch(e, values, group, size, () => { e.Dispose(); disposed = true; });
group++;
}
}
finally
{
if (!disposed)
e.Dispose();
}
}
static IEnumerable<T> GetBatch<T>(IEnumerator<T> e, List<T> values, int group, int size, Action dispose)
{
var min = (group - 1) * size + 1;
var max = group * size;
var hasValue = false;
while (values.Count < min && e.MoveNext())
{
values.Add(e.Current);
}
for (var i = min; i <= max; i++)
{
if (i <= values.Count)
{
hasValue = true;
}
else if (hasValue = e.MoveNext())
{
values.Add(e.Current);
}
else
{
dispose();
}
if (hasValue)
yield return values[i - 1];
else
yield break;
}
}
}

Can work with infinite generators:
a.Zip(a.Skip(1), (x, y) => Enumerable.Repeat(x, 1).Concat(Enumerable.Repeat(y, 1)))
.Zip(a.Skip(2), (xy, z) => xy.Concat(Enumerable.Repeat(z, 1)))
.Where((x, i) => i % 3 == 0)
Demo code: https://ideone.com/GKmL7M
using System;
using System.Collections.Generic;
using System.Linq;
public class Test
{
private static void DoIt(IEnumerable<int> a)
{
Console.WriteLine(String.Join(" ", a));
foreach (var x in a.Zip(a.Skip(1), (x, y) => Enumerable.Repeat(x, 1).Concat(Enumerable.Repeat(y, 1))).Zip(a.Skip(2), (xy, z) => xy.Concat(Enumerable.Repeat(z, 1))).Where((x, i) => i % 3 == 0))
Console.WriteLine(String.Join(" ", x));
Console.WriteLine();
}
public static void Main()
{
DoIt(new int[] {1});
DoIt(new int[] {1, 2});
DoIt(new int[] {1, 2, 3});
DoIt(new int[] {1, 2, 3, 4});
DoIt(new int[] {1, 2, 3, 4, 5});
DoIt(new int[] {1, 2, 3, 4, 5, 6});
}
}
1
1 2
1 2 3
1 2 3
1 2 3 4
1 2 3
1 2 3 4 5
1 2 3
1 2 3 4 5 6
1 2 3
4 5 6
But actually I would prefer to write corresponding method without linq.

Using Linq to get the last N elements of a collection?

Given a collection, is there a way to get the last N elements of that collection? If there isn't a method in the framework, what would be the best way to write an extension method to do this?

collection.Skip(Math.Max(0, collection.Count() - N));
This approach preserves item order without a dependency on any sorting, and has broad compatibility across several LINQ providers.
It is important to take care not to call Skip with a negative number. Some providers, such as the Entity Framework, will produce an ArgumentException when presented with a negative argument. The call to Math.Max avoids this neatly.
The class below has all of the essentials for extension methods, which are: a static class, a static method, and use of the this keyword.
public static class MiscExtensions
{
// Ex: collection.TakeLast(5);
public static IEnumerable<T> TakeLast<T>(this IEnumerable<T> source, int N)
{
return source.Skip(Math.Max(0, source.Count() - N));
}
}
A brief note on performance:
Because the call to Count() can cause enumeration of certain data structures, this approach has the risk of causing two passes over the data. This isn't really a problem with most enumerables; in fact, optimizations exist already for Lists, Arrays, and even EF queries to evaluate the Count() operation in O(1) time.
If, however, you must use a forward-only enumerable and would like to avoid making two passes, consider a one-pass algorithm like Lasse V. Karlsen or Mark Byers describe. Both of these approaches use a temporary buffer to hold items while enumerating, which are yielded once the end of the collection is found.

coll.Reverse().Take(N).Reverse().ToList();
public static IEnumerable<T> TakeLast<T>(this IEnumerable<T> coll, int N)
{
return coll.Reverse().Take(N).Reverse();
}
UPDATE: To address clintp's problem: a) Using the TakeLast() method I defined above solves the problem, but if you really want the do it without the extra method, then you just have to recognize that while Enumerable.Reverse() can be used as an extension method, you aren't required to use it that way:
List<string> mystring = new List<string>() { "one", "two", "three" };
mystring = Enumerable.Reverse(mystring).Take(2).Reverse().ToList();

.NET Core 2.0+ provides the LINQ method TakeLast():
https://learn.microsoft.com/en-us/dotnet/api/system.linq.enumerable.takelast
example:
Enumerable
.Range(1, 10)
.TakeLast(3) // <--- takes last 3 items
.ToList()
.ForEach(i => System.Console.WriteLine(i))
// outputs:
// 8
// 9
// 10

Note: I missed your question title which said Using Linq, so my answer does not in fact use Linq.
If you want to avoid caching a non-lazy copy of the entire collection, you could write a simple method that does it using a linked list.
The following method will add each value it finds in the original collection into a linked list, and trim the linked list down to the number of items required. Since it keeps the linked list trimmed to this number of items the entire time through iterating through the collection, it will only keep a copy of at most N items from the original collection.
It does not require you to know the number of items in the original collection, nor iterate over it more than once.
Usage:
IEnumerable<int> sequence = Enumerable.Range(1, 10000);
IEnumerable<int> last10 = sequence.TakeLast(10);
...
Extension method:
public static class Extensions
{
public static IEnumerable<T> TakeLast<T>(this IEnumerable<T> collection,
int n)
{
if (collection == null)
throw new ArgumentNullException(nameof(collection));
if (n < 0)
throw new ArgumentOutOfRangeException(nameof(n), $"{nameof(n)} must be 0 or greater");
LinkedList<T> temp = new LinkedList<T>();
foreach (var value in collection)
{
temp.AddLast(value);
if (temp.Count > n)
temp.RemoveFirst();
}
return temp;
}
}

Here's a method that works on any enumerable but uses only O(N) temporary storage:
public static class TakeLastExtension
{
public static IEnumerable<T> TakeLast<T>(this IEnumerable<T> source, int takeCount)
{
if (source == null) { throw new ArgumentNullException("source"); }
if (takeCount < 0) { throw new ArgumentOutOfRangeException("takeCount", "must not be negative"); }
if (takeCount == 0) { yield break; }
T[] result = new T[takeCount];
int i = 0;
int sourceCount = 0;
foreach (T element in source)
{
result[i] = element;
i = (i + 1) % takeCount;
sourceCount++;
}
if (sourceCount < takeCount)
{
takeCount = sourceCount;
i = 0;
}
for (int j = 0; j < takeCount; ++j)
{
yield return result[(i + j) % takeCount];
}
}
}
Usage:
List<int> l = new List<int> {4, 6, 3, 6, 2, 5, 7};
List<int> lastElements = l.TakeLast(3).ToList();
It works by using a ring buffer of size N to store the elements as it sees them, overwriting old elements with new ones. When the end of the enumerable is reached the ring buffer contains the last N elements.

I am surprised that no one has mentioned it, but SkipWhile does have a method that uses the element's index.
public static IEnumerable<T> TakeLastN<T>(this IEnumerable<T> source, int n)
{
if (source == null)
throw new ArgumentNullException("Source cannot be null");
int goldenIndex = source.Count() - n;
return source.SkipWhile((val, index) => index < goldenIndex);
}
//Or if you like them one-liners (in the spirit of the current accepted answer);
//However, this is most likely impractical due to the repeated calculations
collection.SkipWhile((val, index) => index < collection.Count() - N)
The only perceivable benefit that this solution presents over others is that you can have the option to add in a predicate to make a more powerful and efficient LINQ query, instead of having two separate operations that traverse the IEnumerable twice.
public static IEnumerable<T> FilterLastN<T>(this IEnumerable<T> source, int n, Predicate<T> pred)
{
int goldenIndex = source.Count() - n;
return source.SkipWhile((val, index) => index < goldenIndex && pred(val));
}

Use EnumerableEx.TakeLast in RX's System.Interactive assembly. It's an O(N) implementation like #Mark's, but it uses a queue rather than a ring-buffer construct (and dequeues items when it reaches buffer capacity).
(NB: This is the IEnumerable version - not the IObservable version, though the implementation of the two is pretty much identical)

If you are dealing with a collection with a key (e.g. entries from a database) a quick (i.e. faster than the selected answer) solution would be
collection.OrderByDescending(c => c.Key).Take(3).OrderBy(c => c.Key);

If you don't mind dipping into Rx as part of the monad, you can use TakeLast:
IEnumerable<int> source = Enumerable.Range(1, 10000);
IEnumerable<int> lastThree = source.AsObservable().TakeLast(3).AsEnumerable();

I tried to combine efficiency and simplicity and end up with this :
public static IEnumerable<T> TakeLast<T>(this IEnumerable<T> source, int count)
{
if (source == null) { throw new ArgumentNullException("source"); }
Queue<T> lastElements = new Queue<T>();
foreach (T element in source)
{
lastElements.Enqueue(element);
if (lastElements.Count > count)
{
lastElements.Dequeue();
}
}
return lastElements;
}
About
performance : In C#, Queue<T> is implemented using a circular buffer so there is no object instantiation done each loop (only when the queue is growing up). I did not set queue capacity (using dedicated constructor) because someone might call this extension with count = int.MaxValue . For extra performance you might check if source implement IList<T> and if yes, directly extract the last values using array indexes.

If using a third-party library is an option, MoreLinq defines TakeLast() which does exactly this.

It is a little inefficient to take the last N of a collection using LINQ as all the above solutions require iterating across the collection. TakeLast(int n) in System.Interactive also has this problem.
If you have a list a more efficient thing to do is slice it using the following method
/// Select from start to end exclusive of end using the same semantics
/// as python slice.
/// <param name="list"> the list to slice</param>
/// <param name="start">The starting index</param>
/// <param name="end">The ending index. The result does not include this index</param>
public static List<T> Slice<T>
(this IReadOnlyList<T> list, int start, int? end = null)
{
if (end == null)
{
end = list.Count();
}
if (start < 0)
{
start = list.Count + start;
}
if (start >= 0 && end.Value > 0 && end.Value > start)
{
return list.GetRange(start, end.Value - start);
}
if (end < 0)
{
return list.GetRange(start, (list.Count() + end.Value) - start);
}
if (end == start)
{
return new List<T>();
}
throw new IndexOutOfRangeException(
"count = " + list.Count() +
" start = " + start +
" end = " + end);
}
with
public static List<T> GetRange<T>( this IReadOnlyList<T> list, int index, int count )
{
List<T> r = new List<T>(count);
for ( int i = 0; i < count; i++ )
{
int j=i + index;
if ( j >= list.Count )
{
break;
}
r.Add(list[j]);
}
return r;
}
and some test cases
[Fact]
public void GetRange()
{
IReadOnlyList<int> l = new List<int>() { 0, 10, 20, 30, 40, 50, 60 };
l
.GetRange(2, 3)
.ShouldAllBeEquivalentTo(new[] { 20, 30, 40 });
l
.GetRange(5, 10)
.ShouldAllBeEquivalentTo(new[] { 50, 60 });
}
[Fact]
void SliceMethodShouldWork()
{
var list = new List<int>() { 1, 3, 5, 7, 9, 11 };
list.Slice(1, 4).ShouldBeEquivalentTo(new[] { 3, 5, 7 });
list.Slice(1, -2).ShouldBeEquivalentTo(new[] { 3, 5, 7 });
list.Slice(1, null).ShouldBeEquivalentTo(new[] { 3, 5, 7, 9, 11 });
list.Slice(-2)
.Should()
.BeEquivalentTo(new[] {9, 11});
list.Slice(-2,-1 )
.Should()
.BeEquivalentTo(new[] {9});
}

I know it's to late to answer this question. But if you are working with collection of type IList<> and you don't care about an order of the returned collection, then this method is working faster. I've used Mark Byers answer and made a little changes. So now method TakeLast is:
public static IEnumerable<T> TakeLast<T>(IList<T> source, int takeCount)
{
if (source == null) { throw new ArgumentNullException("source"); }
if (takeCount < 0) { throw new ArgumentOutOfRangeException("takeCount", "must not be negative"); }
if (takeCount == 0) { yield break; }
if (source.Count > takeCount)
{
for (int z = source.Count - 1; takeCount > 0; z--)
{
takeCount--;
yield return source[z];
}
}
else
{
for(int i = 0; i < source.Count; i++)
{
yield return source[i];
}
}
}
For test I have used Mark Byers method and kbrimington's andswer. This is test:
IList<int> test = new List<int>();
for(int i = 0; i<1000000; i++)
{
test.Add(i);
}
Stopwatch stopwatch = new Stopwatch();
stopwatch.Start();
IList<int> result = TakeLast(test, 10).ToList();
stopwatch.Stop();
Stopwatch stopwatch1 = new Stopwatch();
stopwatch1.Start();
IList<int> result1 = TakeLast2(test, 10).ToList();
stopwatch1.Stop();
Stopwatch stopwatch2 = new Stopwatch();
stopwatch2.Start();
IList<int> result2 = test.Skip(Math.Max(0, test.Count - 10)).Take(10).ToList();
stopwatch2.Stop();
And here are results for taking 10 elements:
and for taking 1000001 elements results are:

Here's my solution:
public static class EnumerationExtensions
{
public static IEnumerable<T> TakeLast<T>(this IEnumerable<T> input, int count)
{
if (count <= 0)
yield break;
var inputList = input as IList<T>;
if (inputList != null)
{
int last = inputList.Count;
int first = last - count;
if (first < 0)
first = 0;
for (int i = first; i < last; i++)
yield return inputList[i];
}
else
{
// Use a ring buffer. We have to enumerate the input, and we don't know in advance how many elements it will contain.
T[] buffer = new T[count];
int index = 0;
count = 0;
foreach (T item in input)
{
buffer[index] = item;
index = (index + 1) % buffer.Length;
count++;
}
// The index variable now points at the next buffer entry that would be filled. If the buffer isn't completely
// full, then there are 'count' elements preceding index. If the buffer *is* full, then index is pointing at
// the oldest entry, which is the first one to return.
//
// If the buffer isn't full, which means that the enumeration has fewer than 'count' elements, we'll fix up
// 'index' to point at the first entry to return. That's easy to do; if the buffer isn't full, then the oldest
// entry is the first one. :-)
//
// We'll also set 'count' to the number of elements to be returned. It only needs adjustment if we've wrapped
// past the end of the buffer and have enumerated more than the original count value.
if (count < buffer.Length)
index = 0;
else
count = buffer.Length;
// Return the values in the correct order.
while (count > 0)
{
yield return buffer[index];
index = (index + 1) % buffer.Length;
count--;
}
}
}
public static IEnumerable<T> SkipLast<T>(this IEnumerable<T> input, int count)
{
if (count <= 0)
return input;
else
return input.SkipLastIter(count);
}
private static IEnumerable<T> SkipLastIter<T>(this IEnumerable<T> input, int count)
{
var inputList = input as IList<T>;
if (inputList != null)
{
int first = 0;
int last = inputList.Count - count;
if (last < 0)
last = 0;
for (int i = first; i < last; i++)
yield return inputList[i];
}
else
{
// Aim to leave 'count' items in the queue. If the input has fewer than 'count'
// items, then the queue won't ever fill and we return nothing.
Queue<T> elements = new Queue<T>();
foreach (T item in input)
{
elements.Enqueue(item);
if (elements.Count > count)
yield return elements.Dequeue();
}
}
}
}
The code is a bit chunky, but as a drop-in reusable component, it should perform as well as it can in most scenarios, and it'll keep the code that's using it nice and concise. :-)
My TakeLast for non-IList`1 is based on the same ring buffer algorithm as that in the answers by #Mark Byers and #MackieChan further up. It's interesting how similar they are -- I wrote mine completely independently. Guess there's really just one way to do a ring buffer properly. :-)
Looking at #kbrimington's answer, an additional check could be added to this for IQuerable<T> to fall back to the approach that works well with Entity Framework -- assuming that what I have at this point does not.

Honestly I'm not super proud of the answer, but for small collections you could use the following:
var lastN = collection.Reverse().Take(n).Reverse();
A bit hacky but it does the job ;)

My solution is based on ranges, introduced in C# version 8.
public static IEnumerable<T> TakeLast<T>(this IEnumerable<T> source, int N)
{
return source.ToArray()[(source.Count()-N)..];
}
After running a benchmark with most rated solutions (and my humbly proposed solution):
public static class TakeLastExtension
{
public static IEnumerable<T> TakeLastMarkByers<T>(this IEnumerable<T> source, int takeCount)
{
if (source == null) { throw new ArgumentNullException("source"); }
if (takeCount < 0) { throw new ArgumentOutOfRangeException("takeCount", "must not be negative"); }
if (takeCount == 0) { yield break; }
T[] result = new T[takeCount];
int i = 0;
int sourceCount = 0;
foreach (T element in source)
{
result[i] = element;
i = (i + 1) % takeCount;
sourceCount++;
}
if (sourceCount < takeCount)
{
takeCount = sourceCount;
i = 0;
}
for (int j = 0; j < takeCount; ++j)
{
yield return result[(i + j) % takeCount];
}
}
public static IEnumerable<T> TakeLastKbrimington<T>(this IEnumerable<T> source, int N)
{
return source.Skip(Math.Max(0, source.Count() - N));
}
public static IEnumerable<T> TakeLastJamesCurran<T>(this IEnumerable<T> source, int N)
{
return source.Reverse().Take(N).Reverse();
}
public static IEnumerable<T> TakeLastAlex<T>(this IEnumerable<T> source, int N)
{
return source.ToArray()[(source.Count()-N)..];
}
}
Test
[MemoryDiagnoser]
public class TakeLastBenchmark
{
[Params(10000)]
public int N;
private readonly List<string> l = new();
[GlobalSetup]
public void Setup()
{
for (var i = 0; i < this.N; i++)
{
this.l.Add($"i");
}
}
[Benchmark]
public void Benchmark1_MarkByers()
{
var lastElements = l.TakeLastMarkByers(3).ToList();
}
[Benchmark]
public void Benchmark2_Kbrimington()
{
var lastElements = l.TakeLastKbrimington(3).ToList();
}
[Benchmark]
public void Benchmark3_JamesCurran()
{
var lastElements = l.TakeLastJamesCurran(3).ToList();
}
[Benchmark]
public void Benchmark4_Alex()
{
var lastElements = l.TakeLastAlex(3).ToList();
}
}
Program.cs:
var summary = BenchmarkRunner.Run(typeof(TakeLastBenchmark).Assembly);
Command dotnet run --project .\TestsConsole2.csproj -c Release --logBuildOutput
The results were following:
// * Summary *
BenchmarkDotNet=v0.13.2, OS=Windows 10 (10.0.19044.1889/21H2/November2021Update)
AMD Ryzen 5 5600X, 1 CPU, 12 logical and 6 physical cores
.NET SDK=6.0.401
[Host] : .NET 6.0.9 (6.0.922.41905), X64 RyuJIT AVX2
DefaultJob : .NET 6.0.9 (6.0.922.41905), X64 RyuJIT AVX2
Method
N
Mean
Error
StdDev
Gen0
Gen1
Allocated
Benchmark1_MarkByers
10000
89,390.53 ns
1,735.464 ns
1,704.457 ns
-
-
248 B
Benchmark2_Kbrimington
10000
46.15 ns
0.410 ns
0.363 ns
0.0076
-
128 B
Benchmark3_JamesCurran
10000
2,703.15 ns
46.298 ns
67.862 ns
4.7836
0.0038
80264 B
Benchmark4_Alex
10000
2,513.48 ns
48.661 ns
45.517 ns
4.7607
-
80152 B
Turns out the solution proposed by #Kbrimington to be the most efficient in terms of memory alloc as well as raw performance.

Below the real example how to take last 3 elements from a collection (array):
// split address by spaces into array
string[] adrParts = adr.Split(new string[] { " " },StringSplitOptions.RemoveEmptyEntries);
// take only 3 last items in array
adrParts = adrParts.SkipWhile((value, index) => { return adrParts.Length - index > 3; }).ToArray();

Using This Method To Get All Range Without Error
public List<T> GetTsRate( List<T> AllT,int Index,int Count)
{
List<T> Ts = null;
try
{
Ts = AllT.ToList().GetRange(Index, Count);
}
catch (Exception ex)
{
Ts = AllT.Skip(Index).ToList();
}
return Ts ;
}

Little different implementation with usage of circular buffer. The benchmarks show that the method is circa two times faster than ones using Queue (implementation of TakeLast in System.Linq), however not without a cost - it needs a buffer which grows along with the requested number of elements, even if you have a small collection you can get huge memory allocation.
public IEnumerable<T> TakeLast<T>(IEnumerable<T> source, int count)
{
int i = 0;
if (count < 1)
yield break;
if (source is IList<T> listSource)
{
if (listSource.Count < 1)
yield break;
for (i = listSource.Count < count ? 0 : listSource.Count - count; i < listSource.Count; i++)
yield return listSource[i];
}
else
{
bool move = true;
bool filled = false;
T[] result = new T[count];
using (var enumerator = source.GetEnumerator())
while (move)
{
for (i = 0; (move = enumerator.MoveNext()) && i < count; i++)
result[i] = enumerator.Current;
filled |= move;
}
if (filled)
for (int j = i; j < count; j++)
yield return result[j];
for (int j = 0; j < i; j++)
yield return result[j];
}
}

//detailed code for the problem
//suppose we have a enumerable collection 'collection'
var lastIndexOfCollection=collection.Count-1 ;
var nthIndexFromLast= lastIndexOfCollection- N;
var desiredCollection=collection.GetRange(nthIndexFromLast, N);
---------------------------------------------------------------------
// use this one liner
var desiredCollection=collection.GetRange((collection.Count-(1+N)), N);

Split List into Sublists with LINQ

Is there any way I can separate a List<SomeObject> into several separate lists of SomeObject, using the item index as the delimiter of each split?
Let me exemplify:
I have a List<SomeObject> and I need a List<List<SomeObject>> or List<SomeObject>[], so that each of these resulting lists will contain a group of 3 items of the original list (sequentially).
eg.:
Original List: [a, g, e, w, p, s, q, f, x, y, i, m, c]
Resulting lists: [a, g, e], [w, p, s], [q, f, x], [y, i, m], [c]
I'd also need the resulting lists size to be a parameter of this function.

Try the following code.
public static List<List<T>> Split<T>(IList<T> source)
{
return source
.Select((x, i) => new { Index = i, Value = x })
.GroupBy(x => x.Index / 3)
.Select(x => x.Select(v => v.Value).ToList())
.ToList();
}
The idea is to first group the elements by indexes. Dividing by three has the effect of grouping them into groups of 3. Then convert each group to a list and the IEnumerable of List to a List of Lists

I just wrote this, and I think it's a little more elegant than the other proposed solutions:
/// <summary>
/// Break a list of items into chunks of a specific size
/// </summary>
public static IEnumerable<IEnumerable<T>> Chunk<T>(this IEnumerable<T> source, int chunksize)
{
while (source.Any())
{
yield return source.Take(chunksize);
source = source.Skip(chunksize);
}
}

In general the approach suggested by CaseyB works fine, in fact if you are passing in a List<T> it is hard to fault it, perhaps I would change it to:
public static IEnumerable<IEnumerable<T>> ChunkTrivialBetter<T>(this IEnumerable<T> source, int chunksize)
{
var pos = 0;
while (source.Skip(pos).Any())
{
yield return source.Skip(pos).Take(chunksize);
pos += chunksize;
}
}
Which will avoid massive call chains. Nonetheless, this approach has a general flaw. It materializes two enumerations per chunk, to highlight the issue try running:
foreach (var item in Enumerable.Range(1, int.MaxValue).Chunk(8).Skip(100000).First())
{
Console.WriteLine(item);
}
// wait forever
To overcome this we can try Cameron's approach, which passes the above test in flying colors as it only walks the enumeration once.
Trouble is that it has a different flaw, it materializes every item in each chunk, the trouble with that approach is that you run high on memory.
To illustrate that try running:
foreach (var item in Enumerable.Range(1, int.MaxValue)
.Select(x => x + new string('x', 100000))
.Clump(10000).Skip(100).First())
{
Console.Write('.');
}
// OutOfMemoryException
Finally, any implementation should be able to handle out of order iteration of chunks, for example:
Enumerable.Range(1,3).Chunk(2).Reverse().ToArray()
// should return [3],[1,2]
Many highly optimal solutions like my first revision of this answer failed there. The same issue can be seen in casperOne's optimized answer.
To address all these issues you can use the following:
namespace ChunkedEnumerator
{
public static class Extensions
{
class ChunkedEnumerable<T> : IEnumerable<T>
{
class ChildEnumerator : IEnumerator<T>
{
ChunkedEnumerable<T> parent;
int position;
bool done = false;
T current;
public ChildEnumerator(ChunkedEnumerable<T> parent)
{
this.parent = parent;
position = -1;
parent.wrapper.AddRef();
}
public T Current
{
get
{
if (position == -1 || done)
{
throw new InvalidOperationException();
}
return current;
}
}
public void Dispose()
{
if (!done)
{
done = true;
parent.wrapper.RemoveRef();
}
}
object System.Collections.IEnumerator.Current
{
get { return Current; }
}
public bool MoveNext()
{
position++;
if (position + 1 > parent.chunkSize)
{
done = true;
}
if (!done)
{
done = !parent.wrapper.Get(position + parent.start, out current);
}
return !done;
}
public void Reset()
{
// per http://msdn.microsoft.com/en-us/library/system.collections.ienumerator.reset.aspx
throw new NotSupportedException();
}
}
EnumeratorWrapper<T> wrapper;
int chunkSize;
int start;
public ChunkedEnumerable(EnumeratorWrapper<T> wrapper, int chunkSize, int start)
{
this.wrapper = wrapper;
this.chunkSize = chunkSize;
this.start = start;
}
public IEnumerator<T> GetEnumerator()
{
return new ChildEnumerator(this);
}
System.Collections.IEnumerator System.Collections.IEnumerable.GetEnumerator()
{
return GetEnumerator();
}
}
class EnumeratorWrapper<T>
{
public EnumeratorWrapper (IEnumerable<T> source)
{
SourceEumerable = source;
}
IEnumerable<T> SourceEumerable {get; set;}
Enumeration currentEnumeration;
class Enumeration
{
public IEnumerator<T> Source { get; set; }
public int Position { get; set; }
public bool AtEnd { get; set; }
}
public bool Get(int pos, out T item)
{
if (currentEnumeration != null && currentEnumeration.Position > pos)
{
currentEnumeration.Source.Dispose();
currentEnumeration = null;
}
if (currentEnumeration == null)
{
currentEnumeration = new Enumeration { Position = -1, Source = SourceEumerable.GetEnumerator(), AtEnd = false };
}
item = default(T);
if (currentEnumeration.AtEnd)
{
return false;
}
while(currentEnumeration.Position < pos)
{
currentEnumeration.AtEnd = !currentEnumeration.Source.MoveNext();
currentEnumeration.Position++;
if (currentEnumeration.AtEnd)
{
return false;
}
}
item = currentEnumeration.Source.Current;
return true;
}
int refs = 0;
// needed for dispose semantics
public void AddRef()
{
refs++;
}
public void RemoveRef()
{
refs--;
if (refs == 0 && currentEnumeration != null)
{
var copy = currentEnumeration;
currentEnumeration = null;
copy.Source.Dispose();
}
}
}
public static IEnumerable<IEnumerable<T>> Chunk<T>(this IEnumerable<T> source, int chunksize)
{
if (chunksize < 1) throw new InvalidOperationException();
var wrapper = new EnumeratorWrapper<T>(source);
int currentPos = 0;
T ignore;
try
{
wrapper.AddRef();
while (wrapper.Get(currentPos, out ignore))
{
yield return new ChunkedEnumerable<T>(wrapper, chunksize, currentPos);
currentPos += chunksize;
}
}
finally
{
wrapper.RemoveRef();
}
}
}
class Program
{
static void Main(string[] args)
{
int i = 10;
foreach (var group in Enumerable.Range(1, int.MaxValue).Skip(10000000).Chunk(3))
{
foreach (var n in group)
{
Console.Write(n);
Console.Write(" ");
}
Console.WriteLine();
if (i-- == 0) break;
}
var stuffs = Enumerable.Range(1, 10).Chunk(2).ToArray();
foreach (var idx in new [] {3,2,1})
{
Console.Write("idx " + idx + " ");
foreach (var n in stuffs[idx])
{
Console.Write(n);
Console.Write(" ");
}
Console.WriteLine();
}
/*
10000001 10000002 10000003
10000004 10000005 10000006
10000007 10000008 10000009
10000010 10000011 10000012
10000013 10000014 10000015
10000016 10000017 10000018
10000019 10000020 10000021
10000022 10000023 10000024
10000025 10000026 10000027
10000028 10000029 10000030
10000031 10000032 10000033
idx 3 7 8
idx 2 5 6
idx 1 3 4
*/
Console.ReadKey();
}
}
}
There is also a round of optimisations you could introduce for out-of-order iteration of chunks, which is out of scope here.
As to which method you should choose? It totally depends on the problem you are trying to solve. If you are not concerned with the first flaw the simple answer is incredibly appealing.
Note as with most methods, this is not safe for multi threading, stuff can get weird if you wish to make it thread safe you would need to amend EnumeratorWrapper.

You could use a number of queries that use Take and Skip, but that would add too many iterations on the original list, I believe.
Rather, I think you should create an iterator of your own, like so:
public static IEnumerable<IEnumerable<T>> GetEnumerableOfEnumerables<T>(
IEnumerable<T> enumerable, int groupSize)
{
// The list to return.
List<T> list = new List<T>(groupSize);
// Cycle through all of the items.
foreach (T item in enumerable)
{
// Add the item.
list.Add(item);
// If the list has the number of elements, return that.
if (list.Count == groupSize)
{
// Return the list.
yield return list;
// Set the list to a new list.
list = new List<T>(groupSize);
}
}
// Return the remainder if there is any,
if (list.Count != 0)
{
// Return the list.
yield return list;
}
}
You can then call this and it is LINQ enabled so you can perform other operations on the resulting sequences.
In light of Sam's answer, I felt there was an easier way to do this without:
Iterating through the list again (which I didn't do originally)
Materializing the items in groups before releasing the chunk (for large chunks of items, there would be memory issues)
All of the code that Sam posted
That said, here's another pass, which I've codified in an extension method to IEnumerable<T> called Chunk:
public static IEnumerable<IEnumerable<T>> Chunk<T>(this IEnumerable<T> source,
int chunkSize)
{
// Validate parameters.
if (source == null) throw new ArgumentNullException(nameof(source));
if (chunkSize <= 0) throw new ArgumentOutOfRangeException(nameof(chunkSize),
"The chunkSize parameter must be a positive value.");
// Call the internal implementation.
return source.ChunkInternal(chunkSize);
}
Nothing surprising up there, just basic error checking.
Moving on to ChunkInternal:
private static IEnumerable<IEnumerable<T>> ChunkInternal<T>(
this IEnumerable<T> source, int chunkSize)
{
// Validate parameters.
Debug.Assert(source != null);
Debug.Assert(chunkSize > 0);
// Get the enumerator. Dispose of when done.
using (IEnumerator<T> enumerator = source.GetEnumerator())
do
{
// Move to the next element. If there's nothing left
// then get out.
if (!enumerator.MoveNext()) yield break;
// Return the chunked sequence.
yield return ChunkSequence(enumerator, chunkSize);
} while (true);
}
Basically, it gets the IEnumerator<T> and manually iterates through each item. It checks to see if there any items currently to be enumerated. After each chunk is enumerated through, if there aren't any items left, it breaks out.
Once it detects there are items in the sequence, it delegates the responsibility for the inner IEnumerable<T> implementation to ChunkSequence:
private static IEnumerable<T> ChunkSequence<T>(IEnumerator<T> enumerator,
int chunkSize)
{
// Validate parameters.
Debug.Assert(enumerator != null);
Debug.Assert(chunkSize > 0);
// The count.
int count = 0;
// There is at least one item. Yield and then continue.
do
{
// Yield the item.
yield return enumerator.Current;
} while (++count < chunkSize && enumerator.MoveNext());
}
Since MoveNext was already called on the IEnumerator<T> passed to ChunkSequence, it yields the item returned by Current and then increments the count, making sure never to return more than chunkSize items and moving to the next item in the sequence after every iteration (but short-circuited if the number of items yielded exceeds the chunk size).
If there are no items left, then the InternalChunk method will make another pass in the outer loop, but when MoveNext is called a second time, it will still return false, as per the documentation (emphasis mine):
If MoveNext passes the end of the collection, the enumerator is
positioned after the last element in the collection and MoveNext
returns false. When the enumerator is at this position, subsequent
calls to MoveNext also return false until Reset is called.
At this point, the loop will break, and the sequence of sequences will terminate.
This is a simple test:
static void Main()
{
string s = "agewpsqfxyimc";
int count = 0;
// Group by three.
foreach (IEnumerable<char> g in s.Chunk(3))
{
// Print out the group.
Console.Write("Group: {0} - ", ++count);
// Print the items.
foreach (char c in g)
{
// Print the item.
Console.Write(c + ", ");
}
// Finish the line.
Console.WriteLine();
}
}
Output:
Group: 1 - a, g, e,
Group: 2 - w, p, s,
Group: 3 - q, f, x,
Group: 4 - y, i, m,
Group: 5 - c,
An important note, this will not work if you don't drain the entire child sequence or break at any point in the parent sequence. This is an important caveat, but if your use case is that you will consume every element of the sequence of sequences, then this will work for you.
Additionally, it will do strange things if you play with the order, just as Sam's did at one point.

Ok, here's my take on it:
completely lazy: works on infinite enumerables
no intermediate copying/buffering
O(n) execution time
works also when inner sequences are only partially consumed
public static IEnumerable<IEnumerable<T>> Chunks<T>(this IEnumerable<T> enumerable,
int chunkSize)
{
if (chunkSize < 1) throw new ArgumentException("chunkSize must be positive");
using (var e = enumerable.GetEnumerator())
while (e.MoveNext())
{
var remaining = chunkSize; // elements remaining in the current chunk
var innerMoveNext = new Func<bool>(() => --remaining > 0 && e.MoveNext());
yield return e.GetChunk(innerMoveNext);
while (innerMoveNext()) {/* discard elements skipped by inner iterator */}
}
}
private static IEnumerable<T> GetChunk<T>(this IEnumerator<T> e,
Func<bool> innerMoveNext)
{
do yield return e.Current;
while (innerMoveNext());
}
Example Usage
var src = new [] {1, 2, 3, 4, 5, 6};
var c3 = src.Chunks(3); // {{1, 2, 3}, {4, 5, 6}};
var c4 = src.Chunks(4); // {{1, 2, 3, 4}, {5, 6}};
var sum = c3.Select(c => c.Sum()); // {6, 15}
var count = c3.Count(); // 2
var take2 = c3.Select(c => c.Take(2)); // {{1, 2}, {4, 5}}
Explanations
The code works by nesting two yield based iterators.
The outer iterator must keep track of how many elements have been effectively consumed by the inner (chunk) iterator. This is done by closing over remaining with innerMoveNext(). Unconsumed elements of a chunk are discarded before the next chunk is yielded by the outer iterator.
This is necessary because otherwise you get inconsistent results, when the inner enumerables are not (completely) consumed (e.g. c3.Count() would return 6).
Note: The answer has been updated to address the shortcomings pointed out by #aolszowka.

Update .NET 6.0
.NET 6.0 added a new native Chunk method to the System.Linq namespace:
public static System.Collections.Generic.IEnumerable<TSource[]> Chunk<TSource> (
this System.Collections.Generic.IEnumerable<TSource> source, int size);
Using this new method every chunk except the last will be of size size. The last chunk will contain the remaining elements and may be of a smaller size.
Here is an example:
var list = Enumerable.Range(1, 100);
var chunkSize = 10;
foreach(var chunk in list.Chunk(chunkSize)) //Returns a chunk with the correct size.
{
Parallel.ForEach(chunk, (item) =>
{
//Do something Parallel here.
Console.WriteLine(item);
});
}
You’re probably thinking, well why not use Skip and Take? Which is true, I think this is just a bit more concise and makes things just that little bit more readable.

completely lazy, no counting or copying:
public static class EnumerableExtensions
{
public static IEnumerable<IEnumerable<T>> Split<T>(this IEnumerable<T> source, int len)
{
if (len == 0)
throw new ArgumentNullException();
var enumer = source.GetEnumerator();
while (enumer.MoveNext())
{
yield return Take(enumer.Current, enumer, len);
}
}
private static IEnumerable<T> Take<T>(T head, IEnumerator<T> tail, int len)
{
while (true)
{
yield return head;
if (--len == 0)
break;
if (tail.MoveNext())
head = tail.Current;
else
break;
}
}
}

I think the following suggestion would be the fastest. I am sacrificing the lazyness of the source Enumerable for the ability to use Array.Copy and knowing ahead of the time the length of each of my sublists.
public static IEnumerable<T[]> Chunk<T>(this IEnumerable<T> items, int size)
{
T[] array = items as T[] ?? items.ToArray();
for (int i = 0; i < array.Length; i+=size)
{
T[] chunk = new T[Math.Min(size, array.Length - i)];
Array.Copy(array, i, chunk, 0, chunk.Length);
yield return chunk;
}
}

For anyone interested in a packaged/maintained solution, the MoreLINQ library provides the Batch extension method which matches your requested behavior:
IEnumerable<char> source = "Example string";
IEnumerable<IEnumerable<char>> chunksOfThreeChars = source.Batch(3);
The Batch implementation is similar to Cameron MacFarland's answer, with the addition of an overload for transforming the chunk/batch before returning, and performs quite well.

I wrote a Clump extension method several years ago. Works great, and is the fastest implementation here. :P
/// <summary>
/// Clumps items into same size lots.
/// </summary>
/// <typeparam name="T"></typeparam>
/// <param name="source">The source list of items.</param>
/// <param name="size">The maximum size of the clumps to make.</param>
/// <returns>A list of list of items, where each list of items is no bigger than the size given.</returns>
public static IEnumerable<IEnumerable<T>> Clump<T>(this IEnumerable<T> source, int size)
{
if (source == null)
throw new ArgumentNullException("source");
if (size < 1)
throw new ArgumentOutOfRangeException("size", "size must be greater than 0");
return ClumpIterator<T>(source, size);
}
private static IEnumerable<IEnumerable<T>> ClumpIterator<T>(IEnumerable<T> source, int size)
{
Debug.Assert(source != null, "source is null.");
T[] items = new T[size];
int count = 0;
foreach (var item in source)
{
items[count] = item;
count++;
if (count == size)
{
yield return items;
items = new T[size];
count = 0;
}
}
if (count > 0)
{
if (count == size)
yield return items;
else
{
T[] tempItems = new T[count];
Array.Copy(items, tempItems, count);
yield return tempItems;
}
}
}

We can improve #JaredPar's solution to do true lazy evaluation. We use a GroupAdjacentBy method that yields groups of consecutive elements with the same key:
sequence
.Select((x, i) => new { Value = x, Index = i })
.GroupAdjacentBy(x=>x.Index/3)
.Select(g=>g.Select(x=>x.Value))
Because the groups are yielded one-by-one, this solution works efficiently with long or infinite sequences.

System.Interactive provides Buffer() for this purpose. Some quick testing shows performance is similar to Sam's solution.

I find this little snippet does the job quite nicely.
public static IEnumerable<List<T>> Chunked<T>(this List<T> source, int chunkSize)
{
var offset = 0;
while (offset < source.Count)
{
yield return source.GetRange(offset, Math.Min(source.Count - offset, chunkSize));
offset += chunkSize;
}
}

Here's a list splitting routine I wrote a couple months ago:
public static List<List<T>> Chunk<T>(
List<T> theList,
int chunkSize
)
{
List<List<T>> result = theList
.Select((x, i) => new {
data = x,
indexgroup = i / chunkSize
})
.GroupBy(x => x.indexgroup, x => x.data)
.Select(g => new List<T>(g))
.ToList();
return result;
}

We found David B's solution worked the best. But we adapted it to a more general solution:
list.GroupBy(item => item.SomeProperty)
.Select(group => new List<T>(group))
.ToArray();

What about this one?
var input = new List<string> { "a", "g", "e", "w", "p", "s", "q", "f", "x", "y", "i", "m", "c" };
var k = 3
var res = Enumerable.Range(0, (input.Count - 1) / k + 1)
.Select(i => input.GetRange(i * k, Math.Min(k, input.Count - i * k)))
.ToList();
As far as I know, GetRange() is linear in terms of number of items taken. So this should perform well.

This is an old question but this is what I ended up with; it enumerates the enumerable only once, but does create lists for each of the partitions. It doesn't suffer from unexpected behavior when ToArray() is called as some of the implementations do:
public static IEnumerable<IEnumerable<T>> Partition<T>(IEnumerable<T> source, int chunkSize)
{
if (source == null)
{
throw new ArgumentNullException("source");
}
if (chunkSize < 1)
{
throw new ArgumentException("Invalid chunkSize: " + chunkSize);
}
using (IEnumerator<T> sourceEnumerator = source.GetEnumerator())
{
IList<T> currentChunk = new List<T>();
while (sourceEnumerator.MoveNext())
{
currentChunk.Add(sourceEnumerator.Current);
if (currentChunk.Count == chunkSize)
{
yield return currentChunk;
currentChunk = new List<T>();
}
}
if (currentChunk.Any())
{
yield return currentChunk;
}
}
}

Old code, but this is what I've been using:
public static IEnumerable<List<T>> InSetsOf<T>(this IEnumerable<T> source, int max)
{
var toReturn = new List<T>(max);
foreach (var item in source)
{
toReturn.Add(item);
if (toReturn.Count == max)
{
yield return toReturn;
toReturn = new List<T>(max);
}
}
if (toReturn.Any())
{
yield return toReturn;
}
}

This following solution is the most compact I could come up with that is O(n).
public static IEnumerable<T[]> Chunk<T>(IEnumerable<T> source, int chunksize)
{
var list = source as IList<T> ?? source.ToList();
for (int start = 0; start < list.Count; start += chunksize)
{
T[] chunk = new T[Math.Min(chunksize, list.Count - start)];
for (int i = 0; i < chunk.Length; i++)
chunk[i] = list[start + i];
yield return chunk;
}
}

If the list is of type system.collections.generic you can use the "CopyTo" method available to copy elements of your array to other sub arrays. You specify the start element and number of elements to copy.
You could also make 3 clones of your original list and use the "RemoveRange" on each list to shrink the list to the size you want.
Or just create a helper method to do it for you.

It's an old solution but I had a different approach. I use Skip to move to desired offset and Take to extract desired number of elements:
public static IEnumerable<IEnumerable<T>> Chunk<T>(this IEnumerable<T> source,
int chunkSize)
{
if (chunkSize <= 0)
throw new ArgumentOutOfRangeException($"{nameof(chunkSize)} should be > 0");
var nbChunks = (int)Math.Ceiling((double)source.Count()/chunkSize);
return Enumerable.Range(0, nbChunks)
.Select(chunkNb => source.Skip(chunkNb*chunkSize)
.Take(chunkSize));
}

Another way is using Rx Buffer operator
//using System.Linq;
//using System.Reactive.Linq;
//using System.Reactive.Threading.Tasks;
var observableBatches = anAnumerable.ToObservable().Buffer(size);
var batches = aList.ToObservable().Buffer(size).ToList().ToTask().GetAwaiter().GetResult();

The question was how to "Split List into Sublists with LINQ", but sometimes you may want those sub-lists to be references to the original list, not copies. This allows you to modify the original list from the sub-lists. In that case, this may work for you.
public static IEnumerable<Memory<T>> RefChunkBy<T>(this T[] array, int size)
{
if (size < 1 || array is null)
{
throw new ArgumentException("chunkSize must be positive");
}
var index = 0;
var counter = 0;
for (int i = 0; i < array.Length; i++)
{
if (counter == size)
{
yield return new Memory<T>(array, index, size);
index = i;
counter = 0;
}
counter++;
if (i + 1 == array.Length)
{
yield return new Memory<T>(array, index, array.Length - index);
}
}
}
Usage:
var src = new[] { 1, 2, 3, 4, 5, 6 };
var c3 = RefChunkBy(src, 3); // {{1, 2, 3}, {4, 5, 6}};
var c4 = RefChunkBy(src, 4); // {{1, 2, 3, 4}, {5, 6}};
// as extension method
var c3 = src.RefChunkBy(3); // {{1, 2, 3}, {4, 5, 6}};
var c4 = src.RefChunkBy(4); // {{1, 2, 3, 4}, {5, 6}};
var sum = c3.Select(c => c.Span.ToArray().Sum()); // {6, 15}
var count = c3.Count(); // 2
var take2 = c3.Select(c => c.Span.ToArray().Take(2)); // {{1, 2}, {4, 5}}
Feel free to make this code better.

Using modular partitioning:
public IEnumerable<IEnumerable<string>> Split(IEnumerable<string> input, int chunkSize)
{
var chunks = (int)Math.Ceiling((double)input.Count() / (double)chunkSize);
return Enumerable.Range(0, chunks).Select(id => input.Where(s => s.GetHashCode() % chunks == id));
}

Just putting in my two cents. If you wanted to "bucket" the list (visualize left to right), you could do the following:
public static List<List<T>> Buckets<T>(this List<T> source, int numberOfBuckets)
{
List<List<T>> result = new List<List<T>>();
for (int i = 0; i < numberOfBuckets; i++)
{
result.Add(new List<T>());
}
int count = 0;
while (count < source.Count())
{
var mod = count % numberOfBuckets;
result[mod].Add(source[count]);
count++;
}
return result;
}

public static List<List<T>> GetSplitItemsList<T>(List<T> originalItemsList, short number)
{
var listGroup = new List<List<T>>();
int j = number;
for (int i = 0; i < originalItemsList.Count; i += number)
{
var cList = originalItemsList.Take(j).Skip(i).ToList();
j += number;
listGroup.Add(cList);
}
return listGroup;
}

To insert my two cents...
By using the list type for the source to be chunked, I found another very compact solution:
public static IEnumerable<IEnumerable<TSource>> Chunk<TSource>(this IEnumerable<TSource> source, int chunkSize)
{
// copy the source into a list
var chunkList = source.ToList();
// return chunks of 'chunkSize' items
while (chunkList.Count > chunkSize)
{
yield return chunkList.GetRange(0, chunkSize);
chunkList.RemoveRange(0, chunkSize);
}
// return the rest
yield return chunkList;
}

I took the primary answer and made it to be an IOC container to determine where to split. (For who is really looking to only split on 3 items, in reading this post while searching for an answer?)
This method allows one to split on any type of item as needed.
public static List<List<T>> SplitOn<T>(List<T> main, Func<T, bool> splitOn)
{
int groupIndex = 0;
return main.Select( item => new
{
Group = (splitOn.Invoke(item) ? ++groupIndex : groupIndex),
Value = item
})
.GroupBy( it2 => it2.Group)
.Select(x => x.Select(v => v.Value).ToList())
.ToList();
}
So for the OP the code would be
var it = new List<string>()
{ "a", "g", "e", "w", "p", "s", "q", "f", "x", "y", "i", "m", "c" };
int index = 0;
var result = SplitOn(it, (itm) => (index++ % 3) == 0 );

So performatic as the Sam Saffron's approach.
public static IEnumerable<IEnumerable<T>> Batch<T>(this IEnumerable<T> source, int size)
{
if (source == null) throw new ArgumentNullException(nameof(source));
if (size <= 0) throw new ArgumentOutOfRangeException(nameof(size), "Size must be greater than zero.");
return BatchImpl(source, size).TakeWhile(x => x.Any());
}
static IEnumerable<IEnumerable<T>> BatchImpl<T>(this IEnumerable<T> source, int size)
{
var values = new List<T>();
var group = 1;
var disposed = false;
var e = source.GetEnumerator();
try
{
while (!disposed)
{
yield return GetBatch(e, values, group, size, () => { e.Dispose(); disposed = true; });
group++;
}
}
finally
{
if (!disposed)
e.Dispose();
}
}
static IEnumerable<T> GetBatch<T>(IEnumerator<T> e, List<T> values, int group, int size, Action dispose)
{
var min = (group - 1) * size + 1;
var max = group * size;
var hasValue = false;
while (values.Count < min && e.MoveNext())
{
values.Add(e.Current);
}
for (var i = min; i <= max; i++)
{
if (i <= values.Count)
{
hasValue = true;
}
else if (hasValue = e.MoveNext())
{
values.Add(e.Current);
}
else
{
dispose();
}
if (hasValue)
yield return values[i - 1];
else
yield break;
}
}
}

Can work with infinite generators:
a.Zip(a.Skip(1), (x, y) => Enumerable.Repeat(x, 1).Concat(Enumerable.Repeat(y, 1)))
.Zip(a.Skip(2), (xy, z) => xy.Concat(Enumerable.Repeat(z, 1)))
.Where((x, i) => i % 3 == 0)
Demo code: https://ideone.com/GKmL7M
using System;
using System.Collections.Generic;
using System.Linq;
public class Test
{
private static void DoIt(IEnumerable<int> a)
{
Console.WriteLine(String.Join(" ", a));
foreach (var x in a.Zip(a.Skip(1), (x, y) => Enumerable.Repeat(x, 1).Concat(Enumerable.Repeat(y, 1))).Zip(a.Skip(2), (xy, z) => xy.Concat(Enumerable.Repeat(z, 1))).Where((x, i) => i % 3 == 0))
Console.WriteLine(String.Join(" ", x));
Console.WriteLine();
}
public static void Main()
{
DoIt(new int[] {1});
DoIt(new int[] {1, 2});
DoIt(new int[] {1, 2, 3});
DoIt(new int[] {1, 2, 3, 4});
DoIt(new int[] {1, 2, 3, 4, 5});
DoIt(new int[] {1, 2, 3, 4, 5, 6});
}
}
1
1 2
1 2 3
1 2 3
1 2 3 4
1 2 3
1 2 3 4 5
1 2 3
1 2 3 4 5 6
1 2 3
4 5 6
But actually I would prefer to write corresponding method without linq.

How to take all but the last element in a sequence using LINQ?

Let's say I have a sequence.
IEnumerable<int> sequence = GetSequenceFromExpensiveSource();
// sequence now contains: 0,1,2,3,...,999999,1000000
Getting the sequence is not cheap and is dynamically generated, and I want to iterate through it once only.
I want to get 0 - 999999 (i.e. everything but the last element)
I recognize that I could do something like:
sequence.Take(sequence.Count() - 1);
but that results in two enumerations over the big sequence.
Is there a LINQ construct that lets me do:
sequence.TakeAllButTheLastElement();

The Enumerable.SkipLast(IEnumerable<TSource>, Int32) method was added in .NET Standard 2.1. It does exactly what you want.
IEnumerable<int> sequence = GetSequenceFromExpensiveSource();
var allExceptLast = sequence.SkipLast(1);
From https://learn.microsoft.com/en-us/dotnet/api/system.linq.enumerable.skiplast
Returns a new enumerable collection that contains the elements from source with the last count elements of the source collection omitted.

I don't know a Linq solution - But you can easily code the algorithm by yourself using generators (yield return).
public static IEnumerable<T> TakeAllButLast<T>(this IEnumerable<T> source) {
var it = source.GetEnumerator();
bool hasRemainingItems = false;
bool isFirst = true;
T item = default(T);
do {
hasRemainingItems = it.MoveNext();
if (hasRemainingItems) {
if (!isFirst) yield return item;
item = it.Current;
isFirst = false;
}
} while (hasRemainingItems);
}
static void Main(string[] args) {
var Seq = Enumerable.Range(1, 10);
Console.WriteLine(string.Join(", ", Seq.Select(x => x.ToString()).ToArray()));
Console.WriteLine(string.Join(", ", Seq.TakeAllButLast().Select(x => x.ToString()).ToArray()));
}
Or as a generalized solution discarding the last n items (using a queue like suggested in the comments):
public static IEnumerable<T> SkipLastN<T>(this IEnumerable<T> source, int n) {
var it = source.GetEnumerator();
bool hasRemainingItems = false;
var cache = new Queue<T>(n + 1);
do {
if (hasRemainingItems = it.MoveNext()) {
cache.Enqueue(it.Current);
if (cache.Count > n)
yield return cache.Dequeue();
}
} while (hasRemainingItems);
}
static void Main(string[] args) {
var Seq = Enumerable.Range(1, 4);
Console.WriteLine(string.Join(", ", Seq.Select(x => x.ToString()).ToArray()));
Console.WriteLine(string.Join(", ", Seq.SkipLastN(3).Select(x => x.ToString()).ToArray()));
}

As an alternative to creating your own method and in a case the elements order is not important, the next will work:
var result = sequence.Reverse().Skip(1);

Because I'm not a fan of explicitly using an Enumerator, here's an alternative. Note that the wrapper methods are needed to let invalid arguments throw early, rather than deferring the checks until the sequence is actually enumerated.
public static IEnumerable<T> DropLast<T>(this IEnumerable<T> source)
{
if (source == null)
throw new ArgumentNullException("source");
return InternalDropLast(source);
}
private static IEnumerable<T> InternalDropLast<T>(IEnumerable<T> source)
{
T buffer = default(T);
bool buffered = false;
foreach (T x in source)
{
if (buffered)
yield return buffer;
buffer = x;
buffered = true;
}
}
As per Eric Lippert's suggestion, it easily generalizes to n items:
public static IEnumerable<T> DropLast<T>(this IEnumerable<T> source, int n)
{
if (source == null)
throw new ArgumentNullException("source");
if (n < 0)
throw new ArgumentOutOfRangeException("n",
"Argument n should be non-negative.");
return InternalDropLast(source, n);
}
private static IEnumerable<T> InternalDropLast<T>(IEnumerable<T> source, int n)
{
Queue<T> buffer = new Queue<T>(n + 1);
foreach (T x in source)
{
buffer.Enqueue(x);
if (buffer.Count == n + 1)
yield return buffer.Dequeue();
}
}
Where I now buffer before yielding instead of after yielding, so that the n == 0 case does not need special handling.

With C# 8.0 you can use Ranges and indices for that.
var allButLast = sequence[..^1];
By default C# 8.0 requires .NET Core 3.0 or .NET Standard 2.1 (or above). Check this thread to use with older implementations.

Nothing in the BCL (or MoreLinq I believe), but you could create your own extension method.
public static IEnumerable<T> TakeAllButLast<T>(this IEnumerable<T> source)
{
using (var enumerator = source.GetEnumerator())
bool first = true;
T prev;
while(enumerator.MoveNext())
{
if (!first)
yield return prev;
first = false;
prev = enumerator.Current;
}
}
}

It would be helpful if .NET Framework was shipped with extension method like this.
public static IEnumerable<T> SkipLast<T>(this IEnumerable<T> source, int count)
{
var enumerator = source.GetEnumerator();
var queue = new Queue<T>(count + 1);
while (true)
{
if (!enumerator.MoveNext())
break;
queue.Enqueue(enumerator.Current);
if (queue.Count > count)
yield return queue.Dequeue();
}
}

if you don't have time to roll out your own extension, here's a quicker way:
var next = sequence.First();
sequence.Skip(1)
.Select(s =>
{
var selected = next;
next = s;
return selected;
});

A slight expansion on Joren's elegant solution:
public static IEnumerable<T> Shrink<T>(this IEnumerable<T> source, int left, int right)
{
int i = 0;
var buffer = new Queue<T>(right + 1);
foreach (T x in source)
{
if (i >= left) // Read past left many elements at the start
{
buffer.Enqueue(x);
if (buffer.Count > right) // Build a buffer to drop right many elements at the end
yield return buffer.Dequeue();
}
else i++;
}
}
public static IEnumerable<T> WithoutLast<T>(this IEnumerable<T> source, int n = 1)
{
return source.Shrink(0, n);
}
public static IEnumerable<T> WithoutFirst<T>(this IEnumerable<T> source, int n = 1)
{
return source.Shrink(n, 0);
}
Where shrink implements a simple count forward to drop the first left many elements and the same discarded buffer to drop the last right many elements.

If you can get the Count or Length of an enumerable, which in most cases you can, then just Take(n - 1)
Example with arrays
int[] arr = new int[] { 1, 2, 3, 4, 5 };
int[] sub = arr.Take(arr.Length - 1).ToArray();
Example with IEnumerable<T>
IEnumerable<int> enu = Enumerable.Range(1, 100);
IEnumerable<int> sub = enu.Take(enu.Count() - 1);

A slight variation on the accepted answer, which (for my tastes) is a bit simpler:
public static IEnumerable<T> AllButLast<T>(this IEnumerable<T> enumerable, int n = 1)
{
// for efficiency, handle degenerate n == 0 case separately
if (n == 0)
{
foreach (var item in enumerable)
yield return item;
yield break;
}
var queue = new Queue<T>(n);
foreach (var item in enumerable)
{
if (queue.Count == n)
yield return queue.Dequeue();
queue.Enqueue(item);
}
}

Why not just .ToList<type>() on the sequence, then call count and take like you did originally..but since it's been pulled into a list, it shouldnt do an expensive enumeration twice. Right?

The solution that I use for this problem is slightly more elaborate.
My util static class contains an extension method MarkEnd which converts the T-items in EndMarkedItem<T>-items. Each element is marked with an extra int, which is either 0; or (in case one is particularly interested in the last 3 items) -3, -2, or -1 for the last 3 items.
This could be useful on its own, e.g. when you want to create a list in a simple foreach-loop with commas after each element except the last 2, with the second-to-last item followed by a conjunction word (such as “and” or “or”), and the last element followed by a point.
For generating the entire list without the last n items, the extension method ButLast simply iterates over the EndMarkedItem<T>s while EndMark == 0.
If you don’t specify tailLength, only the last item is marked (in MarkEnd()) or dropped (in ButLast()).
Like the other solutions, this works by buffering.
using System;
using System.Collections.Generic;
using System.Linq;
namespace Adhemar.Util.Linq {
public struct EndMarkedItem<T> {
public T Item { get; private set; }
public int EndMark { get; private set; }
public EndMarkedItem(T item, int endMark) : this() {
Item = item;
EndMark = endMark;
}
}
public static class TailEnumerables {
public static IEnumerable<T> ButLast<T>(this IEnumerable<T> ts) {
return ts.ButLast(1);
}
public static IEnumerable<T> ButLast<T>(this IEnumerable<T> ts, int tailLength) {
return ts.MarkEnd(tailLength).TakeWhile(te => te.EndMark == 0).Select(te => te.Item);
}
public static IEnumerable<EndMarkedItem<T>> MarkEnd<T>(this IEnumerable<T> ts) {
return ts.MarkEnd(1);
}
public static IEnumerable<EndMarkedItem<T>> MarkEnd<T>(this IEnumerable<T> ts, int tailLength) {
if (tailLength < 0) {
throw new ArgumentOutOfRangeException("tailLength");
}
else if (tailLength == 0) {
foreach (var t in ts) {
yield return new EndMarkedItem<T>(t, 0);
}
}
else {
var buffer = new T[tailLength];
var index = -buffer.Length;
foreach (var t in ts) {
if (index < 0) {
buffer[buffer.Length + index] = t;
index++;
}
else {
yield return new EndMarkedItem<T>(buffer[index], 0);
buffer[index] = t;
index++;
if (index == buffer.Length) {
index = 0;
}
}
}
if (index >= 0) {
for (var i = index; i < buffer.Length; i++) {
yield return new EndMarkedItem<T>(buffer[i], i - buffer.Length - index);
}
for (var j = 0; j < index; j++) {
yield return new EndMarkedItem<T>(buffer[j], j - index);
}
}
else {
for (var k = 0; k < buffer.Length + index; k++) {
yield return new EndMarkedItem<T>(buffer[k], k - buffer.Length - index);
}
}
}
}
}
}

public static IEnumerable<T> NoLast<T> (this IEnumerable<T> items) {
if (items != null) {
var e = items.GetEnumerator();
if (e.MoveNext ()) {
T head = e.Current;
while (e.MoveNext ()) {
yield return head; ;
head = e.Current;
}
}
}
}

I don't think it can get more succinct than this - also ensuring to Dispose the IEnumerator<T>:
public static IEnumerable<T> SkipLast<T>(this IEnumerable<T> source)
{
using (var it = source.GetEnumerator())
{
if (it.MoveNext())
{
var item = it.Current;
while (it.MoveNext())
{
yield return item;
item = it.Current;
}
}
}
}
Edit: technically identical to this answer.

This is a general and IMHO elegant solution that will handle all cases correctly:
using System;
using System.Collections.Generic;
using System.Linq;
public class Program
{
public static void Main()
{
IEnumerable<int> r = Enumerable.Range(1, 20);
foreach (int i in r.AllButLast(3))
Console.WriteLine(i);
Console.ReadKey();
}
}
public static class LinqExt
{
public static IEnumerable<T> AllButLast<T>(this IEnumerable<T> enumerable, int n = 1)
{
using (IEnumerator<T> enumerator = enumerable.GetEnumerator())
{
Queue<T> queue = new Queue<T>(n);
for (int i = 0; i < n && enumerator.MoveNext(); i++)
queue.Enqueue(enumerator.Current);
while (enumerator.MoveNext())
{
queue.Enqueue(enumerator.Current);
yield return queue.Dequeue();
}
}
}
}

You could write:
var list = xyz.Select(x=>x.Id).ToList();
list.RemoveAt(list.Count - 1);

My traditional IEnumerable approach:
/// <summary>
/// Skips first element of an IEnumerable
/// </summary>
/// <typeparam name="U">Enumerable type</typeparam>
/// <param name="models">The enumerable</param>
/// <returns>IEnumerable of type skipping first element</returns>
private IEnumerable<U> SkipFirstEnumerable<U>(IEnumerable<U> models)
{
using (var e = models.GetEnumerator())
{
if (!e.MoveNext()) return;
for (;e.MoveNext();) yield return e.Current;
yield return e.Current;
}
}
/// <summary>
/// Skips last element of an IEnumerable
/// </summary>
/// <typeparam name="U">Enumerable type</typeparam>
/// <param name="models">The enumerable</param>
/// <returns>IEnumerable of type skipping last element</returns>
private IEnumerable<U> SkipLastEnumerable<U>(IEnumerable<U> models)
{
using (var e = models.GetEnumerator())
{
if (!e.MoveNext()) return;
yield return e.Current;
for (;e.MoveNext();) yield return e.Current;
}
}

Could be:
var allBuLast = sequence.TakeWhile(e => e != sequence.Last());
I guess it should be like de "Where" but preserving the order(?).

If speed is a requirement, this old school way should be the fastest, even though the code doesn't look as smooth as linq could make it.
int[] newSequence = int[sequence.Length - 1];
for (int x = 0; x < sequence.Length - 1; x++)
{
newSequence[x] = sequence[x];
}
This requires that the sequence is an array since it has a fixed length and indexed items.

A simple way would be to just convert to a queue and dequeue until only the number of items you want to skip is left.
public static IEnumerable<T> SkipLast<T>(this IEnumerable<T> source, int n)
{
var queue = new Queue<T>(source);
while (queue.Count() > n)
{
yield return queue.Dequeue();
}
}

I would probably do something like this:
sequence.Where(x => x != sequence.LastOrDefault())
This is one iteration with a check that it isn't the last one for each time though.