Optimal LINQ query to get a random sub collection – Shuffle

Further to mquander’s answer and Dan Blanchard’s comment, here’s a LINQ-friendly extension method that performs a Fisher-Yates-Durstenfeld shuffle:

// take n random items from yourCollection
var randomItems = yourCollection.Shuffle().Take(n);

// ...

public static class EnumerableExtensions
{
    public static IEnumerable<T> Shuffle<T>(this IEnumerable<T> source)
    {
        return source.Shuffle(new Random());
    }

    public static IEnumerable<T> Shuffle<T>(this IEnumerable<T> source, Random rng)
    {
        if (source == null) throw new ArgumentNullException("source");
        if (rng == null) throw new ArgumentNullException("rng");

        return source.ShuffleIterator(rng);
    }

    private static IEnumerable<T> ShuffleIterator<T>(
        this IEnumerable<T> source, Random rng)
    {
        var buffer = source.ToList();
        for (int i = 0; i < buffer.Count; i++)
        {
            int j = rng.Next(i, buffer.Count);
            yield return buffer[j];

            buffer[j] = buffer[i];
        }
    }
}

Leave a Comment