public void KNNSearchTest()
{
var parameters = new SmallWorld <float[], float> .Parameters();
var graph = new SmallWorld <float[], float>(CosineDistance.NonOptimized, DefaultRandomGenerator.Instance, parameters);
graph.AddItems(vectors);
int bestWrong = 0;
float maxError = float.MinValue;
for (int i = 0; i < vectors.Count; ++i)
{
var result = graph.KNNSearch(vectors[i], 20);
var best = result.OrderBy(r => r.Distance).First();
Assert.AreEqual(20, result.Count);
if (best.Id != i)
{
bestWrong++;
}
maxError = Math.Max(maxError, best.Distance);
}
Assert.AreEqual(0, bestWrong);
Assert.AreEqual(0, maxError, FloatError);
}
public void KNNSearchTestAlgorithm4(bool expandBestSelection, bool keepPrunedConnections)
{
var parameters = new SmallWorld <float[], float> .Parameters()
{
NeighbourHeuristic = NeighbourSelectionHeuristic.SelectHeuristic, ExpandBestSelection = expandBestSelection, KeepPrunedConnections = keepPrunedConnections
};
var graph = new SmallWorld <float[], float>(CosineDistance.NonOptimized, DefaultRandomGenerator.Instance, parameters);
graph.AddItems(vectors);
int bestWrong = 0;
float maxError = float.MinValue;
for (int i = 0; i < vectors.Count; ++i)
{
var result = graph.KNNSearch(vectors[i], 20);
var best = result.OrderBy(r => r.Distance).First();
Assert.AreEqual(20, result.Count);
if (best.Id != i)
{
bestWrong++;
}
maxError = Math.Max(maxError, best.Distance);
}
Assert.AreEqual(0, bestWrong);
Assert.AreEqual(0, maxError, FloatError);
}
public void SerializeDeserializeTest()
{
byte[] buffer;
string original;
// restrict scope of original graph
var stream = new MemoryStream();
{
var parameters = new SmallWorld <float[], float> .Parameters()
{
M = 15,
LevelLambda = 1 / Math.Log(15),
};
var graph = new SmallWorld <float[], float>(CosineDistance.NonOptimized, DefaultRandomGenerator.Instance, parameters);
graph.AddItems(vectors);
graph.SerializeGraph(stream);
original = graph.Print();
}
stream.Position = 0;
var copy = SmallWorld <float[], float> .DeserializeGraph(vectors, CosineDistance.NonOptimized, DefaultRandomGenerator.Instance, stream);
Assert.AreEqual(original, copy.Print());
}
private static void BuildAndSave(string pathPrefix)
{
var world = new SmallWorld <float[], float>(CosineDistance.SIMDForUnits, DefaultRandomGenerator.Instance, new Parameters()
{
EnableDistanceCacheForConstruction = true, InitialDistanceCacheSize = SampleSize, NeighbourHeuristic = NeighbourSelectionHeuristic.SelectHeuristic, KeepPrunedConnections = true, ExpandBestSelection = true
});
Console.Write($"Generating {SampleSize} sample vectos... ");
var clock = Stopwatch.StartNew();
var sampleVectors = RandomVectors(Dimensionality, SampleSize);
Console.WriteLine($"Done in {clock.ElapsedMilliseconds} ms.");
Console.WriteLine("Building HNSW graph... ");
using (var listener = new MetricsEventListener(EventSources.GraphBuildEventSource.Instance))
{
clock = Stopwatch.StartNew();
for (int i = 0; i < (SampleSize / SampleIncrSize); i++)
{
world.AddItems(sampleVectors.Skip(i * SampleIncrSize).Take(SampleIncrSize).ToArray());
Console.WriteLine($"\nAt {i+1} of {SampleSize / SampleIncrSize} Elapsed: {clock.ElapsedMilliseconds} ms.\n");
}
Console.WriteLine($"Done in {clock.ElapsedMilliseconds} ms.");
}
Console.Write($"Saving HNSW graph to '${Path.Combine(Directory.GetCurrentDirectory(), pathPrefix)}'... ");
clock = Stopwatch.StartNew();
BinaryFormatter formatter = new BinaryFormatter();
MemoryStream sampleVectorsStream = new MemoryStream();
formatter.Serialize(sampleVectorsStream, sampleVectors);
File.WriteAllBytes($"{pathPrefix}.{VectorsPathSuffix}", sampleVectorsStream.ToArray());
using (var f = File.Open($"{pathPrefix}.{GraphPathSuffix}", FileMode.Create))
{
world.SerializeGraph(f);
}
Console.WriteLine($"Done in {clock.ElapsedMilliseconds} ms.");
}
