/// <summary>
/// Returns a sample of the data
/// </summary>
/// <param name="data"></param>
/// <param name="nofSamples"></param>
/// <returns></returns>
private float[][] GetUniqueRandomNumbers(float[][] data, int nofSamples)
{
float[][] tempData = new float[nofSamples][];
for (int i = 0; i < nofSamples; ++i)
{
tempData[i] = new float[data[0].Count()];
}
HashSet <int> numbers = new HashSet <int>();
int numbersLeft = nofSamples;
int destinationIndex = 0;
while (numbersLeft > 0)
{
int rand = RandomGen.Next(0, data.Count());
if (!numbers.Contains(rand))
{
numbers.Add(rand);
numbersLeft--;
CopyArray(data, tempData, rand, destinationIndex);
destinationIndex++;
}
}
return(tempData);
}
private float[,] FindStartingCentersEMD(float[][] data, int k)
{
// select random centers
Console.WriteLine("K-means++ finding good starting centers...");
// first get some samples of all data to speed up the algorithm
int maxSamples = Math.Min(k * 20, data.Length);
float[][] dataTemp = GetUniqueRandomNumbers(data, maxSamples);
float[,] centers = new float[k, dataTemp[0].Count()];
// first cluster center is random
List <int> centerIndices = new List <int>();
int index = -1;
using (var progress = new ProgressBar())
{
progress.Report((double)(1) / k, 1);
for (int c = 0; c < k; ++c) // get a new cluster center one by one
{
float[] distancesToBestCenter = Enumerable.Repeat(float.MaxValue, dataTemp.Count()).ToArray();
if (c == 0)
{
index = RandomGen.Next(0, dataTemp.Count());
centerIndices.Add(index);
CopyArray(dataTemp, centers, index, c);
}
else
{
Parallel.For(0, Global.NOF_THREADS,
i =>
{
for (int j = Util.GetWorkItemsIndices(dataTemp.Count(), Global.NOF_THREADS, i).Item1;
j < Util.GetWorkItemsIndices(dataTemp.Count(), Global.NOF_THREADS, i).Item2; ++j)
{ // go through all dataTemp
for (int m = 0; m < c; ++m) // go through centers
{
float tempDistance = GetEarthMoverDistance(dataTemp, centers, j, m);
if (tempDistance < distancesToBestCenter[j])
{
distancesToBestCenter[j] = tempDistance;
}
}
}
});
SquareArray(distancesToBestCenter);
float sum = distancesToBestCenter.Sum();
for (int p = 0; p < distancesToBestCenter.Count(); ++p)
{
distancesToBestCenter[p] /= sum;
}
int centerIndexSample = Util.SampleDistribution(distancesToBestCenter);
while (centerIndices.Contains(centerIndexSample))
{
centerIndexSample = Util.SampleDistribution(distancesToBestCenter);
}
CopyArray(dataTemp, centers, centerIndexSample, c);
centerIndices.Add(centerIndexSample);
}
progress.Report((double)(c + 1) / k, c + 1);
}
}
return(centers);
}
/// <summary>
/// Returns an array where the element at index i contains the cluster entry associated with the entry
/// </summary>
/// <param name="data"></param>
/// <param name="k"></param>
/// <returns></returns>
public int[] ClusterEMD(float[][] data, int k, int nofRuns, int[] _bestCenters = null)
{
Console.WriteLine("K-means++ (EMD) clustering {0} elements into {1} clusters with {2} runs...", data.Count(), k, nofRuns);
int filenameId = RandomGen.Next(0, 10000000);
DateTime start = DateTime.UtcNow;
int[] bestCenters = new int[data.Count()];
int[] recordCenters = new int[data.Count()]; // we return indices only, the centers are discarded
// load previous indices if passed
bool skipInit = false;
if (_bestCenters != null)
{
skipInit = true;
Array.Copy(_bestCenters, bestCenters, _bestCenters.Length);
Array.Copy(_bestCenters, recordCenters, _bestCenters.Length);
}
double recordDistance = double.MaxValue;
for (int run = 0; run < nofRuns; ++run)
{
float[,] centers = new float[k, data[0].Count()];
Console.WriteLine("K-means++ starting clustering...");
double lastDistance = double.MaxValue;
bool distanceChanged = true;
if (!skipInit)
{
bestCenters = new int[data.Count()];
centers = FindStartingCentersEMD(data, k);
}
else
{
// find new cluster centers // todo: it isnt theoretically sound to take the mean when using EMD distance metric
centers = CalculateNewCenters(data, bestCenters, k);
skipInit = false;
}
float[,] centerCenterDistances = new float[k, k];
while (distanceChanged)
{
// calculate cluster-cluster distances to use triangle inequality
CalculateClusterDistancesEMD(centerCenterDistances, centers);
// find closest cluster for each element
long sharedLoopCounter = 0;
double totalDistance = 0;
using (var progress = new ProgressBar())
{
Parallel.For(0, Global.NOF_THREADS,
i =>
{
double threadDistance = 0;
long iter = 0;
for (int j = Util.GetWorkItemsIndices(data.Length, Global.NOF_THREADS, i).Item1;
j < Util.GetWorkItemsIndices(data.Length, Global.NOF_THREADS, i).Item2; ++j)
{ // go through all data
// assume previous cluster was good, this is better for the triangle inequality
double distance = GetEarthMoverDistance(data, centers, j, bestCenters[j]);
int bestIndex = bestCenters[j];
for (int m = 0; m < k; m++) // go through centers
{
if (centerCenterDistances[bestIndex, m] < 2 * distance && bestIndex != m)
{
double tempDistance = GetEarthMoverDistance(data, centers, j, m);
if (tempDistance < distance)
{
distance = tempDistance;
bestIndex = m;
}
}
}
bestCenters[j] = bestIndex;
threadDistance += distance;
iter++;
if (iter % 100000 == 0)
{
Interlocked.Add(ref sharedLoopCounter, 100000);
AddDouble(ref totalDistance, threadDistance);
threadDistance = 0;
progress.Report((double)Interlocked.Read(ref sharedLoopCounter) / data.Length, sharedLoopCounter);
}
}
Interlocked.Add(ref sharedLoopCounter, iter % 100000);
progress.Report((double)Interlocked.Read(ref sharedLoopCounter) / data.Length, sharedLoopCounter);
AddDouble(ref totalDistance, threadDistance);
});
}
centers = CalculateNewCenters(data, bestCenters, k);
totalDistance /= data.Length;
distanceChanged = !(totalDistance == lastDistance);
double diff = lastDistance - totalDistance;
Console.WriteLine("Saving intermediate table to file...");
FileHandler.SaveToFile(recordCenters, "EMDTable_temp_" + filenameId + ".txt");
if (totalDistance < recordDistance)
{
recordDistance = totalDistance;
Array.Copy(bestCenters, recordCenters, recordCenters.Length);
}
Console.WriteLine("Current average distance: {0} Improvement: {1}, {2}%", totalDistance, diff,
100.0 * (1.0 - totalDistance / lastDistance));
lastDistance = totalDistance;
}
}
Console.WriteLine("Best distance found: " + recordDistance);
TimeSpan elapsed = DateTime.UtcNow - start;
Console.WriteLine("K-means++ clustering (EMD) completed in {0}d {1}h {2}m {3}s", elapsed.Days, elapsed.Hours, elapsed.Minutes, elapsed.Seconds);
// print starting hand chart
return(recordCenters);
}
private static void CalculateOCHSOpponentClusters()
{
Console.WriteLine("Calculating {0} opponent clusters for OCHS using Monte Carlo Sampling...", Global.nofOpponentClusters);
DateTime start = DateTime.UtcNow;
histogramsPreflop = new float[169][]; // c# doesnt allow more than int max indices (its 2019, bitch pls)
for (int i = 0; i < 169; ++i)
{
histogramsPreflop[i] = new float[Global.preflopHistogramSize];
}
long sharedLoopCounter = 0;
using (var progress = new ProgressBar())
{
progress.Report((double)Interlocked.Read(ref sharedLoopCounter) / (169 * Global.nofMCSimsPerPreflopHand), sharedLoopCounter);
Parallel.For(0, 169,
i =>
{
int[] cards = new int[2];
Global.indexer_2.unindex(Global.indexer_2.rounds - 1, i, cards);
long deadCardMask = (1L << cards[0]) + (1L << cards[1]);
for (int steps = 0; steps < Global.nofMCSimsPerPreflopHand; steps++)
{
int cardFlop1 = RandomGen.Next(0, 52);
while (((1L << cardFlop1) & deadCardMask) != 0)
{
cardFlop1 = RandomGen.Next(0, 52);
}
deadCardMask |= (1L << cardFlop1);
int cardFlop2 = RandomGen.Next(0, 52);
while (((1L << cardFlop2) & deadCardMask) != 0)
{
cardFlop2 = RandomGen.Next(0, 52);
}
deadCardMask |= (1L << cardFlop2);
int cardFlop3 = RandomGen.Next(0, 52);
while (((1L << cardFlop3) & deadCardMask) != 0)
{
cardFlop3 = RandomGen.Next(0, 52);
}
deadCardMask |= (1L << cardFlop3);
int cardTurn = RandomGen.Next(0, 52);
while (((1L << cardTurn) & deadCardMask) != 0)
{
cardTurn = RandomGen.Next(0, 52);
}
deadCardMask |= (1L << cardTurn);
int cardRiver = RandomGen.Next(0, 52);
while (((1L << cardRiver) & deadCardMask) != 0)
{
cardRiver = RandomGen.Next(0, 52);
}
deadCardMask |= (1L << cardRiver);
int[] strength = new int[3];
for (int card1Opponent = 0; card1Opponent < 51; card1Opponent++)
{
if (((1L << card1Opponent) & deadCardMask) != 0)
{
continue;
}
deadCardMask |= (1L << card1Opponent);
for (int card2Opponent = card1Opponent + 1; card2Opponent < 52; card2Opponent++)
{
if (((1L << card2Opponent) & deadCardMask) != 0)
{
continue;
}
ulong handSevenCards = (1uL << cards[0]) + (1uL << cards[1]) + (1uL << cardFlop1) + (1uL << cardFlop2) + (1uL << cardFlop3) + (1uL << cardTurn) + (1uL << cardRiver);
ulong handOpponentSevenCards = (1uL << cardFlop1) + (1uL << cardFlop2) + (1uL << cardFlop3) + (1uL << cardTurn) + (1uL << cardRiver) + (1uL << card1Opponent) + (1uL << card2Opponent);
int valueSevenCards = Global.handEvaluator.Evaluate(handSevenCards);
int valueOpponentSevenCards = Global.handEvaluator.Evaluate(handOpponentSevenCards);
int index = (valueSevenCards > valueOpponentSevenCards ? 0 : valueSevenCards == valueOpponentSevenCards ? 1 : 2);
strength[index] += 1;
}
}
float equity = (strength[0] + strength[1] / 2.0f) / (strength[0] + strength[1] + strength[2]);
histogramsPreflop[i][(Math.Min(Global.preflopHistogramSize - 1, (int)(equity * (float)Global.preflopHistogramSize)))] += 1;
deadCardMask = (1L << cards[0]) + (1L << cards[1]);
Interlocked.Add(ref sharedLoopCounter, 1);
progress.Report((double)Interlocked.Read(ref sharedLoopCounter) / (169 * Global.nofMCSimsPerPreflopHand), sharedLoopCounter);
}
});
}
TimeSpan elapsed = DateTime.UtcNow - start;
Console.WriteLine("Calculating opponent clusters completed in {0}d {1}h {2}m {3}s", elapsed.Days,
elapsed.Hours, elapsed.Minutes, elapsed.Seconds);
Console.WriteLine("Calculated histograms: ");
int[] cardsOutput = new int[2];
for (int i = 0; i < 169; ++i)
{
cardsOutput = new int[2];
Global.indexer_2.unindex(Global.indexer_2.rounds - 1, i, cardsOutput);
Hand hand = new Hand();
hand.Cards.Add(new Card(cardsOutput[0]));
hand.Cards.Add(new Card(cardsOutput[1]));
hand.PrintColoredCards();
Console.Write(": ");
for (int j = 0; j < Global.preflopHistogramSize; ++j)
{
Console.Write(histogramsPreflop[i][j] + " ");
}
Console.WriteLine();
}
}