/// <summary>
/// Seperates a dataset into clusters or groups with similar characteristics
/// </summary>
/// <param name="clusters">A collection of data clusters</param>
/// <param name="data">An array containing data to b eclustered</param>
/// <returns>A collection of clusters of data</returns>
public static ClusterCollection ClusterDataSet(ClusterCollection clusters, double [,] data)
{
double [] dataPoint;
double [] clusterMean;
double firstClusterDistance = 0.0;
double secondClusterDistance = 0.0;
int rowCount = data.GetUpperBound(0) + 1;
int fieldCount = data.GetUpperBound(1) + 1;
int position = 0;
// create a new collection of clusters
ClusterCollection newClusters = new ClusterCollection();
for (int count = 0; count < clusters.Count; count++)
{
Cluster newCluster = new Cluster();
newClusters.Add(newCluster);
}
if (clusters.Count <= 0)
{
throw new SystemException("Cluster Count Cannot Be Zero!");
}
//((20+30)/2), ((170+160)/2), ((80+120)/2)
for (int row = 0; row < rowCount; row++)
{
dataPoint = new double[fieldCount];
for (int field = 0; field < fieldCount; field++)
{
dataPoint.SetValue((data[row, field]), field);
}
for (int cluster = 0; cluster < clusters.Count; cluster++)
{
clusterMean = clusters[cluster].ClusterMean;
if (cluster == 0)
{
firstClusterDistance = KMeans.EuclideanDistance(dataPoint, clusterMean);
position = cluster;
}
else
{
secondClusterDistance = KMeans.EuclideanDistance(dataPoint, clusterMean);
if (firstClusterDistance > secondClusterDistance)
{
firstClusterDistance = secondClusterDistance;
position = cluster;
}
}
}
newClusters[position].Add(dataPoint);
}
return(newClusters);
}
/// <summary>
/// Seperates a dataset into clusters or groups with similar characteristics
/// </summary>
/// <param name="clusterCount">The number of clusters or groups to form</param>
/// <param name="data">An array containing data that will be clustered</param>
/// <returns>A collection of clusters of data</returns>
public static ClusterCollection ClusterDataSet(int clusterCount, double [,] data)
{
//bool stableClusterFormation = false;
int clusterNumber = 0;
int rowCount = data.GetUpperBound(0) + 1;
int fieldCount = data.GetUpperBound(1) + 1;
int stableClustersCount = 0;
int iterationCount = 0;
double [] dataPoint;
Random random = new Random();
Cluster cluster = null;
ClusterCollection clusters = new ClusterCollection();
System.Collections.ArrayList clusterNumbers = new System.Collections.ArrayList(clusterCount);
while (clusterNumbers.Count < clusterCount)
{
clusterNumber = random.Next(0, rowCount - 1);
if (!clusterNumbers.Contains(clusterNumber))
{
cluster = new Cluster();
clusterNumbers.Add(clusterNumber);
dataPoint = new double[fieldCount];
for (int field = 0; field < fieldCount; field++)
{
dataPoint.SetValue((data[clusterNumber, field]), field);
}
cluster.Add(dataPoint);
clusters.Add(cluster);
}
}
while (stableClustersCount != clusters.Count)
{
stableClustersCount = 0;
ClusterCollection newClusters = KMeans.ClusterDataSet(clusters, data);
for (int clusterIndex = 0; clusterIndex < clusters.Count; clusterIndex++)
{
if ((KMeans.EuclideanDistance(newClusters[clusterIndex].ClusterMean, clusters[clusterIndex].ClusterMean)) == 0)
{
stableClustersCount++;
}
}
iterationCount++;
clusters = newClusters;
}
return(clusters);
}
// K-Means
private void Kmeans(Dictionary<int, Dictionary<int, double>> data, int clusters, string type, string codage)
{
double[,] db = null;
if (data.Count > 1)
if (codage != "Binaire")
db = convertData(data);
else
db = convertDataBin(data);
else
return;
Console.WriteLine("Donnees convertie");
cluster = KMeans.ClusterDataSet(clusters, db, type);
//MessageBox.Show(this,"Nombre de cluster : " + cluster.Count);
Console.WriteLine("Kmeans calcule");
//Dictionary<int, int> stationCluster = new Dictionary<int, int>();
stationCluster = new Dictionary<int, int>();
for (int i = 0; i < cluster.Count; i++)
{
Console.WriteLine("Cluster : " + i + " - Taille : " + cluster[i].Count);
//string s = "Cluster " + i + ", taille = " + cluster[i].getValues.Count + " : ";
foreach (int z in cluster[i].getValues)
{
//Console.WriteLine(stations[z]);
int temp = stations[z];
stationCluster.Add(temp, i);
//string s = stations[z] + " : " + i ;
}
}
ScrollableMaps maps = new ScrollableMaps();
maps.drawClusters(stationCluster);
PictureBox map = maps.mapBox;
map.SizeMode = PictureBoxSizeMode.Zoom;
map.Dock = DockStyle.Fill;
Panel tempPanel = new Panel();
tempPanel.Dock = DockStyle.Fill;
combo1 = new ComboBox();
combo1.Text = "Affichage des statistiques pour les clusters";
combo1.Items.Add("Tous les clusters");
combo1.Items.Add("Altitudes");
combo1.Items.Add("Point of Interest");
for (int i = 0; i < cluster.Count; i++)
combo1.Items.Add(i);
combo1.SelectedIndexChanged += changeCluster;
combo1.Dock = DockStyle.Top;
tempPanel.Controls.Add(combo1);
tempPanel.Controls.Add(map);
panel.addControls(tempPanel);
}
/// <summary>
/// Seperates a dataset into clusters or groups with similar characteristics
/// </summary>
/// <param name="clusterCount">The number of clusters or groups to form</param>
/// <param name="data">An array containing data that will be clustered</param>
/// <returns>A collection of clusters of data</returns>
public static ClusterCollection ClusterDataSet(int clusterCount, double[,] data, string type)
{
//bool stableClusterFormation = false;
int clusterNumber = 0;
int rowCount = data.GetUpperBound(0) + 1;
int fieldCount = data.GetUpperBound(1) + 1;
int stableClustersCount = 0;
int iterationCount = 0;
double[] dataPoint;
Random random = new Random();
Cluster cluster = null;
ClusterCollection clusters = new ClusterCollection();
System.Collections.ArrayList clusterNumbers = new System.Collections.ArrayList(clusterCount);
while (clusterNumbers.Count < clusterCount)
{
clusterNumber = random.Next(0, rowCount - 1);
if (!clusterNumbers.Contains(clusterNumber))
{
cluster = new Cluster();
clusterNumbers.Add(clusterNumber);
dataPoint = new double[fieldCount];
for (int field = 0; field < fieldCount; field++)
{
dataPoint.SetValue((data[clusterNumber, field]), field);
}
cluster.Add(dataPoint);
clusters.Add(cluster);
}
}
int compteur = 0;
while (stableClustersCount != clusters.Count)
{
stableClustersCount = 0;
bool isNotGood = false;
ClusterCollection newClusters = KMeans.ClusterDataSet(clusters, data, type);
for (int tempo = 0; tempo < newClusters.Count; tempo++)
{
if (newClusters[tempo].Count < 1)
{
isNotGood = true;
}
}
if (compteur == 10)
{
return(clusters);
}
if (isNotGood)
{
compteur++;
continue;
}
for (int clusterIndex = 0; clusterIndex < clusters.Count; clusterIndex++)
{
double distance = 0;
switch (type)
{
case "DTW":
distance = (KMeans.DtwDistance(newClusters[clusterIndex].ClusterMean, clusters[clusterIndex].ClusterMean));
break;
case "Manhattan":
distance = (KMeans.ManhattanDistance(newClusters[clusterIndex].ClusterMean, clusters[clusterIndex].ClusterMean));
break;
default:
distance = (KMeans.EuclideanDistance(newClusters[clusterIndex].ClusterMean, clusters[clusterIndex].ClusterMean));
break;
}
if (distance == 0)
{
stableClustersCount++;
}
}
iterationCount++;
clusters = newClusters;
}
return(clusters);
}
/// <summary>
/// Seperates a dataset into clusters or groups with similar characteristics
/// </summary>
/// <param name="clusters">A collection of data clusters</param>
/// <param name="data">An array containing data to b eclustered</param>
/// <returns>A collection of clusters of data</returns>
public static ClusterCollection ClusterDataSet(ClusterCollection clusters, double[,] data, string type)
{
double[] dataPoint;
double[] clusterMean;
double firstClusterDistance = 0.0;
double secondClusterDistance = 0.0;
int rowCount = data.GetUpperBound(0) + 1;
int fieldCount = data.GetUpperBound(1) + 1;
int position = 0;
// create a new collection of clusters
ClusterCollection newClusters = new ClusterCollection();
for (int count = 0; count < clusters.Count; count++)
{
Cluster newCluster = new Cluster();
newClusters.Add(newCluster);
}
if (clusters.Count <= 0)
{
throw new SystemException("Cluster Count Cannot Be Zero!");
}
//((20+30)/2), ((170+160)/2), ((80+120)/2)
for (int row = 0; row < rowCount; row++)
{
dataPoint = new double[fieldCount];
for (int field = 0; field < fieldCount; field++)
{
dataPoint.SetValue((data[row, field]), field);
}
for (int cluster = 0; cluster < clusters.Count; cluster++)
{
clusterMean = clusters[cluster].ClusterMean;
if (cluster == 0)
{
switch (type)
{
case "DTW":
firstClusterDistance = KMeans.DtwDistance(dataPoint, clusterMean);
break;
case "Manhattan":
firstClusterDistance = KMeans.ManhattanDistance(dataPoint, clusterMean);
break;
default:
firstClusterDistance = KMeans.EuclideanDistance(dataPoint, clusterMean);
break;
}
position = cluster;
}
else
{
switch (type)
{
case "DTW":
secondClusterDistance = KMeans.DtwDistance(dataPoint, clusterMean);
break;
case "Manhattan":
secondClusterDistance = KMeans.ManhattanDistance(dataPoint, clusterMean);
break;
default:
secondClusterDistance = KMeans.EuclideanDistance(dataPoint, clusterMean);
break;
}
if (firstClusterDistance > secondClusterDistance)
{
firstClusterDistance = secondClusterDistance;
position = cluster;
}
}
}
newClusters[position].Add(dataPoint);
newClusters[position].AddValue(row);
}
return newClusters;
}
/// <summary>
/// Seperates a dataset into clusters or groups with similar characteristics
/// </summary>
/// <param name="clusterCount">The number of clusters or groups to form</param>
/// <param name="data">An array containing data that will be clustered</param>
/// <returns>A collection of clusters of data</returns>
public static ClusterCollection ClusterDataSet(int clusterCount, double[,] data, string type)
{
//bool stableClusterFormation = false;
int clusterNumber = 0;
int rowCount = data.GetUpperBound(0) + 1;
int fieldCount = data.GetUpperBound(1) + 1;
int stableClustersCount = 0;
int iterationCount = 0;
double[] dataPoint;
Random random = new Random();
Cluster cluster = null;
ClusterCollection clusters = new ClusterCollection();
System.Collections.ArrayList clusterNumbers = new System.Collections.ArrayList(clusterCount);
while (clusterNumbers.Count < clusterCount)
{
clusterNumber = random.Next(0, rowCount - 1);
if (!clusterNumbers.Contains(clusterNumber))
{
cluster = new Cluster();
clusterNumbers.Add(clusterNumber);
dataPoint = new double[fieldCount];
for (int field = 0; field < fieldCount; field++)
{
dataPoint.SetValue((data[clusterNumber, field]), field);
}
cluster.Add(dataPoint);
clusters.Add(cluster);
}
}
int compteur = 0;
while (stableClustersCount != clusters.Count)
{
stableClustersCount = 0;
bool isNotGood = false;
ClusterCollection newClusters = KMeans.ClusterDataSet(clusters, data, type);
for (int tempo = 0; tempo < newClusters.Count; tempo++)
if (newClusters[tempo].Count < 1)
isNotGood = true;
if (compteur == 10)
return clusters;
if (isNotGood)
{
compteur++;
continue;
}
for (int clusterIndex = 0; clusterIndex < clusters.Count; clusterIndex++)
{
double distance = 0;
switch (type)
{
case "DTW":
distance = (KMeans.DtwDistance(newClusters[clusterIndex].ClusterMean, clusters[clusterIndex].ClusterMean));
break;
case "Manhattan":
distance = (KMeans.ManhattanDistance(newClusters[clusterIndex].ClusterMean, clusters[clusterIndex].ClusterMean));
break;
default:
distance = (KMeans.EuclideanDistance(newClusters[clusterIndex].ClusterMean, clusters[clusterIndex].ClusterMean));
break;
}
if (distance == 0)
{
stableClustersCount++;
}
}
iterationCount++;
clusters = newClusters;
}
return clusters;
}
