/// <summary>
/// Starts the task.
/// </summary>
/// <param name="dataSet">The list of objects that to be converted.</param>
/// <param name="distanceMetric">The distance metric used to scale down dimensions.</param>
public void Start(IdentifiableDataPointCollection dataSet, IDistanceMetric distanceMetric)
{
var args = new TaskRunnerArgumentSet {
Data = dataSet, DistanceMetric = distanceMetric
};
var task = Task.Factory.StartNew <DataConversionResult>(TaskRunner, args);
// Make sure Success and Failure events are run within the caller thread.
TaskScheduler currentContext = TaskScheduler.FromCurrentSynchronizationContext();
task.ContinueWith(TaskComplete, currentContext);
task.ContinueWith(TaskFaulted, CancellationToken.None, TaskContinuationOptions.OnlyOnFaulted, currentContext);
}
public KMeans(IdentifiableDataPointCollection dataCollection, int[] centroidIndicies, IDistanceMetric distanceMetric, int maxIterations = 100)
{
this.dataCollection = dataCollection;
this.maxIterations = maxIterations;
this.distanceMetric = distanceMetric;
if (centroidIndicies.Length != centroidIndicies.Distinct().Count())
{
throw new ArgumentException(
"Array contains dublicate indicies, which is not allowed.", "centroidIndicies");
}
this.centroids = centroidIndicies
.Select(index => this.dataCollection[index].Clone())
.ToList();
EnsureDistinctCentroid();
}
public KMeans(IdentifiableDataPointCollection dataCollection, int k, IDistanceMetric distanceMetric, int maxIterations = 100)
{
if (k < 1)
{
throw new ArgumentException("Clusters cannot be generated for less than one centroid");
}
this.dataCollection = dataCollection;
this.maxIterations = maxIterations;
this.distanceMetric = distanceMetric;
this.centroids = dataCollection
.OrderBy(dataPoint => Guid.NewGuid()) // Random order
.Take(k)
.Select(dataPoint => dataPoint.Clone())
.ToList();
EnsureDistinctCentroid();
}
public IdentifiableDataPointCollection Generate()
{
distanceMetric = new EuclideanMetric();
dataCollection = new IdentifiableDataPointCollection();
int id = 0;
int dimentions = 5;
dataCollection = new IdentifiableDataPointCollection();
for (int i = 0; i < collectionSize; i++)
{
dataPoint = new IdentifiableDataPoint(++id, dimentions);
dataCollection.AddItem(dataPoint);
}
for (int i = 0; i < collectionSize; i++)
{
if ((i % 10) < 9)
{
dataCollection[i].AddAttribute("Gender", 1d);
}
else
{
dataCollection[i].AddAttribute("Gender", 0d);
}
if ((i % 10) < 4)
{
dataCollection[i].AddAttribute("Income", 1d);
}
else if ((i % 10) > 8)
{
dataCollection[i].AddAttribute("Income", 0.1429);
}
else
{
dataCollection[i].AddAttribute("Income", 0.2858d);
}
dataCollection[i].AddAttribute("Age", 0.16d);
if ((i % 10) < 2 || (i % 10) > 3)
{
dataCollection[i].AddAttribute("Purchase", 1d);
}
else
{
dataCollection[i].AddAttribute("Purchase", 0.5d);
}
if ((i % 10) < 2)
{
dataCollection[i].AddAttribute("Control", 0.5d);
}
else if ((i % 10) > 8)
{
dataCollection[i].AddAttribute("Control", 0d);
}
else
{
dataCollection[i].AddAttribute("Control", 1d);
}
}
return(dataCollection);
}
