/// <summary>
/// Load data directly, not via a file.
/// </summary>
/// <param name="initialClassification">Initial classification.</param>
/// <param name="originalOrder">Original order. If omitted, an arbitrary ordering of points will be defined.</param>
public void LoadData(Classification <UnsignedPoint, string> initialClassification, IList <UnsignedPoint> originalOrder = null)
{
InitialClassification = initialClassification;
if (originalOrder == null)
{
InputOrder = InitialClassification.Points().ToList();
}
else
{
InputOrder = originalOrder.ToList();
}
InputDataIds = new Dictionary <UnsignedPoint, string>();
foreach (var point in InitialClassification.Points())
{
InputDataIds[point] = point.UniqueId.ToString();
}
}
/// <summary>
/// Create a classifier to categorize points further, building on top of an existing classification.
/// </summary>
/// <param name="points">Points to categorize.</param>
/// <param name="bitsPerDimension">Bits per dimension.</param>
public HilbertClassifier(Classification <UnsignedPoint, string> c, int bitsPerDimension)
{
// Steps 1 and 2b (Receive points and classify all points as they are already classified).
Clusters = c;
BitsPerDimension = bitsPerDimension;
IdsToPoints = new Dictionary <int, UnsignedPoint>();
foreach (var p in Clusters.Points())
{
IdsToPoints[p.UniqueId] = p;
}
}
/// <summary>
/// Create a classifier to cluster from scratch, with no regard to any previous categorization.
/// </summary>
/// <param name="points">Points to categorize.</param>
/// <param name="bitsPerDimension">Bits per dimension.</param>
public HilbertClassifier(IEnumerable <UnsignedPoint> points, int bitsPerDimension)
{
var labelCounter = 1;
// Steps 1 and 2a (Receive points and classify all points in separate clusters of size one).
Clusters = new Classification <UnsignedPoint, string>(points, p => (labelCounter++).ToString());
BitsPerDimension = bitsPerDimension;
IdsToPoints = new Dictionary <int, UnsignedPoint>();
foreach (var p in Clusters.Points())
{
IdsToPoints[p.UniqueId] = p;
}
}
/// <summary>
/// Create an index of all the points in a Classification, optionally adding a new dimension to each point to hold
/// that point's classification index.
/// </summary>
/// <param name="clusters">Clusters of points, which could be UnsignedPoints or HilbertPoints.</param>
/// <param name="bitsPerDimension">Bits per dimension to use when transforming UnsignedPoints into HilbertPoints,
/// should that be necessary.
/// If a non-positive number, compute the value by studying the data, using the smallest number capable of accommodating
/// the largest coordinate values.</param>
/// <param name="addClassificationDimension">If set to <c>true</c> add a classification dimension to the end of each point.
/// The value will be the index of that point's cluster. Cluster ordering is arbitrary and dependent on the order that
/// the set Classification.LabelToPoints.Values iterates over them.</param>
public HilbertIndex(Classification <UnsignedPoint, string> clusters, int bitsPerDimension = 0, bool addClassificationDimension = false)
{
if (bitsPerDimension <= 0)
{
bitsPerDimension = FindBitsPerDimension(clusters.Points());
}
UnsortedPoints = new List <HilbertPoint>();
foreach (var clusterWithNumber in clusters.LabelToPoints.Values.Select((c, i) => new { Cluster = c, Index = (uint)i }))
{
UnsortedPoints.AddRange(
clusterWithNumber.Cluster
.Select(p => addClassificationDimension ? p.AppendCoordinate(clusterWithNumber.Index) : p)
.Select(p => HilbertPoint.CastOrConvert(p, bitsPerDimension, true))
);
}
InitIndexing();
}