| public Learn ( double x, double weights = null ) : KMeansClusterCollection | ||
| x | double | The model inputs. |
| weights | double | The weight of importance for each input sample. |
| return | KMeansClusterCollection | |
public override KMeansClusterCollection Learn(double[][] x, double[] weights = null)
{
// Initial argument checking
if (x == null)
throw new ArgumentNullException("x");
if (x.Length < K)
throw new ArgumentException("Not enough points. There should be more points than the number K of clusters.");
if (weights == null)
weights = Vector.Ones(x.Length);
if (x.Length != weights.Length)
throw new ArgumentException("Data weights vector must be the same length as data samples.");
double weightSum = weights.Sum();
if (weightSum <= 0)
throw new ArgumentException("Not enough points. There should be more points than the number K of clusters.");
int cols = x[0].Length;
for (int i = 0; i < x.Length; i++)
if (x[0].Length != cols)
throw new DimensionMismatchException("data", "The points matrix should be rectangular. The vector at position {} has a different length than previous ones.");
int k = Clusters.Count;
KMeans kmeans = new KMeans(2)
{
Distance = (IDistance<double[]>)Clusters.Distance,
ComputeError = false,
ComputeCovariances = false,
UseSeeding = UseSeeding,
Tolerance = Tolerance,
MaxIterations = MaxIterations,
};
double[][] centroids = Clusters.Centroids;
double[][][] clusters = new double[k][][];
double[] distortions = new double[k];
// 1. Start with all data points in one cluster
clusters[0] = x;
// 2. Repeat steps 3 to 6 (k-1) times to obtain K centroids
for (int current = 1; current < k; current++)
{
// 3. Choose cluster with largest distortion
int choosen; distortions.Max(current, out choosen);
// 4. Split cluster into two sub-clusters
var splits = split(clusters[choosen], kmeans);
clusters[choosen] = splits.Item1;
clusters[current] = splits.Item2;
// 5. Replace chosen centroid and add a new one
centroids[choosen] = kmeans.Clusters.Centroids[0];
centroids[current] = kmeans.Clusters.Centroids[1];
// Recompute distortions for the updated clusters
distortions[choosen] = kmeans.Clusters[0].Distortion(clusters[choosen]);
distortions[current] = kmeans.Clusters[1].Distortion(clusters[current]);
// 6. Increment cluster count (current = current + 1)
}
return Clusters;
}
public void binary_split_new_method()
{
#region doc_sample1
// Use a fixed seed for reproducibility
Accord.Math.Random.Generator.Seed = 0;
// Declare some data to be clustered
double[][] input =
{
new double[] { -5, -2, -1 },
new double[] { -5, -5, -6 },
new double[] { 2, 1, 1 },
new double[] { 1, 1, 2 },
new double[] { 1, 2, 2 },
new double[] { 3, 1, 2 },
new double[] { 11, 5, 4 },
new double[] { 15, 5, 6 },
new double[] { 10, 5, 6 },
};
// Create a new binary split with 3 clusters
BinarySplit binarySplit = new BinarySplit(3);
// Learn a data partitioning using the Binary Split algorithm
KMeansClusterCollection clustering = binarySplit.Learn(input);
// Predict group labels for each point
int[] output = clustering.Decide(input);
// As a result, the first two observations should belong to the
// same cluster (thus having the same label). The same should
// happen to the next four observations and to the last three.
#endregion
Assert.AreEqual(output[0], output[1]);
Assert.AreEqual(output[2], output[3]);
Assert.AreEqual(output[2], output[4]);
Assert.AreEqual(output[2], output[5]);
Assert.AreEqual(output[6], output[7]);
Assert.AreEqual(output[6], output[8]);
Assert.AreNotEqual(output[0], output[2]);
Assert.AreNotEqual(output[2], output[6]);
Assert.AreNotEqual(output[0], output[6]);
int[] labels2 = binarySplit.Clusters.Nearest(input);
Assert.IsTrue(output.IsEqual(labels2));
}
