ClustersDiscover Method

public static IndexPartition<double> Discover(
	DoubleMatrix data,
	int maximumNumberOfParts
)

using System;

namespace Novacta.Analytics.CodeExamples
{
    public class ClustersDiscoverExample0  
    {
        public void Main()
        {
            // Set the number of items and features under study.
            const int numberOfItems = 12;
            int numberOfFeatures = 7;

            // Create a matrix that will represent
            // an artificial data set,
            // having 12 items (rows) and 7 features (columns).
            // This will store the observations which
            // partition discovery will be based on.
            var data = DoubleMatrix.Dense(
                numberOfRows: numberOfItems,
                numberOfColumns: numberOfFeatures);

            // Fill the data rows by sampling from a different 
            // distribution while, respectively, drawing observations 
            // for items 0 to 3, 4 to 7, and 8 to 11: these will be the 
            // three different parts expected to be included in the 
            // optimal partition.
            double mu = 1.0;
            var g = new GaussianDistribution(mu: mu, sigma: .01);

            IndexCollection range = IndexCollection.Range(0, 3);
            for (int j = 0; j < numberOfFeatures; j++)
            {
                data[range, j] = g.Sample(sampleSize: range.Count);
            }

            mu += 5.0;
            g.Mu = mu;
            range = IndexCollection.Range(4, 7);
            for (int j = 0; j < numberOfFeatures; j++)
            {
                data[range, j] = g.Sample(sampleSize: range.Count);
            }

            mu += 5.0;
            g.Mu = mu;
            range = IndexCollection.Range(8, 11);
            for (int j = 0; j < numberOfFeatures; j++)
            {
                data[range, j] = g.Sample(sampleSize: range.Count);
            }

            Console.WriteLine("The data set:");
            Console.WriteLine(data);

            // Define the maximum number of parts allowed in the
            // partition to be discovered.
            int maximumNumberOfParts = 3;

            // Select the best partition.
            IndexPartition<double> optimalPartition =
                Clusters.Discover(
                    data,
                    maximumNumberOfParts);

            // Show the results.
            Console.WriteLine();
            Console.WriteLine(
                "The optimal partition:");
            Console.WriteLine(optimalPartition);

            Console.WriteLine();
            Console.WriteLine("The Davies-Bouldin Index for the optimal partition:");
            var dbi = IndexPartition.DaviesBouldinIndex(
                data,
                optimalPartition);
            Console.WriteLine(dbi);
        }
    }
}

// Executing method Main() produces the following output:
// 
// The data set:
// 1.00443413       1.00220674       0.998272394      1.00269053       0.996789222      1.00089097       1.00413588       
// 0.997933228      0.993625618      1.01576579       1.02088407       1.00505243       1.00840849       0.996769171      
// 1.01157148       0.993373518      1.01292534       1.00980881       0.985070715      0.999051426      1.00490173       
// 0.984314579      0.978064595      0.991518637      0.992424337      1.01228209       0.995401166      0.990271674      
// 5.99388101       5.98782501       5.99234977       6.00720306       5.99391035       5.99483769       6.01287673       
// 5.9959073        6.00295384       5.99060985       6.00210944       5.9964148        6.00144991       5.9847536        
// 6.00236976       6.00235032       6.00327886       6.01032821       5.98648754       6.0157819        5.98911535       
// 6.01095691       5.98513671       5.99782074       5.989109         6.0223965        6.01074213       6.00275269       
// 10.9874226       11.0066379       11.0105315       10.9944047       10.9989296       11.009567        10.9938497       
// 11.0044736       10.9993181       11.0126423       10.9974367       10.9946015       10.9885624       11.0013196       
// 10.9766909       10.9908217       11.012074        10.9924937       10.9886034       11.007384        10.9891406       
// 10.9974049       10.9925417       10.9969562       11.0226839       10.9973201       11.007219        11.005672        
// 
// 
// 
// The optimal partition:
// [(0),  8, 9, 10, 11]
// [(1),  0, 1, 2, 3]
// [(2),  4, 5, 6, 7]
// 
// 
// The Davies-Bouldin Index for the optimal partition:
// 0.0034476806923814927