public void Learn(double[][] observations, int amountOfClusters)
{
var kmeans = new KMeans(amountOfClusters);
_clusters = kmeans.Learn(observations);
}
static void Main(string[] args)
{
Console.SetWindowSize(100, 50);
// Read in the Online Retail feature dataset
// TODO: change the path to point to your data directory
string dataDirPath = @"\\Mac\Home\Documents\c-sharp-machine-learning\ch.6\input-data";
// Load the data into a data frame
string dataPath = Path.Combine(dataDirPath, "features.csv");
Console.WriteLine("Loading {0}\n\n", dataPath);
var ecommerceDF = Frame.ReadCsv(
dataPath,
hasHeaders: true,
inferTypes: true
);
Console.WriteLine("* Shape: {0}, {1}", ecommerceDF.RowCount, ecommerceDF.ColumnCount);
string[] features = new string[] { "NetRevenuePercentile", "AvgUnitPricePercentile", "AvgQuantityPercentile" };
Console.WriteLine("* Features: {0}\n\n", String.Join(", ", features));
var normalizedDf = Frame.CreateEmpty <int, string>();
var average = ecommerceDF.Columns[features].Sum() / ecommerceDF.RowCount;
foreach (string feature in features)
{
normalizedDf.AddColumn(feature, (ecommerceDF[feature] - average[feature]) / ecommerceDF[feature].StdDev());
}
double[][] sampleSet = BuildJaggedArray(
normalizedDf.Columns[features].ToArray2D <double>(),
normalizedDf.RowCount,
features.Length
);
// Create a new K-Means algorithm with n clusters
Accord.Math.Random.Generator.Seed = 0;
int[] numClusters = new int[] { 4, 5, 6, 7, 8 };
List <string> clusterNames = new List <string>();
List <double> silhouetteScores = new List <double>();
for (int i = 0; i < numClusters.Length; i++)
{
KMeans kmeans = new KMeans(numClusters[i]);
KMeansClusterCollection clusters = kmeans.Learn(sampleSet);
int[] labels = clusters.Decide(sampleSet);
string colname = String.Format("Cluster-{0}", numClusters[i]);
clusterNames.Add(colname);
normalizedDf.AddColumn(colname, labels);
ecommerceDF.AddColumn(colname, labels);
Console.WriteLine("\n\n\n##################### {0} ###########################", colname);
Console.WriteLine("\n\n* Centroids for {0} clusters:", numClusters[i]);
PrintCentroidsInfo(clusters.Centroids, features);
Console.WriteLine("\n");
VisualizeClusters(normalizedDf, colname, "NetRevenuePercentile", "AvgUnitPricePercentile");
VisualizeClusters(normalizedDf, colname, "AvgUnitPricePercentile", "AvgQuantityPercentile");
VisualizeClusters(normalizedDf, colname, "NetRevenuePercentile", "AvgQuantityPercentile");
for (int j = 0; j < numClusters[i]; j++)
{
GetTopNItemsPerCluster(ecommerceDF, j, colname);
}
double silhouetteScore = CalculateSilhouetteScore(normalizedDf, features, numClusters[i], colname);
Console.WriteLine("\n\n* Silhouette Score: {0}", silhouetteScore.ToString("0.0000"));
silhouetteScores.Add(silhouetteScore);
Console.WriteLine("\n\n##############################################################\n\n\n");
}
for (int i = 0; i < clusterNames.Count; i++)
{
Console.WriteLine("- Silhouette Score for {0}: {1}", clusterNames[i], silhouetteScores[i].ToString("0.0000"));
}
Console.WriteLine("\n\n\nDONE!!");
Console.ReadKey();
}