public void DistanceMatrixThrowArgumentNullExceptionItShouldOnDistanceMetric()
{
collectionSize = 111;
generatedDataCollection = new GenerateIdentifiableDataPointCollection(collectionSize);
dataCollection = generatedDataCollection.Generate();
Assert.Catch <ArgumentNullException>(() => { new DistanceMatrix(dataCollection, null); });
}
public void KMeansClusteringWorksOnTwoDimensions()
{
var dataSet = new IdentifiableDataPointCollection();
var p1 = new IdentifiableDataPoint(0, 2);
var p2 = new IdentifiableDataPoint(1, 2);
var p3 = new IdentifiableDataPoint(2, 2);
var p4 = new IdentifiableDataPoint(3, 2);
p1.AddAttribute("Gender", 1);
p1.AddAttribute("Income", 1);
p2.AddAttribute("Gender", 0);
p2.AddAttribute("Income", 0.1429);
p3.AddAttribute("Gender", 1);
p3.AddAttribute("Income", 0.2858);
p4.AddAttribute("Gender", 1);
p4.AddAttribute("Income", 1);
dataSet.AddItem(p1);
dataSet.AddItem(p2);
dataSet.AddItem(p3);
dataSet.AddItem(p4);
var kmeans2 = new KMeans(dataSet, new [] { 0, 1, 2 }, new EuclideanMetric());
var result2 = kmeans2.Calculate();
Assert.AreEqual(2, result2.Clusters[0].Members.Count);
Assert.AreEqual(1, result2.Clusters[1].Members.Count);
Assert.AreEqual(1, result2.Clusters[2].Members.Count);
}
public void DistanceMatrixShouldReturnLargerCorrectDistanceMatrix()
{
double difference;
collectionSize = 111;
distanceMetric = new EuclideanMetric();
generatedDataCollection = new GenerateIdentifiableDataPointCollection(collectionSize);
dataCollection = generatedDataCollection.Generate();
distanceMatrix = new DistanceMatrix(dataCollection, distanceMetric);
expectedMatrix = ExpectedMatrix();
for (int row = 0; row < distanceMatrix.Rows; row++)
{
for (int col = 0; col < distanceMatrix.Columns; col++)
{
difference = distanceMatrix[row, col] - expectedMatrix[row, col];
if (!(difference < 0.01 && difference > -0.01 && distanceMatrix[row, col] >= 0))
{
Assert.Fail("{0}, row = {1}, col = {2}", difference, row, col);
}
}
}
}
public void KMeansShouldCalculateCorrectCentroidsInOneDimension()
{
var dataSet = new IdentifiableDataPointCollection();
var p1 = new IdentifiableDataPoint(0, 1);
var p2 = new IdentifiableDataPoint(1, 1);
var p3 = new IdentifiableDataPoint(2, 1);
var p4 = new IdentifiableDataPoint(3, 1);
p1.AddAttribute("Gender", 1);
p2.AddAttribute("Gender", 0);
p3.AddAttribute("Gender", 1);
p4.AddAttribute("Gender", 1);
dataSet.AddItem(p1);
dataSet.AddItem(p2);
dataSet.AddItem(p3);
dataSet.AddItem(p4);
var kmeans2 = new KMeans(dataSet, new [] { 0, 1 }, new EuclideanMetric());
var result2 = kmeans2.Calculate();
double[] centroid1 = { 1 };
double[] centroid2 = { 0 };
Assert.AreEqual(centroid1, result2.Clusters[0].Centroid.Coordinates);
Assert.AreEqual(centroid2, result2.Clusters[1].Centroid.Coordinates);
}
public void KMeansShouldClusterDataPointsInOneDimensionCorrectly()
{
var dataSet = new IdentifiableDataPointCollection();
var p1 = new IdentifiableDataPoint(0, 1);
var p2 = new IdentifiableDataPoint(1, 1);
var p3 = new IdentifiableDataPoint(2, 1);
var p4 = new IdentifiableDataPoint(3, 1);
p1.AddAttribute("Gender", 1);
p2.AddAttribute("Gender", 0);
p3.AddAttribute("Gender", 1);
p4.AddAttribute("Gender", 1);
dataSet.AddItem(p1);
dataSet.AddItem(p2);
dataSet.AddItem(p3);
dataSet.AddItem(p4);
var kmeans2 = new KMeans(dataSet, new [] { 0, 1 }, new EuclideanMetric());
var result2 = kmeans2.Calculate();
var cluster1Members = result2.Clusters[0].Members.Select(e => e.Member).ToArray();
var cluster2Members = result2.Clusters[1].Members.Select(e => e.Member).ToArray();
Assert.AreEqual(3, cluster1Members.Length);
Assert.Contains(p1, cluster1Members);
Assert.Contains(p3, cluster1Members);
Assert.Contains(p4, cluster1Members);
Assert.AreEqual(1, cluster2Members.Length);
Assert.Contains(p2, cluster2Members);
}
public void SetUp()
{
var config = SetupMockConfiguration();
var reader = new StringReader(Resources.SampleData);
var importer = new CsvDataImporter(reader, config);
dataSet = importer.Run();
}
private void DataImportTask_Complete(Task <IdentifiableDataPointCollection> task)
{
ToggleUserInputControls(true);
Result = task.Result;
DataVisualizationForm form = new DataVisualizationForm(Result);
form.Show();
}
public DataVisualizationForm(IdentifiableDataPointCollection dataSet)
: this()
{
this.dataSet = dataSet;
distanceMetric = DistanceMetric(currentDistanceMatrix);
dataConversionTask = new DataConversionTask();
dataConversionTask.Success += DataConversionTask_Success;
dataConversionTask.Failure += DataConversionTask_Failure;
}
static void LocalOutlierFactorD(int kNeighbours, IdentifiableDataPointCollection dataCollection, IDistanceMetric distanceMetric)
{
DistanceMatrix distanceMatrix = new DistanceMatrix(dataCollection, distanceMetric);
var outlierDetection = new LocalOutlierFactor(distanceMatrix, kNeighbours);
var list = outlierDetection.Run();
foreach (var person in list)
{
Console.WriteLine("Person: {0} has the Local Outlier Factor of {1}", person.ID, person.LocalOutlierFactor);
}
}
public void KMeansCentroidsArePlacedRightInFiveDimensions()
{
var dataSet = new IdentifiableDataPointCollection();
var p1 = new IdentifiableDataPoint(0, 5);
var p2 = new IdentifiableDataPoint(1, 5);
var p3 = new IdentifiableDataPoint(2, 5);
var p4 = new IdentifiableDataPoint(3, 5);
p1.AddAttribute("Gender", 1);
p1.AddAttribute("Income", 1);
p1.AddAttribute("Age", 0.16);
p1.AddAttribute("Purchase", 0.5);
p1.AddAttribute("Control", 1);
p2.AddAttribute("Gender", 0);
p2.AddAttribute("Income", 0.1429);
p2.AddAttribute("Age", 0.16);
p2.AddAttribute("Purchase", 1);
p2.AddAttribute("Control", 0);
p3.AddAttribute("Gender", 1);
p3.AddAttribute("Income", 0.2858);
p3.AddAttribute("Age", 0.16);
p3.AddAttribute("Purchase", 1);
p3.AddAttribute("Control", 1);
p4.AddAttribute("Gender", 1);
p4.AddAttribute("Income", 1);
p4.AddAttribute("Age", 0.16);
p4.AddAttribute("Purchase", 1);
p4.AddAttribute("Control", 0.5);
dataSet.AddItem(p1);
dataSet.AddItem(p2);
dataSet.AddItem(p3);
dataSet.AddItem(p4);
var kmeans2 = new KMeans(dataSet, new [] { 0, 1, 2 }, new EuclideanMetric());
var result2 = kmeans2.Calculate();
double[] _centroid1 = { 1, 0.2858, 0.16, 1, 1 };
double[] _centroid2 = { 1, 1, 0.16, 0.75, 0.75 };
double[] _centroid3 = { 0, 0.1429, 0.16, 1, 0 };
Assert.AreEqual(_centroid2, result2.Clusters[0].Centroid.Coordinates);
Assert.AreEqual(_centroid3, result2.Clusters[1].Centroid.Coordinates);
Assert.AreEqual(_centroid1, result2.Clusters[2].Centroid.Coordinates);
}
public IdentifiableDataPointCollection Run()
{
var dataSet = new IdentifiableDataPointCollection();
var csv = new CsvReader(reader);
csv.Configuration.Delimiter = FieldDelimiter;
var idCounter = 0;
while (csv.Read())
{
IdentifiableDataPoint dataPoint = ParseRow(csv, idCounter++);
dataSet.AddItem(dataPoint);
}
return(dataSet);
}
static void MultiDimensionalScaling(StreamWriter writer, IdentifiableDataPointCollection dataCollection, IDistanceMetric distanceMetric)
{
writer.WriteLine("MDS coordinates");
DistanceMatrix distanceMatrix = new DistanceMatrix(dataCollection, distanceMetric);
var mds = new MultiDimensionalScaling(distanceMatrix);
Matrix resultMatrix = mds.Calculate(); //a shitty name
int limiter = 20;
if (limiter > resultMatrix.Columns)
{
limiter = resultMatrix.Columns;
}
char letter = 'A';
//Print file index
writer.Write(" ");
for (int columnIndex = 0; columnIndex < limiter; columnIndex++, letter++)
{
if (letter >= 'z')
{
letter = 'A';
}
writer.Write(" {0} |", letter);
}
writer.WriteLine();
//Print the coordinates
letter = 'X';
for (int rowIndex = 0; rowIndex < 2; rowIndex++)
{
writer.Write(" {0} |", letter++);
for (int columnIndex = 0; columnIndex < limiter; columnIndex++)
{
writer.Write("{0,5:N2}|", resultMatrix[rowIndex, columnIndex]);
}
writer.Write("\r\n");
}
writer.WriteLine("\r\n");
}
public void CentroidsHaveDistinctValues()
{
var dataSet = new IdentifiableDataPointCollection();
var p1 = new IdentifiableDataPoint(0, 2);
var p2 = new IdentifiableDataPoint(1, 2);
var p3 = new IdentifiableDataPoint(2, 2);
p1.AddAttribute("Gender", 1);
p1.AddAttribute("Income", 1);
p2.AddAttribute("Gender", 1);
p2.AddAttribute("Income", 1);
p3.AddAttribute("Gender", 0);
p3.AddAttribute("Income", 0);
dataSet.AddItem(p1);
dataSet.AddItem(p2);
dataSet.AddItem(p3);
Assert.Throws <InvalidOperationException>(() => new KMeans(dataSet, new [] { 0, 1 }, new EuclideanMetric()));
}
public void CalculateWithZeroClusters()
{
var dataSet = new IdentifiableDataPointCollection();
var p1 = new IdentifiableDataPoint(0, 1);
var p2 = new IdentifiableDataPoint(1, 1);
var p3 = new IdentifiableDataPoint(2, 1);
var p4 = new IdentifiableDataPoint(3, 1);
p1.AddAttribute("Gender", 1);
p2.AddAttribute("Gender", 0);
p3.AddAttribute("Gender", 1);
p4.AddAttribute("Gender", 1);
dataSet.AddItem(p1);
dataSet.AddItem(p2);
dataSet.AddItem(p3);
dataSet.AddItem(p4);
Assert.Throws <ArgumentException>(() => new KMeans(dataSet, 0, new EuclideanMetric()));
}
static void DistanceMatrix(StreamWriter writer, IdentifiableDataPointCollection dataCollection, IDistanceMetric distanceMetric)
{
writer.WriteLine("MatrixFull");
DistanceMatrix matrix = new DistanceMatrix(dataCollection, distanceMetric);
int limiter = 20; //For the full, use matrix.Rank;
char letter = 'A';
writer.WriteLine(" | A | B | C | D | E | F | G | H | I | J |");
for (int rowIndex = 0; rowIndex < limiter; rowIndex++)
{
writer.Write(" {0} |", letter++);
for (int columnIndex = 0; columnIndex < limiter; columnIndex++)
{
writer.Write("{0,5:N2}|", matrix[rowIndex, columnIndex]);
}
if (letter >= 'z')
{
letter = 'A';
}
writer.Write("\r\n");
}
writer.Write("\r\n\r\n");
}
