public void TestRestrictiveBoxMethod(string path, DistanceMetric dist, bool useBoxMethod)
{
var features = ReadFeatures(path);
var clusterer = new UMCAverageLinkageClusterer <UMCLight, UMCClusterLight>
{
ShouldTestClustersWithinTolerance = useBoxMethod,
Parameters =
{
CentroidRepresentation = ClusterCentroidRepresentation.Mean,
DistanceFunction = DistanceFactory <UMCLight> .CreateDistanceFunction(dist),
OnlyClusterSameChargeStates = true,
Tolerances =
{
Mass = 10,
DriftTime = .3,
Net = .03
}
}
};
var clusters = clusterer.Cluster(features);
var i = 0;
clusters.ForEach(x => x.Id = i++);
WriteClusters(clusters);
}
public void TestDistanceDistributions(string path, DistanceMetric dist)
{
var features = ReadFeatures(path);
var clusterer = new UMCAverageLinkageClusterer <UMCLight, UMCClusterLight>
{
ShouldTestClustersWithinTolerance = false,
Parameters =
{
CentroidRepresentation = ClusterCentroidRepresentation.Mean,
DistanceFunction = DistanceFactory <UMCLight> .CreateDistanceFunction(dist),
OnlyClusterSameChargeStates = true,
Tolerances =
{
Mass = 10,
DriftTime = .3,
Net = .03
}
}
};
var clusters = clusterer.Cluster(features);
var distances = new List <double>();
foreach (var cluster in clusters)
{
var centroid = new UMCLight();
centroid.MassMonoisotopicAligned = cluster.MassMonoisotopic;
centroid.Net = cluster.Net;
centroid.DriftTime = cluster.DriftTime;
var func = clusterer.Parameters.DistanceFunction;
foreach (var feature in cluster.Features)
{
var distance = func(feature, centroid);
distances.Add(distance);
}
distances.Sort();
var sum = 0;
foreach (var distance in distances)
{
sum++;
Console.WriteLine("{0},{1}", distance, sum);
}
}
}
//[TestCase(@"ClusterData\clusterData-merged-nodelin.txt")]
public void TestWeightedAverageLinkage(string path)
{
Console.WriteLine("Test: " + path);
var features = GetClusterData(Path.Combine(TestPaths.TestFilesDirectory, path));
Assert.IsNotEmpty(features);
var cluster = new UMCClusterLight();
cluster.Id = features[0].Id;
features.ForEach(x => cluster.AddChildFeature(x));
var maps = new Dictionary <int, UMCClusterLight>();
var average = new UMCAverageLinkageClusterer <UMCLight, UMCClusterLight>();
average.Parameters = new FeatureClusterParameters <UMCLight>();
average.Parameters.CentroidRepresentation = ClusterCentroidRepresentation.Mean;
average.Parameters.Tolerances = new Algorithms.FeatureTolerances();
var distance = new WeightedEuclideanDistance <UMCLight>();
average.Parameters.DistanceFunction = distance.EuclideanDistance;
var clusters = average.Cluster(features);
Console.WriteLine("dataset\tfeature\tmass\tnet\tdrift");
foreach (var newCluster in clusters)
{
foreach (var feature in newCluster.Features)
{
Console.WriteLine("{0},{1},{2},{3},{4}", feature.GroupId,
feature.Id,
feature.Net,
feature.MassMonoisotopicAligned,
feature.DriftTime);
}
}
}
//[TestCase(@"ClusterData\clusterData-single-1500.txt")]
public void TestAverageLinkage(string path)
{
Console.WriteLine("Average Linkage Test: " + path);
var features = GetClusterData(Path.Combine(TestPaths.TestFilesDirectory, path));
Assert.IsNotEmpty(features);
var cluster = new UMCClusterLight();
cluster.Id = features[0].Id;
features.ForEach(x => cluster.AddChildFeature(x));
var maps = new Dictionary <int, UMCClusterLight>();
var average = new UMCAverageLinkageClusterer <UMCLight, UMCClusterLight>();
average.Parameters = new FeatureClusterParameters <UMCLight>();
average.Parameters.CentroidRepresentation = ClusterCentroidRepresentation.Median;
average.Parameters.Tolerances = new Algorithms.FeatureTolerances();
average.Parameters.Tolerances.Net = .02;
average.Parameters.Tolerances.Mass = 6;
average.Parameters.Tolerances.DriftTime = .3;
var distance = new WeightedEuclideanDistance <UMCLight>();
average.Parameters.DistanceFunction = distance.EuclideanDistance;
var euclid = new EuclideanDistanceMetric <UMCLight>();
average.Parameters.DistanceFunction = euclid.EuclideanDistance;
var clusters = average.Cluster(features);
Console.WriteLine("Clusters = {0}", clusters.Count);
var id = 1;
foreach (var testCluster in clusters)
{
testCluster.CalculateStatistics(ClusterCentroidRepresentation.Mean);
var distances = new List <double>();
// Show a sampling of 5 results
var threshold = (int)(testCluster.Features.Count / (double)5);
if (threshold < 1)
{
threshold = 1;
}
testCluster.Id = id++;
var featureID = 0;
foreach (var feature in testCluster.Features)
{
featureID++;
if (featureID % threshold == 0)
{
Console.WriteLine("{0},{1},{2},{3}",
feature.Net,
feature.MassMonoisotopicAligned,
feature.DriftTime,
testCluster.Id);
}
var newDistance = distance.EuclideanDistance(feature, testCluster);
distances.Add(newDistance);
}
//Console.WriteLine();
//Console.WriteLine("Distances");
//distances.ForEach(x => Console.WriteLine(x));
//Console.WriteLine();
}
}
public void TestRestrictiveBoxMethod(string path, DistanceMetric dist, bool useBoxMethod)
{
var features = ReadFeatures(path);
var clusterer = new UMCAverageLinkageClusterer<UMCLight, UMCClusterLight>
{
ShouldTestClustersWithinTolerance = useBoxMethod,
Parameters =
{
CentroidRepresentation = ClusterCentroidRepresentation.Mean,
DistanceFunction = DistanceFactory<UMCLight>.CreateDistanceFunction(dist),
OnlyClusterSameChargeStates = true,
Tolerances =
{
Mass = 10,
DriftTime = .3,
Net = .03
}
}
};
var clusters = clusterer.Cluster(features);
var i = 0;
clusters.ForEach(x => x.Id = i++);
WriteClusters(clusters);
}
public void TestDistanceDistributions(string path, DistanceMetric dist)
{
var features = ReadFeatures(path);
var clusterer = new UMCAverageLinkageClusterer<UMCLight, UMCClusterLight>
{
ShouldTestClustersWithinTolerance = false,
Parameters =
{
CentroidRepresentation = ClusterCentroidRepresentation.Mean,
DistanceFunction = DistanceFactory<UMCLight>.CreateDistanceFunction(dist),
OnlyClusterSameChargeStates = true,
Tolerances =
{
Mass = 10,
DriftTime = .3,
Net = .03
}
}
};
var clusters = clusterer.Cluster(features);
var distances = new List<double>();
foreach (var cluster in clusters)
{
var centroid = new UMCLight();
centroid.MassMonoisotopicAligned = cluster.MassMonoisotopic;
centroid.Net = cluster.Net;
centroid.DriftTime = cluster.DriftTime;
var func = clusterer.Parameters.DistanceFunction;
foreach (var feature in cluster.Features)
{
var distance = func(feature, centroid);
distances.Add(distance);
}
distances.Sort();
var sum = 0;
foreach (var distance in distances)
{
sum++;
Console.WriteLine("{0},{1}", distance, sum);
}
}
}
