public void sparse_features_medium()
{
// Cluster generator settings
var maxRadius = 100;
var minRadius = 10;
var clusterCount = 10;
// Data size
var featureDim = 100;
var obsCount = 2000;
var inputFeaturesTypes = new InputFeatureTypes[featureDim];
for (var i = 0; i < featureDim; i++)
{
inputFeaturesTypes[i] = InputFeatureTypes.Ordinal;
}
var sparseOrdinalSet = new InstanceRepresentation(
inputFeaturesTypes,
sparse: true);
var clusterGenerator = new SyntheticDataGenerator(maxRadius, minRadius, obsCount, clusterCount, featureDim);
var trueClusterLabels = new List <int>();
using (var obsGetter = clusterGenerator.GenerateClusterObservations().GetEnumerator())
{
var isNextObservation = obsGetter.MoveNext();
while (isNextObservation)
{
var cluster = obsGetter.Current.Item1;
var obs = obsGetter.Current.Item2;
trueClusterLabels.Add(cluster);
sparseOrdinalSet.AddInstance(obs);
isNextObservation = obsGetter.MoveNext();
}
}
var clustering = new MiniBatchClustering(clusterCount, 100, 2000);
clustering.Train(sparseOrdinalSet);
var categories = clustering.Cluster(sparseOrdinalSet);
var metricsGenerator = new MetricsGenerator();
metricsGenerator.Add(Metrics.Purity);
for (var i = 0; i < categories.Length; i++)
{
metricsGenerator.AddResult(categories[i], trueClusterLabels[i]);
metricsGenerator.UpdateMetrics();
}
var purity = metricsGenerator.GetMetric(Metrics.Purity);
Assert.True(purity + Epsilon - 0.6 > 0);
}
public void place_clusters()
{
var maxRadius = 100;
var minRadius = 10;
var clusterCount = 10;
var featureDim = 20;
var obsCount = 1000;
var clusterGenerator = new SyntheticDataGenerator(maxRadius, minRadius, obsCount, clusterCount, featureDim);
//using (var textWriter = new StreamWriter(path + csvFileName))
using (var obsGetter = clusterGenerator.GenerateClusterObservations().GetEnumerator())
{
var isNextObservation = obsGetter.MoveNext();
while (isNextObservation)
{
var obs = obsGetter.Current.Item2;
//textWriter.WriteLine(string.Join(',', obs));
isNextObservation = obsGetter.MoveNext();
}
}
}
public void Load(SyntheticDataGenerator dataGenerator)
{
dataGenerator.LoadSequence(this, clipID.ToString(), datasetName);
}