private int GetNearestCluster(GenericVector v)
{
var cluster = Centroids
.OrderBy(Cluster => GenericVector.Distance(Cluster.Value, v))
.Select(pair => pair.Key)
.FirstOrDefault();
return(cluster);
}
public GenericVector Sum(GenericVector vectorToSum)
{
if (Size != vectorToSum.Size)
{
throw new Exception("GenericVector size of vectorToSum not equal to instance vector size");
}
for (var i = 0; i < Points.Count; i++)
{
Points[i] += vectorToSum.Points[i];
}
return(this);
}
public static void Main(string[] args)
{
var dataSet = new Dictionary <int, GenericVector>();
var parsedData = File
.ReadAllLines("data.csv")
.Select(line => line
.Split(',')
.Select(float.Parse)
.ToList()
)
.ToList();
for (var i = 0; i < parsedData.Count(); i++)
{
for (var j = 0; j < parsedData[i].Count; j++)
{
if (!dataSet.ContainsKey(j))
{
dataSet[j] = new GenericVector();
}
dataSet[j].Add(parsedData[i][j]);
}
}
var kmeans = new kmeans
{
Clusters = 4,
DataSet = dataSet.Values.ToList(),
Iterations = 100
};
kmeans.Run();
kmeans.PrintClusters();
Console.WriteLine(kmeans.SquaredErrors());
}
public double SquaredErrors()
{
return(DataSet
.Select(x => Math.Pow(GenericVector.Distance(x, Centroids[x.Cluster]), 2))
.Sum());
}
public static double Distance(GenericVector a, GenericVector b)
{
var aMinusBpoints = a.Points.Select((t, i) => t - b.Points[i]).ToList();
return(Math.Sqrt(aMinusBpoints.Sum(item => Math.Pow(item, 2))));
}
public bool IsBiggerAs(GenericVector v)
{
return(Points.Where((p, i) => p > v.Points[i]).Count() > Points.Count);
}
