C# 클래스 KdKeys.DataMining.Clustering.KMeans.KMeansParallel

This class implement a KMeans clustering algorithm
파일 보기 프로젝트 열기: spatial-computing/strabo-learning-ocr-transformation 1 사용 예제들

공개 메소드들

메소드 설명
ClusterDataSet ( ClusterCollection clusters, double data ) : ClusterCollection

Seperates a dataset into clusters or groups with similar characteristics

ClusterDataSet ( int clusterCount, double data ) : ClusterCollection

Seperates a dataset into clusters or groups with similar characteristics

ClusterDataSetRandomSeeding ( int k, double data ) : ClusterCollection

Seperates a dataset into clusters or groups with similar characteristics

ClusterMean ( double cluster ) : double[]

Calculates The Mean Of A Cluster OR The Cluster Center

ClusterPartialDataSet ( ClusterCollection clusters, double data, int start, int count ) : int[]
EuclideanDistance ( double X, double Y ) : double

Calculates the Euclidean Distance Measure between two data points

KMeansParallel ( ) : System
ManhattanDistance ( double X, double Y ) : double

Calculates the Manhattan Distance Measure between two data points

RandomSeeding ( int k, double data ) : ClusterCollection
Serialize ( System myObject, string writeToXmlPath ) : bool

Saves or Serializes a Cluster Collection To an Xml file

메소드 상세

ClusterDataSet() 공개 메소드

Seperates a dataset into clusters or groups with similar characteristics
public ClusterDataSet ( ClusterCollection clusters, double data ) : ClusterCollection
clusters ClusterCollection A collection of data clusters
data double An array containing data to b eclustered
리턴 ClusterCollection

ClusterDataSet() 공개 메소드

Seperates a dataset into clusters or groups with similar characteristics
public ClusterDataSet ( int clusterCount, double data ) : ClusterCollection
clusterCount int The number of clusters or groups to form
data double An array containing data that will be clustered
리턴 ClusterCollection

ClusterDataSetRandomSeeding() 공개 메소드

Seperates a dataset into clusters or groups with similar characteristics
public ClusterDataSetRandomSeeding ( int k, double data ) : ClusterCollection
k int
data double An array containing data that will be clustered
리턴 ClusterCollection

ClusterMean() 공개 메소드

Calculates The Mean Of A Cluster OR The Cluster Center
public ClusterMean ( double cluster ) : double[]
cluster double /// A two-dimensional array containing a dataset of numeric values ///
리턴 double[]

ClusterPartialDataSet() 공개 메소드

public ClusterPartialDataSet ( ClusterCollection clusters, double data, int start, int count ) : int[]
clusters ClusterCollection
data double
start int
count int
리턴 int[]

EuclideanDistance() 공개 메소드

Calculates the Euclidean Distance Measure between two data points
public EuclideanDistance ( double X, double Y ) : double
X double An array with the values of an object or datapoint
Y double An array with the values of an object or datapoint
리턴 double

KMeansParallel() 공개 메소드

public KMeansParallel ( ) : System
리턴 System

ManhattanDistance() 공개 메소드

Calculates the Manhattan Distance Measure between two data points
public ManhattanDistance ( double X, double Y ) : double
X double An array with the values of an object or datapoint
Y double An array with the values of an object or datapoint
리턴 double

RandomSeeding() 공개 메소드

public RandomSeeding ( int k, double data ) : ClusterCollection
k int
data double
리턴 ClusterCollection

Serialize() 공개 정적인 메소드

Saves or Serializes a Cluster Collection To an Xml file
public static Serialize ( System myObject, string writeToXmlPath ) : bool
myObject System A serializable object to be persisted to an Xml file
writeToXmlPath string The location of the Xml file tha will contain serialized data
리턴 bool