You are here:
Start »
AVL.NET »
AVL.KMeansClustering Method
AVL.KMeansClustering Method
Clusters data using KMeans algorithm.
| Namespace: | AvlNet |
|---|
| Assembly: | AVL.NET.dll |
|---|
Syntax
public static void KMeansClustering(
float[][] inData,
int inClusters,
int inMaxIterations,
int inSeed,
float inTerminationFactor,
AvlNet.KMeansClusteringMethod inClusteringMethod,
out AvlNet.Matrix outCentroids,
out int[] outPointToClusterAssignment,
out float outDistanceSum
)
Parameters
|
Name |
Type |
Range |
Default |
Description |
 | inData | float | | | Data set, array of examples. |
| inClusters | int | <2, +INF> | 2 | Number of clusters to extract. Default value: 2. |
| inMaxIterations | int | <10, 1000> | 200 | Maximal number of procedure iterations. Default value: 200. |
| inSeed | int | <0, INF> | 5489 | Seed to init random engine. Default value: 5489. |
| inTerminationFactor | float | <1.0f, 2.0f> | 1.5f | Additional factor of procedure stop. Default value: 1.5f. |
| inClusteringMethod | AvlNet.KMeansClusteringMethod | | KMeansPlusPlus | KMeans variant to use. Default value: KMeansPlusPlus. |
 | outCentroids | AvlNet.Matrix | | | Resulting centroid points in feature space. |
| outPointToClusterAssignment | int | | | Array of input point assignments to generated clusters. |
| outDistanceSum | float | | | Sum of squared distances from points to its respective cluster centroids. |
Errors
| Error type |
Description |
| DomainError |
Empty dataset on input in KMeansClustering. |
| DomainError |
Cannot make more clusters than there is data in input dataset. |
| DomainError |
Inconsistent number of data coordinates in input dataset in KMeansClustering. |
See also
