mlpack  2.2.5
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Pages
Public Member Functions | List of all members
MaxVarianceNewCluster Class Reference

When an empty cluster is detected, this class takes the point furthest from the centroid of the cluster with maximum variance as a new cluster. More...

Public Member Functions

 MaxVarianceNewCluster ()
 Default constructor required by EmptyClusterPolicy. More...
 
template<typename MetricType , typename MatType >
size_t EmptyCluster (const MatType &data, const size_t emptyCluster, const arma::mat &oldCentroids, arma::mat &newCentroids, arma::Col< size_t > &clusterCounts, MetricType &metric, const size_t iteration)
 Take the point furthest from the centroid of the cluster with maximum variance to be a new cluster. More...
 
template<typename Archive >
void Serialize (Archive &ar, const unsigned int version)
 Serialize the object. More...
 

Detailed Description

When an empty cluster is detected, this class takes the point furthest from the centroid of the cluster with maximum variance as a new cluster.

Definition at line 26 of file max_variance_new_cluster.hpp.

Constructor & Destructor Documentation

Default constructor required by EmptyClusterPolicy.

Definition at line 30 of file max_variance_new_cluster.hpp.

Member Function Documentation

size_t EmptyCluster ( const MatType &  data,
const size_t  emptyCluster,
const arma::mat &  oldCentroids,
arma::mat &  newCentroids,
arma::Col< size_t > &  clusterCounts,
MetricType &  metric,
const size_t  iteration 
)

Take the point furthest from the centroid of the cluster with maximum variance to be a new cluster.

Template Parameters
MatTypeType of data (arma::mat or arma::sp_mat).
Parameters
dataDataset on which clustering is being performed.
emptyClusterIndex of cluster which is empty.
oldCentroidsCentroids of each cluster (one per column), at the start of the iteration.
newCentroidsCentroids of each cluster (one per column), at the end of the iteration. This will be modified!
clusterCountsNumber of points in each cluster.
assignmentsCluster assignments of each point.
Returns
Number of points changed.
void Serialize ( Archive &  ar,
const unsigned int  version 
)

Serialize the object.


The documentation for this class was generated from the following file: