kinetica.AggregateKMeansRequest Class Reference

A set of parameters for Kinetica.aggregateKMeans(string,IList{string},int,double,IDictionary{string, string}). More...

Inheritance diagram for kinetica.AggregateKMeansRequest:

Collaboration diagram for kinetica.AggregateKMeansRequest:

Classes
struct	Options
	Optional parameters. More...

Public Member Functions
	AggregateKMeansRequest ()
	Constructs an AggregateKMeansRequest object with default parameters. More...
	AggregateKMeansRequest (string table_name, IList< string > column_names, int k, double tolerance, IDictionary< string, string > options=null)
	Constructs an AggregateKMeansRequest object with the specified parameters. More...
Public Member Functions inherited from kinetica.KineticaData
	KineticaData (KineticaType type)
	Constructor from Kinetica Type More...
	KineticaData (System.Type type=null)
	Default constructor, with optional System.Type More...
object	Get (int fieldPos)
	Retrieve a specific property from this object More...
void	Put (int fieldPos, object fieldValue)
	Write a specific property to this object More...

Properties
string	table_name [get, set]
	Name of the table on which the operation will be performed. More...
IList< string >	column_names [get, set]
	List of column names on which the operation would be performed. More...
int	k = new List<string>() [get, set]
	The number of mean points to be determined by the algorithm. More...
double	tolerance [get, set]
	Stop iterating when the distances between successive points is less than the given tolerance. More...
IDictionary< string, string >	options [get, set]
	Optional parameters. More...
Properties inherited from kinetica.KineticaData
Schema	Schema [get]
	Avro Schema for this class More...

Additional Inherited Members
Static Public Member Functions inherited from kinetica.KineticaData
static RecordSchema	SchemaFromType (System.Type t, KineticaType ktype=null)
	Create an Avro Schema from a System.Type and a KineticaType. More...

Detailed Description

A set of parameters for Kinetica.aggregateKMeans(string,IList{string},int,double,IDictionary{string, string}).

This endpoint runs the k-means algorithm - a heuristic algorithm that attempts to do k-means clustering. An ideal k-means clustering algorithm selects k points such that the sum of the mean squared distances of each member of the set to the nearest of the k points is minimized. The k-means algorithm however does not necessarily produce such an ideal cluster. It begins with a randomly selected set of k points and then refines the location of the points iteratively and settles to a local minimum. Various parameters and options are provided to control the heuristic search.
NOTE: The Kinetica instance being accessed must be running a CUDA (GPU-based) build to service this request.

Definition at line 30 of file AggregateKMeans.cs.

Constructor & Destructor Documentation

kinetica.AggregateKMeansRequest.AggregateKMeansRequest ( )

inline

Constructs an AggregateKMeansRequest object with default parameters.

Definition at line 122 of file AggregateKMeans.cs.

kinetica.AggregateKMeansRequest.AggregateKMeansRequest ( string  table_name, IList< string >  column_names, int  k, double  tolerance, IDictionary< string, string >  options = null  )

inline

Constructs an AggregateKMeansRequest object with the specified parameters.

Parameters

table_name	Name of the table on which the operation will be performed. Must be an existing table or collection.
column_names	List of column names on which the operation would be performed. If n columns are provided then each of the k result points will have n dimensions corresponding to the n columns.
k	The number of mean points to be determined by the algorithm.
tolerance	Stop iterating when the distances between successive points is less than the given tolerance.
options	Optional parameters. WHITEN: When set to 1 each of the columns is first normalized by its stdv - default is not to whiten. MAX_ITERS: Number of times to try to hit the tolerance limit before giving up - default is 10. NUM_TRIES: Number of times to run the k-means algorithm with a different randomly selected starting points - helps avoid local minimum. Default is 1. The default value is an empty Dictionary.

Definition at line 162 of file AggregateKMeans.cs.

Property Documentation

IList<string> kinetica.AggregateKMeansRequest.column_names

getset

List of column names on which the operation would be performed.

If n columns are provided then each of the k result points will have n dimensions corresponding to the n columns.

Definition at line 84 of file AggregateKMeans.cs.

int kinetica.AggregateKMeansRequest.k = new List<string>()

getset

The number of mean points to be determined by the algorithm.

Definition at line 88 of file AggregateKMeans.cs.

IDictionary<string, string> kinetica.AggregateKMeansRequest.options

getset

Optional parameters.

• WHITEN: When set to 1 each of the columns is first normalized by its stdv - default is not to whiten.
• MAX_ITERS: Number of times to try to hit the tolerance limit before giving up - default is 10.
• NUM_TRIES: Number of times to run the k-means algorithm with a different randomly selected starting points - helps avoid local minimum. Default is 1.

The default value is an empty Dictionary.

Definition at line 117 of file AggregateKMeans.cs.

string kinetica.AggregateKMeansRequest.table_name

getset

Name of the table on which the operation will be performed.

Must be an existing table or collection.

Definition at line 78 of file AggregateKMeans.cs.

double kinetica.AggregateKMeansRequest.tolerance

getset

Stop iterating when the distances between successive points is less than the given tolerance.

Definition at line 92 of file AggregateKMeans.cs.

---

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

• Kinetica/Protocol/AggregateKMeans.cs