Class DatasetSplitter

Utility class for creating training / test / cross validation indexes from the original index.

Inheritance

System.Object

DatasetSplitter

Inherited Members

System.Object.Equals(System.Object)

System.Object.Equals(System.Object, System.Object)

System.Object.GetHashCode()

System.Object.GetType()

System.Object.MemberwiseClone()

System.Object.ReferenceEquals(System.Object, System.Object)

System.Object.ToString()

Namespace: Lucene.Net.Classification.Utils

Assembly: Lucene.Net.Classification.dll

Syntax

public class DatasetSplitter

Constructors

DatasetSplitter(Double, Double)

Create a DatasetSplitter by giving test and cross validation IDXs sizes

Declaration

public DatasetSplitter(double testRatio, double crossValidationRatio)

Parameters

Type	Name	Description
System.Double	testRatio	the ratio of the original index to be used for the test IDX as a System.Double between 0.0 and 1.0
System.Double	crossValidationRatio	the ratio of the original index to be used for the c.v. IDX as a System.Double between 0.0 and 1.0

Methods

Split(AtomicReader, Directory, Directory, Directory, Analyzer, String[])

Split a given index into 3 indexes for training, test and cross validation tasks respectively

Declaration

public virtual void Split(AtomicReader originalIndex, Directory trainingIndex, Directory testIndex, Directory crossValidationIndex, Analyzer analyzer, params string[] fieldNames)

Parameters

Type	Name	Description
AtomicReader	originalIndex	an AtomicReader on the source index
Directory	trainingIndex	a Directory used to write the training index
Directory	testIndex	a Directory used to write the test index
Directory	crossValidationIndex	a Directory used to write the cross validation index
Analyzer	analyzer	Analyzer used to create the new docs
System.String[]	fieldNames	names of fields that need to be put in the new indexes or null if all should be used

Exceptions

Type	Condition
System.IO.IOException	if any writing operation fails on any of the indexes