jsat.datatransform

Interface DataTransform

All Superinterfaces:

Cloneable, Serializable

All Known Subinterfaces:

InPlaceInvertibleTransform, InPlaceTransform, InvertibleTransform

All Known Implementing Classes:

AutoDeskewTransform, BDS, DataTransformBase, DataTransformProcess, DenseSparceTransform, FastICA, Imputer, InsertMissingValuesTransform, InverseOfTransform, JLTransform, KernelPCA, LinearTransform, LRS, MutualInfoFS, NominalToNumeric, NumericalToHistogram, Nystrom, PCA, PNormNormalization, PolynomialTransform, RBFNet, ReliefF, RemoveAttributeTransform, RFF_RBF, SBS, SFS, StandardizeTransform, UnitVarianceTransform, WhitenedPCA, WhitenedZCA, ZeroMeanTransform

public interface DataTransform
extends Cloneable, Serializable

A pre-processing step may be desirable before training. If a pre-processing step is used, it is necessary to also apply the same transform on the input being sent to the learning algorithm. This interface provides the needed mechanism.
A transform may or may not require training, it could be fully specified at construction, or learned from the data set. Learning is done via the fit method. Many DataTransforms will include a constructor that takes a dataset as a parameter. These transforms will fit the data when constructed, and exist for convenience.

Author:

Edward Raff

Method Summary

Modifier and Type	Method and Description
DataTransform	clone()
void	fit(DataSet data) Fits this transform to the given dataset.
DataPoint	transform(DataPoint dp) Returns a new data point that is a transformation of the original data point.

Method Detail

transform

DataPoint transform(DataPoint dp)

Returns a new data point that is a transformation of the original data point. This new data point is a different object, but may contain the same references as the original data point. It is not guaranteed that you can mutate the transformed point without having a side effect on the original point.

Parameters:

dp - the data point to apply a transformation to

Returns:

a transformed data point

fit

void fit(DataSet data)

Fits this transform to the given dataset. Some transforms can only be learned from classification or regression datasets. If an incompatible dataset type is given, a FailedToFitException exception may be thrown.

Parameters:

data - the dataset to fir this transform to

Throws:

FailedToFitException - if the dataset type is not compatible with the transform

clone

DataTransform clone()