Package adams.ml.model

Interface Algorithm<T extends Model>

Type Parameters:

T - the type of model to generate

All Superinterfaces:

CapabilitiesHandler, Destroyable, OptionHandler

All Known Subinterfaces:

Classifier, Clusterer, IncrementalAlgorithm<T>, IncrementalClassifier, IncrementalClusterer, IncrementalMultiTargetClassifier, IncrementalMultiTargetRegressor, IncrementalRegressor, MultiTargetClassifier, MultiTargetRegressor, Regressor

All Known Implementing Classes:

AbstractClassifier, AbstractClusterer, AbstractMultiTargetClassifier, AbstractMultiTargetRegressor, AbstractRegressor, WekaClassifier, WekaClusterer, WekaRegressor

public interface Algorithm<T extends Model>
extends CapabilitiesHandler, OptionHandler

Interface for machine learning algorithms.

Version:

$Revision$

Author:

FracPete (fracpete at waikato dot ac dot nz)

Method Summary

Modifier and Type	Method	Description
T	buildModel(Dataset data)	Builds a model from the data.
Capabilities	getCapabilities()	Returns the algorithm's capabilities in terms of data.
String	handles(Dataset data, boolean strict)	Checks whether the data can be handled.

Methods inherited from interface adams.core.Destroyable

destroy

Methods inherited from interface adams.core.option.OptionHandler

cleanUpOptions, defineOptions, getOptionManager, toCommandLine

Method Detail

getCapabilities

Capabilities getCapabilities()

Returns the algorithm's capabilities in terms of data.

Specified by:

getCapabilities in interface CapabilitiesHandler

Returns:

the algorithm's capabilities

handles

String handles(Dataset data,
               boolean strict)

Checks whether the data can be handled.

Parameters:

data - the data to check

strict - whether to perform a strict check

Returns:

null if data can be handled, otherwise error message

buildModel

T buildModel(Dataset data)
      throws Exception

Builds a model from the data.

Parameters:

data - the data to use for building the model

Returns:

the generated model

Throws:

Exception - if the build fails