jsat.parameters

Class GridSearch

java.lang.Object

jsat.parameters.ModelSearch

jsat.parameters.GridSearch

All Implemented Interfaces:

Serializable, Cloneable, Classifier, Regressor

public class GridSearch
extends ModelSearch

GridSearch is a simple method for tuning the parameters of a classification or regression algorithm. It naively tries all possible pairs of parameter values given. For this reason, it works best when only a small number of parameters need to be turned.
The model it takes must implement the Parameterized interface. By default, no parameters are selected for optimizations. This is because parameters value ranges are often algorithm specific. As such, the user must specify the parameters and the values to test using the addParameter methods.

Author:

Edward Raff

See Also:

addParameter(jsat.parameters.DoubleParameter, double[]), addParameter(jsat.parameters.IntParameter, int[]), Serialized Form

Field Summary

Fields inherited from class jsat.parameters.ModelSearch

baseClassifier, baseRegressor, classificationTargetScore, folds, regressionTargetScore, reuseSameCVFolds, searchParams, trainedClassifier, trainedRegressor, trainFinalModel, trainModelsInParallel

Constructor Summary

Constructors

Constructor and Description
GridSearch(Classifier baseClassifier, int folds) Creates a new GridSearch to tune the specified parameters of a classification model.
GridSearch(GridSearch toCopy) Copy constructor
GridSearch(Regressor baseRegressor, int folds) Creates a new GridSearch to tune the specified parameters of a regression model.

Method Summary

Modifier and Type	Method and Description
void	addParameter(DoubleParameter param, double... initialSearchValues) Adds a new double parameter to be altered for the model being tuned.
void	addParameter(IntParameter param, int... initialSearchValues) Adds a new int parameter to be altered for the model being tuned.
void	addParameter(String name, double... initialSearchValues) Adds a new double parameter to be altered for the model being tuned.
void	addParameter(String name, int... initialSearchValues) Adds a new integer parameter to be altered for the model being tuned.
int	autoAddParameters(DataSet data) This method will automatically populate the search space with parameters based on which Parameter objects return non-null distributions.
int	autoAddParameters(DataSet data, int paramsEach) This method will automatically populate the search space with parameters based on which Parameter objects return non-null distributions. Note, using this method with Cross Validation has the potential for over-estimating the accuracy of results if the data set is actually used to for parameter guessing.
GridSearch	clone()
boolean	isUseWarmStarts()
void	setUseWarmStarts(boolean useWarmStarts) Sets whether or not warm starts are used, but only if the model in use supports warm starts.
void	train(RegressionDataSet dataSet)
void	train(RegressionDataSet dataSet, ExecutorService threadPool)
void	trainC(ClassificationDataSet dataSet) Trains the classifier and constructs a model for classification using the given data set.
void	trainC(ClassificationDataSet dataSet, ExecutorService threadPool) Trains the classifier and constructs a model for classification using the given data set.

Methods inherited from class jsat.parameters.ModelSearch

classify, getBaseClassifier, getBaseRegressor, getClassificationTargetScore, getParameterByName, getRegressionTargetScore, getTrainedClassifier, getTrainedRegressor, isReuseSameCVFolds, isTrainFinalModel, isTrainModelsInParallel, regress, setClassificationTargetScore, setRegressionTargetScore, setReuseSameCVFolds, setTrainFinalModel, setTrainModelsInParallel, supportsWeightedData

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

GridSearch

public GridSearch(Regressor baseRegressor,
                  int folds)

Creates a new GridSearch to tune the specified parameters of a regression model. The parameters still need to be specified by calling addParameter(jsat.parameters.DoubleParameter, double[])

Parameters:

baseRegressor - the regressor to tune the parameters of

folds - the number of folds of cross-validation to perform to evaluate each combination of parameters

Throws:

FailedToFitException - if the base regressor does not implement Parameterized

GridSearch

public GridSearch(Classifier baseClassifier,
                  int folds)

Creates a new GridSearch to tune the specified parameters of a classification model. The parameters still need to be specified by calling addParameter(jsat.parameters.DoubleParameter, double[])

Parameters:

baseClassifier - the classifier to tune the parameters of

folds - the number of folds of cross-validation to perform to evaluate each combination of parameters

Throws:

FailedToFitException - if the base classifier does not implement Parameterized

GridSearch

public GridSearch(GridSearch toCopy)

Copy constructor

Parameters:

toCopy - the object to copy

Method Detail

autoAddParameters

public int autoAddParameters(DataSet data)

This method will automatically populate the search space with parameters based on which Parameter objects return non-null distributions. Each parameter will be tested with 10 different values

Note, using this method with Cross Validation has the potential for over-estimating the accuracy of results if the data set is actually used to for parameter guessing.

It is possible for this method to return 0, indicating that no default parameters could be found. The intended interpretation is that there are no parameters that you need to tune to get good performance from the given model. Though there will be cases where the author has simply missed a class.

Parameters:

data - the data set to get parameter estimates from

Returns:

the number of parameters added

autoAddParameters

public int autoAddParameters(DataSet data,
                             int paramsEach)

This method will automatically populate the search space with parameters based on which Parameter objects return non-null distributions.

Note, using this method with Cross Validation has the potential for over-estimating the accuracy of results if the data set is actually used to for parameter guessing.

Parameters:

data - the data set to get parameter estimates from

paramsEach - the number of parameters value to try for each parameter found

Returns:

the number of parameters added

setUseWarmStarts

public void setUseWarmStarts(boolean useWarmStarts)

Sets whether or not warm starts are used, but only if the model in use supports warm starts. This is set to true by default.

Parameters:

useWarmStarts - true if warm starts should be used when possible, false otherwise.

isUseWarmStarts

public boolean isUseWarmStarts()

Returns:

true if warm starts will be used when possible. false if they will not.

addParameter

public void addParameter(DoubleParameter param,
                         double... initialSearchValues)

Adds a new double parameter to be altered for the model being tuned.

Parameters:

param - the model parameter

initialSearchValues - the values to try for the specified parameter

addParameter

public void addParameter(String name,
                         double... initialSearchValues)

Adds a new double parameter to be altered for the model being tuned.

Parameters:

name - the name of the parameter

initialSearchValues - the values to try for the specified parameter

addParameter

public void addParameter(IntParameter param,
                         int... initialSearchValues)

Adds a new int parameter to be altered for the model being tuned.

Parameters:

param - the model parameter

initialSearchValues - the values to try for the specified parameter

addParameter

public void addParameter(String name,
                         int... initialSearchValues)

Adds a new integer parameter to be altered for the model being tuned.

Parameters:

name - the name of the parameter

initialSearchValues - the values to try for the specified parameter

train

public void train(RegressionDataSet dataSet,
                  ExecutorService threadPool)

train

public void train(RegressionDataSet dataSet)

trainC

public void trainC(ClassificationDataSet dataSet,
                   ExecutorService threadPool)

Description copied from interface: Classifier

Trains the classifier and constructs a model for classification using the given data set. If the training method knows how, it will used the threadPool to conduct training in parallel. This method will block until the training has completed.

Parameters:

dataSet - the data set to train on

threadPool - the source of threads to use.

trainC

public void trainC(ClassificationDataSet dataSet)

Description copied from interface: Classifier

Trains the classifier and constructs a model for classification using the given data set.

Parameters:

dataSet - the data set to train on

clone

public GridSearch clone()

Specified by:

clone in interface Classifier

Specified by:

clone in interface Regressor

Specified by:

clone in class ModelSearch