GridSearchParameterLearner

java.lang.Object
- net.sf.tweety.machinelearning.ParameterTrainer<S,T>
- - net.sf.tweety.machinelearning.GridSearchParameterLearner<S,T>

Type Parameters:

S - the type of observations.

T - the type of categories.

All Implemented Interfaces:

Trainer<S,T>
```
public class GridSearchParameterLearner<S extends Observation,T extends Category>
extends ParameterTrainer<S,T>
```
A grid-search approach for learning parameters. For each parameter with I=[l,u] being the boundaries for the parameter value of a given trainer, I is divided into partitions number of partitions. For each partition of each parameter the border points are chosen and a new classifier is learned with given parameter combination. From all combinations the combination where the classifier performs best is chosen. If depth > 1, the process is iterated: after selecting the best interval combination of the parameters, these intervals are again divided and the process is repeated depth many times.

Author:

Matthias Thimm

Constructor Summary

Constructors
Constructor	Description
`GridSearchParameterLearner(Trainer<S,T> trainer, ClassificationTester<S,T> tester, int depth, int partitions)`	Creates a new grid-search parameter learner with the given arguments.

Method Summary

Modifier and Type Method Description

ParameterSet learnParameters(TrainingSet<S,T> trainingSet)
Learns the best parameters of the given trainer for the training set.
- Methods inherited from class net.sf.tweety.machinelearning.ParameterTrainer
  getParameterSet, setParameterSet, train, train
- Methods inherited from class java.lang.Object
  equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Constructor Detail
  - GridSearchParameterLearner
```
public GridSearchParameterLearner(Trainer<S,T> trainer,
                                  ClassificationTester<S,T> tester,
                                  int depth,
                                  int partitions)
```
    Creates a new grid-search parameter learner with the given arguments.
    
    Parameters:
    
    trainer - some trainer.
    
    tester - some classification tester for measuring performance.
    
    depth - the depth of the recursion.
    
    partitions - the number of partitions.
- Method Detail
  - learnParameters
```
public ParameterSet learnParameters(TrainingSet<S,T> trainingSet)
```
    Description copied from class: ParameterTrainer
    
    Learns the best parameters of the given trainer for the training set.
    
    Specified by:
    
    learnParameters in class ParameterTrainer<S extends Observation,T extends Category>
    
    Parameters:
    
    trainingSet - a training set
    
    Returns:
    
    the best parameters for the training set.