edu.cmu.minorthird.classify
Interface Dataset

All Superinterfaces:

Visible

All Known Implementing Classes:

BasicDataset, CoreRelationalDataset, MultiDataset, RandomAccessDataset, RealRelationalDataset, SegmentDataset, SemiSupervisedDataset, SequenceDataset

public interface Dataset
extends Visible

A set of examples for learning.

Author:

William Cohen

Nested Class Summary

static interface

Dataset.Split A partitioning of the dataset into a number of train/test partitions

Method Summary

void	add(Example example) Add a new example to the dataset.
void	add(Example example, boolean compress) Add a new example to the dataset.
FeatureFactory	getFeatureFactory() Get the FeatureFactory associated with the dataset
ExampleSchema	getSchema() Get the schema associated with the dataset
java.util.Iterator<Example>	iterator() Return an iterator over all examples.
Dataset	shallowCopy() Make a shallow copy of the dataset.
void	shuffle() Randomly re-order the examples.
void	shuffle(java.util.Random r) Randomly re-order the examples.
int	size() Return the number of examples.
Dataset.Split	split(Splitter<Example> splitter) Partition the dataset as required by the splitter.

Methods inherited from interface edu.cmu.minorthird.util.gui.Visible

toGUI

Method Detail

getFeatureFactory

FeatureFactory getFeatureFactory()

Get the FeatureFactory associated with the dataset

getSchema

ExampleSchema getSchema()

Get the schema associated with the dataset

add

void add(Example example)

Add a new example to the dataset.

add

void add(Example example,
         boolean compress)

Add a new example to the dataset. Specifying whether or not to compress it.

iterator

java.util.Iterator<Example> iterator()

Return an iterator over all examples. This iterator must always return examples in the order in which they were added, unless the data has been shuffled.

size

int size()

Return the number of examples.

shuffle

void shuffle(java.util.Random r)

Randomly re-order the examples.

shuffle

void shuffle()

Randomly re-order the examples.

shallowCopy

Dataset shallowCopy()

Make a shallow copy of the dataset. Examples are shared, but not the ordering of the examples.

split

Dataset.Split split(Splitter<Example> splitter)

Partition the dataset as required by the splitter.