org.encog.ml.data.market

Class MarketMLDataSet

java.lang.Object

org.encog.ml.data.basic.BasicMLDataSet

org.encog.neural.data.basic.BasicNeuralDataSet

org.encog.ml.data.temporal.TemporalMLDataSet

org.encog.ml.data.market.MarketMLDataSet

All Implemented Interfaces:

Serializable, Iterable<MLDataPair>, MLDataSet, NeuralDataSet

public class MarketMLDataSet
extends TemporalMLDataSet

A data set that is designed to hold market data. This class is based on the TemporalNeuralDataSet. This class is designed to load financial data from external sources. This class is designed to track financial data across days. However, it should be usable with other levels of granularity as well.

Author:

jheaton

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class org.encog.ml.data.basic.BasicMLDataSet

BasicMLDataSet.BasicMLIterator

Field Summary

Fields inherited from class org.encog.ml.data.temporal.TemporalMLDataSet

ADD_NOT_SUPPORTED

Constructor Summary

Constructors

Constructor and Description
MarketMLDataSet(MarketLoader loader, int inputWindowSize, int predictWindowSize) Construct a market data set object.

Method Summary

Methods

Modifier and Type	Method and Description
void	addDescription(TemporalDataDescription desc) Add one description of the type of market data that we are seeking at each datapoint.
TemporalPoint	createPoint(Date when) Create a datapoint at the specified date.
NeuralData	generateInputForPrediction(Date date) To be implemented later.
MarketLoader	getLoader()
void	load(Date begin, Date end) Load data from the loader.

Methods inherited from class org.encog.ml.data.temporal.TemporalMLDataSet

add, add, add, calculateActualSetSize, calculateNeuronCounts, calculatePointsInRange, calculateStartIndex, clear, createPoint, generate, generateInputNeuralData, generateOutputNeuralData, getDescriptions, getDesiredSetSize, getHighSequence, getInputNeuronCount, getInputWindowSize, getLowSequence, getOutputNeuronCount, getPoints, getPredictWindowSize, getSequenceFromDate, getSequenceGrandularity, getStartingPoint, isPointInRange, setDesiredSetSize, setHighSequence, setInputWindowSize, setLowSequence, setPredictWindowSize, setSequenceGrandularity, setStartingPoint, sortPoints

Methods inherited from class org.encog.ml.data.basic.BasicMLDataSet

clone, close, get, getData, getIdealSize, getInputSize, getRecord, getRecordCount, isSupervised, iterator, openAdditional, setData, size, toList

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.encog.ml.data.MLDataSet

close, get, getIdealSize, getInputSize, getRecord, getRecordCount, isSupervised, openAdditional, size

Methods inherited from interface java.lang.Iterable

iterator

Constructor Detail

MarketMLDataSet

public MarketMLDataSet(MarketLoader loader,
               int inputWindowSize,
               int predictWindowSize)

Construct a market data set object.

Parameters:

loader - The loader to use to get the financial data.

inputWindowSize - The input window size, that is how many datapoints do we use to predict.

predictWindowSize - How many datapoints do we want to predict.

Method Detail

addDescription

public void addDescription(TemporalDataDescription desc)

Add one description of the type of market data that we are seeking at each datapoint.

Overrides:

addDescription in class TemporalMLDataSet

Parameters:

desc - The data description.

createPoint

public TemporalPoint createPoint(Date when)

Create a datapoint at the specified date.

Overrides:

createPoint in class TemporalMLDataSet

Parameters:

when - The date to create the point at.

Returns:

Returns the TemporalPoint created for the specified date.

generateInputForPrediction

public NeuralData generateInputForPrediction(Date date)

To be implemented later.

Parameters:

date - NOT USED

Returns:

NOT USED

getLoader

public MarketLoader getLoader()

Returns:

The loader that is being used for this set.

load

public void load(Date begin,
        Date end)

Load data from the loader.

Parameters:

begin - The beginning date.

end - The ending date.