com.sjm.machlearn.dataset
Class DataSet

java.lang.Object
  |
  +--com.sjm.machlearn.util.MainClass
        |
        +--com.sjm.machlearn.dataset.DataSet

public class DataSet

extends MainClass

DataSet.java : class that holds a whole data set of examples together.

Field Summary

protected Example[]	data
protected FeatureIdList	idlist
protected double[]	weights

Fields inherited from class com.sjm.machlearn.util.MainClass

debug, debug_level, debug_listeners

Constructor Summary

DataSet(DataSet ds)

DataSet(Example[] ex)

DataSet(Feature[][] featurematrix)

DataSet(FeatureIdList fid)

DataSet(FeatureIdList idl, Example[] dt)

DataSet(java.lang.String namesfile, java.lang.String datafile)

Method Summary

void	copyWeights(DataSet ds)
void	copyWeights(double[] wgts)
int	countOutput(java.lang.String value)
int[]	createMapping(boolean randomize)
Example	get(int index)
DataSet[]	getBootStrapReplicate()
double	getEntropy()
double	getEntropyWgt()
FeatureId	getFeatureId(int index)
int	getFeatureIndex(FeatureId featureid)
FeatureIdList	getIdList()
int	getMajorityOutputIndex()
int	getMajorityOutputIndexWgt()
int[]	getOutputCounts()
double[]	getOutputCountsWgt()
Feature	getOutputFeature()
Feature	getOutputFeature(int example_index)
FeatureId	getOutputFeatureId()
int	getOutputIndex()
int[]	getOutputValueIds()
double	getTotalWeights()
double	getWeight(int index)
boolean	hasFeature(FeatureId featureid)
void	initializeWeights()
void	merge(DataSet newSet)
void	normalizeWeights()
int	numFeatures()
java.lang.String	printFeatureIdList()
protected void	readData(java.lang.String datafile)
boolean	sameOutputValue()
void	setWeight(int index, double val)
int	size()
DataSet[]	splitDataSet(int numSets, boolean randomize)
DataSet[][]	splitDataSetFolds(int numfolds, boolean randomize) splitDataSetFolds() : splits the dataset into an array of n-folds.
DataSet[]	splitJackKnife(int index)
DataSet[]	splitRandom(double testpercent) splitRandom() : splits the data into two subsets, based upon the testpercent.
void	write(java.lang.String namesfile, java.lang.String datafile)
void	writeData(java.lang.String datafile)
void	writeNames(java.lang.String namesfile)

Methods inherited from class com.sjm.machlearn.util.MainClass

_internalError, _internalError, addDebugListener, debugMesg, debugMesg, debugMesg, debugMesg, debugMesg, debugMesg, debugOff, debugOn, internalError, internalError, setDebug, setDebugLevel

Methods inherited from class java.lang.Object

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

Field Detail

idlist

protected FeatureIdList idlist

data

protected Example[] data

weights

protected double[] weights

Constructor Detail

DataSet

public DataSet(DataSet ds)

DataSet

public DataSet(Example[] ex)

DataSet

public DataSet(FeatureIdList fid)

DataSet

public DataSet(Feature[][] featurematrix)
        throws InvalidFeature,
               NoOutputException,
               MultipleOutputException

DataSet

public DataSet(FeatureIdList idl,
               Example[] dt)

DataSet

public DataSet(java.lang.String namesfile,
               java.lang.String datafile)
        throws java.lang.Exception

Method Detail

copyWeights

public void copyWeights(double[] wgts)

copyWeights

public void copyWeights(DataSet ds)

initializeWeights

public void initializeWeights()

getIdList

public FeatureIdList getIdList()

getFeatureId

public FeatureId getFeatureId(int index)

getOutputValueIds

public int[] getOutputValueIds()

hasFeature

public boolean hasFeature(FeatureId featureid)

getFeatureIndex

public int getFeatureIndex(FeatureId featureid)
                    throws MissingFeatureException

get

public Example get(int index)

getOutputIndex

public int getOutputIndex()

getWeight

public double getWeight(int index)

setWeight

public void setWeight(int index,
                      double val)

getTotalWeights

public double getTotalWeights()

normalizeWeights

public void normalizeWeights()

sameOutputValue

public boolean sameOutputValue()

getMajorityOutputIndex

public int getMajorityOutputIndex()

getMajorityOutputIndexWgt

public int getMajorityOutputIndexWgt()

getOutputFeature

public Feature getOutputFeature()

getOutputFeatureId

public FeatureId getOutputFeatureId()

getOutputFeature

public Feature getOutputFeature(int example_index)

getOutputCounts

public int[] getOutputCounts()

getOutputCountsWgt

public double[] getOutputCountsWgt()

getEntropyWgt

public double getEntropyWgt()

getEntropy

public double getEntropy()

size

public int size()

numFeatures

public int numFeatures()

countOutput

public int countOutput(java.lang.String value)
                throws InvalidFeature

writeNames

public void writeNames(java.lang.String namesfile)
                throws java.lang.Exception

writeData

public void writeData(java.lang.String datafile)
               throws java.lang.Exception

write

public void write(java.lang.String namesfile,
                  java.lang.String datafile)
           throws java.lang.Exception

readData

protected void readData(java.lang.String datafile)
                 throws java.lang.Exception

merge

public void merge(DataSet newSet)

splitRandom

public DataSet[] splitRandom(double testpercent)

splitRandom() : splits the data into two subsets, based upon the testpercent. examples are chosen randomly from this dataset. DataSet[0] = smaller part of the dataset. DataSet[1] = rest of the dataset.

splitJackKnife

public DataSet[] splitJackKnife(int index)

splitDataSetFolds

public DataSet[][] splitDataSetFolds(int numfolds,
                                     boolean randomize)

splitDataSetFolds() : splits the dataset into an array of n-folds. 1st index is the fold number. 2nd index is 0=trainset 1=testset

splitDataSet

public DataSet[] splitDataSet(int numSets,
                              boolean randomize)

getBootStrapReplicate

public DataSet[] getBootStrapReplicate()

createMapping

public int[] createMapping(boolean randomize)

printFeatureIdList

public java.lang.String printFeatureIdList()