edu.harvard.seas.iis.abilities.classify
Class DataSet

java.lang.Object
  weka.core.Instances
      edu.harvard.seas.iis.abilities.classify.DataSet

All Implemented Interfaces:

java.io.Serializable, weka.core.RevisionHandler

Direct Known Subclasses:

UserDataSet

public class DataSet
extends weka.core.Instances

See Also:

Serialized Form

Field Summary

Fields inherited from class weka.core.Instances

ARFF_DATA, ARFF_RELATION, FILE_EXTENSION, SERIALIZED_OBJ_FILE_EXTENSION

Constructor Summary

DataSet(weka.core.Instances insts)

DataSet(java.lang.String name, weka.core.FastVector baseAttrNames, int suspectedCapacity)

Method Summary

void	addInstances(weka.core.Instances insts)
double[]	attributeToDoubleArray(java.lang.String name)
static DataSet	fromArffFile(java.io.File f) A convenience method that creates an instance of a UserDataSet from an ARFF file
static DataSet	fromArffFiles(java.io.File[] files) Creates a single UserDataSet object from multiple ARFF files
DataSet	getExplicitInstances() Convenience method which returns a subset of the data containing only explicit examples
DataSet	getImplicitInstances() Convenience method which returns a subset of the data containing only implicit examples
DataSet	getInstancesForUser(java.lang.String user)
DataSet	getInstancesWithAttributeValueEqual(weka.core.Attribute att, java.lang.String attVal)
DataSet	getInstancesWithAttributeValueGreaterThan(weka.core.Attribute att, double attVal)
DataSet	getInstancesWithAttributeValueNotEqual(weka.core.Attribute att, java.lang.String attVal)
DataSet	getInstancesWithAttributeValues(weka.core.Attribute att, java.util.Collection<java.lang.String> values)
int	getNumExplicitInstances()
int	getNumImplicitInstances()
java.util.Vector<java.lang.String>	getValuesOfStringOrNominalAttribute(weka.core.Attribute attr)
void	saveAsARFF(java.lang.String outfile)
void	saveAsBothARFFandCSV(java.lang.String outFile)
void	saveAsCSV(java.lang.String outfile) Saves the data set in the CSV format
void	setValue(weka.core.Attribute attr, java.lang.String value, InstanceFilter condition) Sets the value of an attribute to a particular value for all instances that match the condition

Methods inherited from class weka.core.Instances

add, attribute, attribute, attributeStats, attributeToDoubleArray, checkForAttributeType, checkForStringAttributes, checkInstance, classAttribute, classIndex, compactify, delete, delete, deleteAttributeAt, deleteAttributeType, deleteStringAttributes, deleteWithMissing, deleteWithMissing, deleteWithMissingClass, enumerateAttributes, enumerateInstances, equalHeaders, firstInstance, getRandomNumberGenerator, getRevision, insertAttributeAt, instance, kthSmallestValue, kthSmallestValue, lastInstance, main, meanOrMode, meanOrMode, mergeInstances, numAttributes, numClasses, numDistinctValues, numDistinctValues, numInstances, randomize, readInstance, relationName, renameAttribute, renameAttribute, renameAttributeValue, renameAttributeValue, resample, resampleWithWeights, resampleWithWeights, setClass, setClassIndex, setRelationName, sort, sort, stratify, stringFreeStructure, sumOfWeights, swap, test, testCV, toString, toSummaryString, trainCV, trainCV, variance, variance

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

DataSet

public DataSet(java.lang.String name,
               weka.core.FastVector baseAttrNames,
               int suspectedCapacity)

DataSet

public DataSet(weka.core.Instances insts)

Method Detail

addInstances

public void addInstances(weka.core.Instances insts)

getInstancesWithAttributeValueEqual

public DataSet getInstancesWithAttributeValueEqual(weka.core.Attribute att,
                                                   java.lang.String attVal)

getInstancesWithAttributeValueNotEqual

public DataSet getInstancesWithAttributeValueNotEqual(weka.core.Attribute att,
                                                      java.lang.String attVal)

getInstancesWithAttributeValues

public DataSet getInstancesWithAttributeValues(weka.core.Attribute att,
                                               java.util.Collection<java.lang.String> values)

getInstancesWithAttributeValueGreaterThan

public DataSet getInstancesWithAttributeValueGreaterThan(weka.core.Attribute att,
                                                         double attVal)

getExplicitInstances

public DataSet getExplicitInstances()

Convenience method which returns a subset of the data containing only explicit examples

Returns:

getImplicitInstances

public DataSet getImplicitInstances()

Convenience method which returns a subset of the data containing only implicit examples

Returns:

getInstancesForUser

public DataSet getInstancesForUser(java.lang.String user)

getNumImplicitInstances

public int getNumImplicitInstances()

getNumExplicitInstances

public int getNumExplicitInstances()

getValuesOfStringOrNominalAttribute

public java.util.Vector<java.lang.String> getValuesOfStringOrNominalAttribute(weka.core.Attribute attr)

setValue

public void setValue(weka.core.Attribute attr,
                     java.lang.String value,
                     InstanceFilter condition)

Sets the value of an attribute to a particular value for all instances that match the condition

Parameters:

attr -

value -

condition - if null, then all instances are set to the given value

attributeToDoubleArray

public double[] attributeToDoubleArray(java.lang.String name)

saveAsBothARFFandCSV

public void saveAsBothARFFandCSV(java.lang.String outFile)
                          throws java.io.IOException

Throws:

java.io.IOException

saveAsARFF

public void saveAsARFF(java.lang.String outfile)
                throws java.io.IOException

Parameters:

outfile -

Throws:

java.io.IOException

saveAsCSV

public void saveAsCSV(java.lang.String outfile)
               throws java.io.IOException

Saves the data set in the CSV format

Parameters:

outfile -

Throws:

java.io.IOException

fromArffFile

public static DataSet fromArffFile(java.io.File f)
                            throws java.io.IOException

A convenience method that creates an instance of a UserDataSet from an ARFF file

Parameters:

f -

Returns:

Throws:

java.io.IOException

fromArffFiles

public static DataSet fromArffFiles(java.io.File[] files)
                             throws java.io.IOException

Creates a single UserDataSet object from multiple ARFF files

Parameters:

files -

Returns:

Throws:

java.io.IOException