weka.core
Class AbstractInstance

java.lang.Object
  weka.core.AbstractInstance

All Implemented Interfaces:

Serializable, Copyable, Instance, RevisionHandler

Direct Known Subclasses:

DenseInstance, SparseInstance

public abstract class AbstractInstance
extends Object
implements Instance, Serializable, RevisionHandler

Abstract class providing common functionality for the original instance implementations.

Version:

$Revision: 8034 $

Author:

Eibe Frank (eibe@cs.waikato.ac.nz)

See Also:

Serialized Form

Constructor Summary

AbstractInstance()

Method Summary

Attribute	attribute(int index) Returns the attribute with the given index.
Attribute	attributeSparse(int indexOfIndex) Returns the attribute with the given index in the sparse representation.
Attribute	classAttribute() Returns class attribute.
int	classIndex() Returns the class attribute's index.
boolean	classIsMissing() Tests if an instance's class is missing.
double	classValue() Returns an instance's class value in internal format.
Instances	dataset() Returns the dataset this instance has access to.
void	deleteAttributeAt(int position) Deletes an attribute at the given position (0 to numAttributes() - 1).
Enumeration	enumerateAttributes() Returns an enumeration of all the attributes.
boolean	equalHeaders(Instance inst) Tests if the headers of two instances are equivalent.
String	equalHeadersMsg(Instance inst) Checks if the headers of two instances are equivalent.
String	getRevision() Returns the revision string.
boolean	hasMissingValue() Tests whether an instance has a missing value.
void	insertAttributeAt(int position) Inserts an attribute at the given position (0 to numAttributes()).
boolean	isMissing(Attribute att) Tests if a specific value is "missing".
boolean	isMissing(int attIndex) Tests if a specific value is "missing".
boolean	isMissingSparse(int indexOfIndex) Tests if a specific value is "missing", given an index in the sparse representation.
int	numClasses() Returns the number of class labels.
Instances	relationalValue(Attribute att) Returns the relational value of a relational attribute.
Instances	relationalValue(int attIndex) Returns the relational value of a relational attribute.
void	setClassMissing() Sets the class value of an instance to be "missing".
void	setClassValue(double value) Sets the class value of an instance to the given value (internal floating-point format).
void	setClassValue(String value) Sets the class value of an instance to the given value.
void	setDataset(Instances instances) Sets the reference to the dataset.
void	setMissing(Attribute att) Sets a specific value to be "missing".
void	setMissing(int attIndex) Sets a specific value to be "missing".
void	setValue(Attribute att, double value) Sets a specific value in the instance to the given value (internal floating-point format).
void	setValue(Attribute att, String value) Sets a value of an nominal or string attribute to the given value.
void	setValue(int attIndex, String value) Sets a value of a nominal or string attribute to the given value.
void	setWeight(double weight) Sets the weight of an instance.
String	stringValue(Attribute att) Returns the value of a nominal, string, date, or relational attribute for the instance as a string.
String	stringValue(int attIndex) Returns the value of a nominal, string, date, or relational attribute for the instance as a string.
String	toString() Returns the description of one instance.
String	toString(Attribute att) Returns the description of one value of the instance as a string.
String	toString(int attIndex) Returns the description of one value of the instance as a string.
double	value(Attribute att) Returns an instance's attribute value in internal format.
double	valueSparse(int indexOfIndex) Returns an instance's attribute value in internal format, given an index in the sparse representation.
double	weight() Returns the instance's weight.

Methods inherited from class java.lang.Object

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

Methods inherited from interface weka.core.Instance

index, mergeInstance, numAttributes, numValues, replaceMissingValues, setValue, setValueSparse, toDoubleArray, toStringNoWeight, value

Methods inherited from interface weka.core.Copyable

copy

Constructor Detail

AbstractInstance

public AbstractInstance()

Method Detail

attribute

public Attribute attribute(int index)

Returns the attribute with the given index.

Specified by:

attribute in interface Instance

Parameters:

index - the attribute's index

Returns:

the attribute at the given position

Throws:

UnassignedDatasetException - if instance doesn't have access to a dataset

attributeSparse

public Attribute attributeSparse(int indexOfIndex)

Returns the attribute with the given index in the sparse representation.

Specified by:

attributeSparse in interface Instance

Parameters:

indexOfIndex - the index of the attribute's index

Returns:

the attribute at the given position

Throws:

UnassignedDatasetException - if instance doesn't have access to a dataset

classAttribute

public Attribute classAttribute()

Returns class attribute.

Specified by:

classAttribute in interface Instance

Returns:

the class attribute

Throws:

UnassignedDatasetException - if the class is not set or the instance doesn't have access to a dataset

classIndex

public int classIndex()

Returns the class attribute's index.

Specified by:

classIndex in interface Instance

Returns:

the class index as an integer

Throws:

UnassignedDatasetException - if instance doesn't have access to a dataset

classIsMissing

public boolean classIsMissing()

Tests if an instance's class is missing.

Specified by:

classIsMissing in interface Instance

Returns:

true if the instance's class is missing

Throws:

UnassignedClassException - if the class is not set or the instance doesn't have access to a dataset

classValue

public double classValue()

Returns an instance's class value in internal format. (ie. as a floating-point number)

Specified by:

classValue in interface Instance

Returns:

the corresponding value as a double (If the corresponding attribute is nominal (or a string) then it returns the value's index as a double).

Throws:

UnassignedClassException - if the class is not set or the instance doesn't have access to a dataset

dataset

public Instances dataset()

Returns the dataset this instance has access to. (ie. obtains information about attribute types from) Null if the instance doesn't have access to a dataset.

Specified by:

dataset in interface Instance

Returns:

the dataset the instance has accesss to

deleteAttributeAt

public void deleteAttributeAt(int position)

Deletes an attribute at the given position (0 to numAttributes() - 1). Only succeeds if the instance does not have access to any dataset because otherwise inconsistencies could be introduced.

Specified by:

deleteAttributeAt in interface Instance

Parameters:

position - the attribute's position

Throws:

RuntimeException - if the instance has access to a dataset

enumerateAttributes

public Enumeration enumerateAttributes()

Returns an enumeration of all the attributes.

Specified by:

enumerateAttributes in interface Instance

Returns:

enumeration of all the attributes

Throws:

UnassignedDatasetException - if the instance doesn't have access to a dataset

equalHeaders

public boolean equalHeaders(Instance inst)

Tests if the headers of two instances are equivalent.

Specified by:

equalHeaders in interface Instance

Parameters:

inst - another instance

Returns:

true if the header of the given instance is equivalent to this instance's header

Throws:

UnassignedDatasetException - if instance doesn't have access to any dataset

equalHeadersMsg

public String equalHeadersMsg(Instance inst)

Checks if the headers of two instances are equivalent. If not, then returns a message why they differ.

Specified by:

equalHeadersMsg in interface Instance

Parameters:

dataset - another instance

Returns:

null if the header of the given instance is equivalent to this instance's header, otherwise a message with details on why they differ

hasMissingValue

public boolean hasMissingValue()

Tests whether an instance has a missing value. Skips the class attribute if set.

Specified by:

hasMissingValue in interface Instance

Returns:

true if instance has a missing value.

Throws:

UnassignedDatasetException - if instance doesn't have access to any dataset

insertAttributeAt

public void insertAttributeAt(int position)

Inserts an attribute at the given position (0 to numAttributes()). Only succeeds if the instance does not have access to any dataset because otherwise inconsistencies could be introduced.

Specified by:

insertAttributeAt in interface Instance

Parameters:

position - the attribute's position

Throws:

RuntimeException - if the instance has accesss to a dataset

IllegalArgumentException - if the position is out of range

isMissing

public boolean isMissing(int attIndex)

Tests if a specific value is "missing".

Specified by:

isMissing in interface Instance

Parameters:

attIndex - the attribute's index

Returns:

true if the value is "missing"

isMissingSparse

public boolean isMissingSparse(int indexOfIndex)

Tests if a specific value is "missing", given an index in the sparse representation.

Specified by:

isMissingSparse in interface Instance

Parameters:

indexOfIndex - the index of the attribute's index

Returns:

true if the value is "missing"

isMissing

public boolean isMissing(Attribute att)

Tests if a specific value is "missing". The given attribute has to belong to a dataset.

Specified by:

isMissing in interface Instance

Parameters:

att - the attribute

Returns:

true if the value is "missing"

numClasses

public int numClasses()

Returns the number of class labels.

Specified by:

numClasses in interface Instance

Returns:

the number of class labels as an integer if the class attribute is nominal, 1 otherwise.

Throws:

UnassignedDatasetException - if instance doesn't have access to any dataset

setClassMissing

public void setClassMissing()

Sets the class value of an instance to be "missing". A deep copy of the vector of attribute values is performed before the value is set to be missing.

Specified by:

setClassMissing in interface Instance

Throws:

UnassignedClassException - if the class is not set

UnassignedDatasetException - if the instance doesn't have access to a dataset

setClassValue

public void setClassValue(double value)

Sets the class value of an instance to the given value (internal floating-point format). A deep copy of the vector of attribute values is performed before the value is set.

Specified by:

setClassValue in interface Instance

Parameters:

value - the new attribute value (If the corresponding attribute is nominal (or a string) then this is the new value's index as a double).

Throws:

UnassignedClassException - if the class is not set

UnaddignedDatasetException - if the instance doesn't have access to a dataset

setClassValue

public final void setClassValue(String value)

Sets the class value of an instance to the given value. A deep copy of the vector of attribute values is performed before the value is set.

Specified by:

setClassValue in interface Instance

Parameters:

value - the new class value (If the class is a string attribute and the value can't be found, the value is added to the attribute).

Throws:

UnassignedClassException - if the class is not set

UnassignedDatasetException - if the dataset is not set

IllegalArgumentException - if the attribute is not nominal or a string, or the value couldn't be found for a nominal attribute

setDataset

public final void setDataset(Instances instances)

Sets the reference to the dataset. Does not check if the instance is compatible with the dataset. Note: the dataset does not know about this instance. If the structure of the dataset's header gets changed, this instance will not be adjusted automatically.

Specified by:

setDataset in interface Instance

Parameters:

instances - the reference to the dataset

setMissing

public final void setMissing(int attIndex)

Sets a specific value to be "missing". Performs a deep copy of the vector of attribute values before the value is set to be missing.

Specified by:

setMissing in interface Instance

Parameters:

attIndex - the attribute's index

setMissing

public final void setMissing(Attribute att)

Sets a specific value to be "missing". Performs a deep copy of the vector of attribute values before the value is set to be missing. The given attribute has to belong to a dataset.

Specified by:

setMissing in interface Instance

Parameters:

att - the attribute

setValue

public final void setValue(int attIndex,
                           String value)

Sets a value of a nominal or string attribute to the given value. Performs a deep copy of the vector of attribute values before the value is set.

Specified by:

setValue in interface Instance

Parameters:

attIndex - the attribute's index

value - the new attribute value (If the attribute is a string attribute and the value can't be found, the value is added to the attribute).

Throws:

UnassignedDatasetException - if the dataset is not set

IllegalArgumentException - if the selected attribute is not nominal or a string, or the supplied value couldn't be found for a nominal attribute

setValue

public final void setValue(Attribute att,
                           double value)

Sets a specific value in the instance to the given value (internal floating-point format). Performs a deep copy of the vector of attribute values before the value is set, so if you are planning on calling setValue many times it may be faster to create a new instance using toDoubleArray. The given attribute has to belong to a dataset.

Specified by:

setValue in interface Instance

Parameters:

att - the attribute

value - the new attribute value (If the corresponding attribute is nominal (or a string) then this is the new value's index as a double).

setValue

public final void setValue(Attribute att,
                           String value)

Sets a value of an nominal or string attribute to the given value. Performs a deep copy of the vector of attribute values before the value is set, so if you are planning on calling setValue many times it may be faster to create a new instance using toDoubleArray. The given attribute has to belong to a dataset.

Specified by:

setValue in interface Instance

Parameters:

att - the attribute

value - the new attribute value (If the attribute is a string attribute and the value can't be found, the value is added to the attribute).

Throws:

IllegalArgumentException - if the the attribute is not nominal or a string, or the value couldn't be found for a nominal attribute

setWeight

public final void setWeight(double weight)

Sets the weight of an instance.

Specified by:

setWeight in interface Instance

Parameters:

weight - the weight

relationalValue

public final Instances relationalValue(int attIndex)

Returns the relational value of a relational attribute.

Specified by:

relationalValue in interface Instance

Parameters:

attIndex - the attribute's index

Returns:

the corresponding relation as an Instances object

Throws:

IllegalArgumentException - if the attribute is not a relation-valued attribute

UnassignedDatasetException - if the instance doesn't belong to a dataset.

relationalValue

public final Instances relationalValue(Attribute att)

Returns the relational value of a relational attribute.

Specified by:

relationalValue in interface Instance

Parameters:

att - the attribute

Returns:

the corresponding relation as an Instances object

Throws:

IllegalArgumentException - if the attribute is not a relation-valued attribute

UnassignedDatasetException - if the instance doesn't belong to a dataset.

stringValue

public final String stringValue(int attIndex)

Returns the value of a nominal, string, date, or relational attribute for the instance as a string.

Specified by:

stringValue in interface Instance

Parameters:

attIndex - the attribute's index

Returns:

the value as a string

Throws:

IllegalArgumentException - if the attribute is not a nominal, string, date, or relation-valued attribute.

UnassignedDatasetException - if the instance doesn't belong to a dataset.

stringValue

public final String stringValue(Attribute att)

Returns the value of a nominal, string, date, or relational attribute for the instance as a string.

Specified by:

stringValue in interface Instance

Parameters:

att - the attribute

Returns:

the value as a string

Throws:

IllegalArgumentException - if the attribute is not a nominal, string, date, or relation-valued attribute.

UnassignedDatasetException - if the instance doesn't belong to a dataset.

toString

public String toString()

Returns the description of one instance. If the instance doesn't have access to a dataset, it returns the internal floating-point values. Quotes string values that contain whitespace characters.

Overrides:

toString in class Object

Returns:

the instance's description as a string

toString

public final String toString(int attIndex)

Returns the description of one value of the instance as a string. If the instance doesn't have access to a dataset, it returns the internal floating-point value. Quotes string values that contain whitespace characters, or if they are a question mark.

Specified by:

toString in interface Instance

Parameters:

attIndex - the attribute's index

Returns:

the value's description as a string

toString

public final String toString(Attribute att)

Returns the description of one value of the instance as a string. If the instance doesn't have access to a dataset it returns the internal floating-point value. Quotes string values that contain whitespace characters, or if they are a question mark. The given attribute has to belong to a dataset.

Specified by:

toString in interface Instance

Parameters:

att - the attribute

Returns:

the value's description as a string

value

public double value(Attribute att)

Returns an instance's attribute value in internal format. The given attribute has to belong to a dataset.

Specified by:

value in interface Instance

Parameters:

att - the attribute

Returns:

the specified value as a double (If the corresponding attribute is nominal (or a string) then it returns the value's index as a double).

valueSparse

public double valueSparse(int indexOfIndex)

Returns an instance's attribute value in internal format, given an index in the sparse representation.

Specified by:

valueSparse in interface Instance

Parameters:

indexOfIndex - the index of the attribute's index

Returns:

the specified value as a double (If the corresponding attribute is nominal (or a string) then it returns the value's index as a double).

weight

public final double weight()

Returns the instance's weight.

Specified by:

weight in interface Instance

Returns:

the instance's weight as a double

getRevision

public String getRevision()

Returns the revision string.

Specified by:

getRevision in interface RevisionHandler

Returns:

the revision