Package com.yahoo.labs.samoa.instances

Class Instances

java.lang.Object

com.yahoo.labs.samoa.instances.Instances

All Implemented Interfaces:

java.io.Serializable

Direct Known Subclasses:

InstancesHeader

public class Instances
extends java.lang.Object
implements java.io.Serializable

The Class Instances.

Author:

abifet

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field	Description
protected ArffLoader	arff	The arff.
static java.lang.String	ARFF_DATA	The keyword used to denote the start of the arff data section
static java.lang.String	ARFF_RELATION	The keyword used to denote the start of an arff header
protected java.util.HashMap<java.lang.String,java.lang.Integer>	hsAttributesIndices	A Hash that stores the indices of features.
protected int[]	indicesIrrelevants	Indices of irrelevant features.
protected int[]	indicesRelevants	Indices of relevant features.
protected InstanceInformation	instanceInformation	The instance information.
protected java.util.List<Instance>	instances	The instances.

Constructor Summary

Constructors

Constructor	Description
Instances()	Instantiates a new instances.
Instances(Instances chunk)	Instantiates a new instances.
Instances(Instances chunk, int capacity)	Instantiates a new instances.
Instances(Instances chunk, int first, int toCopy)	Instantiates a new instances.
Instances(java.io.Reader reader, int size, int classAttribute)	Instantiates a new instances.
Instances(java.io.Reader reader, Range range)	Instantiates a new instances.
Instances(java.io.StringReader st, int capacity)	Instantiates a new instances.
Instances(java.lang.String st, Attribute[] v, int capacity)	Instantiates a new instances.
Instances(java.lang.String st, java.util.List<Attribute> v, int capacity)	Instantiates a new instances.

Method Summary

Modifier and Type	Method	Description
void	add(Instance inst)	Adds the.
Attribute	attribute(int w)	Attribute.
Attribute	attribute(java.lang.String name)
Attribute	classAttribute()	Class attribute.
int	classIndex()	Class index.
protected void	copyInstances(int from, Instances dest, int num)
void	delete()	Delete.
void	delete(int index)	Delete.
void	deleteAttributeAt(java.lang.Integer integer)	Delete attribute at.
Instance	get(int k)
int[]	getIndicesIrrelevants()	Returns the indices of the irrelevant features indicesIrrelevants.
int[]	getIndicesRelevants()	Returns the indices of the relevant features indicesRelevants.
java.lang.String	getRelationName()	Gets the relation name.
protected int	indexOf(Attribute att)	Returns the index of an Attribute.
void	insertAttributeAt(Attribute attribute, int position)	Insert attribute at.
Instance	instance(int num)	Instance.
double	meanOrMode(int j)	Mean or mode.
int	numAttributes()	Num attributes.
int	numClasses()	Num classes.
int	numInstances()	Num instances.
void	randomize(java.util.Random random)	Randomize.
boolean	readInstance(java.io.Reader fileReader)	Read instance.
void	set(int i, Instance inst)
void	setAttributes(Attribute[] v)
void	setAttributes(Attribute[] v, int[] indexValues)
void	setAttributes(java.util.List<Attribute> v, java.util.List<java.lang.Integer> indexValues)
void	setClassIndex(int classIndex)	Sets the class index.
void	setIndicesRelevants(int[] indicesRelevants)	Sets the indices of relevant features.
void	setRangeOutputIndices(Range range)
void	setRelationName(java.lang.String string)	Sets the relation name.
int	size()
void	stratify(int numFolds)	Stratify.
protected void	stratStep(int numFolds)
protected java.lang.String	stringWithoutHeader()	Returns the instances in the dataset as a string in ARFF format.
void	swap(int i, int j)	Swap.
Instances	testCV(int numFolds, int numFold)	Test cv.
java.lang.String	toString()	Returns the dataset as a string in ARFF format.
Instances	trainCV(int numFolds, int numFold)
Instances	trainCV(int numFolds, int numFold, java.util.Random random)	Train cv.

Methods inherited from class java.lang.Object

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

Field Detail

ARFF_RELATION

public static final java.lang.String ARFF_RELATION

The keyword used to denote the start of an arff header

See Also:

Constant Field Values

ARFF_DATA

public static final java.lang.String ARFF_DATA

The keyword used to denote the start of the arff data section

See Also:

Constant Field Values

instanceInformation

protected InstanceInformation instanceInformation

The instance information.

instances

protected java.util.List<Instance> instances

The instances.

arff

protected ArffLoader arff

The arff.

hsAttributesIndices

protected java.util.HashMap<java.lang.String,java.lang.Integer> hsAttributesIndices

A Hash that stores the indices of features.

indicesRelevants

protected int[] indicesRelevants

Indices of relevant features.

indicesIrrelevants

protected int[] indicesIrrelevants

Indices of irrelevant features.

Constructor Detail

Instances

public Instances(Instances chunk)

Instantiates a new instances.

Parameters:

chunk - the chunk

Instances

public Instances()

Instantiates a new instances.

Instances

public Instances(java.io.Reader reader,
                 int size,
                 int classAttribute)

Instantiates a new instances.

Parameters:

reader - the reader

size - the size

classAttribute - the class attribute

Instances

public Instances(java.io.Reader reader,
                 Range range)

Instantiates a new instances.

Parameters:

reader - the reader

range -

Instances

public Instances(Instances chunk,
                 int capacity)

Instantiates a new instances.

Parameters:

chunk - the chunk

capacity - the capacity

Instances

public Instances(java.lang.String st,
                 Attribute[] v,
                 int capacity)

Instantiates a new instances.

Parameters:

st - the st

v - the v

capacity - the capacity

Instances

public Instances(java.lang.String st,
                 java.util.List<Attribute> v,
                 int capacity)

Instantiates a new instances.

Parameters:

st - the st

v - the v

capacity - the capacity

Instances

public Instances(Instances chunk,
                 int first,
                 int toCopy)

Instantiates a new instances.

Parameters:

chunk - the chunk

first - the first instance

toCopy - the j

Instances

public Instances(java.io.StringReader st,
                 int capacity)

Instantiates a new instances.

Parameters:

st - the st

capacity - the capacity

Method Detail

setRelationName

public void setRelationName(java.lang.String string)

Sets the relation name.

Parameters:

string - the new relation name

getRelationName

public java.lang.String getRelationName()

Gets the relation name.

Returns:

the relation name

classIndex

public int classIndex()

Class index.

Returns:

the int

setClassIndex

public void setClassIndex(int classIndex)

Sets the class index.

Parameters:

classIndex - the new class index

classAttribute

public Attribute classAttribute()

Class attribute.

Returns:

the attribute

numAttributes

public int numAttributes()

Num attributes.

Returns:

the int

attribute

public Attribute attribute(int w)

Attribute.

Parameters:

w - the w

Returns:

the attribute

numClasses

public int numClasses()

Num classes.

Returns:

the int

deleteAttributeAt

public void deleteAttributeAt(java.lang.Integer integer)

Delete attribute at.

Parameters:

integer - the integer

insertAttributeAt

public void insertAttributeAt(Attribute attribute,
                              int position)

Insert attribute at.

Parameters:

attribute - the attribute

position - the position

instance

public Instance instance(int num)

Instance.

Parameters:

num - the num

Returns:

the instance

numInstances

public int numInstances()

Num instances.

Returns:

the int

add

public void add(Instance inst)

Adds the.

Parameters:

inst - the inst

randomize

public void randomize(java.util.Random random)

Randomize.

Parameters:

random - the random

stratify

public void stratify(int numFolds)

Stratify.

Parameters:

numFolds - the num folds

stratStep

protected void stratStep(int numFolds)

trainCV

public Instances trainCV(int numFolds,
                         int numFold,
                         java.util.Random random)

Train cv.

Parameters:

numFolds - the num folds

numFold -

random - the random

Returns:

the instances

trainCV

public Instances trainCV(int numFolds,
                         int numFold)

copyInstances

protected void copyInstances(int from,
                             Instances dest,
                             int num)

testCV

public Instances testCV(int numFolds,
                        int numFold)

Test cv.

Parameters:

numFolds - the num folds

numFold - the num fold

Returns:

the instances

meanOrMode

public double meanOrMode(int j)

Mean or mode.

Parameters:

j - the j

Returns:

the double

readInstance

public boolean readInstance(java.io.Reader fileReader)

Read instance.

Parameters:

fileReader - the file reader

Returns:

true, if successful

delete

public void delete()

Delete.

delete

public void delete(int index)

Delete.

swap

public void swap(int i,
                 int j)

Swap.

Parameters:

i - the i

j - the j

attribute

public Attribute attribute(java.lang.String name)

size

public int size()

set

public void set(int i,
                Instance inst)

get

public Instance get(int k)

setRangeOutputIndices

public void setRangeOutputIndices(Range range)

setAttributes

public void setAttributes(Attribute[] v)

setAttributes

public void setAttributes(Attribute[] v,
                          int[] indexValues)

setAttributes

public void setAttributes(java.util.List<Attribute> v,
                          java.util.List<java.lang.Integer> indexValues)

toString

public java.lang.String toString()

Returns the dataset as a string in ARFF format. Strings are quoted if they contain whitespace characters, or if they are a question mark.

Overrides:

toString in class java.lang.Object

Returns:

the dataset in ARFF format as a string

stringWithoutHeader

protected java.lang.String stringWithoutHeader()

Returns the instances in the dataset as a string in ARFF format. Strings are quoted if they contain whitespace characters, or if they are a question mark.

Returns:

the dataset in ARFF format as a string

indexOf

protected int indexOf(Attribute att)

Returns the index of an Attribute.

Parameters:

att - , the attribute.

getIndicesRelevants

public int[] getIndicesRelevants()

Returns the indices of the relevant features indicesRelevants.

Returns:

indicesRelevants

getIndicesIrrelevants

public int[] getIndicesIrrelevants()

Returns the indices of the irrelevant features indicesIrrelevants.

Returns:

indicesIrrelevants

setIndicesRelevants

public void setIndicesRelevants(int[] indicesRelevants)

Sets the indices of relevant features. This method also sets the irrelevant ones since it is the set complement.

Parameters:

indicesRelevants -