Package edu.cmu.tetrad.data

Class CovarianceMatrix

java.lang.Object

edu.cmu.tetrad.data.CovarianceMatrix

All Implemented Interfaces:

DataModel, ICovarianceMatrix, KnowledgeTransferable, VariableSource, TetradSerializable, Serializable

Direct Known Subclasses:

CorrelationMatrix

public class CovarianceMatrix
extends Object
implements ICovarianceMatrix

Stores a covariance matrix together with variable names and sample size, intended as a representation of a data set. When constructed from a continuous data set, the matrix is not checked for positive definiteness; however, when a covariance matrix is supplied, its positive definiteness is always checked. If the sample size is less than the number of variables, the positive definiteness is "spot-checked"--that is, checked for various submatrices.

Version:

$Id: $Id

Author:

josephramsey

See Also:

• CorrelationMatrix
• Serialized Form

Constructor Summary

Constructors

Constructor	Description
CovarianceMatrix(CovarianceMatrix covMatrix)	Copy constructor.
CovarianceMatrix(DataSet dataSet)	Constructs a new covariance matrix from the given data set.
CovarianceMatrix(DataSet dataSet, boolean biasCorrected)	Constructor for CovarianceMatrix.
CovarianceMatrix(ICovarianceMatrix covMatrix)	Constructor for CovarianceMatrix.
CovarianceMatrix(List<Node> variables, double[][] matrix, int sampleSize)	Constructor for CovarianceMatrix.
CovarianceMatrix(List<Node> variables, Matrix matrix, int sampleSize)	Protected constructor to construct a new covariance matrix using the supplied continuous variables and the the given symmetric, positive definite matrix and sample size.

Method Summary

Modifier and Type	Method	Description
final void	clearSelection()	clearSelection.
DataModel	copy()	copy.
final int	getDimension()	getDimension.
final Knowledge	getKnowledge()	Getter for the field knowledge.
final Matrix	getMatrix()	getMatrix.
final String	getName()	Gets the name of the covariance matrix.
final int	getSampleSize()	The size of the sample used to calculated this covariance matrix.
final List<String>	getSelectedVariableNames()	getSelectedVariableNames.
Matrix	getSelection(int[] rows, int[] cols)	Returns a submatrix based on the specified rows and columns.
final int	getSize()	getSize.
final ICovarianceMatrix	getSubmatrix(int[] indices)	getSubmatrix.
final CovarianceMatrix	getSubmatrix(String[] submatrixVarNames)	getSubmatrix.
final ICovarianceMatrix	getSubmatrix(List<String> submatrixVarNames)	getSubmatrix.
final double	getValue(int i, int j)	Retrieves the value from the covariance matrix at the specified row and column indices.
Node	getVariable(String name)	Retrieves a Node instance from the covariance matrix corresponding to the specified variable name.
final String	getVariableName(int index)	Retrieves the name of the variable at the specified index from the covariance matrix.
final List<String>	getVariableNames()	getVariableNames.
final List<Node>	getVariables()	Getter for the field variables.
boolean	isContinuous()	isContinuous.
boolean	isDiscrete()	isDiscrete.
boolean	isMixed()	isMixed.
final boolean	isSelected(Node variable)	Checks if the specified node is selected in the covariance matrix.
boolean	isSingular()	isSingular.
void	removeVariables(List<String> remaining)	Removes variables from the covariance matrix, retaining only the variables specified in the provided list.
final void	select(Node variable)	Selects a specified variable in the covariance matrix.
static ICovarianceMatrix	serializableInstance()	Generates a simple exemplar of this class to test serialization.
final void	setKnowledge(Knowledge knowledge)	Sets the knowledge associated with the ICovarianceMatrix.
void	setMatrix(Matrix matrix)	Sets the covariance matrix.
final void	setName(String name)	Sets the name of the covariance matrix.
final void	setSampleSize(int sampleSize)	Sets the sample size used in the covariance matrix.
void	setValue(int i, int j, double v)	Sets the value of the covariance matrix at the specified indices.
void	setVariables(List<Node> variables)	Sets the list of Node variables for the covariance matrix.
final String	toString()	Prints out the matrix

Methods inherited from class java.lang.Object

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

Constructor Details

CovarianceMatrix

public CovarianceMatrix(DataSet dataSet)

Constructs a new covariance matrix from the given data set.

Parameters:

dataSet - a DataSet object

Throws:

IllegalArgumentException - if this is not a continuous data set.

CovarianceMatrix

public CovarianceMatrix(DataSet dataSet,
 boolean biasCorrected)

Constructor for CovarianceMatrix.

Parameters:

dataSet - a DataSet object

biasCorrected - a boolean

CovarianceMatrix

public CovarianceMatrix(List<Node> variables,
 Matrix matrix,
 int sampleSize)

Protected constructor to construct a new covariance matrix using the supplied continuous variables and the the given symmetric, positive definite matrix and sample size. The number of variables must equal the dimension of the array.

Parameters:

variables - the list of variables (in order) for the covariance matrix.

matrix - an square array of containing covariances.

sampleSize - the sample size of the data for these covariances.

Throws:

IllegalArgumentException - if the given matrix is not symmetric (to a tolerance of 1.e-5) and positive definite, if the number of variables does not equal the dimension of m, or if the sample size is not positive.

CovarianceMatrix

public CovarianceMatrix(List<Node> variables,
 double[][] matrix,
 int sampleSize)

Constructor for CovarianceMatrix.

Parameters:

variables - a List object

matrix - an array of objects

sampleSize - a int

CovarianceMatrix

public CovarianceMatrix(CovarianceMatrix covMatrix)

Copy constructor.

Parameters:

covMatrix - a CovarianceMatrix object

CovarianceMatrix

public CovarianceMatrix(ICovarianceMatrix covMatrix)

Constructor for CovarianceMatrix.

Parameters:

covMatrix - a ICovarianceMatrix object

Method Details

serializableInstance

public static ICovarianceMatrix serializableInstance()

Generates a simple exemplar of this class to test serialization.

Returns:

a ICovarianceMatrix object

getVariables

public final List<Node> getVariables()

Getter for the field variables.

Specified by:

getVariables in interface ICovarianceMatrix

Specified by:

getVariables in interface VariableSource

Returns:

the list of variables (unmodifiable).

setVariables

public void setVariables(List<Node> variables)

Sets the list of Node variables for the covariance matrix.

Specified by:

setVariables in interface ICovarianceMatrix

Parameters:

variables - a list of Node objects representing the variables to be set in the covariance matrix

getVariableNames

public final List<String> getVariableNames()

getVariableNames.

Specified by:

getVariableNames in interface ICovarianceMatrix

Specified by:

getVariableNames in interface VariableSource

Returns:

the variable names, in order.

getVariableName

public final String getVariableName(int index)

Retrieves the name of the variable at the specified index from the covariance matrix.

Specified by:

getVariableName in interface ICovarianceMatrix

Parameters:

index - the index of the variable whose name is to be retrieved

Returns:

the name of the variable at the specified index

getDimension

public final int getDimension()

getDimension.

Specified by:

getDimension in interface ICovarianceMatrix

Returns:

the dimension of the covariance matrix.

getSampleSize

public final int getSampleSize()

The size of the sample used to calculated this covariance matrix.

Specified by:

getSampleSize in interface ICovarianceMatrix

Returns:

The sample size (> 0).

setSampleSize

public final void setSampleSize(int sampleSize)

Sets the sample size used in the covariance matrix.

Specified by:

setSampleSize in interface ICovarianceMatrix

Parameters:

sampleSize - the sample size to be set

getName

public final String getName()

Gets the name of the covariance matrix.

Specified by:

getName in interface DataModel

Specified by:

getName in interface ICovarianceMatrix

Returns:

a String object

setName

public final void setName(String name)

Sets the name of the covariance matrix.

Sets the name of the covariance matrix.

Specified by:

setName in interface DataModel

Specified by:

setName in interface ICovarianceMatrix

Parameters:

name - the new name of the covariance matrix

getKnowledge

public final Knowledge getKnowledge()

Getter for the field knowledge.

Specified by:

getKnowledge in interface ICovarianceMatrix

Specified by:

getKnowledge in interface KnowledgeTransferable

Returns:

the knowledge associated with this data.

setKnowledge

public final void setKnowledge(Knowledge knowledge)

Sets the knowledge associated with the ICovarianceMatrix.

Associates knowledge with this data.

Specified by:

setKnowledge in interface ICovarianceMatrix

Specified by:

setKnowledge in interface KnowledgeTransferable

Parameters:

knowledge - the knowledge to set

getSubmatrix

public final ICovarianceMatrix getSubmatrix(int[] indices)

getSubmatrix.

Specified by:

getSubmatrix in interface ICovarianceMatrix

Parameters:

indices - an array of objects

Returns:

a submatrix of the covariance matrix with variables in the given order.

getSubmatrix

public final ICovarianceMatrix getSubmatrix(List<String> submatrixVarNames)

getSubmatrix.

Specified by:

getSubmatrix in interface ICovarianceMatrix

Parameters:

submatrixVarNames - a List object

Returns:

a ICovarianceMatrix object

getSubmatrix

public final CovarianceMatrix getSubmatrix(String[] submatrixVarNames)

getSubmatrix.

Specified by:

getSubmatrix in interface ICovarianceMatrix

Parameters:

submatrixVarNames - an array of String objects

Returns:

a submatrix of this matrix, with variables in the given order.

getValue

public final double getValue(int i,
 int j)

Retrieves the value from the covariance matrix at the specified row and column indices.

Specified by:

getValue in interface ICovarianceMatrix

Parameters:

i - the row index

j - the column index

Returns:

the value at the specified indices in the matrix

getSize

public final int getSize()

getSize.

Specified by:

getSize in interface ICovarianceMatrix

Returns:

the size of the square matrix.

getMatrix

public final Matrix getMatrix()

getMatrix.

Specified by:

getMatrix in interface ICovarianceMatrix

Returns:

a the covariance matrix (not a copy).

setMatrix

public void setMatrix(Matrix matrix)

Sets the covariance matrix.

Specified by:

setMatrix in interface ICovarianceMatrix

Parameters:

matrix - the matrix to set

select

public final void select(Node variable)

Selects a specified variable in the covariance matrix.

Specified by:

select in interface ICovarianceMatrix

Parameters:

variable - the node variable to be selected

clearSelection

public final void clearSelection()

clearSelection.

Specified by:

clearSelection in interface ICovarianceMatrix

isSelected

public final boolean isSelected(Node variable)

Checks if the specified node is selected in the covariance matrix.

Specified by:

isSelected in interface ICovarianceMatrix

Parameters:

variable - the node to check for selection

Returns:

true if the node is selected, false otherwise

getSelectedVariableNames

public final List<String> getSelectedVariableNames()

getSelectedVariableNames.

Specified by:

getSelectedVariableNames in interface ICovarianceMatrix

Returns:

a List object

toString

public final String toString()

Prints out the matrix

Specified by:

toString in interface DataModel

Specified by:

toString in interface ICovarianceMatrix

Overrides:

toString in class Object

Returns:

a String object

isContinuous

public boolean isContinuous()

isContinuous.

Specified by:

isContinuous in interface DataModel

Returns:

true if the data model is continuous, false otherwise.

isDiscrete

public boolean isDiscrete()

isDiscrete.

Specified by:

isDiscrete in interface DataModel

Returns:

true if the data model is discrete, false otherwise.

isMixed

public boolean isMixed()

isMixed.

Specified by:

isMixed in interface DataModel

Returns:

true if the data model is mixed continuous/discrete, false otherwise.

getSelection

public Matrix getSelection(int[] rows,
 int[] cols)

Returns a submatrix based on the specified rows and columns.

Specified by:

getSelection in interface ICovarianceMatrix

Parameters:

rows - an array of integers representing the row indices to be included in the selection.

cols - an array of integers representing the column indices to be included in the selection.

Returns:

a Matrix object containing the selected rows and columns.

getVariable

public Node getVariable(String name)

Retrieves a Node instance from the covariance matrix corresponding to the specified variable name.

Specified by:

getVariable in interface DataModel

Specified by:

getVariable in interface ICovarianceMatrix

Parameters:

name - the name of the variable to retrieve

Returns:

the Node associated with the specified variable name

copy

public DataModel copy()

copy.

Specified by:

copy in interface DataModel

Returns:

a copy of the data model.

setValue

public void setValue(int i,
 int j,
 double v)

Sets the value of the covariance matrix at the specified indices.

Specified by:

setValue in interface ICovarianceMatrix

Parameters:

i - the row index

j - the column index

v - the value to set at the specified indices

removeVariables

public void removeVariables(List<String> remaining)

Removes variables from the covariance matrix, retaining only the variables specified in the provided list.

Specified by:

removeVariables in interface ICovarianceMatrix

Parameters:

remaining - a list of variable names to retain in the covariance matrix.

isSingular

public boolean isSingular()

isSingular.

Returns:

a boolean