CorrectedMutualInformation

class otagrum.CorrectedMutualInformation(*args)

CorrectedMutualInformation class.

Parameters:

data2-d sequence of float

The data set.

Methods

clearCaches()	Clear cache containing the cross-entropies that are used to compute mutual information.
compute2PtCorrectedInformation(*args)	Return the corrected mutual information between variables X and Y conditionally to the variable set U (possibly empty).
compute3PtCorrectedInformation(*args)	Return the corrected three-point information between variables X, Y and Z conditionally to the variable set U (possibly empty).
getAlpha()	Returns the alpha correction value of mutual information when using the Naive KMode.
getDataDescription()	Return the description (variable names) of the underlying data set.
getDimension()	Returns the dimension of the underlying data set.
getSize()	Returns the size of the underlying data set.
setAlpha(alpha)	Displays the skeleton graph to dot
setCMode(cmode)	Change the copula model used for computing corrected mutual information.
setKMode(kmode)	Change the correction mode for mutual information.

getCMode
getKMode

__init__(*args)

clearCaches()

Clear cache containing the cross-entropies that are used to compute mutual information.

compute2PtCorrectedInformation(*args)

Return the corrected mutual information between variables X and Y conditionally to the variable set U (possibly empty).

Parameters:

Xint

X node id.

Yint

Y node id.

Ulist

List of node ids in the (possibly empty) set U

Returns:

infofloat

The corrected mutual information I’(X;Y|U).

Notes

The mutual information is computed from the cross-entropy H of the copula using the relation I(X;Y|U) = H(X,U) + H(Y,U) - H(X,Y,U) - H(U).

compute3PtCorrectedInformation(*args)

Return the corrected three-point information between variables X, Y and Z conditionally to the variable set U (possibly empty).

Parameters:

Xint

X node id.

Yint

Y node id.

Zint

Z node id.

Ulist

List of node ids in the (possibly empty) set U

Returns:

infofloat

The corrected three-point information I’(X;Y;Z|U).

Notes

The three-point information is computed from mutual information using the relation I(X;Y;Z|U) = I(X;Y|U) - I(X;Y|U,Z).

getAlpha()

Returns the alpha correction value of mutual information when using the Naive KMode.

Returns:

alphafloat

Correction value.

getDataDescription()

Return the description (variable names) of the underlying data set.

Returns:

descriptionDescription

Data description.

getDimension()

Returns the dimension of the underlying data set.

Returns:

dimensionint

Dimension of the data set.

getSize()

Returns the size of the underlying data set.

Returns:

sizeint

Size of the data set.

setAlpha(alpha)

Displays the skeleton graph to dot

Parameters:

pdagpyAgrum.UndiGraph

dag

Returns:

dotstr

Dot format representation

setCMode(cmode)

Change the copula model used for computing corrected mutual information.

Parameters:

cmodeCorrectedMutualInformation.CModeTypes

Copula model (Gaussian or Bernstein).

setKMode(kmode)

Change the correction mode for mutual information.

Parameters:

kmodeCorrectedMutualInformation.KModeTypes

Correction mode (NoCorr or Naive)