corelay.processor.laplacian

A module that contains processors for computing the graph Laplacian, which is mainly used for spectral embeddings.

Functions

Converts the specified matrix to a flat representation.

Classes

`Laplacian`	The abstract base class for processors that compute a graph Laplacian.
`RandomWalkNormalLaplacian`	A `Processor` that computes the normal random walk graph Laplacian.
`SymmetricNormalLaplacian`	A `Processor` that computes the normal symmetric graph Laplacian.

corelay.processor.laplacian.a1ifmat(matrix: ndarray[Any, Any] | matrix[Any, Any]) → ndarray[Any, Any][source]

Converts the specified matrix to a flat representation. If the matrix is already a flat NumPy array, it is returned as is.

Parameters:: matrix (numpy.ndarray[Any, Any] | numpy.matrix[Any, Any]) – The input matrix to be converted.
Returns:: Returns the converted matrix. If the input was a NumPy matrix, it is returned as a flat NumPy array. Otherwise, the input is returned as is.
Return type:: numpy.ndarray[Any, Any]

class corelay.processor.laplacian.Laplacian[source]

The abstract base class for processors that compute a graph Laplacian.

Parameters:

is_output (bool) – A value indicating whether this Laplacian processor is the output of a Pipeline. Defaults to False.
is_checkpoint (bool | None) – A value indicating whether check-pointed pipeline computations should start at this point, if there exists a previously computed checkpoint value. Defaults to False.
io (Storable | None) – An IO object that is used to cache intermediate results of the Pipeline, which can then be re-used in this run or in subsequent runs of the Pipeline. Defaults to an instance of NoStorage.

An collections.OrderedDict with all public class attributes, i.e., all class attributes not enclosed with double underscores.

class corelay.processor.laplacian.SymmetricNormalLaplacian[source]

A Processor that computes the normal symmetric graph Laplacian.

Parameters:

is_output (bool) – A value indicating whether this SymmetricNormalLaplacian Laplacian processor is the output of a Pipeline. Defaults to False.
is_checkpoint (bool | None) – A value indicating whether check-pointed pipeline computations should start at this point, if there exists a previously computed checkpoint value. Defaults to False.
io (Storable | None) – An IO object that is used to cache intermediate results of the Pipeline, which can then be re-used in this run or in subsequent runs of the Pipeline. Defaults to an instance of NoStorage.

function(data: Any) → Any[source]

Computes the symmetric normal graph Laplacian.

Parameters:: data (Any) – The graph affinity/similarity matrix. This can be a NumPy array or a sparse matrix.
Returns:: Returns the symmetric normal graph Laplacian, which is a sparse representation of the symmetric graph Laplacian matrix.
Return type:: Any

An collections.OrderedDict with all public class attributes, i.e., all class attributes not enclosed with double underscores.

class corelay.processor.laplacian.RandomWalkNormalLaplacian[source]

A Processor that computes the normal random walk graph Laplacian.

Parameters:

is_output (bool) – A value indicating whether this RandomWalkNormalLaplacian Laplacian processor is the output of a Pipeline. Defaults to False.
is_checkpoint (bool | None) – A value indicating whether check-pointed pipeline computations should start at this point, if there exists a previously computed checkpoint value. Defaults to False.
io (Storable | None) – An IO object that is used to cache intermediate results of the Pipeline, which can then be re-used in this run or in subsequent runs of the Pipeline. Defaults to an instance of NoStorage.

function(data: Any) → Any[source]

Computes the random walk normal graph Laplacian.

Parameters:: data (Any) – The graph affinity/similarity matrix. This can be a NumPy array or a sparse matrix.
Returns:: Returns the random walk normal graph Laplacian, which is a sparse representation of the random walk graph Laplacian matrix.
Return type:: Any

An collections.OrderedDict with all public class attributes, i.e., all class attributes not enclosed with double underscores.