topobench.transforms.data_manipulations package

Submodules

topobench.transforms.data_manipulations.calculate_simplicial_curvature module

A transform that calculates the simplicial curvature of the input graph.

class topobench.transforms.data_manipulations.calculate_simplicial_curvature.CalculateSimplicialCurvature(**kwargs)

Bases: BaseTransform

A transform that calculates the simplicial curvature of the input graph.

Parameters:

**kwargsoptional

Parameters for the transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

one_cell_curvature(data: Data) → Data

Calculate the one cell curvature of the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

Data with the one cell curvature.

two_cell_curvature(data: Data) → Data

Calculate the two cell curvature of the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

Data with the two cell curvature.

zero_cell_curvature(data: Data) → Data

Calculate the zero cell curvature of the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

Data with the zero cell curvature.

topobench.transforms.data_manipulations.equal_gaus_features module

This module contains a transform that generates equal Gaussian features for all nodes in the input graph.

class topobench.transforms.data_manipulations.equal_gaus_features.EqualGausFeatures(**kwargs)

Bases: BaseTransform

A transform that generates equal Gaussian features for all nodes.

Parameters:

**kwargsoptional

Additional arguments for the class. It should contain the following keys: - mean (float): The mean of the Gaussian distribution. - std (float): The standard deviation of the Gaussian distribution. - num_features (int): The number of features to generate.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

topobench.transforms.data_manipulations.group_homophily module

A transform that canculates group combinatorial homophily of the input hypergraph.

class topobench.transforms.data_manipulations.group_homophily.GroupCombinatorialHomophily(**kwargs)

Bases: BaseTransform

Calculates group combinatorial homophily of the input hypergraph.

This transformation implements the methodology from the paper: “Combinatorial Characterizations and Impossibilities for Higher-order Homophily”. It computes homophily metrics for hypergraphs by analyzing the relationship between node labels within hyperedges.

Parameters:

**kwargsdict, optional

Additional parameters for the transform. - top_k : int, default=3

Number of top hyperedge cardinalities to analyze.

Attributes:

typestr

Identifier for the transform type.

top_kint

Number of top hyperedge cardinalities to analyze.

calculate_D_matrix(H, labels, he_cardinalities, unique_labels, class_node_idxs)

Calculate the degree matrices D and D_t for the hypergraph.

Parameters:

Htorch.Tensor

Dense incidence matrix of the hypergraph.

labelstorch.Tensor

Node labels.

he_cardinalitiestorch.Tensor

Cardinality of each hyperedge.

unique_labelsdict

Dictionary mapping labels to their counts.

class_node_idxsdict

Dictionary mapping labels to node indices.

Returns:

tuple[torch.Tensor, torch.Tensor]

• D_t_class : Type-t degree distribution matrix for each class

• D : Degree matrix counting same-label nodes in hyperedges

calculate_affinity_score(n_nodes, X_mod, t, k)

Calculate affinity score.

Parameters:

n_nodesint

Total number of nodes.

X_modint

Total number of nodes in a class.

tint

Type-t degree.

kint

Max hyperedge cardinality.

Returns:

torch.Tensor

The affinity matrix.

calculate_baseline_matrix(he_cardinalities, unique_labels, class_node_idxs, count_labels, n_nodes)

Calculate the baseline affinity matrix for comparison.

Parameters:

he_cardinalitiestorch.Tensor

Cardinality of each hyperedge.

unique_labelsdict

Dictionary mapping labels to their counts.

class_node_idxsdict

Dictionary mapping labels to node indices.

count_labelstorch.Tensor

Count of nodes for each label.

n_nodesint

Total number of nodes in the hypergraph.

Returns:

torch.Tensor

Baseline matrix containing expected affinity scores for each class and degree type.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

topobench.transforms.data_manipulations.identity_transform module

Identity transform that does nothing to the input data.

class topobench.transforms.data_manipulations.identity_transform.IdentityTransform(**kwargs)

Bases: BaseTransform

An identity transform that does nothing to the input data.

Parameters:

**kwargsoptional

Parameters for the base transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The same data.

topobench.transforms.data_manipulations.infere_knn_connectivity module

InfereKNNConnectivity class definition.

class topobench.transforms.data_manipulations.infere_knn_connectivity.InfereKNNConnectivity(**kwargs)

Bases: BaseTransform

Transform to infer point cloud connectivity.

The transform generates the k-nearest neighbor connectivity of the input point cloud.

Parameters:

**kwargsoptional

Parameters for the base transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

topobench.transforms.data_manipulations.infere_radius_connectivity module

InfereRadiusConnectivity class definition.

class topobench.transforms.data_manipulations.infere_radius_connectivity.InfereRadiusConnectivity(**kwargs)

Bases: BaseTransform

Class to infer point cloud connectivity.

The transform generates the radius connectivity of the input point cloud.

Parameters:

**kwargsoptional

Parameters for the base transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

topobench.transforms.data_manipulations.keep_only_connected_component module

KeepOnlyConnectedComponent class definition.

class topobench.transforms.data_manipulations.keep_only_connected_component.KeepOnlyConnectedComponent(**kwargs)

Bases: BaseTransform

Class to keep only the largest connected components of the input graph.

Parameters:

**kwargsoptional

Parameters for the base transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

topobench.transforms.data_manipulations.keep_selected_data_fields module

A transform that keeps only the selected fields of the input data.

class topobench.transforms.data_manipulations.keep_selected_data_fields.KeepSelectedDataFields(**kwargs)

Bases: BaseTransform

A transform that keeps only the selected fields of the input data.

Parameters:

**kwargsoptional

Parameters for the base transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

topobench.transforms.data_manipulations.mp_homophily module

A transform that canculates message passing homophily of the input hypergraph.

class topobench.transforms.data_manipulations.mp_homophily.MessagePassingHomophily(**kwargs)

Bases: BaseTransform

Calculates message passing homophily of the input data.

This transformation implements the methodology from the paper: “Hypergraph Neural Networks through the Lens of Message Passing: A Common Perspective to Homophily and Architecture Design”. It computes homophily metrics for hypergraphs by analyzing the relationship between node labels within hyperedges.

Parameters:

**kwargsdict, optional

Additional parameters for the transform. - top_k : int, default=3

Number of top hyperedge cardinalities to analyze.

Attributes:

typestr

Identifier for the transform type.

top_kint

Number of top hyperedge cardinalities to analyze.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

topobench.transforms.data_manipulations.node_degrees module

Node degrees transform.

class topobench.transforms.data_manipulations.node_degrees.NodeDegrees(**kwargs)

Bases: BaseTransform

A transform that calculates the node degrees of the input graph.

Parameters:

**kwargsoptional

Parameters for the base transform.

calculate_node_degrees(data: Data, field: str) → Data

Calculate the node degrees of the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

fieldstr

The field to calculate the node degrees.

Returns:

torch_geometric.data.Data

The transformed data.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

topobench.transforms.data_manipulations.node_features_to_float module

A transform that converts the node features of the input graph to float.

class topobench.transforms.data_manipulations.node_features_to_float.NodeFeaturesToFloat(**kwargs)

Bases: BaseTransform

A transform that converts the node features of the input graph to float.

Parameters:

**kwargsoptional

Parameters for the base transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

topobench.transforms.data_manipulations.one_hot_degree_features module

One hot degree features transform.

class topobench.transforms.data_manipulations.one_hot_degree_features.OneHotDegreeFeatures(max_degree: int, degrees_fields: str, features_fields: str, cat: bool = False, **kwargs)

Bases: BaseTransform

Class for one hot degree features transform.

A transform that adds the node degree as one hot encodings to the node features.

Parameters:

max_degreeint

The maximum degree of the graph.

degrees_fieldsstr

The field containing the node degrees.

features_fieldsstr

The field containing the node features.

catbool, optional

If set to True, the one hot encodings are concatenated to the node features (default: False).

**kwargsoptional

Additional arguments for the class.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

topobench.transforms.data_manipulations.redefine_simplicial_neighbourhoods module

An transform that redifines simplicial complex neighbourhood.

class topobench.transforms.data_manipulations.redefine_simplicial_neighbourhoods.RedefineSimplicialNeighbourhoods(**kwargs)

Bases: BaseTransform

An transform that redifines simplicial complex neighbourhood.

Parameters:

**kwargsoptional

Parameters for the base transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The same data.

Module contents

Data manipulations module with automated exports.

class topobench.transforms.data_manipulations.CalculateSimplicialCurvature(**kwargs)

Bases: BaseTransform

A transform that calculates the simplicial curvature of the input graph.

Parameters:

**kwargsoptional

Parameters for the transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

one_cell_curvature(data: Data) → Data

Calculate the one cell curvature of the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

Data with the one cell curvature.

two_cell_curvature(data: Data) → Data

Calculate the two cell curvature of the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

Data with the two cell curvature.

zero_cell_curvature(data: Data) → Data

Calculate the zero cell curvature of the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

Data with the zero cell curvature.

class topobench.transforms.data_manipulations.EqualGausFeatures(**kwargs)

Bases: BaseTransform

A transform that generates equal Gaussian features for all nodes.

Parameters:

**kwargsoptional

Additional arguments for the class. It should contain the following keys: - mean (float): The mean of the Gaussian distribution. - std (float): The standard deviation of the Gaussian distribution. - num_features (int): The number of features to generate.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

class topobench.transforms.data_manipulations.GroupCombinatorialHomophily(**kwargs)

Bases: BaseTransform

Calculates group combinatorial homophily of the input hypergraph.

This transformation implements the methodology from the paper: “Combinatorial Characterizations and Impossibilities for Higher-order Homophily”. It computes homophily metrics for hypergraphs by analyzing the relationship between node labels within hyperedges.

Parameters:

**kwargsdict, optional

Additional parameters for the transform. - top_k : int, default=3

Number of top hyperedge cardinalities to analyze.

Attributes:

typestr

Identifier for the transform type.

top_kint

Number of top hyperedge cardinalities to analyze.

calculate_D_matrix(H, labels, he_cardinalities, unique_labels, class_node_idxs)

Calculate the degree matrices D and D_t for the hypergraph.

Parameters:

Htorch.Tensor

Dense incidence matrix of the hypergraph.

labelstorch.Tensor

Node labels.

he_cardinalitiestorch.Tensor

Cardinality of each hyperedge.

unique_labelsdict

Dictionary mapping labels to their counts.

class_node_idxsdict

Dictionary mapping labels to node indices.

Returns:

tuple[torch.Tensor, torch.Tensor]

• D_t_class : Type-t degree distribution matrix for each class

• D : Degree matrix counting same-label nodes in hyperedges

calculate_affinity_score(n_nodes, X_mod, t, k)

Calculate affinity score.

Parameters:

n_nodesint

Total number of nodes.

X_modint

Total number of nodes in a class.

tint

Type-t degree.

kint

Max hyperedge cardinality.

Returns:

torch.Tensor

The affinity matrix.

calculate_baseline_matrix(he_cardinalities, unique_labels, class_node_idxs, count_labels, n_nodes)

Calculate the baseline affinity matrix for comparison.

Parameters:

he_cardinalitiestorch.Tensor

Cardinality of each hyperedge.

unique_labelsdict

Dictionary mapping labels to their counts.

class_node_idxsdict

Dictionary mapping labels to node indices.

count_labelstorch.Tensor

Count of nodes for each label.

n_nodesint

Total number of nodes in the hypergraph.

Returns:

torch.Tensor

Baseline matrix containing expected affinity scores for each class and degree type.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

class topobench.transforms.data_manipulations.IdentityTransform(**kwargs)

Bases: BaseTransform

An identity transform that does nothing to the input data.

Parameters:

**kwargsoptional

Parameters for the base transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The same data.

class topobench.transforms.data_manipulations.InfereKNNConnectivity(**kwargs)

Bases: BaseTransform

Transform to infer point cloud connectivity.

The transform generates the k-nearest neighbor connectivity of the input point cloud.

Parameters:

**kwargsoptional

Parameters for the base transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

class topobench.transforms.data_manipulations.InfereRadiusConnectivity(**kwargs)

Bases: BaseTransform

Class to infer point cloud connectivity.

The transform generates the radius connectivity of the input point cloud.

Parameters:

**kwargsoptional

Parameters for the base transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

class topobench.transforms.data_manipulations.KeepOnlyConnectedComponent(**kwargs)

Bases: BaseTransform

Class to keep only the largest connected components of the input graph.

Parameters:

**kwargsoptional

Parameters for the base transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

class topobench.transforms.data_manipulations.KeepSelectedDataFields(**kwargs)

Bases: BaseTransform

A transform that keeps only the selected fields of the input data.

Parameters:

**kwargsoptional

Parameters for the base transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

class topobench.transforms.data_manipulations.MessagePassingHomophily(**kwargs)

Bases: BaseTransform

Calculates message passing homophily of the input data.

This transformation implements the methodology from the paper: “Hypergraph Neural Networks through the Lens of Message Passing: A Common Perspective to Homophily and Architecture Design”. It computes homophily metrics for hypergraphs by analyzing the relationship between node labels within hyperedges.

Parameters:

**kwargsdict, optional

Additional parameters for the transform. - top_k : int, default=3

Number of top hyperedge cardinalities to analyze.

Attributes:

typestr

Identifier for the transform type.

top_kint

Number of top hyperedge cardinalities to analyze.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

class topobench.transforms.data_manipulations.NodeDegrees(**kwargs)

Bases: BaseTransform

A transform that calculates the node degrees of the input graph.

Parameters:

**kwargsoptional

Parameters for the base transform.

calculate_node_degrees(data: Data, field: str) → Data

Calculate the node degrees of the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

fieldstr

The field to calculate the node degrees.

Returns:

torch_geometric.data.Data

The transformed data.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

class topobench.transforms.data_manipulations.NodeFeaturesToFloat(**kwargs)

Bases: BaseTransform

A transform that converts the node features of the input graph to float.

Parameters:

**kwargsoptional

Parameters for the base transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

class topobench.transforms.data_manipulations.OneHotDegreeFeatures(max_degree: int, degrees_fields: str, features_fields: str, cat: bool = False, **kwargs)

Bases: BaseTransform

Class for one hot degree features transform.

A transform that adds the node degree as one hot encodings to the node features.

Parameters:

max_degreeint

The maximum degree of the graph.

degrees_fieldsstr

The field containing the node degrees.

features_fieldsstr

The field containing the node features.

catbool, optional

If set to True, the one hot encodings are concatenated to the node features (default: False).

**kwargsoptional

Additional arguments for the class.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The transformed data.

class topobench.transforms.data_manipulations.RedefineSimplicialNeighbourhoods(**kwargs)

Bases: BaseTransform

An transform that redifines simplicial complex neighbourhood.

Parameters:

**kwargsoptional

Parameters for the base transform.

forward(data: Data)

Apply the transform to the input data.

Parameters:

datatorch_geometric.data.Data

The input data.

Returns:

torch_geometric.data.Data

The same data.