topobench.data.loaders.graph package#

Submodules#

topobench.data.loaders.graph.hetero_datasets module#

Loaders for Heterophilous Graph datasets.

class topobench.data.loaders.graph.hetero_datasets.HeterophilousGraphDatasetLoader(parameters: DictConfig)[source]#

Bases: AbstractLoader

Load Heterophilous Graph datasets.

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_dir: Root directory for data

  • data_name: Name of the dataset

  • data_type: Type of the dataset (e.g., “heterophilous”)

load_dataset() → Dataset[source]#

Load Heterophilous Graph dataset.

Returns:
Dataset

The loaded Heterophilous Graph dataset.

Raises:
RuntimeError

If dataset loading fails.

topobench.data.loaders.graph.mantra_dataset module#

Loaders for Mantra dataset as graph.

class topobench.data.loaders.graph.mantra_dataset.MantraSimplicialDatasetLoader(parameters: DictConfig, **kwargs)[source]#

Bases: AbstractLoader

Load Mantra dataset with configurable parameters.

Note: for the simplicial datasets it is necessary to include DatasetLoader into the name of the class!

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_dir: Root directory for data

  • data_name: Name of the dataset

  • other relevant parameters

**kwargsdict

Additional keyword arguments.

load_dataset(**kwargs) → MantraDataset[source]#

Load the Citation Hypergraph dataset.

Parameters:
**kwargsdict

Additional keyword arguments for dataset initialization.

Returns:
CitationHypergraphDataset

The loaded Citation Hypergraph dataset with the appropriate data_dir.

Raises:
RuntimeError

If dataset loading fails.

topobench.data.loaders.graph.manual_graph_dataset_loader module#

Loader for manually loaded graph datasets.

class topobench.data.loaders.graph.manual_graph_dataset_loader.ManualGraphDatasetLoader(parameters: DictConfig)[source]#

Bases: AbstractLoader

Load manually provided graph datasets.

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_name: Name of the dataset

  • data_dir: Root directory for data

get_data_dir() → Path[source]#

Get the data directory.

Returns:
Path

The path to the dataset directory.

load_dataset() → Any[source]#

Load the manual graph dataset.

Returns:
DataloadDataset

The dataset object containing the manually loaded graph.

topobench.data.loaders.graph.modecule_datasets module#

Loaders for Molecule datasets (ZINC and AQSOL).

class topobench.data.loaders.graph.modecule_datasets.MoleculeDatasetLoader(parameters: DictConfig)[source]#

Bases: AbstractLoader

Load molecule datasets (ZINC and AQSOL) with predefined splits.

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_dir: Root directory for data

  • data_name: Name of the dataset

  • data_type: Type of the dataset (e.g., “molecule”)

get_data_dir() → Path[source]#

Get the data directory.

Returns:
Path

The path to the dataset directory.

load_dataset() → Dataset[source]#

Load the molecule dataset with predefined splits.

Returns:
Dataset

The combined dataset with predefined splits.

Raises:
RuntimeError

If dataset loading fails.

topobench.data.loaders.graph.ogbg_datasets module#

Loaders for Graph Property Prediction datasets.

class topobench.data.loaders.graph.ogbg_datasets.OGBGDatasetLoader(parameters: DictConfig)[source]#

Bases: AbstractLoader

Load molecule datasets (molhiv, molpcba, ppa) with predefined splits.

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_dir: Root directory for data

  • data_name: Name of the dataset

  • data_type: Type of the dataset (e.g., “molecule”)

get_data_dir() → Path[source]#

Get the data directory.

Returns:
Path

The path to the dataset directory.

load_dataset() → Dataset[source]#

Load the molecule dataset with predefined splits.

Returns:
Dataset

The combined dataset with predefined splits.

Raises:
RuntimeError

If dataset loading fails.

topobench.data.loaders.graph.planetoid_datasets module#

Loaders for PLANETOID datasets.

class topobench.data.loaders.graph.planetoid_datasets.PlanetoidDatasetLoader(parameters: DictConfig)[source]#

Bases: AbstractLoader

Load PLANETOID datasets.

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_dir: Root directory for data

  • data_name: Name of the dataset

  • data_type: Type of the dataset (e.g., “cocitation”)

load_dataset() → Dataset[source]#

Load Planetoid dataset.

Returns:
Dataset

The loaded Planetoid dataset.

Raises:
RuntimeError

If dataset loading fails.

topobench.data.loaders.graph.tu_datasets module#

Loaders for TU datasets.

class topobench.data.loaders.graph.tu_datasets.TUDatasetLoader(parameters: DictConfig)[source]#

Bases: AbstractLoader

Load TU datasets.

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_dir: Root directory for data

  • data_name: Name of the dataset

  • data_type: Type of the dataset (e.g., “graph_classification”)

load_dataset() → Dataset[source]#

Load TU dataset.

Returns:
Dataset

The loaded TU dataset.

Raises:
RuntimeError

If dataset loading fails.

topobench.data.loaders.graph.us_county_demos_dataset_loader module#

Loaders for US County Demos dataset.

class topobench.data.loaders.graph.us_county_demos_dataset_loader.USCountyDemosDatasetLoader(parameters: DictConfig)[source]#

Bases: AbstractLoader

Load US County Demos dataset with configurable year and task variable.

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_dir: Root directory for data

  • data_name: Name of the dataset

  • year: Year of the dataset (if applicable)

  • task_variable: Task variable for the dataset

load_dataset() → USCountyDemosDataset[source]#

Load the US County Demos dataset.

Returns:
USCountyDemosDataset

The loaded US County Demos dataset with the appropriate data_dir.

Raises:
RuntimeError

If dataset loading fails.

Module contents#

Init file for graph load module with automated loader discovery.

class topobench.data.loaders.graph.HeterophilousGraphDatasetLoader(parameters: DictConfig)#

Bases: AbstractLoader

Load Heterophilous Graph datasets.

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_dir: Root directory for data

  • data_name: Name of the dataset

  • data_type: Type of the dataset (e.g., “heterophilous”)

load_dataset() → Dataset#

Load Heterophilous Graph dataset.

Returns:
Dataset

The loaded Heterophilous Graph dataset.

Raises:
RuntimeError

If dataset loading fails.

class topobench.data.loaders.graph.MantraSimplicialDatasetLoader(parameters: DictConfig, **kwargs)#

Bases: AbstractLoader

Load Mantra dataset with configurable parameters.

Note: for the simplicial datasets it is necessary to include DatasetLoader into the name of the class!

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_dir: Root directory for data

  • data_name: Name of the dataset

  • other relevant parameters

**kwargsdict

Additional keyword arguments.

load_dataset(**kwargs) → MantraDataset#

Load the Citation Hypergraph dataset.

Parameters:
**kwargsdict

Additional keyword arguments for dataset initialization.

Returns:
CitationHypergraphDataset

The loaded Citation Hypergraph dataset with the appropriate data_dir.

Raises:
RuntimeError

If dataset loading fails.

class topobench.data.loaders.graph.ManualGraphDatasetLoader(parameters: DictConfig)#

Bases: AbstractLoader

Load manually provided graph datasets.

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_name: Name of the dataset

  • data_dir: Root directory for data

get_data_dir() → Path#

Get the data directory.

Returns:
Path

The path to the dataset directory.

load_dataset() → Any#

Load the manual graph dataset.

Returns:
DataloadDataset

The dataset object containing the manually loaded graph.

class topobench.data.loaders.graph.MoleculeDatasetLoader(parameters: DictConfig)#

Bases: AbstractLoader

Load molecule datasets (ZINC and AQSOL) with predefined splits.

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_dir: Root directory for data

  • data_name: Name of the dataset

  • data_type: Type of the dataset (e.g., “molecule”)

get_data_dir() → Path#

Get the data directory.

Returns:
Path

The path to the dataset directory.

load_dataset() → Dataset#

Load the molecule dataset with predefined splits.

Returns:
Dataset

The combined dataset with predefined splits.

Raises:
RuntimeError

If dataset loading fails.

class topobench.data.loaders.graph.OGBGDatasetLoader(parameters: DictConfig)#

Bases: AbstractLoader

Load molecule datasets (molhiv, molpcba, ppa) with predefined splits.

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_dir: Root directory for data

  • data_name: Name of the dataset

  • data_type: Type of the dataset (e.g., “molecule”)

get_data_dir() → Path#

Get the data directory.

Returns:
Path

The path to the dataset directory.

load_dataset() → Dataset#

Load the molecule dataset with predefined splits.

Returns:
Dataset

The combined dataset with predefined splits.

Raises:
RuntimeError

If dataset loading fails.

class topobench.data.loaders.graph.PlanetoidDatasetLoader(parameters: DictConfig)#

Bases: AbstractLoader

Load PLANETOID datasets.

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_dir: Root directory for data

  • data_name: Name of the dataset

  • data_type: Type of the dataset (e.g., “cocitation”)

load_dataset() → Dataset#

Load Planetoid dataset.

Returns:
Dataset

The loaded Planetoid dataset.

Raises:
RuntimeError

If dataset loading fails.

class topobench.data.loaders.graph.TUDatasetLoader(parameters: DictConfig)#

Bases: AbstractLoader

Load TU datasets.

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_dir: Root directory for data

  • data_name: Name of the dataset

  • data_type: Type of the dataset (e.g., “graph_classification”)

load_dataset() → Dataset#

Load TU dataset.

Returns:
Dataset

The loaded TU dataset.

Raises:
RuntimeError

If dataset loading fails.

class topobench.data.loaders.graph.USCountyDemosDatasetLoader(parameters: DictConfig)#

Bases: AbstractLoader

Load US County Demos dataset with configurable year and task variable.

Parameters:
parametersDictConfig
Configuration parameters containing:

  • data_dir: Root directory for data

  • data_name: Name of the dataset

  • year: Year of the dataset (if applicable)

  • task_variable: Task variable for the dataset

load_dataset() → USCountyDemosDataset#

Load the US County Demos dataset.

Returns:
USCountyDemosDataset

The loaded US County Demos dataset with the appropriate data_dir.

Raises:
RuntimeError

If dataset loading fails.

On this page

This Page