citeseer

Bases: graph_dataloader

A dataloader class for the Citeseer dataset.

This class extends graph_dataloader to handle the Citeseer graph dataset, which is another benchmark dataset for graph-based machine learning tasks.

Attributes:

Name	Type	Description
data_profile	dict	Metadata and download links specific to the Citeseer dataset.
graph	graph	The loaded graph structure for the Citeseer dataset.

Methods:

Name	Description
__init__	Initializes the dataloader for the Citeseer dataset.
get_train_test_idx	Generates train and test indices for the Citeseer dataset.

Source code in tinybig/data/graph_dataloader.py

class citeseer(graph_dataloader):
    """
    A dataloader class for the Citeseer dataset.

    This class extends `graph_dataloader` to handle the Citeseer graph dataset,
    which is another benchmark dataset for graph-based machine learning tasks.

    Attributes
    ----------
    data_profile: dict
        Metadata and download links specific to the Citeseer dataset.
    graph: graph_class
        The loaded graph structure for the Citeseer dataset.

    Methods
    -------
    __init__(name: str = 'citeseer', train_batch_size: int = 64, test_batch_size: int = 64, ...)
        Initializes the dataloader for the Citeseer dataset.
    get_train_test_idx(X: torch.Tensor = None, y: torch.Tensor = None, ...)
        Generates train and test indices for the Citeseer dataset.
    """
    def __init__(self, name: str = 'citeseer', train_batch_size: int = 64, test_batch_size: int = 64, *args, **kwargs):
        """
        Initializes the dataloader for the Citeseer dataset.

        Parameters
        ----------
        name: str, default = 'citeseer'
            The name of the dataset.
        train_batch_size: int, default = 64
            Batch size for the training dataset.
        test_batch_size: int, default = 64
            Batch size for the testing dataset.

        Returns
        -------
        None
        """
        super().__init__(data_profile=CITESEER_DATA_PROFILE, name=name, train_batch_size=train_batch_size, test_batch_size=test_batch_size)

    def get_train_test_idx(self, X: torch.Tensor = None, y: torch.Tensor = None, *args, **kwargs):
        """
        Generates train and test indices for the Citeseer dataset.

        Parameters
        ----------
        X: torch.Tensor, optional
            Node features (not used in this method).
        y: torch.Tensor, optional
            Labels (not used in this method).

        Returns
        -------
        tuple
            Train indices (`torch.LongTensor`) and test indices (`torch.LongTensor`).

        Notes
        -----
        The train indices are predefined as the first 120 nodes.
        The test indices are predefined as nodes 200 to 1199.
        """
        train_idx = torch.LongTensor(range(120))
        test_idx = torch.LongTensor(range(200, 1200))
        return train_idx, test_idx

__init__(name='citeseer', train_batch_size=64, test_batch_size=64, *args, **kwargs)

Initializes the dataloader for the Citeseer dataset.

Parameters:

Name	Type	Description	Default
name	str	The name of the dataset.	'citeseer'
train_batch_size	int	Batch size for the training dataset.	64
test_batch_size	int	Batch size for the testing dataset.	64

Returns:

Type	Description
None

Source code in tinybig/data/graph_dataloader.py

def __init__(self, name: str = 'citeseer', train_batch_size: int = 64, test_batch_size: int = 64, *args, **kwargs):
    """
    Initializes the dataloader for the Citeseer dataset.

    Parameters
    ----------
    name: str, default = 'citeseer'
        The name of the dataset.
    train_batch_size: int, default = 64
        Batch size for the training dataset.
    test_batch_size: int, default = 64
        Batch size for the testing dataset.

    Returns
    -------
    None
    """
    super().__init__(data_profile=CITESEER_DATA_PROFILE, name=name, train_batch_size=train_batch_size, test_batch_size=test_batch_size)

get_train_test_idx(X=None, y=None, *args, **kwargs)

Generates train and test indices for the Citeseer dataset.

Parameters:

Name	Type	Description	Default
X	Tensor	Node features (not used in this method).	None
y	Tensor	Labels (not used in this method).	None

Returns:

Type	Description
tuple	Train indices (torch.LongTensor) and test indices (torch.LongTensor).

Notes

The train indices are predefined as the first 120 nodes. The test indices are predefined as nodes 200 to 1199.

Source code in tinybig/data/graph_dataloader.py

def get_train_test_idx(self, X: torch.Tensor = None, y: torch.Tensor = None, *args, **kwargs):
    """
    Generates train and test indices for the Citeseer dataset.

    Parameters
    ----------
    X: torch.Tensor, optional
        Node features (not used in this method).
    y: torch.Tensor, optional
        Labels (not used in this method).

    Returns
    -------
    tuple
        Train indices (`torch.LongTensor`) and test indices (`torch.LongTensor`).

    Notes
    -----
    The train indices are predefined as the first 120 nodes.
    The test indices are predefined as nodes 200 to 1199.
    """
    train_idx = torch.LongTensor(range(120))
    test_idx = torch.LongTensor(range(200, 1200))
    return train_idx, test_idx