TwitterDataset(root, name, transform=None, pre_transform=None, pre_filter=None)

Bases: InMemoryDataset

Twitter social network dataset loader for graph-based analysis.

Parameters:
  • root (str) –

    Root directory where the dataset should be saved

  • name (str) –

    Name of the Twitter dataset

  • transform (callable, default: None ) –

    Function/transform that takes in a Data object and returns a transformed version. Default: None

  • pre_transform (callable, default: None ) –

    Function/transform to be applied to the data object before saving. Default: None

  • pre_filter (callable, default: None ) –

    Function that takes in a Data object and returns a boolean value, indicating whether the data object should be included. Default: None
Notes

Dataset Structure:

  • Nodes represent Twitter users
  • Edges represent user interactions/connections
  • Node features from user attributes
  • Labels indicate user categories (0-based indexing)
  • Includes train/val/test splits (80/10/10)
processed_file_names property

Names of processed data files.

Returns:
  • list[str] –

    List of processed file names
Notes

Processed files:

  • data.pt: Contains processed PyTorch Geometric data object
raw_file_names property

Names of required raw files.

Returns:
  • list[str] –

    List of required raw file names
Notes

Required files:

  • data.pt: PyTorch file containing graph data
download()

Download raw data files.

Notes

Empty implementation - data should be manually placed in raw directory

process()

Process raw data into PyTorch Geometric Data format.

Notes

Processing Steps:

  • Load dataset file:

    • Node features (x)
    • Edge indices
    • Node labels

  • Adjust labels:

    • Convert to 0-based indexing
    • Handle label shifts

  • Create Data object with:

    • Edge indices
    • Node features
    • Node labels
    • Train/val/test masks

  • Generate splits:

    • Random permutation
    • Training (80%)
    • Validation (10%)
    • Testing (10%)

  • Create masks:

    • Boolean tensors
    • Node-wise split indicators

  • Optional processing:

    • Apply pre-transform if specified
    • Handle eigenvalue computation

  • Data organization:

    • Collate into list
    • Save processed format

Features:

  • Label adjustment
  • Random split generation
  • Mask creation
  • Optional pre-transform support