Citeseer

class dhg.data.Citeseer(data_root=None)[source]

Bases: dhg.data.base.BaseData

The Citeseer dataset is a citation network dataset for vertex classification task. More details can be found in this website.

  • num_classes: The number of classes: \(6\).

  • num_vertices: The number of vertices: \(3,327\).

  • num_edges: The number of edges: \(9,464\).

  • dim_features: The dimension of features: \(3,703\).

  • features: The vertex feature matrix. torch.Tensor with size \((3,327 \times 3,703)\).

  • edge_list: The edge list. List with length \((9,464 \times 2)\).

  • labels: The label list. torch.LongTensor with size \((3,327, )\).

  • train_mask: The train mask. torch.BoolTensor with size \((3,327, )\).

  • val_mask: The validation mask. torch.BoolTensor with size \((3,327, )\).

  • test_mask: The test mask. torch.BoolTensor with size \((3,327, )\).

Parameters

data_root (str, optional) – The data_root has stored the data. If set to None, this function will auto-download from server and save into the default direction ~/.dhg/datasets/. Defaults to None.