Cora

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

Bases: dhg.data.base.BaseData

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

The content of the Cora dataset includes the following:

  • num_classes: The number of classes: \(7\).

  • num_vertices: The number of vertices: \(2,708\).

  • num_edges: The number of edges: \(10,858\).

  • dim_features: The dimension of features: \(1,433\).

  • features: The vertex feature matrix. torch.Tensor with size \((2,708 \times 1,433)\).

  • edge_list: The edge list. List with length \((10,858 \times 2)\).

  • labels: The label list. torch.LongTensor with size \((2,708, )\).

  • train_mask: The train mask. torch.BoolTensor with size \((2,708, )\).

  • val_mask: The validation mask. torch.BoolTensor with size \((2,708, )\).

  • test_mask: The test mask. torch.BoolTensor with size \((2,708, )\).

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.