pgl.data_loader module: Some benchmark datasets.¶
This package implements some benchmark dataset for graph network and node representation learning.
-
class
pgl.data_loader.
CitationDataset
(name, symmetry_edges=True, self_loop=True)[source]¶ Bases:
object
Citation dataset helps to create data for citation dataset (Pubmed and Citeseer)
- Parameters
name – The name for the dataset (“pubmed” or “citeseer”)
symmetry_edges – Whether to create symmetry edges.
self_loop – Whether to contain self loop edges.
-
graph
¶ The
Graph
data object
-
y
¶ Labels for each nodes
-
num_classes
¶ Number of classes.
-
train_index
¶ The index for nodes in training set.
-
val_index
¶ The index for nodes in validation set.
-
test_index
¶ The index for nodes in test set.
-
class
pgl.data_loader.
CoraDataset
(symmetry_edges=True, self_loop=True)[source]¶ Bases:
object
Cora dataset implementation
- Parameters
symmetry_edges – Whether to create symmetry edges.
self_loop – Whether to contain self loop edges.
-
graph
¶ The
Graph
data object
-
y
¶ Labels for each nodes
-
num_classes
¶ Number of classes.
-
train_index
¶ The index for nodes in training set.
-
val_index
¶ The index for nodes in validation set.
-
test_index
¶ The index for nodes in test set.
-
class
pgl.data_loader.
ArXivDataset
(np_random_seed=123)[source]¶ Bases:
object
ArXiv dataset implementation
- Parameters
np_random_seed – The random seed for numpy.
-
graph
¶ The
Graph
data object.
-
class
pgl.data_loader.
BlogCatalogDataset
(symmetry_edges=True, self_loop=False)[source]¶ Bases:
object
BlogCatalog dataset implementation
- Parameters
symmetry_edges – Whether to create symmetry edges.
self_loop – Whether to contain self loop edges.
-
graph
¶ The
Graph
data object.
-
num_groups
¶ Number of classes.
-
train_index
¶ The index for nodes in training set.
-
test_index
¶ The index for nodes in validation set.