data

class cogdl.data.Data(x=None, edge_index=None, edge_attr=None, y=None, pos=None, **kwargs)

Bases: object

A plain old python object modeling a single graph with various (optional) attributes:

Args:

x (Tensor, optional): Node feature matrix with shape :obj:`[num_nodes,

num_node_features]`. (default: None)

edge_index (LongTensor, optional): Graph connectivity in COO format

with shape [2, num_edges]. (default: None)

edge_attr (Tensor, optional): Edge feature matrix with shape

[num_edges, num_edge_features]. (default: None)

y (Tensor, optional): Graph or node targets with arbitrary shape.

(default: None)

pos (Tensor, optional): Node position matrix with shape

[num_nodes, num_dimensions]. (default: None)

The data object is not restricted to these attributes and can be extented by any other additional data.

apply(func, *keys)

Applies the function func to all attributes *keys. If *keys is not given, func is applied to all present attributes.

cat_dim(key, value)

Returns the dimension in which the attribute key with content value gets concatenated when creating batches.

Note

This method is for internal use only, and should only be overridden if the batch concatenation process is corrupted for a specific data attribute.

clone()

contiguous(*keys)

Ensures a contiguous memory layout for all attributes *keys. If *keys is not given, all present attributes are ensured to have a contiguous memory layout.

cuda(*keys)

edge_subgraph(edge_idx, require_idx=False)

Return the induced edge subgraph.

static from_dict(dictionary)

Creates a data object from a python dictionary.

static from_pyg_data(data)

is_coalesced()

Returns True, if edge indices are ordered and do not contain duplicate entries.

keys

Returns all names of graph attributes.

num_classes

num_edges

Returns the number of edges in the graph.

num_features

Returns the number of features per node in the graph.

num_nodes

sample_adj(batch, size=-1, replace=True)

subgraph(node_idx)

Return the induced node subgraph.

to(device, *keys)

Performs tensor dtype and/or device conversion to all attributes *keys. If *keys is not given, the conversion is applied to all present attributes.

class cogdl.data.Batch(batch=None, **kwargs)

Bases: cogdl.data.data.Data

A plain old python object modeling a batch of graphs as one big (dicconnected) graph. With cogdl.data.Data being the base class, all its methods can also be used here. In addition, single graphs can be reconstructed via the assignment vector batch, which maps each node to its respective graph identifier.

cumsum(key, item)

If True, the attribute key with content item should be added up cumulatively before concatenated together.

Note

This method is for internal use only, and should only be overridden if the batch concatenation process is corrupted for a specific data attribute.

static from_data_list(data_list, follow_batch=[])

Constructs a batch object from a python list holding torch_geometric.data.Data objects. The assignment vector batch is created on the fly. Additionally, creates assignment batch vectors for each key in follow_batch.

num_graphs

Returns the number of graphs in the batch.

class cogdl.data.Dataset(root, transform=None, pre_transform=None, pre_filter=None)

Bases: torch.utils.data.dataset.Dataset

Dataset base class for creating graph datasets. See here for the accompanying tutorial.

Args:

root (string): Root directory where the dataset should be saved. transform (callable, optional): A function/transform that takes in an

cogdl.data.Data object and returns a transformed version. The data object will be transformed before every access. (default: None)

pre_transform (callable, optional): A function/transform that takes in

an cogdl.data.Data object and returns a transformed version. The data object will be transformed before being saved to disk. (default: None)

pre_filter (callable, optional): A function that takes in an

cogdl.data.Data object and returns a boolean value, indicating whether the data object should be included in the final dataset. (default: None)

static add_args(parser)

Add dataset-specific arguments to the parser.

download()

Downloads the dataset to the self.raw_dir folder.

get(idx)

Gets the data object at index idx.

get_evaluator()

get_loss_fn()

num_classes

The number of classes in the dataset.

num_features

Returns the number of features per node in the graph.

process()

Processes the dataset to the self.processed_dir folder.

processed_file_names

The name of the files to find in the self.processed_dir folder in order to skip the processing.

processed_paths

The filepaths to find in the self.processed_dir folder in order to skip the processing.

raw_file_names

The name of the files to find in the self.raw_dir folder in order to skip the download.

raw_paths

The filepaths to find in order to skip the download.

class cogdl.data.DataLoader(dataset, batch_size=1, shuffle=True, **kwargs)

Bases: torch.utils.data.dataloader.DataLoader

Data loader which merges data objects from a cogdl.data.dataset to a mini-batch.

Args:

dataset (Dataset): The dataset from which to load the data. batch_size (int, optional): How may samples per batch to load.

(default: 1)

shuffle (bool, optional): If set to True, the data will be

reshuffled at every epoch (default: True)

static collate_fn(batch)

class cogdl.data.MultiGraphDataset(root=None, transform=None, pre_transform=None, pre_filter=None)

Bases: cogdl.data.dataset.Dataset

static from_data_list(data_list)

Borrowed from PyG

get(idx)

Gets the data object at index idx.

len()

num_classes

The number of classes in the dataset.