cogdl.datasets.han_data

Module Contents

Classes

HANDataset	The network datasets “ACM”, “DBLP” and “IMDB” from the
ACM_HANDataset	The network datasets “ACM”, “DBLP” and “IMDB” from the
DBLP_HANDataset	The network datasets “ACM”, “DBLP” and “IMDB” from the
IMDB_HANDataset	The network datasets “ACM”, “DBLP” and “IMDB” from the

Functions

untar(path, fname, deleteTar=True)	Unpacks the given archive file to the same directory, then (by default)
sample_mask(idx, l)	Create mask.

cogdl.datasets.han_data.untar(path, fname, deleteTar=True)

Unpacks the given archive file to the same directory, then (by default) deletes the archive file.

cogdl.datasets.han_data.sample_mask(idx, l)

Create mask.

class cogdl.datasets.han_data.HANDataset(root, name)

Bases: cogdl.data.Dataset

The network datasets “ACM”, “DBLP” and “IMDB” from the “Heterogeneous Graph Attention Network” paper.

Args:

root (string): Root directory where the dataset should be saved. name (string): The name of the dataset ("han-acm",

"han-dblp", "han-imdb").

property raw_file_names(self)

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

property processed_file_names(self)

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

read_gtn_data(self, folder)

get(self, idx)

Gets the data object at index idx.

apply_to_device(self, device)

download(self)

Downloads the dataset to the self.raw_dir folder.

process(self)

Processes the dataset to the self.processed_dir folder.

__repr__(self)

class cogdl.datasets.han_data.ACM_HANDataset

Bases: cogdl.datasets.han_data.HANDataset

The network datasets “ACM”, “DBLP” and “IMDB” from the “Heterogeneous Graph Attention Network” paper.

Args:

root (string): Root directory where the dataset should be saved. name (string): The name of the dataset ("han-acm",

"han-dblp", "han-imdb").

class cogdl.datasets.han_data.DBLP_HANDataset

Bases: cogdl.datasets.han_data.HANDataset

The network datasets “ACM”, “DBLP” and “IMDB” from the “Heterogeneous Graph Attention Network” paper.

Args:

root (string): Root directory where the dataset should be saved. name (string): The name of the dataset ("han-acm",

"han-dblp", "han-imdb").

class cogdl.datasets.han_data.IMDB_HANDataset

Bases: cogdl.datasets.han_data.HANDataset

The network datasets “ACM”, “DBLP” and “IMDB” from the “Heterogeneous Graph Attention Network” paper.

Args:

root (string): Root directory where the dataset should be saved. name (string): The name of the dataset ("han-acm",

"han-dblp", "han-imdb").