cogdl.datasets.gatne

Module Contents

Classes

GatneDataset

The network datasets “Amazon”, “Twitter” and “YouTube” from the

AmazonDataset

The network datasets “Amazon”, “Twitter” and “YouTube” from the

TwitterDataset

The network datasets “Amazon”, “Twitter” and “YouTube” from the

YouTubeDataset

The network datasets “Amazon”, “Twitter” and “YouTube” from the

Functions

read_gatne_data(folder)

cogdl.datasets.gatne.read_gatne_data(folder)[source]
class cogdl.datasets.gatne.GatneDataset(root, name)[source]

Bases: cogdl.data.Dataset

The network datasets “Amazon”, “Twitter” and “YouTube” from the “Representation Learning for Attributed Multiplex Heterogeneous Network” paper.

Args:

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

"Twitter", "YouTube").

url = https://github.com/THUDM/GATNE/raw/master/data[source]
property raw_file_names(self)[source]

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

property processed_file_names(self)[source]

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

get(self, idx)[source]

Gets the data object at index idx.

download(self)[source]

Downloads the dataset to the self.raw_dir folder.

process(self)[source]

Processes the dataset to the self.processed_dir folder.

__repr__(self)[source]
class cogdl.datasets.gatne.AmazonDataset[source]

Bases: cogdl.datasets.gatne.GatneDataset

The network datasets “Amazon”, “Twitter” and “YouTube” from the “Representation Learning for Attributed Multiplex Heterogeneous Network” paper.

Args:

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

"Twitter", "YouTube").

class cogdl.datasets.gatne.TwitterDataset[source]

Bases: cogdl.datasets.gatne.GatneDataset

The network datasets “Amazon”, “Twitter” and “YouTube” from the “Representation Learning for Attributed Multiplex Heterogeneous Network” paper.

Args:

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

"Twitter", "YouTube").

class cogdl.datasets.gatne.YouTubeDataset[source]

Bases: cogdl.datasets.gatne.GatneDataset

The network datasets “Amazon”, “Twitter” and “YouTube” from the “Representation Learning for Attributed Multiplex Heterogeneous Network” paper.

Args:

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

"Twitter", "YouTube").