from typing import Optional, Callable, List
import os
import shutil
import os.path as osp
import torch
import numpy as np
from torch_geometric.data import (InMemoryDataset, HeteroData, download_url,
extract_zip)
[docs]class OGB_MAG(InMemoryDataset):
r"""The ogbn-mag dataset from the `"Open Graph Benchmark: Datasets for
Machine Learning on Graphs" <https://arxiv.org/abs/2005.00687>`_ paper.
ogbn-mag is a heterogeneous graph composed of a subset of the Microsoft
Academic Graph (MAG).
It contains four types of entities — papers (736,389 nodes), authors
(1,134,649 nodes), institutions (8,740 nodes), and fields of study
(59,965 nodes) — as well as four types of directed relations connecting two
types of entities.
Each paper is associated with a 128-dimensional :obj:`word2vec` feature
vector, while all other node types are not associated with any input
features.
The task is to predict the venue (conference or journal) of each paper.
In total, there are 349 different venues.
Args:
root (string): Root directory where the dataset should be saved.
preprocess (string, optional): Pre-processes the original
dataset by adding structural features (:obj:`"metapath2vec",
:obj:`"TransE") to featureless nodes. (default: :obj:`None`)
transform (callable, optional): A function/transform that takes in an
:obj:`torch_geometric.data.HeteroData` object and returns a
transformed version. The data object will be transformed before
every access. (default: :obj:`None`)
pre_transform (callable, optional): A function/transform that takes in
an :obj:`torch_geometric.data.HeteroData` object and returns a
transformed version. The data object will be transformed before
being saved to disk. (default: :obj:`None`)
"""
url = 'http://snap.stanford.edu/ogb/data/nodeproppred/mag.zip'
urls = {
'metapath2vec': ('https://data.pyg.org/datasets/'
'mag_metapath2vec_emb.zip'),
'transe': ('https://data.pyg.org/datasets/'
'mag_transe_emb.zip'),
}
def __init__(self, root: str, preprocess: Optional[str] = None,
transform: Optional[Callable] = None,
pre_transform: Optional[Callable] = None):
preprocess = None if preprocess is None else preprocess.lower()
self.preprocess = preprocess
assert self.preprocess in [None, 'metapath2vec', 'transe']
super().__init__(root, transform, pre_transform)
self.data, self.slices = torch.load(self.processed_paths[0])
@property
def num_classes(self) -> int:
return int(self.data['paper'].y.max()) + 1
@property
def raw_dir(self) -> str:
return osp.join(self.root, 'mag', 'raw')
@property
def processed_dir(self) -> str:
return osp.join(self.root, 'mag', 'processed')
@property
def raw_file_names(self) -> List[str]:
file_names = [
'node-feat', 'node-label', 'relations', 'split',
'num-node-dict.csv.gz'
]
if self.preprocess is not None:
file_names += [f'mag_{self.preprocess}_emb.pt']
return file_names
@property
def processed_file_names(self) -> str:
if self.preprocess is not None:
return f'data_{self.preprocess}.pt'
else:
return 'data.pt'
def download(self):
if not all([osp.exists(f) for f in self.raw_paths[:5]]):
path = download_url(self.url, self.raw_dir)
extract_zip(path, self.raw_dir)
for file_name in ['node-feat', 'node-label', 'relations']:
path = osp.join(self.raw_dir, 'mag', 'raw', file_name)
shutil.move(path, self.raw_dir)
path = osp.join(self.raw_dir, 'mag', 'split')
shutil.move(path, self.raw_dir)
path = osp.join(self.raw_dir, 'mag', 'raw', 'num-node-dict.csv.gz')
shutil.move(path, self.raw_dir)
shutil.rmtree(osp.join(self.raw_dir, 'mag'))
os.remove(osp.join(self.raw_dir, 'mag.zip'))
if self.preprocess is not None:
path = download_url(self.urls[self.preprocess], self.raw_dir)
extract_zip(path, self.raw_dir)
os.remove(path)
def process(self):
import pandas as pd
data = HeteroData()
path = osp.join(self.raw_dir, 'node-feat', 'paper', 'node-feat.csv.gz')
x_paper = pd.read_csv(path, compression='gzip', header=None,
dtype=np.float32).values
data['paper'].x = torch.from_numpy(x_paper)
path = osp.join(self.raw_dir, 'node-feat', 'paper', 'node_year.csv.gz')
year_paper = pd.read_csv(path, compression='gzip', header=None,
dtype=np.int64).values
data['paper'].year = torch.from_numpy(year_paper).view(-1)
path = osp.join(self.raw_dir, 'node-label', 'paper',
'node-label.csv.gz')
y_paper = pd.read_csv(path, compression='gzip', header=None,
dtype=np.int64).values.flatten()
data['paper'].y = torch.from_numpy(y_paper)
if self.preprocess is None:
path = osp.join(self.raw_dir, 'num-node-dict.csv.gz')
num_nodes_df = pd.read_csv(path, compression='gzip')
for node_type in ['author', 'institution', 'field_of_study']:
data[node_type].num_nodes = num_nodes_df[node_type].tolist()[0]
else:
emb_dict = torch.load(self.raw_paths[-1])
for key, value in emb_dict.items():
if key != 'paper':
data[key].x = value
for edge_type in [('author', 'affiliated_with', 'institution'),
('author', 'writes', 'paper'),
('paper', 'cites', 'paper'),
('paper', 'has_topic', 'field_of_study')]:
f = '___'.join(edge_type)
path = osp.join(self.raw_dir, 'relations', f, 'edge.csv.gz')
edge_index = pd.read_csv(path, compression='gzip', header=None,
dtype=np.int64).values
edge_index = torch.from_numpy(edge_index).t().contiguous()
data[edge_type].edge_index = edge_index
for f, v in [('train', 'train'), ('valid', 'val'), ('test', 'test')]:
path = osp.join(self.raw_dir, 'split', 'time', 'paper',
f'{f}.csv.gz')
idx = pd.read_csv(path, compression='gzip', header=None,
dtype=np.int64).values.flatten()
idx = torch.from_numpy(idx)
mask = torch.zeros(data['paper'].num_nodes, dtype=torch.bool)
mask[idx] = True
data['paper'][f'{v}_mask'] = mask
if self.pre_transform is not None:
data = self.pre_transform(data)
torch.save(self.collate([data]), self.processed_paths[0])
def __repr__(self) -> str:
return 'ogbn-mag()'