import copy
from itertools import repeat, product
import torch
from torch_geometric.data import Dataset
[docs]class InMemoryDataset(Dataset):
r"""Dataset base class for creating graph datasets which fit completely
into memory.
See `here <https://pytorch-geometric.readthedocs.io/en/latest/notes/
create_dataset.html#creating-in-memory-datasets>`__ for the accompanying
tutorial.
Args:
root (string, optional): Root directory where the dataset should be
saved. (default: :obj:`None`)
transform (callable, optional): A function/transform that takes in an
:obj:`torch_geometric.data.Data` 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.Data` object and returns a
transformed version. The data object will be transformed before
being saved to disk. (default: :obj:`None`)
pre_filter (callable, optional): A function that takes in an
:obj:`torch_geometric.data.Data` object and returns a boolean
value, indicating whether the data object should be included in the
final dataset. (default: :obj:`None`)
"""
@property
def raw_file_names(self):
r"""The name of the files to find in the :obj:`self.raw_dir` folder in
order to skip the download."""
raise NotImplementedError
@property
def processed_file_names(self):
r"""The name of the files to find in the :obj:`self.processed_dir`
folder in order to skip the processing."""
raise NotImplementedError
[docs] def download(self):
r"""Downloads the dataset to the :obj:`self.raw_dir` folder."""
raise NotImplementedError
[docs] def process(self):
r"""Processes the dataset to the :obj:`self.processed_dir` folder."""
raise NotImplementedError
def __init__(self, root=None, transform=None, pre_transform=None,
pre_filter=None):
super(InMemoryDataset, self).__init__(root, transform, pre_transform,
pre_filter)
self.data, self.slices = None, None
@property
def num_classes(self):
r"""The number of classes in the dataset."""
y = self.data.y
return y.max().item() + 1 if y.dim() == 1 else y.size(1)
def len(self):
for item in self.slices.values():
return len(item) - 1
return 0
[docs] def get(self, idx):
data = self.data.__class__()
if hasattr(self.data, '__num_nodes__'):
data.num_nodes = self.data.__num_nodes__[idx]
for key in self.data.keys:
item, slices = self.data[key], self.slices[key]
start, end = slices[idx].item(), slices[idx + 1].item()
# print(slices[idx], slices[idx + 1])
if torch.is_tensor(item):
s = list(repeat(slice(None), item.dim()))
s[self.data.__cat_dim__(key, item)] = slice(start, end)
elif start + 1 == end:
s = slices[start]
else:
s = slice(start, end)
data[key] = item[s]
return data
[docs] def collate(self, data_list):
r"""Collates a python list of data objects to the internal storage
format of :class:`torch_geometric.data.InMemoryDataset`."""
keys = data_list[0].keys
data = data_list[0].__class__()
for key in keys:
data[key] = []
slices = {key: [0] for key in keys}
for item, key in product(data_list, keys):
data[key].append(item[key])
if torch.is_tensor(item[key]):
s = slices[key][-1] + item[key].size(
item.__cat_dim__(key, item[key]))
else:
s = slices[key][-1] + 1
slices[key].append(s)
if hasattr(data_list[0], '__num_nodes__'):
data.__num_nodes__ = []
for item in data_list:
data.__num_nodes__.append(item.num_nodes)
for key in keys:
item = data_list[0][key]
if torch.is_tensor(item):
data[key] = torch.cat(data[key],
dim=data.__cat_dim__(key, item))
elif isinstance(item, int) or isinstance(item, float):
data[key] = torch.tensor(data[key])
slices[key] = torch.tensor(slices[key], dtype=torch.long)
return data, slices
def copy(self, idx=None):
if idx is None:
data_list = [self.get(i) for i in range(len(self))]
else:
data_list = [self.get(i) for i in idx]
dataset = copy.copy(self)
dataset.__indices__ = None
dataset.data, dataset.slices = self.collate(data_list)
return dataset