pyg-nightly 2.7.0.dev20250502__py3-none-any.whl → 2.7.0.dev20250504__py3-none-any.whl

{pyg_nightly-2.7.0.dev20250502.dist-info → pyg_nightly-2.7.0.dev20250504.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyg-nightly
-Version: 2.7.0.dev20250502
+Version: 2.7.0.dev20250504
 Summary: Graph Neural Network Library for PyTorch
 Keywords: deep-learning,pytorch,geometric-deep-learning,graph-neural-networks,graph-convolutional-networks
 Author-email: Matthias Fey <matthias@pyg.org>

{pyg_nightly-2.7.0.dev20250502.dist-info → pyg_nightly-2.7.0.dev20250504.dist-info}/RECORD

@@ -1,4 +1,4 @@
-torch_geometric/__init__.py,sha256=3s3xapTQEzq9U-HSeJw1y27iIauP4Q6mXl6ynWcHsD0,1978
+torch_geometric/__init__.py,sha256=sQzmkvhoO3gUcLkGhTtJi5ZIApfl_-Dnsejf7c1o9RI,1978
 torch_geometric/_compile.py,sha256=f-WQeH4VLi5Hn9lrgztFUCSrN_FImjhQa6BxFzcYC38,1338
 torch_geometric/_onnx.py,sha256=V9ffrIKSqhDw6xUZ12lkuSfNs48cQp2EeJ6Z19GfnVw,349
 torch_geometric/backend.py,sha256=lVaf7aLoVaB3M-UcByUJ1G4T4FOK6LXAg0CF4W3E8jo,1575
@@ -55,7 +55,7 @@ torch_geometric/data/temporal.py,sha256=WOJ6gFrTLikaLhUvotyUF5ql14FkE5Ox3hNkdSp6
 torch_geometric/data/view.py,sha256=XjkVSc-UWZFCT4DlXLShZtO8duhFQkS9gq88zZXANsk,1089
 torch_geometric/data/lightning/__init__.py,sha256=w3En1tJfy3kSqe1MycpOyZpHFO3fxBCgNCUOznPA3YU,178
 torch_geometric/data/lightning/datamodule.py,sha256=Bn9iaIfE4NWDDWWMqCvBeZ4bIW1Silx_Ol5CPJCliaQ,29242
-torch_geometric/datasets/__init__.py,sha256=d9nuTCytBvg60lm_WYRAQwjoZxR1H_7JsW8een1k1No,6186
+torch_geometric/datasets/__init__.py,sha256=fgJgc2wztjTJKczuHwXH7L0CgCXw69o_Dtm1KnleMCY,6235
 torch_geometric/datasets/actor.py,sha256=oUxgJIX8bi5hJr1etWNYIFyVQNDDXi1nyVpHGGMEAGQ,4304
 torch_geometric/datasets/airfrans.py,sha256=212gYsk7PvF-qcmvM2YXaOBhFrS79evAGg_sPHXih4w,5439
 torch_geometric/datasets/airports.py,sha256=b3gkv3gY2JkUpmGiz36Z-g7EcnSfU8lBG1YsCOWdJ6k,3758
@@ -71,6 +71,7 @@ torch_geometric/datasets/ba_shapes.py,sha256=sJEQiK3CGlYTdbQBgKeLhO6mY-HRv3nS9Ya
 torch_geometric/datasets/bitcoin_otc.py,sha256=olrsq_Z306-oo17iEQoVif3-CgVIOyVc8twgIMXE0iI,4399
 torch_geometric/datasets/brca_tgca.py,sha256=2lX9oY6T7aPut8NbXFMWS1c2-_FHqCB4hqUzP4_zFsk,3962
 torch_geometric/datasets/citation_full.py,sha256=5WT6_iZ1GWuShuYZJErQ3bWNV4bHwZsYYBYztoTxMzs,4458
+torch_geometric/datasets/city.py,sha256=9EFbPDFlEweVYvZL9V4jmuY_wioKTcax0YxeisZbis4,5138
 torch_geometric/datasets/coauthor.py,sha256=Nma9aLapDE1S7lCC40WazQZbBJ8nMQV3JJZRci-F3XQ,3138
 torch_geometric/datasets/coma.py,sha256=4URaPuXdUJdtZbzWojR-BqxlTyykjtvmXptk3G2Uy9k,4734
 torch_geometric/datasets/cornell.py,sha256=i6wUr2m1U3HCaqMzi-0AZ3Nthdne6_t0ja8qCKYESzE,5311
@@ -513,7 +514,7 @@ torch_geometric/profile/utils.py,sha256=7h6vzTzW8vv-ZqMOz2DV8HHNgC9ViOrN7IR9d3BP
 torch_geometric/sampler/__init__.py,sha256=0h_xJ7CQnlTxF5hUpc81WPQ0QaBtouG8eKK1RzPGA-s,512
 torch_geometric/sampler/base.py,sha256=glbuSNcI0A_y-O3x29jqQpSSqSWxUDKJk5vM8uVF8Gs,26980
 torch_geometric/sampler/hgt_sampler.py,sha256=UAm8_wwzEcziKDJ8-TnfZh1705dXRsy_I5PKhZSDTK8,2721
-torch_geometric/sampler/neighbor_sampler.py,sha256=MAVphWqNf0-cwlHRvdiU8de86dBxwjm3Miam_6s1ep4,33971
+torch_geometric/sampler/neighbor_sampler.py,sha256=G3pw3IHSAPEVeepiw-vJeWDbQwpEW9jr4-Ms_HjcZCA,34080
 torch_geometric/sampler/utils.py,sha256=RJtasO6Q7Pp3oYEOWrbf2DEYuSfuKZOsF2I7-eJDnoA,5485
 torch_geometric/testing/__init__.py,sha256=m3yp_5UnCAxVgzTFofpiVt0vdbl5GwVAve8WTrAaNxo,1319
 torch_geometric/testing/asserts.py,sha256=DLC9HnBgFWuTIiQs2OalsQcXGhOVG-e6R99IWhkO32c,4606
@@ -636,7 +637,7 @@ torch_geometric/utils/undirected.py,sha256=H_nfpI0_WluOG6VfjPyldvcjL4w5USAKWu2x5
 torch_geometric/visualization/__init__.py,sha256=b-HnVesXjyJ_L1N-DnjiRiRVf7lhwKaBQF_2i5YMVSU,208
 torch_geometric/visualization/graph.py,sha256=PoI9tjbEXZVkMUg4CvTLbzqtEfzUwMUcsw57DNBEU0s,14311
 torch_geometric/visualization/influence.py,sha256=CWMvuNA_Nf1sfbJmQgn58yS4OFpeKXeZPe7kEuvkUBw,477
-pyg_nightly-2.7.0.dev20250502.dist-info/licenses/LICENSE,sha256=ic-27cMJc1kWoMEYncz3Ya3Ur2Bi3bNLWib2DT763-o,1067
-pyg_nightly-2.7.0.dev20250502.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
-pyg_nightly-2.7.0.dev20250502.dist-info/METADATA,sha256=uN89LKXFS5kEbe4cQl4Rt5sBrZdeelM03nMSwqZ03gw,62979
-pyg_nightly-2.7.0.dev20250502.dist-info/RECORD,,
+pyg_nightly-2.7.0.dev20250504.dist-info/licenses/LICENSE,sha256=ic-27cMJc1kWoMEYncz3Ya3Ur2Bi3bNLWib2DT763-o,1067
+pyg_nightly-2.7.0.dev20250504.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
+pyg_nightly-2.7.0.dev20250504.dist-info/METADATA,sha256=xhjWav-LGW_50rzAl-sv3_1PoXWiwfWSOt72KhW_8nI,62979
+pyg_nightly-2.7.0.dev20250504.dist-info/RECORD,,

torch_geometric/__init__.py

@@ -31,7 +31,7 @@ from .lazy_loader import LazyLoader
 contrib = LazyLoader('contrib', globals(), 'torch_geometric.contrib')
 graphgym = LazyLoader('graphgym', globals(), 'torch_geometric.graphgym')
 
-__version__ = '2.7.0.dev20250502'
+__version__ = '2.7.0.dev20250504'
 
 __all__ = [
     'Index',

torch_geometric/datasets/__init__.py

@@ -81,6 +81,7 @@ from .git_mol_dataset import GitMolDataset
 from .molecule_gpt_dataset import MoleculeGPTDataset
 from .instruct_mol_dataset import InstructMolDataset
 from .tag_dataset import TAGDataset
+from .city import CityNetwork
 
 from .dbp15k import DBP15K
 from .aminer import AMiner
@@ -199,6 +200,7 @@ homo_datasets = [
     'MoleculeGPTDataset',
     'InstructMolDataset',
     'TAGDataset',
+    'CityNetwork',
 ]
 
 hetero_datasets = [

torch_geometric/datasets/city.py

@@ -0,0 +1,156 @@
+import os.path as osp
+from typing import Callable, Optional
+
+from torch_geometric.data import (
+    Data,
+    InMemoryDataset,
+    download_url,
+    extract_tar,
+)
+from torch_geometric.io import fs
+
+
+class CityNetwork(InMemoryDataset):
+    r"""The City-Networks are introduced in
+    `"Towards Quantifying Long-Range Interactions in Graph Machine Learning:
+    a Large Graph Dataset and a Measurement"
+    <https://arxiv.org/abs/2503.09008>`_ paper.
+    The dataset contains four city networks: `paris`, `shanghai`, `la`,
+    and 'london', where nodes represent junctions and edges represent
+    directed road segments. The task is to predict each node's eccentricity
+    score, which is approximated based on its 16-hop neighborhood. The score
+    indicates how accessible one node is in the network, and is mapped to
+    10 quantiles for transductive classification. See the original
+    `source code <https://github.com/LeonResearch/City-Networks>`_ for more
+    details on the individual networks.
+
+    Args:
+        root (str): Root directory where the dataset should be saved.
+        name (str): The name of the dataset (``"paris"``, ``"shanghai"``,
+            ``"la"``, ``"london"``).
+        augmented (bool, optional): Whether to use the augmented node features
+            from edge features.(default: :obj:`True`)
+        transform (callable, optional): A function/transform that takes in an
+            :class:`~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 :class:`~torch_geometric.data.Data` object and returns a
+            transformed version. The data object will be transformed before
+            being saved to disk. (default: :obj:`None`)
+        force_reload (bool, optional): Whether to re-process the dataset.
+            (default: :obj:`False`)
+
+    **STATS:**
+
+    .. list-table::
+        :widths: 10 10 10 10 10
+        :header-rows: 1
+
+        * - Name
+          - #nodes
+          - #edges
+          - #features
+          - #classes
+        * - paris
+          - 114,127
+          - 182,511
+          - 37
+          - 10
+        * - shanghai
+          - 183,917
+          - 262,092
+          - 37
+          - 10
+        * - la
+          - 240,587
+          - 341,523
+          - 37
+          - 10
+        * - london
+          - 568,795
+          - 756,502
+          - 37
+          - 10
+    """
+    url = "https://github.com/LeonResearch/City-Networks/raw/refs/heads/main/data/"  # noqa: E501
+
+    def __init__(
+        self,
+        root: str,
+        name: str,
+        augmented: bool = True,
+        transform: Optional[Callable] = None,
+        pre_transform: Optional[Callable] = None,
+        force_reload: bool = False,
+        delete_raw: bool = False,
+    ) -> None:
+        self.name = name.lower()
+        assert self.name in ["paris", "shanghai", "la", "london"]
+        self.augmented = augmented
+        self.delete_raw = delete_raw
+        super().__init__(
+            root,
+            transform,
+            pre_transform,
+            force_reload=force_reload,
+        )
+        self.load(self.processed_paths[0])
+
+    @property
+    def raw_dir(self) -> str:
+        return osp.join(self.root, self.name, "raw")
+
+    @property
+    def processed_dir(self) -> str:
+        return osp.join(self.root, self.name, "processed")
+
+    @property
+    def raw_file_names(self) -> str:
+        return f"{self.name}.json"
+
+    @property
+    def processed_file_names(self) -> str:
+        return "data.pt"
+
+    def download(self) -> None:
+        self.download_path = download_url(
+            self.url + f"{self.name}.tar.gz",
+            self.raw_dir,
+        )
+
+    def process(self) -> None:
+        extract_tar(self.download_path, self.raw_dir)
+        data_path = osp.join(self.raw_dir, self.name)
+        node_feat = fs.torch_load(
+            osp.join(
+                data_path,
+                f"node_features{'_augmented' if self.augmented else ''}.pt",
+            ))
+        edge_index = fs.torch_load(osp.join(data_path, "edge_indices.pt"))
+        label = fs.torch_load(
+            osp.join(data_path, "10-chunk_16-hop_node_labels.pt"))
+        train_mask = fs.torch_load(osp.join(data_path, "train_mask.pt"))
+        val_mask = fs.torch_load(osp.join(data_path, "valid_mask.pt"))
+        test_mask = fs.torch_load(osp.join(data_path, "test_mask.pt"))
+        data = Data(
+            x=node_feat,
+            edge_index=edge_index,
+            y=label,
+            train_mask=train_mask,
+            val_mask=val_mask,
+            test_mask=test_mask,
+        )
+        if self.pre_transform is not None:
+            data = self.pre_transform(data)
+
+        self.save([data], self.processed_paths[0])
+
+        if self.delete_raw:
+            fs.rm(data_path)
+
+    def __repr__(self) -> str:
+        return (f"{self.__class__.__name__}("
+                f"root='{self.root}', "
+                f"name='{self.name}', "
+                f"augmented={self.augmented})")

torch_geometric/sampler/neighbor_sampler.py

@@ -279,6 +279,7 @@ class NeighborSampler(BaseSampler):
         self.subgraph_type = SubgraphType(subgraph_type)
         self.disjoint = disjoint
         self.temporal_strategy = temporal_strategy
+        self.keep_orig_edges = False
 
     @property
     def num_neighbors(self) -> NumNeighbors:
@@ -321,7 +322,7 @@ class NeighborSampler(BaseSampler):
     ) -> Union[SamplerOutput, HeteroSamplerOutput]:
         out = node_sample(inputs, self._sample)
         if self.subgraph_type == SubgraphType.bidirectional:
-            out = out.to_bidirectional()
+            out = out.to_bidirectional(keep_orig_edges=self.keep_orig_edges)
         return out
 
     # Edge-based sampling #####################################################
@@ -334,7 +335,7 @@ class NeighborSampler(BaseSampler):
         out = edge_sample(inputs, self._sample, self.num_nodes, self.disjoint,
                           self.node_time, neg_sampling)
         if self.subgraph_type == SubgraphType.bidirectional:
-            out = out.to_bidirectional()
+            out = out.to_bidirectional(keep_orig_edges=self.keep_orig_edges)
         return out
 
     # Other Utilities #########################################################