pyg-nightly 2.7.0.dev20241027__py3-none-any.whl → 2.7.0.dev20241031__py3-none-any.whl

{pyg_nightly-2.7.0.dev20241027.dist-info → pyg_nightly-2.7.0.dev20241031.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyg-nightly
-Version: 2.7.0.dev20241027
+Version: 2.7.0.dev20241031
 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.dev20241027.dist-info → pyg_nightly-2.7.0.dev20241031.dist-info}/RECORD

@@ -1,4 +1,4 @@
-torch_geometric/__init__.py,sha256=Tl6uetEmnPxV5lTY2_aTfQfUqH0ggFyNrrLX9G8gOy0,1904
+torch_geometric/__init__.py,sha256=xvSZWRVIrP2K51ajiMdBNakse3Y6lz77Si0TgGfAPVo,1904
 torch_geometric/_compile.py,sha256=REjj1_qX8YBrva6iqr3AsNiDueTAy2BhLZkdezKL2MY,1322
 torch_geometric/_onnx.py,sha256=V9ffrIKSqhDw6xUZ12lkuSfNs48cQp2EeJ6Z19GfnVw,349
 torch_geometric/backend.py,sha256=lVaf7aLoVaB3M-UcByUJ1G4T4FOK6LXAg0CF4W3E8jo,1575
@@ -11,7 +11,7 @@ torch_geometric/edge_index.py,sha256=r4_24Rhm3YCK0BF-kzLvL7PlY_1tWcXrBDIr7JPDjkw
 torch_geometric/experimental.py,sha256=JbtNNEXjFGI8hZ9raM6-qrZURP6Z5nlDK8QicZUIbz0,4756
 torch_geometric/home.py,sha256=EV54B4Dmiv61GDbkCwtCfWGWJ4eFGwZ8s3KOgGjwYgY,790
 torch_geometric/index.py,sha256=9ChzWFCwj2slNcVBOgfV-wQn-KscJe_y7502w-Vf76w,24045
-torch_geometric/inspector.py,sha256=9M61T9ruSid5-r2aelRAeX9g_7AZ1VMnYAB2KozM71E,19267
+torch_geometric/inspector.py,sha256=nKi5o4Mn6xsG0Ex1GudTEQt_EqnF9mcMqGtp7Shh9sQ,19336
 torch_geometric/isinstance.py,sha256=truZjdU9PxSvjJ6k0d_CLJ2iOpen2o8U-54pbUbNRyE,935
 torch_geometric/lazy_loader.py,sha256=SM0UcXtIdiFge75MKBAWXedoiSOdFDOV0rm1PfoF9cE,908
 torch_geometric/logging.py,sha256=HmHHLiCcM64k-6UYNOSfXPIeSGNAyiGGcn8cD8tlyuQ,858
@@ -149,7 +149,7 @@ torch_geometric/datasets/tosca.py,sha256=nUSF8NQT1GlkwWQLshjWmr8xORsvRHzzIqhUyDC
 torch_geometric/datasets/tu_dataset.py,sha256=14OSaXBgVwT1dX2h1wZ3xVIwoo0GQBEfR3yWh6Q0VF0,7847
 torch_geometric/datasets/twitch.py,sha256=qfEerf-Uaojx2ZvegENowdG4E7RoUT_HUO9xtULadvo,3658
 torch_geometric/datasets/upfd.py,sha256=crqO8uQNz1wC1JOn4prSs8iOGv9LuLK3dZf_KUV9tUE,7010
-torch_geometric/datasets/web_qsp_dataset.py,sha256=3f2x9XlbC1QhEsr_9hoQHCE9_7f9Poy1xpsBpONSY6s,8614
+torch_geometric/datasets/web_qsp_dataset.py,sha256=tCVMFRT1FqlukkrdcN-qS2jYWvVYocy3-_ZeCpWwIEk,8905
 torch_geometric/datasets/webkb.py,sha256=beC1kWeW7cIjYwWyaINQSk-3lmVR85Lus7cKZniHp8Y,4879
 torch_geometric/datasets/wikics.py,sha256=iTzYif1WvbMXnMdhPMfvrkVaAbnM009WiB_f_JWZqhU,3879
 torch_geometric/datasets/wikidata.py,sha256=9mYShF_HlpTmcdLpiaP_tYJ9eQtUOu5vRPvohN6RXqI,4979
@@ -320,7 +320,7 @@ torch_geometric/nn/aggr/patch_transformer.py,sha256=SP--1IaXrHWjjGgH7yIPeO84b5NA
 torch_geometric/nn/aggr/quantile.py,sha256=sRnKyt4CXr9RmjoPyTl4VUvXgSCMl9PG-fhCGsSZ76c,6189
 torch_geometric/nn/aggr/scaler.py,sha256=GV6gxUFBoKYMQTGybwzoPh708OY6k6chtUYmCIbFGXk,4638
 torch_geometric/nn/aggr/set2set.py,sha256=4GdmsjbBIrap3CG2naeFNsYe5eE-fhrNQOXM1-TIxyM,2446
-torch_geometric/nn/aggr/set_transformer.py,sha256=T30oGDQ9ZNihiKUW4EeeU1RpZpVy2W3jjwMEXJI405k,4207
+torch_geometric/nn/aggr/set_transformer.py,sha256=FG7_JizpFX14M6VSCwLSjYXYdJ1ZiQVbvnaYHIraiuM,4213
 torch_geometric/nn/aggr/sort.py,sha256=bvOOWnFkNOBOZih4rqVZQsjfeDX3vmXo1bpPSFD846w,2507
 torch_geometric/nn/aggr/utils.py,sha256=CLJ-ZrVWYIOBpdhQBLAz94dj3cMKKKc3qwGr4DFbiCU,8338
 torch_geometric/nn/aggr/variance_preserving.py,sha256=fu-U_aGYpVLpgSFvVg0ONMe6nqoyv8tZ6Y35qMYTf9w,1126
@@ -426,11 +426,11 @@ torch_geometric/nn/models/correct_and_smooth.py,sha256=wmq-US2r4ocd0a661R8YeDiBe
 torch_geometric/nn/models/deep_graph_infomax.py,sha256=u6j-5-iHBASDCZ776dyfCI1N8wuvIMjeff8kthiX3Q4,4137
 torch_geometric/nn/models/deepgcn.py,sha256=tIgT03cj8MghYlxEozpoGvGG_CwpJrGDxv1Z0CVIUts,4339
 torch_geometric/nn/models/dimenet.py,sha256=Kc5p-rB5q-0e8lY22l-OdQTscTxJh2lTEpeRFMdL4RY,36186
-torch_geometric/nn/models/dimenet_utils.py,sha256=xP_nbzkSSL25GC3rrZ9KP8x9QZ59S-CZuHzCmQ-K0fI,5062
+torch_geometric/nn/models/dimenet_utils.py,sha256=Eyn_EiJqwKvuYj6BtRpSxrzMG3v4Gk98X9MxZ7uvwm4,5069
 torch_geometric/nn/models/g_retriever.py,sha256=VueRImNJlh1WvRWcsSXliSw8RlxlzWlu2WSFs_VQaJc,7749
 torch_geometric/nn/models/gnnff.py,sha256=15dkiLgy0LmH1hnUrpeoHioIp4BPTfjpVATpnGRt9E0,7860
 torch_geometric/nn/models/graph_mixer.py,sha256=mthMeCOikR8gseEsu4oJ3Cd9C35zHSv1p32ROwnG-6s,9246
-torch_geometric/nn/models/graph_unet.py,sha256=WFb7d_DBByMGyXh3AdK2CKNmvMmSKsSUt8l8UnSOovs,5395
+torch_geometric/nn/models/graph_unet.py,sha256=N8TSmJo8AlbZjjcame0xW_jZvMOirL5ahw6qv5Yjpbs,5586
 torch_geometric/nn/models/jumping_knowledge.py,sha256=9JR2EoViXKjcDSLb8tjJm-UHfv1mQCJvZAAEsYa0Ocw,5496
 torch_geometric/nn/models/label_prop.py,sha256=6XYBKp7OLmUgcn-73jXXpYZpef9Za1m0gI9QLv2bMEw,3908
 torch_geometric/nn/models/lightgcn.py,sha256=dXKiBvM96jGKLtYp4l90Fko4he0kKdR9fRw-0ZCqSrA,12466
@@ -618,6 +618,6 @@ torch_geometric/utils/undirected.py,sha256=H_nfpI0_WluOG6VfjPyldvcjL4w5USAKWu2x5
 torch_geometric/visualization/__init__.py,sha256=PyR_4K5SafsJrBr6qWrkjKr6GBL1b7FtZybyXCDEVwY,154
 torch_geometric/visualization/graph.py,sha256=AGKqbtTdL14w7xIhy6n3g4bpCOnujKt-pXHCNzovxB4,4784
 torch_geometric/visualization/influence.py,sha256=CWMvuNA_Nf1sfbJmQgn58yS4OFpeKXeZPe7kEuvkUBw,477
-pyg_nightly-2.7.0.dev20241027.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
-pyg_nightly-2.7.0.dev20241027.dist-info/METADATA,sha256=V-YB9GMG8CPMfeS_IUVL_vtYQ1TluM7FX4F-l-WcO_o,62897
-pyg_nightly-2.7.0.dev20241027.dist-info/RECORD,,
+pyg_nightly-2.7.0.dev20241031.dist-info/WHEEL,sha256=EZbGkh7Ie4PoZfRQ8I0ZuP9VklN_TvcZ6DSE5Uar4z4,81
+pyg_nightly-2.7.0.dev20241031.dist-info/METADATA,sha256=XtBSCkGeEBikzpALrIyETHTimwYY8mA6TyiERxECr7E,62897
+pyg_nightly-2.7.0.dev20241031.dist-info/RECORD,,

torch_geometric/__init__.py

@@ -30,7 +30,7 @@ from .lazy_loader import LazyLoader
 contrib = LazyLoader('contrib', globals(), 'torch_geometric.contrib')
 graphgym = LazyLoader('graphgym', globals(), 'torch_geometric.graphgym')
 
-__version__ = '2.7.0.dev20241027'
+__version__ = '2.7.0.dev20241031'
 
 __all__ = [
     'Index',

torch_geometric/datasets/web_qsp_dataset.py

@@ -21,12 +21,6 @@ def retrieval_via_pcst(
     cost_e: float = 0.5,
 ) -> Tuple[Data, str]:
     c = 0.01
-    if len(textual_nodes) == 0 or len(textual_edges) == 0:
-        desc = textual_nodes.to_csv(index=False) + "\n" + textual_edges.to_csv(
-            index=False,
-            columns=["src", "edge_attr", "dst"],
-        )
-        return data, desc
 
     from pcst_fast import pcst_fast
 
@@ -135,13 +129,17 @@ class WebQSPDataset(InMemoryDataset):
             If :obj:`"test"`, loads the test dataset. (default: :obj:`"train"`)
         force_reload (bool, optional): Whether to re-process the dataset.
             (default: :obj:`False`)
+        use_pcst (bool, optional): Whether to preprocess the dataset's graph
+            with PCST or return the full graphs. (default: :obj:`True`)
     """
     def __init__(
         self,
         root: str,
         split: str = "train",
         force_reload: bool = False,
+        use_pcst: bool = True,
     ) -> None:
+        self.use_pcst = use_pcst
         super().__init__(root, force_reload=force_reload)
 
         if split not in {'train', 'val', 'test'}:
@@ -224,15 +222,22 @@ class WebQSPDataset(InMemoryDataset):
                     edge_index=edge_index,
                     edge_attr=edge_attr,
                 )
-                data, desc = retrieval_via_pcst(
-                    data,
-                    question_embs[i],
-                    nodes,
-                    edges,
-                    topk=3,
-                    topk_e=5,
-                    cost_e=0.5,
-                )
+                if self.use_pcst and len(nodes) > 0 and len(edges) > 0:
+                    data, desc = retrieval_via_pcst(
+                        data,
+                        question_embs[i],
+                        nodes,
+                        edges,
+                        topk=3,
+                        topk_e=5,
+                        cost_e=0.5,
+                    )
+                else:
+                    desc = nodes.to_csv(index=False) + "\n" + edges.to_csv(
+                        index=False,
+                        columns=["src", "edge_attr", "dst"],
+                    )
+
                 data.question = question
                 data.label = label
                 data.desc = desc

torch_geometric/inspector.py

@@ -448,6 +448,10 @@ def type_repr(obj: Any, _globals: Dict[str, Any]) -> str:
         return '...'
 
     if obj.__module__ == 'typing':  # Special logic for `typing.*` types:
+
+        if not hasattr(obj, '_name'):
+            return repr(obj)
+
         name = obj._name
         if name is None:  # In some cases, `_name` is not populated.
             name = str(obj.__origin__).split('.')[-1]

torch_geometric/nn/aggr/set_transformer.py

@@ -38,7 +38,7 @@ class SetTransformerAggregation(Aggregation):
             (default: :obj:`1`)
         concat (bool, optional): If set to :obj:`False`, the seed embeddings
             are averaged instead of concatenated. (default: :obj:`True`)
-        norm (str, optional): If set to :obj:`True`, will apply layer
+        layer_norm (str, optional): If set to :obj:`True`, will apply layer
             normalization. (default: :obj:`False`)
         dropout (float, optional): Dropout probability of attention weights.
             (default: :obj:`0`)

torch_geometric/nn/models/dimenet_utils.py

@@ -1,5 +1,7 @@
 # Shameless steal from: https://github.com/klicperajo/dimenet
 
+import math
+
 import numpy as np
 import sympy as sym
 from scipy import special as sp
@@ -62,8 +64,8 @@ def bessel_basis(n, k):
 
 
 def sph_harm_prefactor(k, m):
-    return ((2 * k + 1) * np.math.factorial(k - abs(m)) /
-            (4 * np.pi * np.math.factorial(k + abs(m))))**0.5
+    return ((2 * k + 1) * math.factorial(k - abs(m)) /
+            (4 * np.pi * math.factorial(k + abs(m))))**0.5
 
 
 def associated_legendre_polynomials(k, zero_m_only=True):

torch_geometric/nn/models/graph_unet.py

@@ -79,12 +79,21 @@ class GraphUNet(torch.nn.Module):
         for conv in self.up_convs:
             conv.reset_parameters()
 
-    def forward(self, x: Tensor, edge_index: Tensor,
-                batch: OptTensor = None) -> Tensor:
+    def forward(
+        self,
+        x: Tensor,
+        edge_index: Tensor,
+        batch: OptTensor = None,
+        edge_weight: Tensor = None,
+    ) -> Tensor:
         """"""  # noqa: D419
         if batch is None:
             batch = edge_index.new_zeros(x.size(0))
-        edge_weight = x.new_ones(edge_index.size(1))
+
+        if edge_weight is None:
+            edge_weight = x.new_ones(edge_index.size(1))
+        assert edge_weight.dim() == 1
+        assert edge_weight.size(0) == edge_index.size(1)
 
         x = self.down_convs[0](x, edge_index, edge_weight)
         x = self.act(x)