pyg-nightly 2.7.0.dev20250525__tar.gz → 2.7.0.dev20250526__tar.gz

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyg-nightly
-Version: 2.7.0.dev20250525
+Version: 2.7.0.dev20250526
 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.dev20250525 → pyg_nightly-2.7.0.dev20250526}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend="flit_core.buildapi"
 
 [project]
 name="pyg-nightly"
-version="2.7.0.dev20250525"
+version="2.7.0.dev20250526"
 authors=[
     {name="Matthias Fey", email="matthias@pyg.org"},
 ]

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/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.dev20250525'
+__version__ = '2.7.0.dev20250526'
 
 __all__ = [
     'Index',

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/data/feature_store.py

@@ -409,7 +409,7 @@ class FeatureStore(ABC):
     def update_tensor(self, tensor: FeatureTensorType, *args,
                       **kwargs) -> bool:
         r"""Updates a :obj:`tensor` in the :class:`FeatureStore` with a new
-        value. Returns whether the update was succesful.
+        value. Returns whether the update was successful.
 
         .. note::
             Implementor classes can choose to define more efficient update

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/data/hetero_data.py

@@ -566,7 +566,7 @@ class HeteroData(BaseData, FeatureStore, GraphStore):
             This is equivalent to writing :obj:`data.x_dict`.
 
         Args:
-            key (str): The attribute to collect from all node and ege types.
+            key (str): The attribute to collect from all node and edge types.
             allow_empty (bool, optional): If set to :obj:`True`, will not raise
                 an error in case the attribute does not exit in any node or
                 edge type. (default: :obj:`False`)

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/data/hypergraph_data.py

@@ -39,7 +39,7 @@ class HyperGraphData(Data):
         edge_index (LongTensor, optional): Hyperedge tensor
             with shape :obj:`[2, num_edges*num_nodes_per_edge]`.
             Where `edge_index[1]` denotes the hyperedge index and
-            `edge_index[0]` denotes the node indicies that are connected
+            `edge_index[0]` denotes the node indices that are connected
             by the hyperedge. (default: :obj:`None`)
             (default: :obj:`None`)
         edge_attr (torch.Tensor, optional): Edge feature matrix with shape

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/datasets/airfrans.py

@@ -25,7 +25,7 @@ class AirfRANS(InMemoryDataset):
     features: the inlet velocity (two components in meter per second), the
     distance to the airfoil (one component in meter), and the normals (two
     components in meter, set to :obj:`0` if the point is not on the airfoil).
-    Each point is given a target of 4 components for the underyling regression
+    Each point is given a target of 4 components for the underlying regression
     task: the velocity (two components in meter per second), the pressure
     divided by the specific mass (one component in meter squared per second
     squared), the turbulent kinematic viscosity (one component in meter squared

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/datasets/tag_dataset.py

@@ -277,7 +277,7 @@ class TAGDataset(InMemoryDataset):
             for k, tensor in all_encoded_token.items():
                 torch.save(tensor, os.path.join(path, f'{k}.pt'))
                 print('Token saved:', os.path.join(path, f'{k}.pt'))
-        os.environ["TOKENIZERS_PARALLELISM"] = 'true'  # supressing warning
+        os.environ["TOKENIZERS_PARALLELISM"] = 'true'  # suppressing warning
         return all_encoded_token
 
     def __repr__(self) -> str:

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/distributed/partition.py

@@ -304,7 +304,7 @@ class Partitioner:
                 elif self.is_node_level_time:
                     node_time = data.time
 
-                # Sort by column to avoid keeping track of permuations in
+                # Sort by column to avoid keeping track of permutations in
                 # `NeighborSampler` when converting to CSC format:
                 global_row, global_col, perm = sort_csc(
                     global_row, global_col, node_time, edge_time)
@@ -361,7 +361,7 @@ class Partitioner:
             'edge_types': self.edge_types,
             'node_offset': list(node_offset.values()) if node_offset else None,
             'is_hetero': self.is_hetero,
-            'is_sorted': True,  # Based on colum/destination.
+            'is_sorted': True,  # Based on columnn/destination.
         }
         with open(osp.join(self.root, 'META.json'), 'w') as f:
             json.dump(meta, f)

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/explain/algorithm/captum.py

@@ -190,7 +190,7 @@ def to_captum_input(
 
     Args:
         x (torch.Tensor or Dict[NodeType, torch.Tensor]): The node features.
-            For heterogeneous graphs this is a dictionary holding node featues
+            For heterogeneous graphs this is a dictionary holding node features
             for each node type.
         edge_index(torch.Tensor or Dict[EdgeType, torch.Tensor]): The edge
             indices. For heterogeneous graphs this is a dictionary holding the

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/explain/metric/faithfulness.py

@@ -13,7 +13,7 @@ def unfaithfulness(
     top_k: Optional[int] = None,
 ) -> float:
     r"""Evaluates how faithful an :class:`~torch_geometric.explain.Explanation`
-    is to an underyling GNN predictor, as described in the
+    is to an underlying GNN predictor, as described in the
     `"Evaluating Explainability for Graph Neural Networks"
     <https://arxiv.org/abs/2208.09339>`_ paper.
 

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/graphgym/models/layer.py

@@ -52,7 +52,7 @@ def new_layer_config(
     has_bias: bool,
     cfg,
 ) -> LayerConfig:
-    r"""Createa a layer configuration for a GNN layer.
+    r"""Create a layer configuration for a GNN layer.
 
     Args:
         dim_in (int): The input feature dimension.

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/graphgym/utils/comp_budget.py

@@ -67,12 +67,12 @@ def dict_to_stats(cfg_dict):
 
 def match_baseline_cfg(cfg_dict, cfg_dict_baseline, verbose=True):
     """Match the computational budget of a given baseline model. The current
-    configuration dictionary will be modifed and returned.
+    configuration dictionary will be modified and returned.
 
     Args:
         cfg_dict (dict): Current experiment's configuration
         cfg_dict_baseline (dict): Baseline configuration
-        verbose (str, optional): If printing matched paramter conunts
+        verbose (str, optional): If printing matched parameter conunts
     """
     from yacs.config import CfgNode as CN
     stats_baseline = dict_to_stats(cfg_dict_baseline)

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/index.py

@@ -104,7 +104,7 @@ class Index(Tensor):
     conversion in case its representation is sorted.
     Caches are filled based on demand (*e.g.*, when calling
     :meth:`Index.get_indptr`), or when explicitly requested via
-    :meth:`Index.fill_cache_`, and are maintaned and adjusted over its
+    :meth:`Index.fill_cache_`, and are maintained and adjusted over its
     lifespan.
 
     This representation ensures optimal computation in GNN message passing

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/loader/link_loader.py

@@ -70,7 +70,7 @@ class LinkLoader(
             :obj:`edge_label_index`. If set, temporal sampling will be
             used such that neighbors are guaranteed to fulfill temporal
             constraints, *i.e.*, neighbors have an earlier timestamp than
-            the ouput edge. The :obj:`time_attr` needs to be set for this
+            the output edge. The :obj:`time_attr` needs to be set for this
             to work. (default: :obj:`None`)
         neg_sampling (NegativeSampling, optional): The negative sampling
             configuration.

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/loader/link_neighbor_loader.py

@@ -117,7 +117,7 @@ class LinkNeighborLoader(LinkLoader):
             :obj:`edge_label_index`. If set, temporal sampling will be
             used such that neighbors are guaranteed to fulfill temporal
             constraints, *i.e.*, neighbors have an earlier timestamp than
-            the ouput edge. The :obj:`time_attr` needs to be set for this
+            the output edge. The :obj:`time_attr` needs to be set for this
             to work. (default: :obj:`None`)
         replace (bool, optional): If set to :obj:`True`, will sample with
             replacement. (default: :obj:`False`)

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/loader/rag_loader.py

@@ -68,7 +68,7 @@ class RAGQueryLoader:
             local_filter (Optional[Callable[[Data, Any], Data]], optional):
                 Optional local transform to apply to data after retrieval.
                 Defaults to None.
-            seed_nodes_kwargs (Optional[Dict[str, Any]], optional): Paramaters
+            seed_nodes_kwargs (Optional[Dict[str, Any]], optional): Parameters
                 to pass into process for fetching seed nodes. Defaults to None.
             seed_edges_kwargs (Optional[Dict[str, Any]], optional): Parameters
                 to pass into process for fetching seed edges. Defaults to None.

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/loader/temporal_dataloader.py

@@ -6,7 +6,7 @@ from torch_geometric.data import TemporalData
 
 
 class TemporalDataLoader(torch.utils.data.DataLoader):
-    r"""A data loader which merges succesive events of a
+    r"""A data loader which merges successive events of a
     :class:`torch_geometric.data.TemporalData` to a mini-batch.
 
     Args:
@@ -15,7 +15,7 @@ class TemporalDataLoader(torch.utils.data.DataLoader):
         batch_size (int, optional): How many samples per batch to load.
             (default: :obj:`1`)
         neg_sampling_ratio (float, optional): The ratio of sampled negative
-            destination nodes to the number of postive destination nodes.
+            destination nodes to the number of positive destination nodes.
             (default: :obj:`0.0`)
         **kwargs (optional): Additional arguments of
             :class:`torch.utils.data.DataLoader`.

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/loader/utils.py

@@ -178,7 +178,7 @@ def filter_hetero_data(
     out = copy.copy(data)
 
     for node_type in out.node_types:
-        # Handle the case of disconneted graph sampling:
+        # Handle the case of disconnected graph sampling:
         if node_type not in node_dict:
             node_dict[node_type] = torch.empty(0, dtype=torch.long)
 
@@ -186,7 +186,7 @@ def filter_hetero_data(
                            node_dict[node_type])
 
     for edge_type in out.edge_types:
-        # Handle the case of disconneted graph sampling:
+        # Handle the case of disconnected graph sampling:
         if edge_type not in row_dict:
             row_dict[edge_type] = torch.empty(0, dtype=torch.long)
         if edge_type not in col_dict:

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/nn/aggr/equilibrium.py

@@ -52,7 +52,7 @@ class MomentumOptimizer(torch.nn.Module):
     layer. It is based on an unrolled Nesterov momentum algorithm.
 
     Args:
-        learning_rate (flaot): learning rate for optimizer.
+        learning_rate (float): learning rate for optimizer.
         momentum (float): momentum for optimizer.
         learnable (bool): If :obj:`True` then the :obj:`learning_rate` and
             :obj:`momentum` will be learnable parameters. If False they

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/nn/conv/dna_conv.py

@@ -163,7 +163,7 @@ class MultiHead(Attention):
     def __repr__(self) -> str:  # pragma: no cover
         return (f'{self.__class__.__name__}({self.in_channels}, '
                 f'{self.out_channels}, heads={self.heads}, '
-                f'groups={self.groups}, dropout={self.droput}, '
+                f'groups={self.groups}, dropout={self.dropout}, '
                 f'bias={self.bias})')
 
 

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/nn/models/captum.py

@@ -94,7 +94,7 @@ def to_captum_model(
             function will return the output of the model for the element at
             the index specified. (default: :obj:`None`)
         metadata (Metadata, optional): The metadata of the heterogeneous graph.
-            Only required if explaning a
+            Only required if explaining a
             :class:`~torch_geometric.data.HeteroData` object.
             (default: :obj:`None`)
     """

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/nn/models/dimenet.py

@@ -755,7 +755,7 @@ class DimeNetPlusPlus(DimeNet):
             interaction blocks after the skip connection. (default: :obj:`2`)
         num_output_layers: (int, optional): Number of linear layers for the
             output blocks. (default: :obj:`3`)
-        act: (str or Callable, optional): The activation funtion.
+        act: (str or Callable, optional): The activation function.
             (default: :obj:`"swish"`)
         output_initializer (str, optional): The initialization method for the
             output layer (:obj:`"zeros"`, :obj:`"glorot_orthogonal"`).
@@ -805,7 +805,7 @@ class DimeNetPlusPlus(DimeNet):
 
         # We are re-using the RBF, SBF and embedding layers of `DimeNet` and
         # redefine output_block and interaction_block in DimeNet++.
-        # Hence, it is to be noted that in the above initalization, the
+        # Hence, it is to be noted that in the above initialization, the
         # variable `num_bilinear` does not have any purpose as it is used
         # solely in the `OutputBlock` of DimeNet:
         self.output_blocks = torch.nn.ModuleList([

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/nn/models/g_retriever.py

@@ -131,7 +131,7 @@ class GRetriever(torch.nn.Module):
         x = self.projector(x)
         xs = x.split(1, dim=0)
 
-        # Handle case where theres more than one embedding for each sample
+        # Handle case where there's more than one embedding for each sample
         xs = [x.squeeze(0) for x in xs]
 
         # Handle questions without node features:
@@ -190,7 +190,7 @@ class GRetriever(torch.nn.Module):
         x = self.projector(x)
         xs = x.split(1, dim=0)
 
-        # Handle case where theres more than one embedding for each sample
+        # Handle case where there's more than one embedding for each sample
         xs = [x.squeeze(0) for x in xs]
 
         # Handle questions without node features:

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/nn/models/gpse.py

@@ -283,7 +283,7 @@ class GNNInductiveHybridMultiHead(torch.nn.Module):
             (default: :obj:`add`)
         has_bn (bool, optional): Whether to apply batch normalization to layer
             outputs. (default: :obj:`True`)
-        has_l2norm (bool, optional): Wheter to apply L2 normalization to the
+        has_l2norm (bool, optional): Whether to apply L2 normalization to the
             layer outputs. (default: :obj:`True`)
         dropout (float, optional): Dropout ratio at layer output.
             (default: :obj:`0.2`)
@@ -951,7 +951,7 @@ def precompute_GPSE(model: GPSE, dataset: Dataset, use_vn: bool = True,
                                                   **kwargs)
 
         batch_out = batch_out.to('cpu', non_blocking=True)
-        # Need to wait for batch_ptr to finish transfering so that start and
+        # Need to wait for batch_ptr to finish transferring so that start and
         # end indices are ready to use
         batch_ptr = batch_ptr.to('cpu', non_blocking=False)
 
@@ -966,7 +966,7 @@ def precompute_GPSE(model: GPSE, dataset: Dataset, use_vn: bool = True,
         pbar.update(len(batch_ptr) - 1)
     pbar.close()
 
-    # Collate dataset and reset indicies and data list
+    # Collate dataset and reset indices and data list
     dataset.transform = orig_dataset_transform
     dataset._indices = None
     dataset._data_list = data_list

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/nn/models/visnet.py

@@ -11,7 +11,7 @@ from torch_geometric.utils import scatter
 
 
 class CosineCutoff(torch.nn.Module):
-    r"""Appies a cosine cutoff to the input distances.
+    r"""Applies a cosine cutoff to the input distances.
 
     .. math::
         \text{cutoffs} =
@@ -572,7 +572,7 @@ class ViS_MP(MessagePassing):
         d_ij: Tensor,
     ) -> Tuple[Tensor, Tensor, Optional[Tensor]]:
         r"""Computes the residual scalar and vector features of the nodes and
-        scalar featues of the edges.
+        scalar features of the edges.
 
         Args:
             x (torch.Tensor): The scalar features of the nodes.

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/nn/norm/layer_norm.py

@@ -30,7 +30,7 @@ class LayerNorm(torch.nn.Module):
         affine (bool, optional): If set to :obj:`True`, this module has
             learnable affine parameters :math:`\gamma` and :math:`\beta`.
             (default: :obj:`True`)
-        mode (str, optinal): The normalization mode to use for layer
+        mode (str, optional): The normalization mode to use for layer
             normalization (:obj:`"graph"` or :obj:`"node"`). If :obj:`"graph"`
             is used, each graph will be considered as an element to be
             normalized. If `"node"` is used, each node will be considered as
@@ -108,7 +108,7 @@ class LayerNorm(torch.nn.Module):
             return F.layer_norm(x, (self.in_channels, ), self.weight,
                                 self.bias, self.eps)
 
-        raise ValueError(f"Unknow normalization mode: {self.mode}")
+        raise ValueError(f"Unknownn normalization mode: {self.mode}")
 
     def __repr__(self):
         return (f'{self.__class__.__name__}({self.in_channels}, '
@@ -130,7 +130,7 @@ class HeteroLayerNorm(torch.nn.Module):
         affine (bool, optional): If set to :obj:`True`, this module has
             learnable affine parameters :math:`\gamma` and :math:`\beta`.
             (default: :obj:`True`)
-        mode (str, optinal): The normalization mode to use for layer
+        mode (str, optional): The normalization mode to use for layer
             normalization (:obj:`"node"`). If `"node"` is used, each node will
             be considered as an element to be normalized.
             (default: :obj:`"node"`)

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/nn/pool/cluster_pool.py

@@ -55,7 +55,7 @@ class ClusterPooling(torch.nn.Module):
         self.in_channels = in_channels
         self.edge_score_method = edge_score_method
         self.dropout = dropout
-        self.threshhold = threshold
+        self.threshold = threshold
 
         self.lin = torch.nn.Linear(2 * in_channels, 1)
 
@@ -116,7 +116,7 @@ class ClusterPooling(torch.nn.Module):
 
         from scipy.sparse.csgraph import connected_components
 
-        edge_contract = edge_index[:, edge_score > self.threshhold]
+        edge_contract = edge_index[:, edge_score > self.threshold]
 
         adj = to_scipy_sparse_matrix(edge_contract, num_nodes=x.size(0))
         _, cluster_np = connected_components(adj, directed=True,

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/nn/to_hetero_with_bases_transformer.py

@@ -380,7 +380,7 @@ class HeteroBasisConv(torch.nn.Module):
 
 
 class LinearAlign(torch.nn.Module):
-    # Aligns representions to the same dimensionality. Note that this will
+    # Aligns representations to the same dimensionality. Note that this will
     # create lazy modules, and as such requires a forward pass in order to
     # initialize parameters.
     def __init__(self, keys: List[Union[NodeType, EdgeType]],

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/testing/decorators.py

@@ -268,7 +268,7 @@ def withMETIS(func: Callable) -> Callable:
     with_metis = WITH_METIS
 
     if with_metis:
-        try:  # Test that METIS can succesfully execute:
+        try:  # Test that METIS can successfully execute:
             # TODO Using `pyg-lib` metis partitioning leads to some weird bugs
             # in the # CI. As such, we require `torch-sparse` for now.
             rowptr = torch.tensor([0, 2, 4, 6])

{pyg_nightly-2.7.0.dev20250525 → pyg_nightly-2.7.0.dev20250526}/torch_geometric/utils/nested.py

@@ -43,7 +43,7 @@ def to_nested_tensor(
         xs = [x]
 
     # This currently copies the data, although `x` is already contiguous.
-    # Sadly, there does not exist any (public) API to preven this :(
+    # Sadly, there does not exist any (public) API to prevent this :(
     return torch.nested.as_nested_tensor(xs)