chore: fix grammar errors across codebase

Fix grammar using Claude Haiku 4.5, then manually correct.

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>

Author: zaz

README.md

@@ -36,13 +36,13 @@ Assess how your model compares against state-of-the-art topological neural netwo
 
 ---
 
-> 🏆 The **TAG-DS Topological Deep Learning Challenge 2025** has concluded! A huge shotout to all participants. Check out the winners and honorable mentions on [`the challenge website`](https://geometric-intelligence.github.io/topobench/tdl-challenge/index.html).
+> 🏆 The **TAG-DS Topological Deep Learning Challenge 2025** has concluded! A huge shout-out to all participants. Check out the winners and honorable mentions on [`the challenge website`](https://geometric-intelligence.github.io/topobench/tdl-challenge/index.html).
 
 ---
 
 ## :pushpin: Overview
 
-`TopoBench` (TB) is a modular Python library designed to standardize benchmarking and accelerate research in Topological Deep Learning (TDL). In particular, TB allows to train and compare the performances of all sorts of Topological Neural Networks (TNNs) across the different topological domains, where by _topological domain_ we refer to a graph, a simplicial complex, a cellular complex, or a hypergraph. For detailed information, please refer to the [`TopoBench: A Framework for Benchmarking Topological Deep Learning`](https://arxiv.org/pdf/2406.06642) paper.
+`TopoBench` (TB) is a modular Python library designed to standardize benchmarking and accelerate research in Topological Deep Learning (TDL). In particular, TB allows training and comparing the performances of all sorts of Topological Neural Networks (TNNs) across the different topological domains, where by _topological domain_ we refer to a graph, a simplicial complex, a cellular complex, or a hypergraph. For detailed information, please refer to the [`TopoBench: A Framework for Benchmarking Topological Deep Learning`](https://arxiv.org/pdf/2406.06642) paper.
 
 <p align="center">
   <img src="resources/workflow.jpg" width="700">

docs/index.rst

@@ -7,7 +7,7 @@
    :width: 1000px
 
 `TopoBench` (TB) is a modular Python library designed to standardize benchmarking and accelerate research in Topological Deep Learning (TDL).
-In particular, TB allows to train and compare the performances of all sorts of Topological Neural Networks (TNNs) across the different topological domains,
+In particular, TB allows training and comparing the performances of all sorts of Topological Neural Networks (TNNs) across the different topological domains,
 where by *topological domain* we refer to a graph, a simplicial complex, a cellular complex, or a hypergraph.
 
 .. figure:: https://github.com/geometric-intelligence/TopoBench/raw/main/resources/workflow.jpg
@@ -20,7 +20,7 @@ where by *topological domain* we refer to a graph, a simplicial complex, a cellu
 
 ``TopoBench`` (TB) is a modular Python library designed to standardize
 benchmarking and accelerate research in Topological Deep Learning (TDL).
-In particular, TB allows to train and compare the performances of all
+In particular, TB allows training and comparing the performances of all
 sorts of Topological Neural Networks (TNNs) across the different
 topological domains, where by *topological domain* we refer to a graph,
 a simplicial complex, a cellular complex, or a hypergraph. For detailed

test/_utils/flow_mocker.py

@@ -6,7 +6,7 @@
 class FlowMocker:
     """Flow mocker.
 
-    Mocker for the flow of the test. It allows to create mock objects and assert them.
+    Mocker for the flow of the test. It allows creating mock objects and asserting them.
 
     Parameters
     ----------
@@ -67,7 +67,7 @@ def setup(self):
                 if mock_alias is not None:
                     if mock_alias in self.mocks:
                         raise KeyError(
-                            f"`{mock_alias}` is already exist in mock dictionary"
+                            f"`{mock_alias}` already exists in mock dictionary"
                         )
                     self.mocks[mock_alias] = self.mocks[patch_obj]
 

test/data/dataload/test_Dataloaders.py

@@ -48,7 +48,7 @@ def test_lift_features(self):
         """Test the collate function.
 
         To test the collate function we use the TBDataloader class to create a dataloader that uses the collate function.
-        We then first check that the batched data has the expected shape. We then convert the batched data back to a list and check that the data in the list is the same as the original data.
+        We first check that the batched data has the expected shape. We then convert the batched data back to a list and check that the data in the list is the same as the original data.
         """
 
         def check_shape(batch, elems, key):

test/transforms/liftings/graph2simplicial/test_latentclique_lifting.py

@@ -68,9 +68,9 @@ def test_lift_topology(self):
         edge_prob_single_adj = self.lifting.forward(self.data_test_one.clone()).adjacency_0
 
         ### TEST #1 ###
-        # if edge_prob == 1 and a the input graph has a single clique,
+        # if edge_prob == 1 and the input graph has a single clique,
         # then the 1-skeleton of the inferred latent SC must have a single clique
-        # (or, equivalently, the SC has a simplex in its facests set if complex_dim = |maximal_clique|-1)
+        # (or, equivalently, the SC has a simplex in its facets set if complex_dim = |maximal_clique|-1)
 
         # Convert adjacency matrix to NetworkX graph
         G_from_latent_complex = nx.from_numpy_matrix(

topobench/data/utils/io_utils.py

@@ -332,7 +332,7 @@ def read_us_county_demos(path, year=2012, y_col="Election"):
 
     # Get new values for FIPS from current index
     # To understand why please print stat.iloc[[516, 517, 518, 519, 520]] for 2012 year
-    # Basically the FIPS values has been shifted
+    # Basically the FIPS values have been shifted
     stat["FIPS"] = stat.reset_index()["index"]
 
     # Create Election variable

topobench/dataloader/dataloader.py

@@ -49,7 +49,7 @@ def __init__(
     ) -> None:
         super().__init__()
 
-        # this line allows to access init params with 'self.hparams' attribute
+        # this line allows accessing init params with 'self.hparams' attribute
         # also ensures init params will be stored in ckpt
         self.save_hyperparameters(
             logger=False,

topobench/model/model.py

@@ -44,7 +44,7 @@ def __init__(
     ) -> None:
         super().__init__()
 
-        # This line allows to access init params with 'self.hparams' attribute
+        # This line allows accessing init params with 'self.hparams' attribute
         # also ensures init params will be stored in ckpt
         self.save_hyperparameters(
             logger=False, ignore=["backbone", "readout", "feature_encoder"]

topobench/transforms/liftings/graph2cell/discrete_configuration_complex_lifting.py

@@ -20,7 +20,7 @@ class DiscreteConfigurationComplexLifting(Graph2CellLifting):
 
     Lift graphs to cell complexes by generating the k-th discrete configuration complex D_k(G) of the graph. This is a cube complex, which is similar to a simplicial complex except each n-dimensional cell is homeomorphic to a n-dimensional cube rather than an n-dimensional simplex.
 
-    The discrete configuration complex of order k consists of all sets of k unique edges or vertices of G, with the additional constraint that if an edge e is in a cell, then neither of the endpoints of e are in the cell. For examples of different graphs and their configuration complexes, see the tutorial.
+    The discrete configuration complex of order k consists of all sets of k unique edges or vertices of G, with the additional constraint that if an edge e is in a cell, then neither of the endpoints of e is in the cell. For examples of different graphs and their configuration complexes, see the tutorial.
 
     Note that since TopoNetx only supports cell complexes of dimension 2, if you generate a configuration complex of order k > 2 this will only produce the 2-skeleton.
 

topobench/transforms/liftings/graph2hypergraph/forman_ricci_curvature_lifting.py

@@ -15,7 +15,7 @@
 class HypergraphFormanRicciCurvatureLifting(Graph2HypergraphLifting):
     """Lift graphs to hypergraph domain using Forman-Ricci curvature based backbone estimation.
 
-    This lifting identifies a network's structure-preserving, coarse geometry, i.e. its backbones, which lend themselves specifically to model information flows across wide areas of the network via hyperedges. To identify this coarse geometry we apply Forman-Ricci curvature to the original graph. Forman-Ricci curvature defines an edge-based network characteristic that reveals properties of a graph's community structure. In particular high absolute Forman-Ricci curvature exhibits a network's backbone, a coarse, structure preserving graph geometry that forms connections between major communities, most suitable to form hyperedges. In addition, Forman-Ricci curvature was found to be especially useful for network analysis since its intuitive notion allows for efficient computation that scales to large networks sizes.
+    This lifting identifies a network's structure-preserving, coarse geometry, i.e. its backbones, which lend themselves specifically to model information flows across wide areas of the network via hyperedges. To identify this coarse geometry we apply Forman-Ricci curvature to the original graph. Forman-Ricci curvature defines an edge-based network characteristic that reveals properties of a graph's community structure. In particular high absolute Forman-Ricci curvature exhibits a network's backbone, a coarse, structure preserving graph geometry that forms connections between major communities, most suitable to form hyperedges. In addition, Forman-Ricci curvature was found to be especially useful for network analysis since its intuitive notion allows for efficient computation that scales to large network sizes.
 
     Parameters
     ----------