Loading deepchem/feat/graph_data.py +25 −35 Original line number Diff line number Diff line Loading @@ -85,13 +85,8 @@ class GraphData: if self.node_features is not None: self.num_edge_features = self.edge_features.shape[1] def to_pyg_data(self, target: np.ndarray): """Convert to PyTorch Geometric Data instance Parameters ---------- target: np.ndarray Graph or node targets with arbitrary shape def to_pyg_graph(self): """Convert to PyTorch Geometric graph data instance Returns ------- Loading @@ -110,9 +105,31 @@ class GraphData: edge_index=torch.from_numpy(self.edge_index), edge_attr=None if self.edge_features is None \ else torch.from_numpy(self.edge_features), y=torch.from_numpy(target), ) def to_dgl_graph(self): """Convert to DGL graph data instance Returns ------- dgl.DGLGraph Graph data for PyTorch Geometric """ try: from dgl import DGLGraph except ModuleNotFoundError: raise ValueError("This function requires DGL to be installed.") g = DGLGraph() g.add_nodes(self.num_nodes) g.add_edges(self.edge_index[0], self.edge_index[1]) g.ndata['x'] = torch.from_numpy(self.node_features) if self.edge_features is not None: g.edata['edge_attr'] = torch.from_numpy(self.edge_features) return g class BatchGraphData(GraphData): """Batch GraphData class Loading Loading @@ -177,30 +194,3 @@ class BatchGraphData(GraphData): edge_features=batch_edge_features, graph_features=batch_graph_features, ) @staticmethod # type: ignore def to_pyg_data(graphs: Sequence[GraphData], targets: Sequence[np.ndarray]): """Convert to PyTorch Geometric Batch instance Parameters ---------- graphs: Sequence[GraphData] List of GraphData targets: Sequence[np.ndarray] List of graph or node targets with arbitrary shape Returns ------- torch_geometric.data.Batch Batch data of graphs for PyTorch Geometric """ try: from torch_geometric.data import Batch except ModuleNotFoundError: raise ValueError( "This function requires PyTorch Geometric to be installed.") data_list = [ graph.to_pyg_data(target) for graph, target in zip(graphs, targets) ] return Batch.from_data_list(data_list=data_list) deepchem/feat/material_featurizers/cgcnn_featurizer.py +0 −1 Original line number Diff line number Diff line Loading @@ -8,7 +8,6 @@ from deepchem.utils.typing import PymatgenStructure from deepchem.feat import MaterialStructureFeaturizer from deepchem.feat.graph_data import GraphData ATOM_INIT_JSON_URL = 'https://deepchemdata.s3-us-west-1.amazonaws.com/datasets/atom_init.json' Loading deepchem/feat/tests/test_graph_data.py +6 −9 Original line number Diff line number Diff line Loading @@ -28,12 +28,15 @@ class TestGraph(unittest.TestCase): assert graph.num_edges == num_edges assert graph.num_edge_features == num_edge_features # check to_pyg_data function target = np.array([1], dtype=np.float) pyg_graph = graph.to_pyg_data(target) # check convert function pyg_graph = graph.to_pyg_graph() from torch_geometric.data import Data assert isinstance(pyg_graph, Data) dgl_graph = graph.to_pyg_graph() from dgl import DGLGraph assert isinstance(dgl_graph, DGLGraph) def test_invalid_graph_data(self): with pytest.raises(ValueError): invalid_node_features_type = list(np.random.random_sample((5, 5))) Loading Loading @@ -87,9 +90,3 @@ class TestGraph(unittest.TestCase): assert batch.num_edges == sum(num_edge_list) assert batch.num_edge_features == num_edge_features assert batch.graph_index.shape == (sum(num_nodes_list),) # check to_pyg_data function targets = np.array([1, 2, 3], dtype=np.float) batch = BatchGraphData.to_pyg_data(graphs=graphs, targets=targets) from torch_geometric.data import Batch assert isinstance(pyg_graph, Batch) requirements.txt +1 −0 Original line number Diff line number Diff line biopython==1.77 dgl==0.4.3.post2 matminer==0.6.3 mdtraj==1.9.4 networkx==2.4 Loading Loading
deepchem/feat/graph_data.py +25 −35 Original line number Diff line number Diff line Loading @@ -85,13 +85,8 @@ class GraphData: if self.node_features is not None: self.num_edge_features = self.edge_features.shape[1] def to_pyg_data(self, target: np.ndarray): """Convert to PyTorch Geometric Data instance Parameters ---------- target: np.ndarray Graph or node targets with arbitrary shape def to_pyg_graph(self): """Convert to PyTorch Geometric graph data instance Returns ------- Loading @@ -110,9 +105,31 @@ class GraphData: edge_index=torch.from_numpy(self.edge_index), edge_attr=None if self.edge_features is None \ else torch.from_numpy(self.edge_features), y=torch.from_numpy(target), ) def to_dgl_graph(self): """Convert to DGL graph data instance Returns ------- dgl.DGLGraph Graph data for PyTorch Geometric """ try: from dgl import DGLGraph except ModuleNotFoundError: raise ValueError("This function requires DGL to be installed.") g = DGLGraph() g.add_nodes(self.num_nodes) g.add_edges(self.edge_index[0], self.edge_index[1]) g.ndata['x'] = torch.from_numpy(self.node_features) if self.edge_features is not None: g.edata['edge_attr'] = torch.from_numpy(self.edge_features) return g class BatchGraphData(GraphData): """Batch GraphData class Loading Loading @@ -177,30 +194,3 @@ class BatchGraphData(GraphData): edge_features=batch_edge_features, graph_features=batch_graph_features, ) @staticmethod # type: ignore def to_pyg_data(graphs: Sequence[GraphData], targets: Sequence[np.ndarray]): """Convert to PyTorch Geometric Batch instance Parameters ---------- graphs: Sequence[GraphData] List of GraphData targets: Sequence[np.ndarray] List of graph or node targets with arbitrary shape Returns ------- torch_geometric.data.Batch Batch data of graphs for PyTorch Geometric """ try: from torch_geometric.data import Batch except ModuleNotFoundError: raise ValueError( "This function requires PyTorch Geometric to be installed.") data_list = [ graph.to_pyg_data(target) for graph, target in zip(graphs, targets) ] return Batch.from_data_list(data_list=data_list)
deepchem/feat/material_featurizers/cgcnn_featurizer.py +0 −1 Original line number Diff line number Diff line Loading @@ -8,7 +8,6 @@ from deepchem.utils.typing import PymatgenStructure from deepchem.feat import MaterialStructureFeaturizer from deepchem.feat.graph_data import GraphData ATOM_INIT_JSON_URL = 'https://deepchemdata.s3-us-west-1.amazonaws.com/datasets/atom_init.json' Loading
deepchem/feat/tests/test_graph_data.py +6 −9 Original line number Diff line number Diff line Loading @@ -28,12 +28,15 @@ class TestGraph(unittest.TestCase): assert graph.num_edges == num_edges assert graph.num_edge_features == num_edge_features # check to_pyg_data function target = np.array([1], dtype=np.float) pyg_graph = graph.to_pyg_data(target) # check convert function pyg_graph = graph.to_pyg_graph() from torch_geometric.data import Data assert isinstance(pyg_graph, Data) dgl_graph = graph.to_pyg_graph() from dgl import DGLGraph assert isinstance(dgl_graph, DGLGraph) def test_invalid_graph_data(self): with pytest.raises(ValueError): invalid_node_features_type = list(np.random.random_sample((5, 5))) Loading Loading @@ -87,9 +90,3 @@ class TestGraph(unittest.TestCase): assert batch.num_edges == sum(num_edge_list) assert batch.num_edge_features == num_edge_features assert batch.graph_index.shape == (sum(num_nodes_list),) # check to_pyg_data function targets = np.array([1, 2, 3], dtype=np.float) batch = BatchGraphData.to_pyg_data(graphs=graphs, targets=targets) from torch_geometric.data import Batch assert isinstance(pyg_graph, Batch)
requirements.txt +1 −0 Original line number Diff line number Diff line biopython==1.77 dgl==0.4.3.post2 matminer==0.6.3 mdtraj==1.9.4 networkx==2.4 Loading
