Class GraphData

python/dgl/data/csv_dataset_base.py:271–318

Class of graph data which is used for DGLGraph construction. Internal use only.

class GraphData(BaseData):
    """Class of graph data which is used for DGLGraph construction. Internal use only."""

    def __init__(self, graph_id, data):
        self.graph_id = np.array(graph_id)
        self.data = data
        _validate_data_length({**{"graph_id": self.graph_id}, **self.data})

    @staticmethod
    def load_from_csv(
        meta: MetaGraph, data_parser: Callable, base_dir=None, separator=","
    ):
        df = BaseData.read_csv(meta.file_name, base_dir, separator)
        graph_ids = BaseData.pop_from_dataframe(df, meta.graph_id_field)
        if graph_ids is None:
            raise DGLError(
                "Missing graph id field [{}] in file [{}].".format(
                    meta.graph_id_field, meta.file_name
                )
            )
        gdata = data_parser(df)
        return GraphData(graph_ids, gdata)

    @staticmethod
    def to_dict(graph_data: "GraphData", graphs_dict: dict) -> dict:
        missing_ids = np.setdiff1d(
            np.array(list(graphs_dict.keys())), graph_data.graph_id
        )
        if len(missing_ids) > 0:
            raise DGLError(
                "Found following graph ids in node/edge CSVs but not in graph CSV: {}.".format(
                    missing_ids
                )
            )
        graph_ids = graph_data.graph_id
        graphs = []
        for graph_id in graph_ids:
            if graph_id not in graphs_dict:
                graphs_dict[graph_id] = dgl_heterograph(
                    {("_V", "_E", "_V"): ([], [])}
                )
        for graph_id in graph_ids:
            graphs.append(graphs_dict[graph_id])
        data = {
            k: F.reshape(_tensor(v), (len(graphs), -1))
            for k, v in graph_data.data.items()
        }
        return graphs, data


class DGLGraphConstructor: