Method load

python/dgl/data/citation_graph.py:239–285

(self)

        save_info(str(self.info_path), {"num_classes": self.num_classes})

    def load(self):
        graphs, _ = load_graphs(str(self.graph_path))

        info = load_info(str(self.info_path))
        graph = graphs[0]
        self._g = graph
        # for compatability
        graph = graph.clone()
        graph.ndata.pop("train_mask")
        graph.ndata.pop("val_mask")
        graph.ndata.pop("test_mask")
        graph.ndata.pop("feat")
        graph.ndata.pop("label")
        graph = to_networkx(graph)

        self._num_classes = info["num_classes"]
        self._g.ndata["train_mask"] = generate_mask_tensor(
            F.asnumpy(self._g.ndata["train_mask"])
        )
        self._g.ndata["val_mask"] = generate_mask_tensor(
            F.asnumpy(self._g.ndata["val_mask"])
        )
        self._g.ndata["test_mask"] = generate_mask_tensor(
            F.asnumpy(self._g.ndata["test_mask"])
        )
        # hack for mxnet compatability

        if self.verbose:
            print("  NumNodes: {}".format(self._g.num_nodes()))
            print("  NumEdges: {}".format(self._g.num_edges()))
            print("  NumFeats: {}".format(self._g.ndata["feat"].shape[1]))
            print("  NumClasses: {}".format(self.num_classes))
            print(
                "  NumTrainingSamples: {}".format(
                    F.nonzero_1d(self._g.ndata["train_mask"]).shape[0]
                )
            )
            print(
                "  NumValidationSamples: {}".format(
                    F.nonzero_1d(self._g.ndata["val_mask"]).shape[0]
                )
            )
            print(
                "  NumTestSamples: {}".format(
                    F.nonzero_1d(self._g.ndata["test_mask"]).shape[0]
                )
            )

    def __getitem__(self, idx):
        assert idx == 0, "This dataset has only one graph"