Method process

python/dgl/data/gindt.py:184–358

Loads input dataset from dataset/NAME/NAME.txt file

(self)

        )

    def process(self):
        """Loads input dataset from dataset/NAME/NAME.txt file"""
        if self.verbose:
            print("loading data...")
        self.file = self._file_path()
        with open(self.file, "r") as f:
            # line_1 == N, total number of graphs
            self.N = int(f.readline().strip())

            for i in range(self.N):
                if (i + 1) % 10 == 0 and self.verbose is True:
                    print("processing graph {}...".format(i + 1))

                grow = f.readline().strip().split()
                # line_2 == [n_nodes, l] is equal to
                # [node number of a graph, class label of a graph]
                n_nodes, glabel = [int(w) for w in grow]

                # relabel graphs
                if glabel not in self.glabel_dict:
                    mapped = len(self.glabel_dict)
                    self.glabel_dict[glabel] = mapped

                self.labels.append(self.glabel_dict[glabel])

                g = dgl_graph(([], []))
                g.add_nodes(n_nodes)

                nlabels = []  # node labels
                nattrs = []  # node attributes if it has
                m_edges = 0

                for j in range(n_nodes):
                    nrow = f.readline().strip().split()

                    # handle edges and attributes(if has)
                    tmp = int(nrow[1]) + 2  # tmp == 2 + #edges
                    if tmp == len(nrow):
                        # no node attributes
                        nrow = [int(w) for w in nrow]
                    elif tmp > len(nrow):
                        nrow = [int(w) for w in nrow[:tmp]]
                        nattr = [float(w) for w in nrow[tmp:]]
                        nattrs.append(nattr)
                    else:
                        raise Exception("edge number is incorrect!")

                    # relabel nodes if it has labels
                    # if it doesn't have node labels, then every nrow[0]==0
                    if not nrow[0] in self.nlabel_dict:
                        mapped = len(self.nlabel_dict)
                        self.nlabel_dict[nrow[0]] = mapped

                    nlabels.append(self.nlabel_dict[nrow[0]])

                    m_edges += nrow[1]
                    g.add_edges(j, nrow[2:])