How to use the cogdl.data.Dataset function in cogdl

context = f.readlines()
        print("class number: ", len(context))
        label = np.zeros((num_node, len(context)))

        for i, line in enumerate(context):
            line = map(int, line.strip().split("\t"))
            for node in line:
                label[node, i] = 1

    y = torch.from_numpy(label).to(torch.float)
    data = Data(x=None, edge_index=edge_index, y=y)

    return data


class EdgelistLabel(Dataset):
    r"""networks from the https://github.com/THUDM/ProNE/raw/master/data

    Args:
        root (string): Root directory where the dataset should be saved.
        name (string): The name of the dataset (:obj:`"Wikipedia"`).
    """

    url = "https://github.com/THUDM/ProNE/raw/master/data"

    def __init__(self, root, name):
        self.name = name
        super(EdgelistLabel, self).__init__(root)
        self.data = torch.load(self.processed_paths[0])

    @property
    def raw_file_names(self):

for line in f:
            items = line.strip().split()
            if items[0] not in test_data:
                test_data[items[0]] = [[], []]
            test_data[items[0]][1 - int(items[3])].append(
                [int(items[1]), int(items[2])]
            )

    data = Data()
    data.train_data = train_data
    data.valid_data = valid_data
    data.test_data = test_data
    return data


class GatneDataset(Dataset):
    r"""The network datasets "Amazon", "Twitter" and "YouTube" from the
    `"Representation Learning for Attributed Multiplex Heterogeneous Network"
    `_ paper.

    Args:
        root (string): Root directory where the dataset should be saved.
        name (string): The name of the dataset (:obj:`"Amazon"`,
            :obj:`"Twitter"`, :obj:`"YouTube"`).
    """

    url = "https://github.com/THUDM/GATNE/raw/master/data"

    def __init__(self, root, name):
        self.name = name
        super(GatneDataset, self).__init__(root)
        self.data = torch.load(self.processed_paths[0])

from itertools import repeat, product

import torch
from cogdl.data import Dataset, Data


class InMemoryDataset(Dataset):
    r"""Dataset base class for creating graph datasets which fit completely
    into memory.
    See `here `__ for the accompanying
    tutorial.

    Args:
        root (string): Root directory where the dataset should be saved.
        transform (callable, optional): A function/transform that takes in an
            :obj:`cogdl.data.Data` object and returns a transformed
            version. The data object will be transformed before every access.
            (default: :obj:`None`)
        pre_transform (callable, optional): A function/transform that takes in
            an :obj:`cogdl.data.Data` object and returns a
            transformed version. The data object will be transformed before
            being saved to disk. (default: :obj:`None`)

import json
import os
import os.path as osp
from itertools import product

import numpy as np
import scipy.io as scio
import tensorflow as tf
import pickle

from cogdl.data import Data, Dataset, download_url

from . import register_dataset


class MatlabMatrix(Dataset):
    r"""networks from the http://leitang.net/code/social-dimension/data/ or http://snap.stanford.edu/node2vec/

    Args:
        root (string): Root directory where the dataset should be saved.
        name (string): The name of the dataset (:obj:`"Blogcatalog"`).
    """

    def __init__(self, root, name, url):
        self.name = name
        self.url = url
        super(MatlabMatrix, self).__init__(root)
        with open(self.processed_paths[0], 'rb') as input:
            self.data = pickle.load(input)

    @property
    def raw_file_names(self):

import json
import os
import os.path as osp
from itertools import product

import numpy as np
import scipy
import torch

from cogdl.data import Data, Dataset, download_url

from . import register_dataset


class MatlabMatrix(Dataset):
    r"""networks from the http://leitang.net/code/social-dimension/data/ or http://snap.stanford.edu/node2vec/

    Args:
        root (string): Root directory where the dataset should be saved.
        name (string): The name of the dataset (:obj:`"Blogcatalog"`).
    """

    def __init__(self, root, name, url):
        self.name = name
        self.url = url
        super(MatlabMatrix, self).__init__(root)
        self.data = torch.load(self.processed_paths[0])

    @property
    def raw_file_names(self):
        splits = [self.name]