自定义数据集类 & 节点预测与边预测任务实践

最新推荐文章于 2023-05-13 12:08:07 发布

m0_38056684

最新推荐文章于 2023-05-13 12:08:07 发布

阅读量306

点赞数

本文链接：https://blog.csdn.net/m0_38056684/article/details/118266320

版权

4-1 自定义数据集类

参看资料来源：

https://github.com/datawhalechina/team-learning-nlp/tree/master/GNN

通过继承InMemoryDataset类来自定义一个数据可全部存储到内存的数据集类。

class InMemoryDataset(root: Optional[str] = None, transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None, pre_filter: Optional[Callable] = None)

InMemoryDataset类的构造函数接口所示

每个数据集都要有一个根文件夹（root），根文件夹下又有两个文件夹，分别是raw_dir和processed_dir。
继承InMemoryDataset类的每个数据集类可以传递一个transform函数，一个pre_transform函数和一个pre_filter函数。

为了创建一个InMemoryDataset，需要实现四个基本方法：

raw_file_names()：是一个属性方法，返回一个文件名列表，包含在raw_dir文件夹中的文件，如果没有则调用process()函数下载文件到raw_dir文件夹。
processed_file_names()：是一个属性方法，返回一个文件名列表，包含在processed_dir文件夹中的文件，如果没有则调用process()函数对样本做预处理然后保存到processed_dir文件夹。
download(): 将原始数据文件下载到raw_dir文件夹。
process(): 对样本做预处理然后保存到processed_dir文件夹。

import torch
from torch_geometric.data import InMemoryDataset, download_url

class MyOwnDataset(InMemoryDataset):
    def __init__(self, root, transform=None, pre_transform=None, pre_filter=None):
        super().__init__(root=root, transform=transform, pre_transform=pre_transform, pre_filter=pre_filter)
        self.data, self.slices = torch.load(self.processed_paths[0])

    @property
    def raw_file_names(self):
        return ['some_file_1', 'some_file_2', ...]

    @property
    def processed_file_names(self):
        return ['data.pt']

    def download(self):
        # Download to `self.raw_dir`.
        download_url(url, self.raw_dir)
        ...

    def process(self):
        # Read data into huge `Data` list.
        data_list = [...]

        if self.pre_filter is not None:
            data_list = [data for data in data_list if self.pre_filter(data)]

        if self.pre_transform is not None:
            data_list = [self.pre_transform(data) for data in data_list]

        data, slices = self.collate(data_list)
        torch.save((data, slices), self.processed_paths[0])

class Planetoid(InMemoryDataset):
    r"""The citation network datasets "Cora", "CiteSeer" and "PubMed" from the
    `"Revisiting Semi-Supervised Learning with Graph Embeddings"
    <https://arxiv.org/abs/1603.08861>`_ paper.
    Nodes represent documents and edges represent citation links.
    Training, validation and test splits are given by binary masks.

    Args:
        root (string): Root directory where the dataset should be saved.
        name (string): The name of the dataset (:obj:`"Cora"`,
            :obj:`"CiteSeer"`, :obj:`"PubMed"`).
        split (string): The type of dataset split
            (:obj:`"public"`, :obj:`"full"`, :obj:`"random"`).
            If set to :obj:`"public"`, the split will be the public fixed split
            from the
            `"Revisiting Semi-Supervised Learning with Graph Embeddings"
            <https://arxiv.org/abs/1603.08861>`_ paper.
            If set to :obj:`"full"`, all nodes except those in the validation
            and test sets will be used for training (as in the
            `"FastGCN: Fast Learning with Graph Convolutional Networks via
            Importance Sampling" <https://arxiv.org/abs/1801.10247>`_ paper).
            If set to :obj:`"random"`, train, validation, and test sets will be
            randomly generated, according to :obj:`num_train_per_class`,
            :obj:`num_val` and :obj:`num_test`. (default: :obj:`"public"`)
        num_train_per_class (int, optional): The number of training samples
            per class in case of :obj:`"random"` split. (default: :obj:`20`)
        num_val (int, optional): The number of validation samples in case of
            :obj:`"random"` split. (default: :obj:`500`)
        num_test (int, optional): The number of test samples in case of
            :obj:`"random"` split. (default: :obj:`1000`)
        transform (callable, optional): A function/transform that takes in an
            :obj:`torch_geometric.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:`torch_geometric.data.Data` object and returns a
            transformed version. The data object will be transformed before
            being saved to disk. (default: :obj:`None`)
    """

    url = 'https://github.com/kimiyoung/planetoid/raw/master/data'

    def __init__(self, root, name, split="public", num_train_per_class=20,
                 num_val=500, num_test=1000, transform=None,
                 pre_transform=None):
        # 这里也可以直接删去self.name与接口中的name，然后把后面self.name的值改为“PubMed”（部分位置要改为小写），即可实现我们的需求
        self.name = name

        super(PlanetoidPubMed, self).__init__(root, transform, pre_transform)
        self.data, self.slices = torch.load(self.processed_paths[0])

        self.split = split
        assert self.split in ['public', 'full', 'random']

        if split == 'full':
            data = self.get(0)
            data.train_mask.fill_(True)
            data.train_mask[data.val_mask | data.test_mask] = False
            self.data, self.slices = self.collate([data])

        elif split == 'random':
            data = self.get(0)
            data.train_mask.fill_(False)
            for c in range(self.num_classes):
                idx = (data.y == c).nonzero(as_tuple=False).view(-1)
                idx = idx[torch.randperm(idx.size(0))[:num_train_per_class]]
                data.train_mask[idx] = True

            remaining = (~data.train_mask).nonzero(as_tuple=False).view(-1)
            remaining = remaining[torch.randperm(remaining.size(0))]

            data.val_mask.fill_(False)
            data.val_mask[remaining[:num_val]] = True

            data.test_mask.fill_(False)
            data.test_mask[remaining[num_val:num_val + num_test]] = True

            self.data, self.slices = self.collate([data])

    @property
    def raw_dir(self):
        return osp.join(self.root, self.name, 'raw')

    @property
    def processed_dir(self):
        return osp.join(self.root, self.name, 'processed')

    @property
    def raw_file_names(self):
        names = ['x', 'tx', 'allx', 'y', 'ty', 'ally', 'graph', 'test.index']
        return ['ind.{}.{}'.format(self.name.lower(), name) for name in names]

    @property
    def processed_file_names(self):
        return 'data.pt'

    def download(self):
        for name in self.raw_file_names:
            download_url('{}/{}'.format(self.url, name), self.raw_dir)

    def process(self):
        data = read_planetoid_data(self.raw_dir, self.name)
        data = data if self.pre_transform is None else self.pre_transform(data)
        torch.save(self.collate([data]), self.processed_paths[0])

    def __repr__(self):
        return '{}()'.format(self.name)

class PlanetoidPubMed(InMemoryDataset):

    url = 'https://github.com/kimiyoung/planetoid/raw/master/data'

    def __init__(self, root='/Dataset/Planetoid/PubMed', transform=None, pre_transform=None, pre_filter=None):

        self.raw = osp.join(root,'raw')
        self.processed = osp.join(root, 'processed')

        super(PlanetoidPubMed, self).__init__(root=root, transform=transform, pre_transform=pre_transform, pre_filter=pre_filter)
        self.data, self.slices = torch.load(self.processed_paths[0])   #  processed_paths来自于Dataset类

    # 定义四个函数，其中前两个是属性获取，采用property修饰器

    # 返回原始文件列表
    @property
    def raw_file_names(self):
        names = ['x', 'tx', 'allx', 'y', 'ty', 'ally', 'graph', 'test.index']
        return ['ind.pubmed.{}'.format(name) for name in names]

    # 返回需要跳过的文件列表
    @property
    def processed_file_names(self):
        return ['data.pt']

    # 下载原生文件
    def download(self):
        for name in self.raw_file_names:
            download_url('{}/{}'.format(self.url, name), self.raw)

    def process(self):
        data = read_planetoid_data(self.raw, "pubmed")
        data_list = [data]

        if self.pre_filter is not None:
            data_list = [data for data in data_list if self.pre_filter(data)]

        if self.pre_transform is not None:
            data_list = [self.pre_transform(data) for data in data_list]

        data, slices = self.collate(data_list)

        torch.save((data, slices), self.processed_paths[0])

    # 显示属性
    def __rper__(self):
        return 'PubMed()'

4-2 节点预测与边预测任务实践

之前介绍过由2层GATConv组成的神经网络，现在重定义一个GAT神经网络，使其能够通过参数定义GATConv的层数，以及每一层GATConv的out_channels。神经网络模型定义如下：

class GAT(torch.nn.Module):
    def __init__(self, num_features, hidden_channels_list, num_classes):
        super(GAT, self).__init__()
        torch.manual_seed(12345)
        hns = [num_features] + hidden_channels_list
        conv_list = []
        for idx in range(len(hidden_channels_list)):
            conv_list.append((GATConv(hns[idx], hns[idx+1]), 'x, edge_index -> x'))
            conv_list.append(ReLU(inplace=True),)

        self.convseq = Sequential('x, edge_index', conv_list)
        self.linear = Linear(hidden_channels_list[-1], num_classes)

    def forward(self, x, edge_index):
        x = self.convseq(x, edge_index)
        x = F.dropout(x, p=0.5, training=self.training)
        x = self.linear(x)
        return x

由于神经网络由多个GATConv顺序相连而构成，因此我们使用了torch_geometric.nn.Sequential容器，详细内容可见于官方文档。

边预测任务，预测两个节点之间是否存在边

import os.path as osp

from torch_geometric.utils import negative_sampling
from torch_geometric.datasets import Planetoid
import torch_geometric.transforms as T
from torch_geometric.utils import train_test_split_edges

dataset = 'Cora'
path = osp.join(osp.dirname(osp.realpath(__file__)), '..', 'data', dataset)
dataset = Planetoid(path, dataset, transform=T.NormalizeFeatures())
data = dataset[0]
data.train_mask = data.val_mask = data.test_mask = data.y = None
data = train_test_split_edges(data)

print(data.edge_index.shape)
# torch.Size([2, 10556])

for key in data.keys:
    print(key, getattr(data, key).shape)

import torch
from torch_geometric.nn import GCNConv

class Net(torch.nn.Module):
    def __init__(self, in_channels, out_channels):
        super(Net, self).__init__()
        self.conv1 = GCNConv(in_channels, 128)
        self.conv2 = GCNConv(128, out_channels)

    def encode(self, x, edge_index):
        x = self.conv1(x, edge_index)
        x = x.relu()
        return self.conv2(x, edge_index)

    def decode(self, z, pos_edge_index, neg_edge_index):
        edge_index = torch.cat([pos_edge_index, neg_edge_index], dim=-1)
        return (z[edge_index[0]] * z[edge_index[1]]).sum(dim=-1)

    def decode_all(self, z):
        prob_adj = z @ z.t()
        return (prob_adj > 0).nonzero(as_tuple=False).t()

    
def get_link_labels(pos_edge_index, neg_edge_index):
    num_links = pos_edge_index.size(1) + neg_edge_index.size(1)
    link_labels = torch.zeros(num_links, dtype=torch.float)
    link_labels[:pos_edge_index.size(1)] = 1.
    return link_labels

def train(data, model, optimizer):
    model.train()

    neg_edge_index = negative_sampling(
        edge_index=data.train_pos_edge_index,
        num_nodes=data.num_nodes,
        num_neg_samples=data.train_pos_edge_index.size(1))

    optimizer.zero_grad()
    z = model.encode(data.x, data.train_pos_edge_index)
    link_logits = model.decode(z, data.train_pos_edge_index, neg_edge_index)
    link_labels = get_link_labels(data.train_pos_edge_index, neg_edge_index).to(data.x.device)
    loss = F.binary_cross_entropy_with_logits(link_logits, link_labels)
    loss.backward()
    optimizer.step()

    return loss

@torch.no_grad()
def test(data, model):
    model.eval()

    z = model.encode(data.x, data.train_pos_edge_index)

    results = []
    for prefix in ['val', 'test']:
        pos_edge_index = data[f'{prefix}_pos_edge_index']
        neg_edge_index = data[f'{prefix}_neg_edge_index']
        link_logits = model.decode(z, pos_edge_index, neg_edge_index)
        link_probs = link_logits.sigmoid()
        link_labels = get_link_labels(pos_edge_index, neg_edge_index)
        results.append(roc_auc_score(link_labels.cpu(), link_probs.cpu()))
    return results



def main():
    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    
    dataset = 'Cora'
    path = osp.join(osp.dirname(osp.realpath(__file__)), '..', 'data', dataset)
    dataset = Planetoid(path, dataset, transform=T.NormalizeFeatures())
    data = dataset[0]
    ground_truth_edge_index = data.edge_index.to(device)
    data.train_mask = data.val_mask = data.test_mask = data.y = None
    data = train_test_split_edges(data)
    data = data.to(device)

    model = Net(dataset.num_features, 64).to(device)
    optimizer = torch.optim.Adam(params=model.parameters(), lr=0.01)

    best_val_auc = test_auc = 0
    for epoch in range(1, 101):
        loss = train(data, model, optimizer)
        val_auc, tmp_test_auc = test(data, model)
        if val_auc > best_val_auc:
            best_val_auc = val_auc
            test_auc = tmp_test_auc
        print(f'Epoch: {epoch:03d}, Loss: {loss:.4f}, Val: {val_auc:.4f}, '
              f'Test: {test_auc:.4f}')

    z = model.encode(data.x, data.train_pos_edge_index)
    final_edge_index = model.decode_all(z)


if __name__ == "__main__":
    main()