PyTorch Geometric GCN 模型训练与验证：基于自定义数据集的图神经网络

import os
import pandas as pd
import torch
import torch.nn as nn
from torch_geometric.data import Data, DataLoader
from torch_geometric.nn import GCNConv
import torch.nn.functional as F
from sklearn.model_selection import train_test_split

# 加载数据并创建PyG数据集类：
class MyDataset(torch.utils.data.Dataset):
    def __init__(self, root, transform=None, pre_transform=None):
        self.edges = pd.read_csv(os.path.join(root, 'edges.csv'), header=None)
        self.features1 = pd.read_csv(os.path.join(root, 'features1.csv'), header=None)
        self.features2 = pd.read_csv(os.path.join(root, 'features2.csv'), header=None)
        self.labels = pd.read_csv(os.path.join(root, 'labels.csv'), header=None)
        self.transform = transform
        self.pre_transform = pre_transform

    def __len__(self):
        return len(self.labels)

    def __getitem__(self, idx):
        edge_index = torch.tensor(self.edges.values, dtype=torch.long).t().contiguous()
        x = torch.stack([torch.tensor(self.features1.iloc[idx].values, dtype=torch.float),
                          torch.tensor(self.features2.iloc[idx].values, dtype=torch.float)], dim=1)
        # 将两个特征向量进行堆叠操作的。具体来说，self.features1.iloc[idx] 和 self.features2.iloc[idx] 是两个Pandas DataFrame对象的行索引为idx的数据，这里假设它们的形状为(n,)，即包含了n个元素的一维数组。
        #torch.stack()函数将两个张量在dim=1进行堆叠操作，即将它们按列方向拼接成一个新的张量。假设两个特征向量都有m个元素，那么堆叠后的张量的形状将为(m,2)，即包含m行、2列的二维数组。
        y = torch.tensor(self.labels.iloc[idx].values, dtype=torch.long)

        # 定义图数据的train_mask和val_mask
        train_mask = torch.zeros(y.size(0), dtype=torch.bool)
        val_mask = torch.zeros(y.size(0), dtype=torch.bool)
        train_mask[:16] = (idx < 16)
        val_mask[16:] = (idx >= 16)

        data = Data(x=x, edge_index=edge_index, y=y, train_mask=train_mask, val_mask=val_mask)

        if self.transform is not None:
            data = self.transform(data)
        return data

# 定义GCN模型：
class GCN(torch.nn.Module):
    def __init__(self, num_node_features, num_classes):
        super(GCN, self).__init__()
        self.conv1 = GCNConv(num_node_features, 16)
        self.conv2 = GCNConv(16, 32)
        self.conv3 = GCNConv(32, num_classes)

    def forward(self, data):
        x, edge_index = data.x, data.edge_index
        x = self.conv1(x, edge_index)
        x = F.relu(x)
        x = self.conv2(x, edge_index)
        x = F.relu(x)
        x = F.dropout(x, training=self.training)
        x = self.conv3(x, edge_index)
        return x

# class GCN(nn.Module):
#     def __init__(self, num_node_features, num_classes):
#         super(GCN, self).__init__()
#         self.conv1 = GCNConv(num_node_features, 32)
#         self.conv2 = GCNConv(32, num_classes)
#     def forward(self, data):
#         x, edge_index = data.x, data.edge_index
#         x = self.conv1(x, edge_index)
#         x = F.relu(x)
#         x = F.dropout(x, training=self.training)
#         x = self.conv2(x, edge_index)
#         return F.log_softmax(x, dim=1)

# 创建训练和验证模型：
def train_model(dataset, model, optimizer, device):
    model.train()
    total_loss = 0.0

    for data in dataset:
        data = data.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = F.cross_entropy(output[data.train_mask], data.y[data.train_mask])
        loss.backward()
        optimizer.step()
        total_loss += loss.item()

    return total_loss / len(dataset)

def validate_model(dataset, model, device):
    model.eval()
    correct = 0
    total = 0

    for data in dataset:
        data = data.to(device)
        output = model(data)
        _, predicted = torch.max(output[data.val_mask], 1)
        total += data.val_mask.sum().item()
        correct += (predicted == data.y[data.val_mask]).sum().item()

    return correct / total

# 加载数据集、创建模型、定义优化器和训练循环，以及验证模型：
if __name__ == '__main__':
    dataset = MyDataset(root="C:\Users\jh\Desktop\data\raw1")
    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

    model = GCN(num_node_features=2, num_classes=3).to(device)
    optimizer = torch.optim.Adam(model.parameters(), lr=0.01)

    train_dataset, val_dataset = train_test_split(dataset, test_size=0.2)
    #将数据集dataset分成训练集（train_dataset）和验证集（val_dataset），其中训练集占80%（test_size=0.2）的比例，验证集占20%的比例。

    train_loader = DataLoader(train_dataset, batch_size=1, shuffle=False)
    val_loader = DataLoader(val_dataset, batch_size=1, shuffle=False)
    #     dataloader = DataLoader(dataset, batch_size=1, shuffle=False)

    epochs = 2000
    for epoch in range(epochs):
        #         train_loss = train_model(dataloader, model, optimizer, device)
        #         val_accuracy = validate_model(dataloader, model, device)
        train_loss = train_model(train_loader, model, optimizer, device)
        val_accuracy = validate_model(val_loader, model, device)
        print(f'Epoch {epoch+1}/{epochs} , Train Loss: {train_loss:.4f} , Val_Acc: {val_accuracy:.4f}')