【论文代码】GraphSAGE（更新ing）

# -*- coding: utf-8 -*-
"""
Created on Fri Oct  8 23:16:13 2021
@author: 86493
"""
import torch
from torch_geometric.datasets import Planetoid
from torch_geometric.transforms import NormalizeFeatures
dataset = Planetoid(root='C:/dataset/Cora/processed', name='Cora', transform=NormalizeFeatures())
print()
print(f'Dataset: {dataset}:')
print('======================')
print(f'Number of graphs: {len(dataset)}')
print(f'Number of features: {dataset.num_features}')
print(f'Number of classes: {dataset.num_classes}')
data = dataset[0]  # Get the first graph object.
print()
print(data)
print('======================')
# Gather some statistics about the graph.
print(f'Number of nodes: {data.num_nodes}')
print(f'Number of edges: {data.num_edges}')
print(f'Average node degree: {data.num_edges / data.num_nodes:.2f}')
print(f'Number of training nodes: {data.train_mask.sum()}')
print(f'Training node label rate: {int(data.train_mask.sum()) / data.num_nodes:.2f}')
print(f'Contains isolated nodes: {data.has_isolated_nodes()}')
print(f'Contains self-loops: {data.has_self_loops()}')
print(f'Is undirected: {data.is_undirected()}')
# 2.可视化节点表征分布的方法
import matplotlib.pyplot as plt
from sklearn.manifold import TSNE
def visualize(h, color):
    z = TSNE(n_components=2).fit_transform(h.detach().cpu().numpy())
    plt.figure(figsize=(10,10))
    plt.xticks([])
    plt.yticks([])
    plt.scatter(z[:, 0], z[:, 1], s=70, c=color, cmap="Set2")
    plt.show()
# 网络的构造
import torch
from torch.nn import Linear
import torch.nn.functional as F
"""
from torch_geometric.nn import GCNConv
class GCN(torch.nn.Module):
    def __init__(self, hidden_channels):
        super(GCN, self).__init__()
        torch.manual_seed(12345)
        self.conv1 = GCNConv(dataset.num_features, hidden_channels)
        self.conv2 = GCNConv(hidden_channels, dataset.num_classes)
    def forward(self, x, edge_index):
        x = self.conv1(x, edge_index)
        x = x.relu()
        x = F.dropout(x, p=0.5, training=self.training)
        x = self.conv2(x, edge_index)
        return x
"""
from torch_geometric.nn import SAGEConv
class SAGE(torch.nn.Module):
    def __init__(self, hidden_channels):
        super(SAGE, self).__init__()
        torch.manual_seed(12345)
        self.conv1 = SAGEConv(dataset.num_features, hidden_channels)
        self.conv2 = SAGEConv(hidden_channels, dataset.num_classes)
    def forward(self, x, edge_index):
        x = self.conv1(x, edge_index)
        x = x.relu()
        x = F.dropout(x, p=0.5, training=self.training)
        x = self.conv2(x, edge_index)
        return x
model = SAGE(hidden_channels=16)
print(model)
# 可视化由未经训练的图神经网络生成的节点表征
model = SAGE(hidden_channels=16)
model.eval()
out = model(data.x, data.edge_index)
visualize(out, color=data.y)
# 图神经网络的训练
model = SAGE(hidden_channels=16)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)
criterion = torch.nn.CrossEntropyLoss()
def train():
      model.train()
      optimizer.zero_grad()  # Clear gradients.
      out = model(data.x, data.edge_index)  # Perform a single forward pass.
      loss = criterion(out[data.train_mask], data.y[data.train_mask])  # Compute the loss solely based on the training nodes.
      loss.backward()  # Derive gradients.
      optimizer.step()  # Update parameters based on gradients.
      return loss
for epoch in range(1, 201):
    loss = train()
    print(f'Epoch: {epoch:03d}, Loss: {loss:.4f}')
# 增加loss折线图
import pandas as pd
df = pd.DataFrame(columns = ["Loss"]) # columns列名
df.index.name = "Epoch" 
for epoch in range(1, 201):
    loss = train()
    #df.loc[epoch] = loss.item()
    df.loc[epoch] = loss.item()
df.plot() 
# 图神经网络的测试
def test():
      model.eval()
      out = model(data.x, data.edge_index)
      pred = out.argmax(dim=1)  # Use the class with highest probability.
      test_correct = pred[data.test_mask] == data.y[data.test_mask]  # Check against ground-truth labels.
      test_acc = int(test_correct.sum()) / int(data.test_mask.sum())  # Derive ratio of correct predictions.
      return test_acc
test_acc = test()
print(f'Test Accuracy: {test_acc:.4f}')
# 可视化由训练后的图神经网络生成的节点表征
model.eval()
out = model(data.x, data.edge_index)
visualize(out, color=data.y)

Dataset: Cora():
======================
Number of graphs: 1
Number of features: 1433
Number of classes: 7
Data(
  x=[2708, 1433], edge_index=[2, 10556], 
  y=[2708], train_mask=[2708], 
  val_mask=[2708], test_mask=[2708]
  )
======================
Number of nodes: 2708
Number of edges: 10556
Average node degree: 3.90
Number of training nodes: 140
Training node label rate: 0.05
Contains isolated nodes: False
Contains self-loops: False
Is undirected: True
SAGE(
  (conv1): SAGEConv(1433, 16)
  (conv2): SAGEConv(16, 7)
)