Node2Vec을 기반으로 Python에서 노드 분류 및 시각화를 구현하는 방법

import networkx as nx 
import numpy as np 
import pandas as pd 
import matplotlib.pyplot as plt 
%matplotlib inline 
from sklearn.manifold import TSNE 
from node2vec import Node2Vec 
# 加载Cora数据集
cora = pd.read_csv('cora/cora.content', sep='\t', header=None)
cited_in = pd.read_csv('cora/cora.cites', sep='\t', header=None,
                       names=['target', 'source'])
nodes, features = cora.iloc[:, :-1], cora.iloc[:, -1]

# 定义函数：构造基于Cora数据集的图结构
def create_graph(nodes, features, cited_in):
    nodes.index = nodes.index.map(str)
    graph = nx.from_pandas_edgelist(cited_in,
                                    source='source',
                                    target='target')
    for index, row in nodes.iterrows():
        node_id = str(row[0])
        features = row.drop(labels=[0])
        node_attrs = {f'attr_{i}': float(x) for i, x in enumerate(features)}
        if graph.has_node(node_id) == True:
            temp = graph.nodes[node_id]
            temp.update(node_attrs)
            graph.add_nodes_from([(node_id, temp)])
        else:
            graph.add_nodes_from([(node_id, node_attrs)])
    return graph
# 构建图
graph = create_graph(nodes, features, cited_in)

# 定义函数：创建基于Cora数据集的嵌入
def create_embeddings(graph):
    # 初始化node2vec实例，指定相关超参数
    n2v = Node2Vec(graph, dimensions=64, walk_length=30,
                   num_walks=200, p=1, q=1, weight_key='attr_weight')
    # 基于指定参数训练得到嵌入向量表达式
    model = n2v.fit(window=10, min_count=1, batch_words=4)
    # 获得所有图中节点的嵌入向量
    embeddings = pd.DataFrame(model.wv.vectors)
    ids = list(map(str, model.wv.index2word))
    # 将原有的特征和id与新获取到的嵌入向量按行合并
    lookup_table = nodes.set_index(0).join(embeddings.set_index(embeddings.index))
    return np.array(lookup_table.dropna().iloc[:, -64:]), np.array(list(range(1, lookup_table.shape[0] + 1)))
# 创建嵌入向量
cora_embeddings, cora_labels = create_embeddings(graph)

from sklearn import svm, model_selection, metrics 
# 使用支持向量机作为示范的分类器
svm_model = svm.SVC(kernel='rbf', C=1, gamma=0.01)
# 进行交叉验证和分类训练
scores = model_selection.cross_val_score(
    svm_model, cora_embeddings, cora_labels, cv=5)
print(scores.mean())

# 定义函数：可视化Nodes2Vec的结果
def visualize_results(embeddings, labels):
    # 使用t-SNE对数据进行降维并绘图
    tsne = TSNE(n_components=2, verbose=1, perplexity=40, n_iter=300)
    tsne_results = tsne.fit_transform(embeddings)
    plt.figure(figsize=(10, 5))
    plt.scatter(tsne_results[:,0], tsne_results[:,1], c=labels)
    plt.colorbar()
    plt.show()
# 可视化结果
visualize_results(cora_embeddings, cora_labels)