Scribd
Upload
4 views

graph_analysis_code

Uploaded by

Bhavan Gowda
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
4 views

graph_analysis_code

Uploaded by

Bhavan Gowda
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

graph_analysis.

py

1 import numpy as np
2 import pandas as pd
3 import networkx as nx
4 from sklearn.metrics import mean_squared_error, r2_score
5 import matplotlib.pyplot as plt
6 from mpl_toolkits.mplot3d import Axes3D
7 import scipy.stats as stats
8 from sklearn.model_selection import train_test_split
9 from sklearn.ensemble import RandomForestRegresso­
r
10
11 def generate_graphs(num_nodes=10):
12 graphs = {
13 "Erdos-Renyi": nx.erdos_renyi_graph(num_nodes, 0.5),
14 "Preferential Attachment": nx.barabasi_albert_grap­
h(num_nodes, 3),
15 "Watts-Strogatz": nx.watts_strogatz_graph­
(num_nodes, 4, 0.1),
16 "1D Lattice": nx.grid_graph(dim=[num_nodes]),
17 }
18 return graphs
19
20 def visualize_and_save(graph, name):
21 pos = nx.spring_layout(graph, dim=3, seed=42)
22 fig = plt.figure()
23 ax = fig.add_subplot(111, projection='3d')
24 for node, (x, y, z) in pos.items():
25 ax.scatter(x, y, z, label=node, s=50)
26 for neighbor in graph.neighbors(node):
27 nx_, ny_, nz_ = pos[neighbor] # Avoid naming conflict
28 ax.plot([x, nx_], [y, ny_], [z, nz_], color='black', alpha=0.5)
29 ax.set_title(name)
30 plt.show()
31
32 adj_matrix = nx.adjacency_matrix(graph).todense()
33 print(f"Adjacency Matrix for {name}:\n", adj_matrix)
34 return adj_matrix
35
36 def create_dataset(graph):
37 features = [
38 (graph.degree[node], nx.clustering(graph, node)) for node in graph.nodes()
39 ]
40 target = [np.random.uniform(0.1, 1.0) for _ in graph.nodes()] # Random target values
41 return pd.DataFrame(features, columns=["Degree", "Clustering"]), np.array(target)
42
43 def train_and_evaluate(graphs):
44 results = {}
45 for name, graph in graphs.items():
46 print(f"\nProcessing {name} graph...")
47
48 adj_matrix = visualize_and_save(graph, name)
49
50 X, y = create_dataset(graph)
51
52 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
53
54 model = RandomForestRegresso­
r(n_estimators=100, random_state=42)
55 model.fit(X_train, y_train)
56
57 y_pred = model.predict(X_test)
58 mse = mean_squared_error(y_test, y_pred)
59 r2 = r2_score(y_test, y_pred)
60
61 _, p_value = stats.ttest_ind(y_test, y_pred)
62
63 results[name] = {
64 "MSE": mse,
65 "R2": r2,
66 "P-value": p_value,
67 "Adjacency Matrix": adj_matrix
68 }
69
70 print(f"Results for {name}: MSE={mse:.4f}, R2={r2:.4f}, P-value={p_value:.4f}")
71
72 return results
73
74 if __name__ == "__main__":
75 graphs = generate_graphs(num_nodes=10)
76
77 results = train_and_evaluate(graphs)
78
79 print("\nORBIT - Orbiter, Radar, Ballistic, Inertial, Trajectory Final Results:")
80 for graph, metrics in results.items():
81 print(f"{graph}: {metrics}")
82

You might also like