Pytorch-Geometric

vision
1

I’m new to Pytorch-geometric, and geometric deep learning. I’m trying to visualize the datasets available in pytorch-geometric, but couldn’t find anything to do so.

How do I visualize these graph datasets. Is there provision to do so in pytorch-geometric? How else can we visualize this ?

1 Like
2 
from torch_geometric.datasets import KarateClub
dataset = KarateClub()

for i in dataset[0]:
  print(i)
# this torch.geometric.datasets object comprises of edge(edge information for each node), x(nodes) and y(labels for each node)

edge,x,y = dataset[0]
numpyx = x[1].numpy()
numpyy = y[1].numpy()
numpyedge = edge[1].numpy()

import networkx as nx

g = nx.Graph(numpyx)

name,edgeinfo = edge

src = edgeinfo[0].numpy()
dst = edgeinfo[1].numpy()
edgelist = zip(src,dst)

for i,j in edgelist:
  g.add_edge(i,j) 

nx.draw_networkx(g)
3

Hi,
What is nx here? Is it networkx library?

4

Yes. My apologies. I’ve now modified the code to include the import line.

5

No problem, Good luck.

6

Actually… there’s an even better way. PyG has something in-built to convert the graph datasets to a networkx graph.

import networkx as nx
import torch
import numpy as np
import pandas as pd
from torch_geometric.datasets import Planetoid
from torch_geometric.utils.convert import to_networkx

dataset1 = Planetoid(root = '/content/cora',name='Cora')

cora = dataset1 [0]

coragraph = to_networkx(cora)

node_labels = cora.y[list(coragraph.nodes)].numpy()

import matplotlib.pyplot as plt
plt.figure(1,figsize=(14,12)) 
nx.draw(coragraph, cmap=plt.get_cmap('Set1'),node_color = node_labels,node_size=75,linewidths=6)
plt.show()
3 Likes
7

Hello all! I am also new in PyG… I am trying to import the dataset using Colab but following your instructions outputs an error: module ‘community’ has no attribute ‘best_partition’. Do you know why this could be happening? Thanks for the help!!

from torch_geometric.datasets import KarateClub

dataset = KarateClub()
AttributeError: module ‘community’ has no attribute ‘best_partition’

8

For future issues, python-louvain already installs networkx package. Therefore, if the previous error appears uninstall both libraries and install back only python-louvain.

9

this is impler:

import networkx as nx

edge_index = torch.tensor([[0, 1, 1, 2],
                           [1, 0, 2, 1]], dtype=torch.long)
x = torch.tensor([[-1], [0], [1]], dtype=torch.float)

data = torch_geometric.data.Data(x=x, edge_index=edge_index)
g = torch_geometric.utils.to_networkx(data, to_undirected=True)
nx.draw(g)

you need matplot lib installed too do conda install -y matplotlib.

10

I tried with enzyme datset in the same way but i didnt get and i tried in this way and it is giving error: please help:


def convert_to_networkx(graph, n_sample=None):
   
    g = to_networkx(graph, node_attrs=["x"])
    y = graph.y.numpy()
    if n_sample is not None:
        if n_sample >= len(g.nodes):
            # If n_sample is larger or equal to the number of nodes, use all nodes
            sampled_nodes = list(g.nodes)
        else:
            # Sample n_sample nodes from the graph
            sampled_nodes = random.sample(list(g.nodes), n_sample)

        g = g.subgraph(sampled_nodes)
        y = y[sampled_nodes]

    return g, y


def plot_graph(g, y):

    plt.figure(figsize=(9, 7))
    nx.draw_spring(g, node_size=30, arrows=False, node_color=y)
    plt.show() 

from torch_geometric.datasets import TUDataset
import random

# Load the Enzymes dataset
dataset = TUDataset(root='/path/to/your/dataset', name='ENZYMES')

# Check the total number of graphs in the dataset
num_graphs_in_dataset = len(dataset)

# Define the number of graphs you want to visualize (e.g., 5 random graphs)
num_graphs_to_visualize = 5

# Ensure you don't sample more graphs than are available in the dataset
if num_graphs_to_visualize > num_graphs_in_dataset:
    num_graphs_to_visualize = num_graphs_in_dataset

# Create a list of unique indices to select random graphs
random_graph_indices = random.sample(range(num_graphs_in_dataset), num_graphs_to_visualize)

# Iterate through the selected graphs
for i in random_graph_indices:
    g, y = convert_to_networkx(dataset[i], n_sample=1000)  # You can adjust n_sample as needed
    plot_graph(g, y)

I am getting error:

Untitled-2.ipynb Cell 4 line 2
     22 for i in random_graph_indices:
     23     print("i=",i )
---> 24     g, y = convert_to_networkx(dataset[i], n_sample=1000)  # You can adjust n_sample as needed
     25     plot_graph(g, y)

Untitled-2.ipynb Cell 4 line 4
     37         sampled_nodes = random.sample(list(g.nodes), n_sample)
     39     g = g.subgraph(sampled_nodes)
---> 40     y = y[sampled_nodes]
     42 return g, y

IndexError: index 1 is out of bounds for axis 0 with size 1

Please help me !! thanks in advance