https://github.com/aditya-ranjan1234/exploring-networkx
Exploring graph theory and network analysis using NetworkX in Python
https://github.com/aditya-ranjan1234/exploring-networkx
Last synced: 5 days ago
JSON representation
Exploring graph theory and network analysis using NetworkX in Python
- Host: GitHub
- URL: https://github.com/aditya-ranjan1234/exploring-networkx
- Owner: Aditya-Ranjan1234
- License: gpl-3.0
- Created: 2025-03-06T19:10:59.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2025-03-06T19:19:10.000Z (7 months ago)
- Last Synced: 2025-03-26T21:35:54.087Z (7 months ago)
- Language: Python
- Homepage:
- Size: 17.7 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Learning NetworkX: Graphs, CNNs, GNNs & More
## Overview
This repository documents my journey in learning NetworkX, an essential Python library for graph-based computations. I explore various applications, including visualizing graphs of Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), and more.
## Why NetworkX?
NetworkX is a powerful tool for:
- Creating and manipulating graphs
- Analyzing network structures
- Visualizing relationships in deep learning models
## Getting Started
### Installation
Ensure you have Python installed, then install NetworkX:
```bash
pip install networkx matplotlib
```
### Basic Usage
```python
import networkx as nx
import matplotlib.pyplot as plt
# Create a simple graph
G = nx.Graph()
G.add_edges_from([(1, 2), (2, 3), (3, 1)])
# Draw the graph
nx.draw(G, with_labels=True)
plt.show()
```
## Applications Explored
- **Graph Visualization**: Understanding how CNN and GNN architectures can be represented as graphs.
- **Model Structure Analysis**: Investigating connections in deep learning architectures.
- **Custom Graphs**: Creating and analyzing networks for AI/ML research.
## Future Goals
- Implement more advanced graph algorithms.
- Explore real-world applications in AI and ML.
- Optimize graph visualizations for large-scale models.