fagan2888 / pyrgg

🔧 Python Random Graph Generator

---

Random Graph Generator

---

Table of contents

• Overview
• Installation
• Usage
• Issues & Bug Reports
• Todo
• Sample Files
• Example Of Usage
• Supported Formats
• Similar Works
• Dependencies
• Contribution
• References
• Citing
• Authors
• License
• Donate
• Changelog
• Code of Conduct

Overview

Pyrgg is an easy-to-use synthetic random graph generator written in Python which supports various graph file formats including DIMACS .gr files. Pyrgg has the ability to generate graphs of different sizes and is designed to provide input files for broad range of graph-based research applications, including but not limited to testing, benchmarking and performance-analysis of graph processing frameworks. Pyrgg target audiences are computer scientists who study graph algorithms and graph processing frameworks.

Open Hub
PyPI Counter
Github Stars

Branch	master	dev
Travis
AppVeyor

Code Quality

Installation

Source Code

• Download Version 0.9 or Latest Source
• pip install -r requirements.txt or pip3 install -r requirements.txt (Need root access)
• python3 setup.py install or python setup.py install (Need root access)

PyPI

• Check Python Packaging User Guide
• pip install pyrgg==0.9 or pip3 install pyrgg==0.9 (Need root access)

Conda

• Check Conda Managing Package
• conda install -c sepandhaghighi pyrgg (Need root access)

Exe Version (Only Windows)

• Download Exe-Version 0.9
• Run PYRGG-0.9.exe

System Requirements

Pyrgg will likely run on a modern dual core PC. Typical configuration is:

• Dual Core CPU (2.0 Ghz+)
• 4GB of RAM

Note that it may run on lower end equipment though good performance is not guaranteed.

Usage

Issues & Bug Reports

Just fill an issue and describe it. I'll check it ASAP! or send an email to [email protected].

TODO

• Formats
  • DIMACS
  • JSON
  • YAML
  • Pickle
  • CSV
  • TSV
  • WEL
  • ASP
  • TGF
  • UCINET DL
  • GML
  • GDF
  • Matrix Market
  • Graph Line
  • GEXF
• Sizes
  • Small
  • Medium
  • Large
• Weighted Graph
  • Signed Weights
• Unweighted Graph
• Dense Graph
• Sparse Graph
• Directed Graph
• Self loop
• Parallel Arc
• Multithreading
• GUI
• Erdős–Rényi model
• Tree

Sample Files

• Sample 1-DIMACS (100 Vertices , 3KB)
• Sample 2-DIMACS (1000 Vertices , 13KB)
• Sample 3-DIMACS (1000000 Vertices , 7MB)
• Sample 4-DIMACS (5000000 Vertices , 37MB)
• Sample 1-JSON (100 Vertices , 11KB)
• Sample 2-JSON (1000 Vertices , 105KB)
• Sample 1-CSV (100 Vertices , 3KB)
• Sample 2-CSV (1000 Vertices , 51KB)
• Sample 1-TSV (100 Vertices , 29KB)
• Sample 2-TSV (1000 Vertices , 420KB)
• Sample 1-WEL (100 Vertices , 5KB)
• Sample 2-WEL (1000 Vertices , 192KB)
• Sample 1-YAML (30 Vertices , 3KB)
• Sample 2-YAML (100 Vertices , 12KB)
• Sample 1-LP (100 Vertices , 7KB)
• Sample 2-LP (1000 Vertices , 76KB)
• Sample 1-Pickle (100 Vertices , 15KB)
• Sample 2-Pickle (1000 Vertices , 209KB)
• Sample 1-TGF (100 Vertices , 4KB)
• Sample 2-TGF (1000 Vertices , 61KB)
• Sample 1-UCINET DL (100 Vertices , 8KB)
• Sample 2-UCINET DL (1000 Vertices , 729KB)
• Sample 1-MTX (100 Vertices , 59KB)
• Sample 2-MTX (1000 Vertices , 1.8MB)
• Sample 1-GL (100 Vertices , 17KB)
• Sample 2-GL (1000 Vertices , 2.4MB)
• Sample 1-GDF (100 Vertices , 21KB)
• Sample 2-GDF (1000 Vertices , 690KB)
• Sample 1-GML (100 Vertices , 120KB)
• Sample 2-GML (1000 Vertices , 2.4MB)
• Sample 1-GEXF (100 Vertices , 63KB)
• Sample 2-GEXF (1000 Vertices , 6.4MB)

Example Of Usage

• Generate synthetic data for graph processing frameworks (some of them mentioned here) performance-analysis
  • Medusa
  • Totem
  • Frog
  • CuSha

Fig. 1. Rand Graph Generation

• Generate synthetic data for graph benchmark suite like GAP

Supported Formats

• DIMACS(.gr)

   	p sp <number of vertices> <number of edges>
   	a <head_1> <tail_1> <weight_1>
  
   	.
   	.
   	.
   	
   	a <head_n> <tail_n> <weight_n>
  

• CSV(.csv)

   	<head_1>,<tail_1>,<weight_1>
  
   	.
   	.
   	.
   	
   	<head_n>,<tail_n>,<weight_n>
  

• TSV(.tsv)

   	<head_1>	<tail_1>	<weight_1>
  
   	.
   	.
   	.
   	
   	<head_n>	<tail_n>	<weight_n>
  

• JSON(.json)

   	{
   	"graph": {
   			"nodes":[
   			{
   				"id": "1"
   			},
  
   			.
   			.
   			.
   			{
   				"id": "n"
   			}
   			],
   			"edges":[
   			{
   				"source": "head_1",
   				"target": "tail_1",
   				"weight": "weight_1"
   			},
  
   			.
   			.
   			.
  
   			{
   				"source": "head_n",
   				"target": "tail_n",
   				"weight": "weight_n"
   			},
   			]
   		}
   	}
  

• YAML(.yaml)

   	graph:
   		edges:
   		- source: "head_1"
   	  	target: "tail_1"
   	  	weight: "weight_1"
   	
   		.
   		.
   		.
  
   		- source: "head_n"
   	  	target: "tail_n"
   	  	weight: "weight_n"
   					
   		nodes:
   		- id: '1'
  
   		.
   		.
   		.
  
   		- id: 'n'
  
  

• Weighted Edge List(.wel)

   	<head_1> <tail_1> <weight_1>
   	
   	.
   	.
   	.
   	
   	<head_n> <tail_n> <weight_n>	
  

• ASP(.lp)

   	node(1).
   	.
   	.
   	.
   	node(n).
   	edge(head_1,tail_1,weight_1).
   	.
   	.
   	.
   	edge(head_n,tail_n,weight_n).
  

• Trivial_Graph_Format(.tgf)

   	1
   	.
   	.
   	.
   	n
   	#
   	1 2 weight_1
   	.
   	.
   	.
   	n k weight_n
  

• UCINET DL Format(.dl)

   	dl
   	format=edgelist1
   	n=<number of vertices>
   	data:
   	1 2 weight_1
   	.
   	.
   	.
   	n k weight_n	
  

• Matrix Market(.mtx)

      %%MatrixMarket matrix coordinate real general
      <number of vertices>  <number of vertices>  <number of edges>
      <head_1>    <tail_1>    <weight_1> 
      .
      .
      .
      <head_n>    <tail_n>    <weight_n> 
  

• Graph Line(.gl)

      <head_1> <tail_1>:<weight_1> <tail_2>:<weight_2>  ... <tail_n>:<weight_n>
      <head_2> <tail_1>:<weight_1> <tail_2>:<weight_2>  ... <tail_n>:<weight_n>
      .
      .
      .
      <head_n> <tail_1>:<weight_1> <tail_2>:<weight_2>  ... <tail_n>:<weight_n>
  

• GDF(.gdf)

      nodedef>name VARCHAR,label VARCHAR
      node_1,node_1_label
      node_2,node_2_label
      .
      .
      .
      node_n,node_n_label
      edgedef>node1 VARCHAR,node2 VARCHAR, weight DOUBLE
      node_1,node_2,weight_1
      node_1,node_3,weight_2
      .
      .
      .
      node_n,node_2,weight_n 
  

• GML(.gml)

      graph
      [
        multigraph 0
        directed  0
        node
        [
         id 1
         label "Node 1"
        ]
        node
        [
         id 2
         label "Node 2"
        ]
        .
        .
        .
        node
        [
         id n
         label "Node n"
        ]
        edge
        [
         source 1
         target 2
         value W1
        ]
        edge
        [
         source 2
         target 4
         value W2
        ]
        .
        .
        .
        edge
        [
         source n
         target r
         value Wn
        ]
      ]
  

• GEXF(.gexf)

      <?xml version="1.0" encoding="UTF-8"?>
      <gexf xmlns="http://www.gexf.net/1.2draft" version="1.2">
          <meta lastmodifieddate="2009-03-20">
              <creator>PyRGG</creator>
              <description>File Name</description>
          </meta>
          <graph defaultedgetype="directed">
              <nodes>
                  <node id="1" label="Node 1" />
                  <node id="2" label="Node 2" />
                  ...
              </nodes>
              <edges>
                  <edge id="1" source="1" target="2" weight="400" />
                  ...
              </edges>
          </graph>
      </gexf>
  

• Pickle(.p) (Binary Format)

Similar Works

• Random Modular Network Generator Generates random graphs with tunable strength of community structure
• randomGraph very simple random graph generator in matlab
• Graph1 Random Graph Generator with Max capacity paths (C++)

Dependencies

master	dev

Citing

If you use pyrgg in your research, please cite the JOSS paper ;-)

@article{Haghighi2017,
  doi = {10.21105/joss.00331},
  url = {https://doi.org/10.21105/joss.00331},
  year  = {2017},
  month = {sep},
  publisher = {The Open Journal},
  volume = {2},
  number = {17},
  author = {Sepand Haghighi},
  title = {Pyrgg: Python Random Graph Generator},
  journal = {The Journal of Open Source Software}
}

JOSS
Zenodo

License

References

Donate to our project

Bitcoin :

1XGr9qbZjBpUQJJSB6WtgBQbDTgrhPLPA

Payping (For Iranian citizens) :